logic: respect class qualifyer in method call for python post processing (#951 )

If the class of a called method is explicitly specified ("Base.__init__()"), only record an ambiguous edge to that method.
logic: Fixed multiple main declarations not shown as separate symbols when declaring file has same name (#950 )
2020-03-30 21:24:23 +02:00 · 2020-03-30 13:49:14 +02:00 · 2020-03-30 12:02:55 +02:00 · 2020-03-29 23:32:49 +02:00 · 2020-03-29 17:26:09 +02:00 · 2020-03-29 17:10:30 +02:00
538 changed files with 18003 additions and 8259 deletions
@@ -9,4 +9,18 @@ install:
 script:
  - COMMIT_HASH=$(git rev-parse HEAD)
  - docker run --name builder coatisoftware/local ${COMMIT_HASH}
+  - docker cp builder:/home/builder/Sourcetrail/release $TRAVIS_BUILD_DIR/release

+deploy:
+  provider: releases
+  api_key:
+    secure: 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
+  file_glob: true
+  file:
+    - "$TRAVIS_BUILD_DIR/release/Sourcetrail*.tar.gz"
+    - "$TRAVIS_BUILD_DIR/release/Sourcetrail*.AppImage"
+  overwrite: true
+  skip_cleanup: true
+  on:
+    tags: true
+    repo: CoatiSoftware/Sourcetrail
@@ -1,5 +1,30 @@
 ### Changelog

+#### 2020.1.106-beta
+released 2019-03-02
+
+* Make content of help dialogs selectable (issue [#805](https://github.com/CoatiSoftware/Sourcetrail/issues/935))
+* Added keyboard controls to move and activate focus in graph and code views using WASD/HJKL/Arrows + Enter/E ([#935](https://github.com/CoatiSoftware/Sourcetrail/issues/935)) (issues [#486](https://github.com/CoatiSoftware/Sourcetrail/issues/486), [#327](https://github.com/CoatiSoftware/Sourcetrail/issues/327), [#214](https://github.com/CoatiSoftware/Sourcetrail/issues/214), [#210](https://github.com/CoatiSoftware/Sourcetrail/issues/210))
+* Fixed a crash in shared memory use ([#912](https://github.com/CoatiSoftware/Sourcetrail/issues/912))
+* Discard non-existing paths in automatic path detection ([#930](https://github.com/CoatiSoftware/Sourcetrail/issues/930))
+* Python: Update python indexer to use jedi 0.16.0 ([#929](https://github.com/CoatiSoftware/Sourcetrail/issues/929))
+* Fixed frequent deadlock after loading project from Start Screen (issue [#924](https://github.com/CoatiSoftware/Sourcetrail/issues/924))
+* C/C++: Updated LLVM/Clang config headers to release 9.0.0 ([#922](https://github.com/CoatiSoftware/Sourcetrail/issues/922))
+* Fix crash in update check on premature Qt object deletion ([#920](https://github.com/CoatiSoftware/Sourcetrail/issues/920))
+* C/C++: Fixed an indexer crash ([#911](https://github.com/CoatiSoftware/Sourcetrail/issues/911))
+* Code: fixed font size not changed in single file view (issue [#916](https://github.com/CoatiSoftware/Sourcetrail/issues/916))
+* Mark required contents with asterisk in Source Group setup (issue [#723](https://github.com/CoatiSoftware/Sourcetrail/issues/723)) ([#914](https://github.com/CoatiSoftware/Sourcetrail/issues/914))
+* Removed multiple dialog steps in Source Group setup (issue [#723](https://github.com/CoatiSoftware/Sourcetrail/issues/723)) ([#913](https://github.com/CoatiSoftware/Sourcetrail/issues/913))
+* Handled non-writeable project location (issue [#735](https://github.com/CoatiSoftware/Sourcetrail/issues/735)) ([#906](https://github.com/CoatiSoftware/Sourcetrail/issues/906))
+* Fixed error help dialog not showing up during indexing (issue [#740](https://github.com/CoatiSoftware/Sourcetrail/issues/740)) ([#904](https://github.com/CoatiSoftware/Sourcetrail/issues/904))
+* Allow changing the log file path in preferences (issue [#156](https://github.com/CoatiSoftware/Sourcetrail/issues/156)) ([#900](https://github.com/CoatiSoftware/Sourcetrail/issues/900))
+* Fix crash when project directory contains non-latin character (issue [#899](https://github.com/CoatiSoftware/Sourcetrail/issues/899)) ([#901](https://github.com/CoatiSoftware/Sourcetrail/issues/901))
+* Graph: Fixed endless recursion on cyclic inheritance edges
+* Add 'close tabs to the right' context menu action to tab bar (issue [#822](https://github.com/CoatiSoftware/Sourcetrail/issues/822)) ([#875](https://github.com/CoatiSoftware/Sourcetrail/issues/875))
+* C/C++: Record calls to cxx destructor on delete keyword (issue [#829](https://github.com/CoatiSoftware/Sourcetrail/issues/829)) ([#863](https://github.com/CoatiSoftware/Sourcetrail/issues/863))
+* Retry pre-filling mandatory empty path settings on startup ([#864](https://github.com/CoatiSoftware/Sourcetrail/issues/864))
+* Improved handling of unloadable source group ([#862](https://github.com/CoatiSoftware/Sourcetrail/issues/862))
+
 #### 2019.4.102
 released 2019-12-20

@@ -7,6 +7,7 @@ set(BUILD_CXX_LANGUAGE_PACKAGE OFF CACHE BOOL "Add C and C++ support to the Sour
 set(BUILD_JAVA_LANGUAGE_PACKAGE OFF CACHE BOOL "Add Java support to the Sourcetrail indexer.")
 set(BUILD_PYTHON_LANGUAGE_PACKAGE OFF CACHE BOOL "Add Python support to the Sourcetrail indexer.")
 set(DOCKER_BUILD OFF CACHE BOOL "Build runs in Docker")
+set(TREAT_WARNINGS_AS_ERRORS ON CACHE BOOL "Treat compiler warnings as errors")

 #set (CMAKE_VERBOSE_MAKEFILE ON)

@@ -88,6 +89,31 @@ if (DOCKER_BUILD)
 	set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -static-libstdc++")
 endif()

+if (TREAT_WARNINGS_AS_ERRORS)
+	if ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "MSVC")
+		# Visual Studio 2017 version 15.9 <= Version <= Visual Studio 2019 Version 16.4
+		if ((MSVC_VERSION GREATER_EQUAL 1916) AND (MSVC_VERSION LESS_EQUAL 1924))
+			# Warning 4003: not enough actual parameters for macro 'identifier'
+			# Warning 4250: 'class1' inherits 'class2::member' via dominance
+			set(WARNINGS_LIST "/wd4003 /wd4250")
+			set(CMAKE_CXX_WARNINGS_FLAGS "/experimental:external /external:anglebrackets /external:W0 /WX")
+			set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${CMAKE_CXX_WARNINGS_FLAGS} ${WARNINGS_LIST}")
+
+			# Treat linker warnings as errors
+			set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} /WX")
+			set(CMAKE_STATIC_LINKER_FLAGS "${CMAKE_STATIC_LINKER_FLAGS} /WX")
+			set(CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} /WX")
+			set(CMAKE_MODULE_LINKER_FLAGS "${CMAKE_MODULE_LINKER_FLAGS} /WX")
+
+			message(STATUS "'Treat warnings as errors' policy is enabled")
+		else()
+			message(STATUS "'Treat warnings as errors' policy is disabled")
+		endif()
+	else()
+		message(STATUS "'Treat warnings as errors' policy is disabled")
+	endif()
+endif()
+
 # For debugging the release build on linux
 #if (UNIX AND "${CMAKE_BUILD_TYPE}" STREQUAL "Release")
 	#add_definitions(-fno-omit-frame-pointer)
@@ -490,6 +516,11 @@ configure_file(
 )

 #configure the versioning file
+configure_file(
+	${CMAKE_SOURCE_DIR}/cmake/version.txt.in
+	${CMAKE_BINARY_DIR}/version.txt
+)
+
 configure_file(
 	${CMAKE_SOURCE_DIR}/cmake/productVersion.h.in
 	${CMAKE_BINARY_DIR}/src/lib_gui/productVersion.h
@@ -753,8 +784,8 @@ set_property(
 if (WIN32)
 	set_target_properties(${TEST_PROJECT_NAME} PROPERTIES COMPILE_FLAGS "/bigobj")
 	set_property(
-		TARGET ${TEST_PROJECT_NAME} 
-			PROPERTY VS_DEBUGGER_WORKING_DIRECTORY 
+		TARGET ${TEST_PROJECT_NAME}
+			PROPERTY VS_DEBUGGER_WORKING_DIRECTORY
 			"${CMAKE_SOURCE_DIR}/bin/test")
 endif ()

@@ -4,6 +4,7 @@ Sponsors [via Patreon](https://www.patreon.com/sourcetrail).

 ## Legendary Coatis

+* Akinobu Fujii
 * David Manouchehri
 * Manik Singhal
 * Mario van Beek
@@ -12,6 +13,7 @@ Sponsors [via Patreon](https://www.patreon.com/sourcetrail).
 ## Super Coatis

 * Alexis Jeandet
+* Anthony Marchini
 * Edward Gibbs
 * Jonathan Nemo
 * Louis St-Amour
@@ -31,13 +33,15 @@ Sponsors [via Patreon](https://www.patreon.com/sourcetrail).
 * John Borland
 * kale
 * Matěj Týč
-* Matt Alexander
 * Nakul Dhotre
 * Nathan
 * Nathan Loofbourrow
 * Rui Pires
 * Sam Tuke
+* Simon
 * Stephan Roslen
+* Tomi Joki-Korpela
+* Tony Hong
 * Traxes
 * Werner de Groot
 * Yang, Wenbo
@@ -4,6 +4,7 @@
 	<window>
 		<background>#494949</background>
 		<separator>#CCCCCC</separator>
+		<focus>#9BF51D</focus>
 		<scrollbar>
 			<background>transparent</background>
 			<handle>#80999999</handle>
@@ -106,7 +107,6 @@

 		<file>
 			<background>#AAAAAA</background>
-			<hover>#999999</hover>

 			<title>
 				<text>black</text>
@@ -130,7 +130,6 @@
 			<title>
 				<text>#A0A0A0</text>
 				<background>transparent</background>
-				<hover>#2F2F2F</hover>
 			</title>

 			<line_number>
@@ -255,7 +254,7 @@
 			<type>
 				<border>
 					<normal>#20FFFFFF</normal>
-					<focus>#FFFFFF</focus>
+					<highlight>#FFFFFF</highlight>
 				</border>
 				<text>
 					<normal>#FFFFFF</normal>
@@ -292,11 +291,11 @@
 			<function>
 				<fill>
 					<normal>#FFCC3B</normal>
-					<focus>#FFD05A</focus>
+					<highlight>#FFD05A</highlight>
 				</fill>
 				<border>
 					<normal>transparent</normal>
-					<focus>#FFFFFF</focus>
+					<highlight>#FFFFFF</highlight>
 				</border>
 				<hatching>
 					<normal>#FFE8A6</normal>
@@ -309,11 +308,11 @@
 			<global_variable>
 				<fill>
 					<normal>#2FC2D6</normal>
-					<focus>#38D3E8</focus>
+					<highlight>#38D3E8</highlight>
 				</fill>
 				<border>
 					<normal>transparent</normal>
-					<focus>#FFFFFF</focus>
+					<highlight>#FFFFFF</highlight>
 				</border>
 				<hatching>
 					<normal>#96DAE3</normal>
@@ -335,7 +334,7 @@
 				</fill>
 				<border>
 					<normal>#80FFFFFF</normal>
-					<focus>#FFFFFF</focus>
+					<highlight>#FFFFFF</highlight>
 				</border>
 				<text>
 					<normal>#FFFFFF</normal>
@@ -357,11 +356,11 @@
 			<file>
 				<fill>
 					<normal>#4E82F6</normal>
-					<focus>#6793F6</focus>
+					<highlight>#6793F6</highlight>
 				</fill>
 				<border>
 					<normal>#20FFFFFF</normal>
-					<focus>#FFFFFF</focus>
+					<highlight>#FFFFFF</highlight>
 				</border>
 				<text>
 					<normal>#FFFFFF</normal>
@@ -382,8 +381,14 @@

 			<access>
 				<fill>
-					<normal>#CCCCCC</normal>
+					<normal>#494949</normal>
 				</fill>
+				<text>
+					<normal>#FFFFFF</normal>
+				</text>
+				<icon>
+					<normal>#FFFFFF</normal>
+				</icon>
 			</access>
 			<bundle>
 				<fill>
@@ -391,7 +396,7 @@
 				</fill>
 				<border>
 					<normal>#80FFFFFF</normal>
-					<focus>#FFFFFF</focus>
+					<highlight>#FFFFFF</highlight>
 				</border>
 				<text>
 					<normal>#FFFFFF</normal>
@@ -451,7 +456,7 @@
 					</text>
 					<border>
 						<normal>#4E82F6</normal>
-						<focus>#6793F6</focus>
+						<highlight>#6793F6</highlight>
 					</border>
 				</file>
 				<namespace>
@@ -463,7 +468,7 @@
 					</text>
 					<border>
 						<normal>#873E3E</normal>
-						<focus>#944444</focus>
+						<highlight>#944444</highlight>
 					</border>
 				</namespace>
 				<inheritance>
@@ -477,55 +482,24 @@
 			</group>
 		</node>
 		<edge>
-			<default>
-				<normal>#797979</normal>
-			</default>
+			<default>#797979</default>
+			<type_use>#797979</type_use>
+			<inheritance>#797979</inheritance>

-			<type_use>
-				<like>default</like>
-			</type_use>
+			<use>#00A0B6</use>
+			<call>#DEA400</call>
+			<call_trail_focus>#FFFFFF</call_trail_focus>
+			<override>#BA5ECC</override>

-			<inheritance>
-				<like>default</like>
-			</inheritance>
+			<type_argument>#D93D5F</type_argument>
+			<template_specialization>#D93D5F</template_specialization>

-			<override>
-				<normal>#BA5ECC</normal>
-			</override>
+			<include>#4E82F6</include>
+			<import>#4E82F6</import>
+			<macro_use>#4E82F6</macro_use>
+			<annotation_use>#4E82F6</annotation_use>

-			<call>
-				<normal>#DEA400</normal>
-				<trail_focus>#FFFFFF</trail_focus>
-			</call>
-
-			<use>
-				<normal>#00A0B6</normal>
-			</use>
-
-			<type_argument>
-				<normal>#D93D5F</normal>
-			</type_argument>
-			<template_specialization>
-				<like>type_argument</like>
-			</template_specialization>
-
-			<include>
-				<normal>#4E82F6</normal>
-			</include>
-			<import>
-				<like>include</like>
-			</import>
-			<macro_use>
-				<like>include</like>
-			</macro_use>
-			<annotation_use>
-				<like>include</like>
-			</annotation_use>
-
-			<aggregation>
-				<normal>#666666</normal>
-				<focus>#6D6D6D</focus>
-			</aggregation>
+			<aggregation>#666666</aggregation>
 		</edge>
 	</graph>

@@ -4,6 +4,7 @@
 	<window>
 		<background>white</background>
 		<separator>#A2A2A2</separator>
+		<focus>#FF5900</focus>
 		<scrollbar>
 			<background>transparent</background>
 			<handle>#80999999</handle>
@@ -106,7 +107,6 @@

 		<file>
 			<background>#D8D8D8</background>
-			<hover>#E0E0E0</hover>

 			<title>
 				<text>black</text>
@@ -130,7 +130,6 @@
 			<title>
 				<text>#909090</text>
 				<background>transparent</background>
-				<hover>#F5F5F5</hover>
 			</title>

 			<line_number>
@@ -253,7 +252,7 @@
 			<type>
 				<border>
 					<normal>#203C3C3C</normal>
-					<focus>#3C3C3C</focus>
+					<highlight>#3C3C3C</highlight>
 				</border>
 			</type>
 			<built_in_type>
@@ -284,11 +283,11 @@
 			<function>
 				<fill>
 					<normal>#F4D07D</normal>
-					<focus>#F4BC3D</focus>
+					<highlight>#F4BC3D</highlight>
 				</fill>
 				<border>
 					<normal>transparent</normal>
-					<focus>#3C3C3C</focus>
+					<highlight>#3C3C3C</highlight>
 				</border>
 				<hatching>
 					<normal>#FFEDC4</normal>
@@ -301,11 +300,11 @@
 			<global_variable>
 				<fill>
 					<normal>#81C1E3</normal>
-					<focus>#72B3D6</focus>
+					<highlight>#72B3D6</highlight>
 				</fill>
 				<border>
 					<normal>transparent</normal>
-					<focus>#3C3C3C</focus>
+					<highlight>#3C3C3C</highlight>
 				</border>
 				<hatching>
 					<normal>#BBDDED</normal>
@@ -327,7 +326,7 @@
 				</fill>
 				<border>
 					<normal>#3D3D3D</normal>
-					<focus>black</focus>
+					<highlight>black</highlight>
 				</border>
 				<icon>
 					<normal>#3D3D3D</normal>
@@ -346,11 +345,11 @@
 			<file>
 				<fill>
 					<normal>#BEE0AF</normal>
-					<focus>#A6D492</focus>
+					<highlight>#A6D492</highlight>
 				</fill>
 				<border>
 					<normal>#203C3C3C</normal>
-					<focus>#3C3C3C</focus>
+					<highlight>#3C3C3C</highlight>
 				</border>
 				<hatching>
 					<normal>#D7F7C8</normal>
@@ -374,7 +373,7 @@
 				</fill>
 				<border>
 					<normal>#803C3C3C</normal>
-					<focus>#3C3C3C</focus>
+					<highlight>#3C3C3C</highlight>
 				</border>
 			</bundle>
 			<count_number>
@@ -425,7 +424,7 @@
 					</text>
 					<border>
 						<normal>#BEE0AF</normal>
-						<focus>#A6D492</focus>
+						<highlight>#A6D492</highlight>
 					</border>
 				</file>
 				<namespace>
@@ -437,7 +436,7 @@
 					</text>
 					<border>
 						<normal>#EFC5C5</normal>
-						<focus>#EFB3B3</focus>
+						<highlight>#EFB3B3</highlight>
 					</border>
 				</namespace>
 				<inheritance>
@@ -451,55 +450,24 @@
 			</group>
 		</node>
 		<edge>
-			<default>
-				<normal>#878787</normal>
-			</default>
+			<default>#878787</default>
+			<type_use>#878787</type_use>
+			<inheritance>#878787</inheritance>

-			<type_use>
-				<like>default</like>
-			</type_use>
+			<use>#4B9FC4</use>
+			<call>#F4BC3D</call>
+			<call_trail_focus>#F56B3D</call_trail_focus>
+			<override>#A37ACC</override>

-			<inheritance>
-				<like>default</like>
-			</inheritance>
+			<type_argument>#CF6B7C</type_argument>
+			<template_specialization>#CF6B7C</template_specialization>

-			<override>
-				<normal>#A37ACC</normal>
-			</override>
+			<include>#719660</include>
+			<import>#719660</import>
+			<macro_use>#719660</macro_use>
+			<annotation_use>#719660</annotation_use>

-			<call>
-				<normal>#F4BC3D</normal>
-				<trail_focus>#F56B3D</trail_focus>
-			</call>
-
-			<use>
-				<normal>#4B9FC4</normal>
-			</use>
-
-			<type_argument>
-				<like>#CF6B7C</like>
-			</type_argument>
-			<template_specialization>
-				<like>type_argument</like>
-			</template_specialization>
-
-			<include>
-				<normal>#719660</normal>
-			</include>
-			<import>
-				<like>include</like>
-			</import>
-			<macro_use>
-				<like>include</like>
-			</macro_use>
-			<annotation_use>
-				<like>include</like>
-			</annotation_use>
-
-			<aggregation>
-				<normal>#CCC</normal>
-				<focus>#BBB</focus>
-			</aggregation>
+			<aggregation>#CCC</aggregation>
 		</edge>
 	</graph>

@@ -4,6 +4,7 @@
 	<window>
 		<background>#272728</background>
 		<separator>#CCC</separator>
+		<focus>#FFFF4D</focus>
 		<scrollbar>
 			<background>transparent</background>
 			<handle>#80999999</handle>
@@ -106,7 +107,6 @@

 		<file>
 			<background>#5C5C5C</background>
-			<hover>#6C6C6C</hover>

 			<title>
 				<text>#F7F7F7</text>
@@ -130,7 +130,6 @@
 			<title>
 				<text>#A0A0A0</text>
 				<background>transparent</background>
-				<hover>#2F2F2F</hover>
 			</title>

 			<line_number>
@@ -256,7 +255,7 @@
 			<type>
 				<border>
 					<normal>#20C3C3C3</normal>
-					<focus>#C3C3C3</focus>
+					<highlight>#C3C3C3</highlight>
 				</border>
 			</type>
 			<built_in_type>
@@ -287,11 +286,11 @@
 			<function>
 				<fill>
 					<normal>#7A681F</normal>
-					<focus>#9C8528</focus>
+					<highlight>#9C8528</highlight>
 				</fill>
 				<border>
 					<normal>transparent</normal>
-					<focus>#C3C3C3</focus>
+					<highlight>#C3C3C3</highlight>
 				</border>
 				<hatching>
 					<normal>#544815</normal>
@@ -304,11 +303,11 @@
 			<global_variable>
 				<fill>
 					<normal>#21516B</normal>
-					<focus>#2A6484</focus>
+					<highlight>#2A6484</highlight>
 				</fill>
 				<border>
 					<normal>transparent</normal>
-					<focus>#C3C3C3</focus>
+					<highlight>#C3C3C3</highlight>
 				</border>
 				<hatching>
 					<normal>#17384A</normal>
@@ -330,7 +329,7 @@
 				</fill>
 				<border>
 					<normal>#80C3C3C3</normal>
-					<focus>#C3C3C3</focus>
+					<highlight>#C3C3C3</highlight>
 				</border>
 				<icon>
 					<normal>#C3C3C3</normal>
@@ -349,11 +348,11 @@
 			<file>
 				<fill>
 					<normal>#1B564E</normal>
-					<focus>#21695F</focus>
+					<highlight>#21695F</highlight>
 				</fill>
 				<border>
 					<normal>#20C3C3C3</normal>
-					<focus>#C3C3C3</focus>
+					<highlight>#C3C3C3</highlight>
 				</border>
 				<hatching>
 					<normal>#123B35</normal>
@@ -377,7 +376,7 @@
 				</fill>
 				<border>
 					<normal>#80C3C3C3</normal>
-					<focus>#C3C3C3</focus>
+					<highlight>#C3C3C3</highlight>
 				</border>
 			</bundle>
 			<count_number>
@@ -428,7 +427,7 @@
 					</text>
 					<border>
 						<normal>#1B564E</normal>
-						<focus>#1E6158</focus>
+						<highlight>#1E6158</highlight>
 					</border>
 				</file>
 				<namespace>
@@ -440,7 +439,7 @@
 					</text>
 					<border>
 						<normal>#78282D</normal>
-						<focus>#872D33</focus>
+						<highlight>#872D33</highlight>
 					</border>
 				</namespace>
 				<inheritance>
@@ -454,55 +453,24 @@
 			</group>
 		</node>
 		<edge>
-			<default>
-				<normal>#797979</normal>
-			</default>
+			<default>#797979</default>
+			<type_use>#797979</type_use>
+			<inheritance>#797979</inheritance>

-			<type_use>
-				<like>default</like>
-			</type_use>
+			<use>#2D6A8C</use>
+			<call>#9C8528</call>
+			<call_trail_focus>#F7F7F7</call_trail_focus>
+			<override>#8A5A94</override>

-			<inheritance>
-				<like>default</like>
-			</inheritance>
+			<type_argument>#C14057</type_argument>
+			<template_specialization>#C14057</template_specialization>

-			<override>
-				<normal>#8A5A94</normal>
-			</override>
+			<include>#247368</include>
+			<import>#247368</import>
+			<macro_use>#247368</macro_use>
+			<annotation_use>#247368</annotation_use>

-			<call>
-				<normal>#9C8528</normal>
-				<trail_focus>#F7F7F7</trail_focus>
-			</call>
-
-			<use>
-				<normal>#2D6A8C</normal>
-			</use>
-
-			<type_argument>
-				<normal>#C14057</normal>
-			</type_argument>
-			<template_specialization>
-				<like>type_argument</like>
-			</template_specialization>
-
-			<include>
-				<normal>#247368</normal>
-			</include>
-			<import>
-				<like>include</like>
-			</import>
-			<macro_use>
-				<like>include</like>
-			</macro_use>
-			<annotation_use>
-				<like>include</like>
-			</annotation_use>
-
-			<aggregation>
-				<normal>#4D4D4D</normal>
-				<focus>#6D6D6D</focus>
-			</aggregation>
+			<aggregation>#4D4D4D</aggregation>
 		</edge>
 	</graph>

@@ -1,22 +1,8 @@
 /*===---- cuda_builtin_vars.h - CUDA built-in variables ---------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- __clang_cuda_cmath.h - Device-side CUDA cmath support ------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -44,12 +30,32 @@
 // implementation.  Declaring in the global namespace and pulling into namespace
 // std covers all of the known knowns.

+#ifdef _OPENMP
+#define __DEVICE__ static __attribute__((always_inline))
+#else
 #define __DEVICE__ static __device__ __inline__ __attribute__((always_inline))
+#endif

+// For C++ 17 we need to include noexcept attribute to be compatible
+// with the header-defined version. This may be removed once
+// variant is supported.
+#if defined(_OPENMP) && defined(__cplusplus) && __cplusplus >= 201703L
+#define __NOEXCEPT noexcept
+#else
+#define __NOEXCEPT
+#endif
+
+#if !(defined(_OPENMP) && defined(__cplusplus))
 __DEVICE__ long long abs(long long __n) { return ::llabs(__n); }
 __DEVICE__ long abs(long __n) { return ::labs(__n); }
 __DEVICE__ float abs(float __x) { return ::fabsf(__x); }
 __DEVICE__ double abs(double __x) { return ::fabs(__x); }
+#endif
+// TODO: remove once variat is supported.
+#if defined(_OPENMP) && defined(__cplusplus)
+__DEVICE__ const float abs(const float __x) { return ::fabsf((float)__x); }
+__DEVICE__ const double abs(const double __x) { return ::fabs((double)__x); }
+#endif
 __DEVICE__ float acos(float __x) { return ::acosf(__x); }
 __DEVICE__ float asin(float __x) { return ::asinf(__x); }
 __DEVICE__ float atan(float __x) { return ::atanf(__x); }
@@ -58,9 +64,11 @@ __DEVICE__ float ceil(float __x) { return ::ceilf(__x); }
 __DEVICE__ float cos(float __x) { return ::cosf(__x); }
 __DEVICE__ float cosh(float __x) { return ::coshf(__x); }
 __DEVICE__ float exp(float __x) { return ::expf(__x); }
-__DEVICE__ float fabs(float __x) { return ::fabsf(__x); }
+__DEVICE__ float fabs(float __x) __NOEXCEPT { return ::fabsf(__x); }
 __DEVICE__ float floor(float __x) { return ::floorf(__x); }
 __DEVICE__ float fmod(float __x, float __y) { return ::fmodf(__x, __y); }
+// TODO: remove when variant is supported
+#ifndef _OPENMP
 __DEVICE__ int fpclassify(float __x) {
  return __builtin_fpclassify(FP_NAN, FP_INFINITE, FP_NORMAL, FP_SUBNORMAL,
                              FP_ZERO, __x);
@@ -69,6 +77,7 @@ __DEVICE__ int fpclassify(double __x) {
  return __builtin_fpclassify(FP_NAN, FP_INFINITE, FP_NORMAL, FP_SUBNORMAL,
                              FP_ZERO, __x);
 }
+#endif
 __DEVICE__ float frexp(float __arg, int *__exp) {
  return ::frexpf(__arg, __exp);
 }
@@ -448,7 +457,10 @@ using ::remainderf;
 using ::remquof;
 using ::rintf;
 using ::roundf;
+// TODO: remove once variant is supported
+#ifndef _OPENMP
 using ::scalblnf;
+#endif
 using ::scalbnf;
 using ::sinf;
 using ::sinhf;
@@ -467,6 +479,7 @@ _GLIBCXX_END_NAMESPACE_VERSION
 } // namespace std
 #endif

+#undef __NOEXCEPT
 #undef __DEVICE__

 #endif
@@ -1,22 +1,8 @@
 /*===-- __clang_cuda_complex_builtins - CUDA impls of runtime complex fns ---===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- __clang_cuda_device_functions.h - CUDA runtime support -----------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -24,15 +10,21 @@
 #ifndef __CLANG_CUDA_DEVICE_FUNCTIONS_H__
 #define __CLANG_CUDA_DEVICE_FUNCTIONS_H__

+#ifndef _OPENMP
 #if CUDA_VERSION < 9000
 #error This file is intended to be used with CUDA-9+ only.
 #endif
+#endif

 // __DEVICE__ is a helper macro with common set of attributes for the wrappers
 // we implement in this file. We need static in order to avoid emitting unused
 // functions and __forceinline__ helps inlining these wrappers at -O1.
 #pragma push_macro("__DEVICE__")
+#ifdef _OPENMP
+#define __DEVICE__ static __attribute__((always_inline))
+#else
 #define __DEVICE__ static __device__ __forceinline__
+#endif

 // libdevice provides fast low precision and slow full-recision implementations
 // for some functions. Which one gets selected depends on
@@ -45,6 +37,15 @@
 #define __FAST_OR_SLOW(fast, slow) slow
 #endif

+// For C++ 17 we need to include noexcept attribute to be compatible
+// with the header-defined version. This may be removed once
+// variant is supported.
+#if defined(_OPENMP) && defined(__cplusplus) && __cplusplus >= 201703L
+#define __NOEXCEPT noexcept
+#else
+#define __NOEXCEPT
+#endif
+
 __DEVICE__ int __all(int __a) { return __nvvm_vote_all(__a); }
 __DEVICE__ int __any(int __a) { return __nvvm_vote_any(__a); }
 __DEVICE__ unsigned int __ballot(int __a) { return __nvvm_vote_ballot(__a); }
@@ -52,8 +53,13 @@ __DEVICE__ unsigned int __brev(unsigned int __a) { return __nv_brev(__a); }
 __DEVICE__ unsigned long long __brevll(unsigned long long __a) {
  return __nv_brevll(__a);
 }
+#if defined(__cplusplus)
 __DEVICE__ void __brkpt() { asm volatile("brkpt;"); }
 __DEVICE__ void __brkpt(int __a) { __brkpt(); }
+#else
+__DEVICE__ void __attribute__((overloadable)) __brkpt(void) { asm volatile("brkpt;"); }
+__DEVICE__ void __attribute__((overloadable)) __brkpt(int __a) { __brkpt(); }
+#endif
 __DEVICE__ unsigned int __byte_perm(unsigned int __a, unsigned int __b,
                                    unsigned int __c) {
  return __nv_byte_perm(__a, __b, __c);
@@ -237,6 +243,9 @@ __DEVICE__ int __ffs(int __a) { return __nv_ffs(__a); }
 __DEVICE__ int __ffsll(long long __a) { return __nv_ffsll(__a); }
 __DEVICE__ int __finite(double __a) { return __nv_isfinited(__a); }
 __DEVICE__ int __finitef(float __a) { return __nv_finitef(__a); }
+#ifdef _MSC_VER
+__DEVICE__ int __finitel(long double __a);
+#endif
 __DEVICE__ int __float2int_rd(float __a) { return __nv_float2int_rd(__a); }
 __DEVICE__ int __float2int_rn(float __a) { return __nv_float2int_rn(__a); }
 __DEVICE__ int __float2int_ru(float __a) { return __nv_float2int_ru(__a); }
@@ -445,8 +454,14 @@ __DEVICE__ float __int_as_float(int __a) { return __nv_int_as_float(__a); }
 __DEVICE__ int __isfinited(double __a) { return __nv_isfinited(__a); }
 __DEVICE__ int __isinf(double __a) { return __nv_isinfd(__a); }
 __DEVICE__ int __isinff(float __a) { return __nv_isinff(__a); }
+#ifdef _MSC_VER
+__DEVICE__ int __isinfl(long double __a);
+#endif
 __DEVICE__ int __isnan(double __a) { return __nv_isnand(__a); }
 __DEVICE__ int __isnanf(float __a) { return __nv_isnanf(__a); }
+#ifdef _MSC_VER
+__DEVICE__ int __isnanl(long double __a);
+#endif
 __DEVICE__ double __ll2double_rd(long long __a) {
  return __nv_ll2double_rd(__a);
 }
@@ -520,8 +535,8 @@ __DEVICE__ unsigned int __sad(int __a, int __b, unsigned int __c) {
 __DEVICE__ float __saturatef(float __a) { return __nv_saturatef(__a); }
 __DEVICE__ int __signbitd(double __a) { return __nv_signbitd(__a); }
 __DEVICE__ int __signbitf(float __a) { return __nv_signbitf(__a); }
-__DEVICE__ void __sincosf(float __a, float *__sptr, float *__cptr) {
-  return __nv_fast_sincosf(__a, __sptr, __cptr);
+__DEVICE__ void __sincosf(float __a, float *__s, float *__c) {
+  return __nv_fast_sincosf(__a, __s, __c);
 }
 __DEVICE__ float __sinf(float __a) { return __nv_fast_sinf(__a); }
 __DEVICE__ int __syncthreads_and(int __a) { return __nvvm_bar0_and(__a); }
@@ -1468,7 +1483,8 @@ __DEVICE__ unsigned int __vsubus4(unsigned int __a, unsigned int __b) {
  return r;
 }
 #endif // CUDA_VERSION >= 9020
-__DEVICE__ int abs(int __a) { return __nv_abs(__a); }
+__DEVICE__ int abs(int __a) __NOEXCEPT { return __nv_abs(__a); }
+__DEVICE__ double fabs(double __a) __NOEXCEPT { return __nv_fabs(__a); }
 __DEVICE__ double acos(double __a) { return __nv_acos(__a); }
 __DEVICE__ float acosf(float __a) { return __nv_acosf(__a); }
 __DEVICE__ double acosh(double __a) { return __nv_acosh(__a); }
@@ -1487,8 +1503,10 @@ __DEVICE__ double cbrt(double __a) { return __nv_cbrt(__a); }
 __DEVICE__ float cbrtf(float __a) { return __nv_cbrtf(__a); }
 __DEVICE__ double ceil(double __a) { return __nv_ceil(__a); }
 __DEVICE__ float ceilf(float __a) { return __nv_ceilf(__a); }
+#ifndef _OPENMP
 __DEVICE__ int clock() { return __nvvm_read_ptx_sreg_clock(); }
 __DEVICE__ long long clock64() { return __nvvm_read_ptx_sreg_clock64(); }
+#endif
 __DEVICE__ double copysign(double __a, double __b) {
  return __nv_copysign(__a, __b);
 }
@@ -1525,7 +1543,6 @@ __DEVICE__ float exp2f(float __a) { return __nv_exp2f(__a); }
 __DEVICE__ float expf(float __a) { return __nv_expf(__a); }
 __DEVICE__ double expm1(double __a) { return __nv_expm1(__a); }
 __DEVICE__ float expm1f(float __a) { return __nv_expm1f(__a); }
-__DEVICE__ double fabs(double __a) { return __nv_fabs(__a); }
 __DEVICE__ float fabsf(float __a) { return __nv_fabsf(__a); }
 __DEVICE__ double fdim(double __a, double __b) { return __nv_fdim(__a, __b); }
 __DEVICE__ float fdimf(float __a, float __b) { return __nv_fdimf(__a, __b); }
@@ -1563,16 +1580,16 @@ __DEVICE__ double j1(double __a) { return __nv_j1(__a); }
 __DEVICE__ float j1f(float __a) { return __nv_j1f(__a); }
 __DEVICE__ double jn(int __n, double __a) { return __nv_jn(__n, __a); }
 __DEVICE__ float jnf(int __n, float __a) { return __nv_jnf(__n, __a); }
-#if defined(__LP64__)
-__DEVICE__ long labs(long __a) { return llabs(__a); };
+#if defined(__LP64__) || defined(_WIN64)
+__DEVICE__ long labs(long __a) __NOEXCEPT { return __nv_llabs(__a); };
 #else
-__DEVICE__ long labs(long __a) { return __nv_abs(__a); };
+__DEVICE__ long labs(long __a) __NOEXCEPT { return __nv_abs(__a); };
 #endif
 __DEVICE__ double ldexp(double __a, int __b) { return __nv_ldexp(__a, __b); }
 __DEVICE__ float ldexpf(float __a, int __b) { return __nv_ldexpf(__a, __b); }
 __DEVICE__ double lgamma(double __a) { return __nv_lgamma(__a); }
 __DEVICE__ float lgammaf(float __a) { return __nv_lgammaf(__a); }
-__DEVICE__ long long llabs(long long __a) { return __nv_llabs(__a); }
+__DEVICE__ long long llabs(long long __a) __NOEXCEPT { return __nv_llabs(__a); }
 __DEVICE__ long long llmax(long long __a, long long __b) {
  return __nv_llmax(__a, __b);
 }
@@ -1597,7 +1614,7 @@ __DEVICE__ float logbf(float __a) { return __nv_logbf(__a); }
 __DEVICE__ float logf(float __a) {
  return __FAST_OR_SLOW(__nv_fast_logf, __nv_logf)(__a);
 }
-#if defined(__LP64__)
+#if defined(__LP64__) || defined(_WIN64)
 __DEVICE__ long lrint(double __a) { return llrint(__a); }
 __DEVICE__ long lrintf(float __a) { return __float2ll_rn(__a); }
 __DEVICE__ long lround(double __a) { return llround(__a); }
@@ -1609,12 +1626,16 @@ __DEVICE__ long lround(double __a) { return round(__a); }
 __DEVICE__ long lroundf(float __a) { return roundf(__a); }
 #endif
 __DEVICE__ int max(int __a, int __b) { return __nv_max(__a, __b); }
+// These functions shouldn't be declared when including this header
+// for math function resolution purposes.
+#ifndef _OPENMP
 __DEVICE__ void *memcpy(void *__a, const void *__b, size_t __c) {
  return __builtin_memcpy(__a, __b, __c);
 }
 __DEVICE__ void *memset(void *__a, int __b, size_t __c) {
  return __builtin_memset(__a, __b, __c);
 }
+#endif
 __DEVICE__ int min(int __a, int __b) { return __nv_min(__a, __b); }
 __DEVICE__ double modf(double __a, double *__b) { return __nv_modf(__a, __b); }
 __DEVICE__ float modff(float __a, float *__b) { return __nv_modff(__a, __b); }
@@ -1698,6 +1719,8 @@ __DEVICE__ double rsqrt(double __a) { return __nv_rsqrt(__a); }
 __DEVICE__ float rsqrtf(float __a) { return __nv_rsqrtf(__a); }
 __DEVICE__ double scalbn(double __a, int __b) { return __nv_scalbn(__a, __b); }
 __DEVICE__ float scalbnf(float __a, int __b) { return __nv_scalbnf(__a, __b); }
+// TODO: remove once variant is supported
+#ifndef _OPENMP
 __DEVICE__ double scalbln(double __a, long __b) {
  if (__b > INT_MAX)
    return __a > 0 ? HUGE_VAL : -HUGE_VAL;
@@ -1712,18 +1735,19 @@ __DEVICE__ float scalblnf(float __a, long __b) {
    return __a > 0 ? 0.f : -0.f;
  return scalbnf(__a, (int)__b);
 }
+#endif
 __DEVICE__ double sin(double __a) { return __nv_sin(__a); }
-__DEVICE__ void sincos(double __a, double *__sptr, double *__cptr) {
-  return __nv_sincos(__a, __sptr, __cptr);
+__DEVICE__ void sincos(double __a, double *__s, double *__c) {
+  return __nv_sincos(__a, __s, __c);
 }
-__DEVICE__ void sincosf(float __a, float *__sptr, float *__cptr) {
-  return __FAST_OR_SLOW(__nv_fast_sincosf, __nv_sincosf)(__a, __sptr, __cptr);
+__DEVICE__ void sincosf(float __a, float *__s, float *__c) {
+  return __FAST_OR_SLOW(__nv_fast_sincosf, __nv_sincosf)(__a, __s, __c);
 }
-__DEVICE__ void sincospi(double __a, double *__sptr, double *__cptr) {
-  return __nv_sincospi(__a, __sptr, __cptr);
+__DEVICE__ void sincospi(double __a, double *__s, double *__c) {
+  return __nv_sincospi(__a, __s, __c);
 }
-__DEVICE__ void sincospif(float __a, float *__sptr, float *__cptr) {
-  return __nv_sincospif(__a, __sptr, __cptr);
+__DEVICE__ void sincospif(float __a, float *__s, float *__c) {
+  return __nv_sincospif(__a, __s, __c);
 }
 __DEVICE__ float sinf(float __a) {
  return __FAST_OR_SLOW(__nv_fast_sinf, __nv_sinf)(__a);
@@ -1763,6 +1787,7 @@ __DEVICE__ float y1f(float __a) { return __nv_y1f(__a); }
 __DEVICE__ double yn(int __a, double __b) { return __nv_yn(__a, __b); }
 __DEVICE__ float ynf(int __a, float __b) { return __nv_ynf(__a, __b); }

+#undef __NOEXCEPT
 #pragma pop_macro("__DEVICE__")
 #pragma pop_macro("__FAST_OR_SLOW")
 #endif // __CLANG_CUDA_DEVICE_FUNCTIONS_H__
@@ -1,22 +1,8 @@
 /*===--- __clang_cuda_intrinsics.h - Device-side CUDA intrinsic wrappers ---===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===-- __clang_cuda_libdevice_declares.h - decls for libdevice functions --===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -24,443 +10,453 @@
 #ifndef __CLANG_CUDA_LIBDEVICE_DECLARES_H__
 #define __CLANG_CUDA_LIBDEVICE_DECLARES_H__

+#if defined(__cplusplus)
 extern "C" {
+#endif

-__device__ int __nv_abs(int __a);
-__device__ double __nv_acos(double __a);
-__device__ float __nv_acosf(float __a);
-__device__ double __nv_acosh(double __a);
-__device__ float __nv_acoshf(float __a);
-__device__ double __nv_asin(double __a);
-__device__ float __nv_asinf(float __a);
-__device__ double __nv_asinh(double __a);
-__device__ float __nv_asinhf(float __a);
-__device__ double __nv_atan2(double __a, double __b);
-__device__ float __nv_atan2f(float __a, float __b);
-__device__ double __nv_atan(double __a);
-__device__ float __nv_atanf(float __a);
-__device__ double __nv_atanh(double __a);
-__device__ float __nv_atanhf(float __a);
-__device__ int __nv_brev(int __a);
-__device__ long long __nv_brevll(long long __a);
-__device__ int __nv_byte_perm(int __a, int __b, int __c);
-__device__ double __nv_cbrt(double __a);
-__device__ float __nv_cbrtf(float __a);
-__device__ double __nv_ceil(double __a);
-__device__ float __nv_ceilf(float __a);
-__device__ int __nv_clz(int __a);
-__device__ int __nv_clzll(long long __a);
-__device__ double __nv_copysign(double __a, double __b);
-__device__ float __nv_copysignf(float __a, float __b);
-__device__ double __nv_cos(double __a);
-__device__ float __nv_cosf(float __a);
-__device__ double __nv_cosh(double __a);
-__device__ float __nv_coshf(float __a);
-__device__ double __nv_cospi(double __a);
-__device__ float __nv_cospif(float __a);
-__device__ double __nv_cyl_bessel_i0(double __a);
-__device__ float __nv_cyl_bessel_i0f(float __a);
-__device__ double __nv_cyl_bessel_i1(double __a);
-__device__ float __nv_cyl_bessel_i1f(float __a);
-__device__ double __nv_dadd_rd(double __a, double __b);
-__device__ double __nv_dadd_rn(double __a, double __b);
-__device__ double __nv_dadd_ru(double __a, double __b);
-__device__ double __nv_dadd_rz(double __a, double __b);
-__device__ double __nv_ddiv_rd(double __a, double __b);
-__device__ double __nv_ddiv_rn(double __a, double __b);
-__device__ double __nv_ddiv_ru(double __a, double __b);
-__device__ double __nv_ddiv_rz(double __a, double __b);
-__device__ double __nv_dmul_rd(double __a, double __b);
-__device__ double __nv_dmul_rn(double __a, double __b);
-__device__ double __nv_dmul_ru(double __a, double __b);
-__device__ double __nv_dmul_rz(double __a, double __b);
-__device__ float __nv_double2float_rd(double __a);
-__device__ float __nv_double2float_rn(double __a);
-__device__ float __nv_double2float_ru(double __a);
-__device__ float __nv_double2float_rz(double __a);
-__device__ int __nv_double2hiint(double __a);
-__device__ int __nv_double2int_rd(double __a);
-__device__ int __nv_double2int_rn(double __a);
-__device__ int __nv_double2int_ru(double __a);
-__device__ int __nv_double2int_rz(double __a);
-__device__ long long __nv_double2ll_rd(double __a);
-__device__ long long __nv_double2ll_rn(double __a);
-__device__ long long __nv_double2ll_ru(double __a);
-__device__ long long __nv_double2ll_rz(double __a);
-__device__ int __nv_double2loint(double __a);
-__device__ unsigned int __nv_double2uint_rd(double __a);
-__device__ unsigned int __nv_double2uint_rn(double __a);
-__device__ unsigned int __nv_double2uint_ru(double __a);
-__device__ unsigned int __nv_double2uint_rz(double __a);
-__device__ unsigned long long __nv_double2ull_rd(double __a);
-__device__ unsigned long long __nv_double2ull_rn(double __a);
-__device__ unsigned long long __nv_double2ull_ru(double __a);
-__device__ unsigned long long __nv_double2ull_rz(double __a);
-__device__ unsigned long long __nv_double_as_longlong(double __a);
-__device__ double __nv_drcp_rd(double __a);
-__device__ double __nv_drcp_rn(double __a);
-__device__ double __nv_drcp_ru(double __a);
-__device__ double __nv_drcp_rz(double __a);
-__device__ double __nv_dsqrt_rd(double __a);
-__device__ double __nv_dsqrt_rn(double __a);
-__device__ double __nv_dsqrt_ru(double __a);
-__device__ double __nv_dsqrt_rz(double __a);
-__device__ double __nv_dsub_rd(double __a, double __b);
-__device__ double __nv_dsub_rn(double __a, double __b);
-__device__ double __nv_dsub_ru(double __a, double __b);
-__device__ double __nv_dsub_rz(double __a, double __b);
-__device__ double __nv_erfc(double __a);
-__device__ float __nv_erfcf(float __a);
-__device__ double __nv_erfcinv(double __a);
-__device__ float __nv_erfcinvf(float __a);
-__device__ double __nv_erfcx(double __a);
-__device__ float __nv_erfcxf(float __a);
-__device__ double __nv_erf(double __a);
-__device__ float __nv_erff(float __a);
-__device__ double __nv_erfinv(double __a);
-__device__ float __nv_erfinvf(float __a);
-__device__ double __nv_exp10(double __a);
-__device__ float __nv_exp10f(float __a);
-__device__ double __nv_exp2(double __a);
-__device__ float __nv_exp2f(float __a);
-__device__ double __nv_exp(double __a);
-__device__ float __nv_expf(float __a);
-__device__ double __nv_expm1(double __a);
-__device__ float __nv_expm1f(float __a);
-__device__ double __nv_fabs(double __a);
-__device__ float __nv_fabsf(float __a);
-__device__ float __nv_fadd_rd(float __a, float __b);
-__device__ float __nv_fadd_rn(float __a, float __b);
-__device__ float __nv_fadd_ru(float __a, float __b);
-__device__ float __nv_fadd_rz(float __a, float __b);
-__device__ float __nv_fast_cosf(float __a);
-__device__ float __nv_fast_exp10f(float __a);
-__device__ float __nv_fast_expf(float __a);
-__device__ float __nv_fast_fdividef(float __a, float __b);
-__device__ float __nv_fast_log10f(float __a);
-__device__ float __nv_fast_log2f(float __a);
-__device__ float __nv_fast_logf(float __a);
-__device__ float __nv_fast_powf(float __a, float __b);
-__device__ void __nv_fast_sincosf(float __a, float *__sptr, float *__cptr);
-__device__ float __nv_fast_sinf(float __a);
-__device__ float __nv_fast_tanf(float __a);
-__device__ double __nv_fdim(double __a, double __b);
-__device__ float __nv_fdimf(float __a, float __b);
-__device__ float __nv_fdiv_rd(float __a, float __b);
-__device__ float __nv_fdiv_rn(float __a, float __b);
-__device__ float __nv_fdiv_ru(float __a, float __b);
-__device__ float __nv_fdiv_rz(float __a, float __b);
-__device__ int __nv_ffs(int __a);
-__device__ int __nv_ffsll(long long __a);
-__device__ int __nv_finitef(float __a);
-__device__ unsigned short __nv_float2half_rn(float __a);
-__device__ int __nv_float2int_rd(float __a);
-__device__ int __nv_float2int_rn(float __a);
-__device__ int __nv_float2int_ru(float __a);
-__device__ int __nv_float2int_rz(float __a);
-__device__ long long __nv_float2ll_rd(float __a);
-__device__ long long __nv_float2ll_rn(float __a);
-__device__ long long __nv_float2ll_ru(float __a);
-__device__ long long __nv_float2ll_rz(float __a);
-__device__ unsigned int __nv_float2uint_rd(float __a);
-__device__ unsigned int __nv_float2uint_rn(float __a);
-__device__ unsigned int __nv_float2uint_ru(float __a);
-__device__ unsigned int __nv_float2uint_rz(float __a);
-__device__ unsigned long long __nv_float2ull_rd(float __a);
-__device__ unsigned long long __nv_float2ull_rn(float __a);
-__device__ unsigned long long __nv_float2ull_ru(float __a);
-__device__ unsigned long long __nv_float2ull_rz(float __a);
-__device__ int __nv_float_as_int(float __a);
-__device__ unsigned int __nv_float_as_uint(float __a);
-__device__ double __nv_floor(double __a);
-__device__ float __nv_floorf(float __a);
-__device__ double __nv_fma(double __a, double __b, double __c);
-__device__ float __nv_fmaf(float __a, float __b, float __c);
-__device__ float __nv_fmaf_ieee_rd(float __a, float __b, float __c);
-__device__ float __nv_fmaf_ieee_rn(float __a, float __b, float __c);
-__device__ float __nv_fmaf_ieee_ru(float __a, float __b, float __c);
-__device__ float __nv_fmaf_ieee_rz(float __a, float __b, float __c);
-__device__ float __nv_fmaf_rd(float __a, float __b, float __c);
-__device__ float __nv_fmaf_rn(float __a, float __b, float __c);
-__device__ float __nv_fmaf_ru(float __a, float __b, float __c);
-__device__ float __nv_fmaf_rz(float __a, float __b, float __c);
-__device__ double __nv_fma_rd(double __a, double __b, double __c);
-__device__ double __nv_fma_rn(double __a, double __b, double __c);
-__device__ double __nv_fma_ru(double __a, double __b, double __c);
-__device__ double __nv_fma_rz(double __a, double __b, double __c);
-__device__ double __nv_fmax(double __a, double __b);
-__device__ float __nv_fmaxf(float __a, float __b);
-__device__ double __nv_fmin(double __a, double __b);
-__device__ float __nv_fminf(float __a, float __b);
-__device__ double __nv_fmod(double __a, double __b);
-__device__ float __nv_fmodf(float __a, float __b);
-__device__ float __nv_fmul_rd(float __a, float __b);
-__device__ float __nv_fmul_rn(float __a, float __b);
-__device__ float __nv_fmul_ru(float __a, float __b);
-__device__ float __nv_fmul_rz(float __a, float __b);
-__device__ float __nv_frcp_rd(float __a);
-__device__ float __nv_frcp_rn(float __a);
-__device__ float __nv_frcp_ru(float __a);
-__device__ float __nv_frcp_rz(float __a);
-__device__ double __nv_frexp(double __a, int *__b);
-__device__ float __nv_frexpf(float __a, int *__b);
-__device__ float __nv_frsqrt_rn(float __a);
-__device__ float __nv_fsqrt_rd(float __a);
-__device__ float __nv_fsqrt_rn(float __a);
-__device__ float __nv_fsqrt_ru(float __a);
-__device__ float __nv_fsqrt_rz(float __a);
-__device__ float __nv_fsub_rd(float __a, float __b);
-__device__ float __nv_fsub_rn(float __a, float __b);
-__device__ float __nv_fsub_ru(float __a, float __b);
-__device__ float __nv_fsub_rz(float __a, float __b);
-__device__ int __nv_hadd(int __a, int __b);
-__device__ float __nv_half2float(unsigned short __h);
-__device__ double __nv_hiloint2double(int __a, int __b);
-__device__ double __nv_hypot(double __a, double __b);
-__device__ float __nv_hypotf(float __a, float __b);
-__device__ int __nv_ilogb(double __a);
-__device__ int __nv_ilogbf(float __a);
-__device__ double __nv_int2double_rn(int __a);
-__device__ float __nv_int2float_rd(int __a);
-__device__ float __nv_int2float_rn(int __a);
-__device__ float __nv_int2float_ru(int __a);
-__device__ float __nv_int2float_rz(int __a);
-__device__ float __nv_int_as_float(int __a);
-__device__ int __nv_isfinited(double __a);
-__device__ int __nv_isinfd(double __a);
-__device__ int __nv_isinff(float __a);
-__device__ int __nv_isnand(double __a);
-__device__ int __nv_isnanf(float __a);
-__device__ double __nv_j0(double __a);
-__device__ float __nv_j0f(float __a);
-__device__ double __nv_j1(double __a);
-__device__ float __nv_j1f(float __a);
-__device__ float __nv_jnf(int __a, float __b);
-__device__ double __nv_jn(int __a, double __b);
-__device__ double __nv_ldexp(double __a, int __b);
-__device__ float __nv_ldexpf(float __a, int __b);
-__device__ double __nv_lgamma(double __a);
-__device__ float __nv_lgammaf(float __a);
-__device__ double __nv_ll2double_rd(long long __a);
-__device__ double __nv_ll2double_rn(long long __a);
-__device__ double __nv_ll2double_ru(long long __a);
-__device__ double __nv_ll2double_rz(long long __a);
-__device__ float __nv_ll2float_rd(long long __a);
-__device__ float __nv_ll2float_rn(long long __a);
-__device__ float __nv_ll2float_ru(long long __a);
-__device__ float __nv_ll2float_rz(long long __a);
-__device__ long long __nv_llabs(long long __a);
-__device__ long long __nv_llmax(long long __a, long long __b);
-__device__ long long __nv_llmin(long long __a, long long __b);
-__device__ long long __nv_llrint(double __a);
-__device__ long long __nv_llrintf(float __a);
-__device__ long long __nv_llround(double __a);
-__device__ long long __nv_llroundf(float __a);
-__device__ double __nv_log10(double __a);
-__device__ float __nv_log10f(float __a);
-__device__ double __nv_log1p(double __a);
-__device__ float __nv_log1pf(float __a);
-__device__ double __nv_log2(double __a);
-__device__ float __nv_log2f(float __a);
-__device__ double __nv_logb(double __a);
-__device__ float __nv_logbf(float __a);
-__device__ double __nv_log(double __a);
-__device__ float __nv_logf(float __a);
-__device__ double __nv_longlong_as_double(long long __a);
-__device__ int __nv_max(int __a, int __b);
-__device__ int __nv_min(int __a, int __b);
-__device__ double __nv_modf(double __a, double *__b);
-__device__ float __nv_modff(float __a, float *__b);
-__device__ int __nv_mul24(int __a, int __b);
-__device__ long long __nv_mul64hi(long long __a, long long __b);
-__device__ int __nv_mulhi(int __a, int __b);
-__device__ double __nv_nan(const signed char *__a);
-__device__ float __nv_nanf(const signed char *__a);
-__device__ double __nv_nearbyint(double __a);
-__device__ float __nv_nearbyintf(float __a);
-__device__ double __nv_nextafter(double __a, double __b);
-__device__ float __nv_nextafterf(float __a, float __b);
-__device__ double __nv_norm3d(double __a, double __b, double __c);
-__device__ float __nv_norm3df(float __a, float __b, float __c);
-__device__ double __nv_norm4d(double __a, double __b, double __c, double __d);
-__device__ float __nv_norm4df(float __a, float __b, float __c, float __d);
-__device__ double __nv_normcdf(double __a);
-__device__ float __nv_normcdff(float __a);
-__device__ double __nv_normcdfinv(double __a);
-__device__ float __nv_normcdfinvf(float __a);
-__device__ float __nv_normf(int __a, const float *__b);
-__device__ double __nv_norm(int __a, const double *__b);
-__device__ int __nv_popc(int __a);
-__device__ int __nv_popcll(long long __a);
-__device__ double __nv_pow(double __a, double __b);
-__device__ float __nv_powf(float __a, float __b);
-__device__ double __nv_powi(double __a, int __b);
-__device__ float __nv_powif(float __a, int __b);
-__device__ double __nv_rcbrt(double __a);
-__device__ float __nv_rcbrtf(float __a);
-__device__ double __nv_rcp64h(double __a);
-__device__ double __nv_remainder(double __a, double __b);
-__device__ float __nv_remainderf(float __a, float __b);
-__device__ double __nv_remquo(double __a, double __b, int *__c);
-__device__ float __nv_remquof(float __a, float __b, int *__c);
-__device__ int __nv_rhadd(int __a, int __b);
-__device__ double __nv_rhypot(double __a, double __b);
-__device__ float __nv_rhypotf(float __a, float __b);
-__device__ double __nv_rint(double __a);
-__device__ float __nv_rintf(float __a);
-__device__ double __nv_rnorm3d(double __a, double __b, double __c);
-__device__ float __nv_rnorm3df(float __a, float __b, float __c);
-__device__ double __nv_rnorm4d(double __a, double __b, double __c, double __d);
-__device__ float __nv_rnorm4df(float __a, float __b, float __c, float __d);
-__device__ float __nv_rnormf(int __a, const float *__b);
-__device__ double __nv_rnorm(int __a, const double *__b);
-__device__ double __nv_round(double __a);
-__device__ float __nv_roundf(float __a);
-__device__ double __nv_rsqrt(double __a);
-__device__ float __nv_rsqrtf(float __a);
-__device__ int __nv_sad(int __a, int __b, int __c);
-__device__ float __nv_saturatef(float __a);
-__device__ double __nv_scalbn(double __a, int __b);
-__device__ float __nv_scalbnf(float __a, int __b);
-__device__ int __nv_signbitd(double __a);
-__device__ int __nv_signbitf(float __a);
-__device__ void __nv_sincos(double __a, double *__b, double *__c);
-__device__ void __nv_sincosf(float __a, float *__b, float *__c);
-__device__ void __nv_sincospi(double __a, double *__b, double *__c);
-__device__ void __nv_sincospif(float __a, float *__b, float *__c);
-__device__ double __nv_sin(double __a);
-__device__ float __nv_sinf(float __a);
-__device__ double __nv_sinh(double __a);
-__device__ float __nv_sinhf(float __a);
-__device__ double __nv_sinpi(double __a);
-__device__ float __nv_sinpif(float __a);
-__device__ double __nv_sqrt(double __a);
-__device__ float __nv_sqrtf(float __a);
-__device__ double __nv_tan(double __a);
-__device__ float __nv_tanf(float __a);
-__device__ double __nv_tanh(double __a);
-__device__ float __nv_tanhf(float __a);
-__device__ double __nv_tgamma(double __a);
-__device__ float __nv_tgammaf(float __a);
-__device__ double __nv_trunc(double __a);
-__device__ float __nv_truncf(float __a);
-__device__ int __nv_uhadd(unsigned int __a, unsigned int __b);
-__device__ double __nv_uint2double_rn(unsigned int __i);
-__device__ float __nv_uint2float_rd(unsigned int __a);
-__device__ float __nv_uint2float_rn(unsigned int __a);
-__device__ float __nv_uint2float_ru(unsigned int __a);
-__device__ float __nv_uint2float_rz(unsigned int __a);
-__device__ float __nv_uint_as_float(unsigned int __a);
-__device__ double __nv_ull2double_rd(unsigned long long __a);
-__device__ double __nv_ull2double_rn(unsigned long long __a);
-__device__ double __nv_ull2double_ru(unsigned long long __a);
-__device__ double __nv_ull2double_rz(unsigned long long __a);
-__device__ float __nv_ull2float_rd(unsigned long long __a);
-__device__ float __nv_ull2float_rn(unsigned long long __a);
-__device__ float __nv_ull2float_ru(unsigned long long __a);
-__device__ float __nv_ull2float_rz(unsigned long long __a);
-__device__ unsigned long long __nv_ullmax(unsigned long long __a,
+#if defined(_OPENMP)
+#define __DEVICE__
+#elif defined(__CUDA__)
+#define __DEVICE__ __device__
+#endif
+
+__DEVICE__ int __nv_abs(int __a);
+__DEVICE__ double __nv_acos(double __a);
+__DEVICE__ float __nv_acosf(float __a);
+__DEVICE__ double __nv_acosh(double __a);
+__DEVICE__ float __nv_acoshf(float __a);
+__DEVICE__ double __nv_asin(double __a);
+__DEVICE__ float __nv_asinf(float __a);
+__DEVICE__ double __nv_asinh(double __a);
+__DEVICE__ float __nv_asinhf(float __a);
+__DEVICE__ double __nv_atan2(double __a, double __b);
+__DEVICE__ float __nv_atan2f(float __a, float __b);
+__DEVICE__ double __nv_atan(double __a);
+__DEVICE__ float __nv_atanf(float __a);
+__DEVICE__ double __nv_atanh(double __a);
+__DEVICE__ float __nv_atanhf(float __a);
+__DEVICE__ int __nv_brev(int __a);
+__DEVICE__ long long __nv_brevll(long long __a);
+__DEVICE__ int __nv_byte_perm(int __a, int __b, int __c);
+__DEVICE__ double __nv_cbrt(double __a);
+__DEVICE__ float __nv_cbrtf(float __a);
+__DEVICE__ double __nv_ceil(double __a);
+__DEVICE__ float __nv_ceilf(float __a);
+__DEVICE__ int __nv_clz(int __a);
+__DEVICE__ int __nv_clzll(long long __a);
+__DEVICE__ double __nv_copysign(double __a, double __b);
+__DEVICE__ float __nv_copysignf(float __a, float __b);
+__DEVICE__ double __nv_cos(double __a);
+__DEVICE__ float __nv_cosf(float __a);
+__DEVICE__ double __nv_cosh(double __a);
+__DEVICE__ float __nv_coshf(float __a);
+__DEVICE__ double __nv_cospi(double __a);
+__DEVICE__ float __nv_cospif(float __a);
+__DEVICE__ double __nv_cyl_bessel_i0(double __a);
+__DEVICE__ float __nv_cyl_bessel_i0f(float __a);
+__DEVICE__ double __nv_cyl_bessel_i1(double __a);
+__DEVICE__ float __nv_cyl_bessel_i1f(float __a);
+__DEVICE__ double __nv_dadd_rd(double __a, double __b);
+__DEVICE__ double __nv_dadd_rn(double __a, double __b);
+__DEVICE__ double __nv_dadd_ru(double __a, double __b);
+__DEVICE__ double __nv_dadd_rz(double __a, double __b);
+__DEVICE__ double __nv_ddiv_rd(double __a, double __b);
+__DEVICE__ double __nv_ddiv_rn(double __a, double __b);
+__DEVICE__ double __nv_ddiv_ru(double __a, double __b);
+__DEVICE__ double __nv_ddiv_rz(double __a, double __b);
+__DEVICE__ double __nv_dmul_rd(double __a, double __b);
+__DEVICE__ double __nv_dmul_rn(double __a, double __b);
+__DEVICE__ double __nv_dmul_ru(double __a, double __b);
+__DEVICE__ double __nv_dmul_rz(double __a, double __b);
+__DEVICE__ float __nv_double2float_rd(double __a);
+__DEVICE__ float __nv_double2float_rn(double __a);
+__DEVICE__ float __nv_double2float_ru(double __a);
+__DEVICE__ float __nv_double2float_rz(double __a);
+__DEVICE__ int __nv_double2hiint(double __a);
+__DEVICE__ int __nv_double2int_rd(double __a);
+__DEVICE__ int __nv_double2int_rn(double __a);
+__DEVICE__ int __nv_double2int_ru(double __a);
+__DEVICE__ int __nv_double2int_rz(double __a);
+__DEVICE__ long long __nv_double2ll_rd(double __a);
+__DEVICE__ long long __nv_double2ll_rn(double __a);
+__DEVICE__ long long __nv_double2ll_ru(double __a);
+__DEVICE__ long long __nv_double2ll_rz(double __a);
+__DEVICE__ int __nv_double2loint(double __a);
+__DEVICE__ unsigned int __nv_double2uint_rd(double __a);
+__DEVICE__ unsigned int __nv_double2uint_rn(double __a);
+__DEVICE__ unsigned int __nv_double2uint_ru(double __a);
+__DEVICE__ unsigned int __nv_double2uint_rz(double __a);
+__DEVICE__ unsigned long long __nv_double2ull_rd(double __a);
+__DEVICE__ unsigned long long __nv_double2ull_rn(double __a);
+__DEVICE__ unsigned long long __nv_double2ull_ru(double __a);
+__DEVICE__ unsigned long long __nv_double2ull_rz(double __a);
+__DEVICE__ unsigned long long __nv_double_as_longlong(double __a);
+__DEVICE__ double __nv_drcp_rd(double __a);
+__DEVICE__ double __nv_drcp_rn(double __a);
+__DEVICE__ double __nv_drcp_ru(double __a);
+__DEVICE__ double __nv_drcp_rz(double __a);
+__DEVICE__ double __nv_dsqrt_rd(double __a);
+__DEVICE__ double __nv_dsqrt_rn(double __a);
+__DEVICE__ double __nv_dsqrt_ru(double __a);
+__DEVICE__ double __nv_dsqrt_rz(double __a);
+__DEVICE__ double __nv_dsub_rd(double __a, double __b);
+__DEVICE__ double __nv_dsub_rn(double __a, double __b);
+__DEVICE__ double __nv_dsub_ru(double __a, double __b);
+__DEVICE__ double __nv_dsub_rz(double __a, double __b);
+__DEVICE__ double __nv_erfc(double __a);
+__DEVICE__ float __nv_erfcf(float __a);
+__DEVICE__ double __nv_erfcinv(double __a);
+__DEVICE__ float __nv_erfcinvf(float __a);
+__DEVICE__ double __nv_erfcx(double __a);
+__DEVICE__ float __nv_erfcxf(float __a);
+__DEVICE__ double __nv_erf(double __a);
+__DEVICE__ float __nv_erff(float __a);
+__DEVICE__ double __nv_erfinv(double __a);
+__DEVICE__ float __nv_erfinvf(float __a);
+__DEVICE__ double __nv_exp10(double __a);
+__DEVICE__ float __nv_exp10f(float __a);
+__DEVICE__ double __nv_exp2(double __a);
+__DEVICE__ float __nv_exp2f(float __a);
+__DEVICE__ double __nv_exp(double __a);
+__DEVICE__ float __nv_expf(float __a);
+__DEVICE__ double __nv_expm1(double __a);
+__DEVICE__ float __nv_expm1f(float __a);
+__DEVICE__ double __nv_fabs(double __a);
+__DEVICE__ float __nv_fabsf(float __a);
+__DEVICE__ float __nv_fadd_rd(float __a, float __b);
+__DEVICE__ float __nv_fadd_rn(float __a, float __b);
+__DEVICE__ float __nv_fadd_ru(float __a, float __b);
+__DEVICE__ float __nv_fadd_rz(float __a, float __b);
+__DEVICE__ float __nv_fast_cosf(float __a);
+__DEVICE__ float __nv_fast_exp10f(float __a);
+__DEVICE__ float __nv_fast_expf(float __a);
+__DEVICE__ float __nv_fast_fdividef(float __a, float __b);
+__DEVICE__ float __nv_fast_log10f(float __a);
+__DEVICE__ float __nv_fast_log2f(float __a);
+__DEVICE__ float __nv_fast_logf(float __a);
+__DEVICE__ float __nv_fast_powf(float __a, float __b);
+__DEVICE__ void __nv_fast_sincosf(float __a, float *__s, float *__c);
+__DEVICE__ float __nv_fast_sinf(float __a);
+__DEVICE__ float __nv_fast_tanf(float __a);
+__DEVICE__ double __nv_fdim(double __a, double __b);
+__DEVICE__ float __nv_fdimf(float __a, float __b);
+__DEVICE__ float __nv_fdiv_rd(float __a, float __b);
+__DEVICE__ float __nv_fdiv_rn(float __a, float __b);
+__DEVICE__ float __nv_fdiv_ru(float __a, float __b);
+__DEVICE__ float __nv_fdiv_rz(float __a, float __b);
+__DEVICE__ int __nv_ffs(int __a);
+__DEVICE__ int __nv_ffsll(long long __a);
+__DEVICE__ int __nv_finitef(float __a);
+__DEVICE__ unsigned short __nv_float2half_rn(float __a);
+__DEVICE__ int __nv_float2int_rd(float __a);
+__DEVICE__ int __nv_float2int_rn(float __a);
+__DEVICE__ int __nv_float2int_ru(float __a);
+__DEVICE__ int __nv_float2int_rz(float __a);
+__DEVICE__ long long __nv_float2ll_rd(float __a);
+__DEVICE__ long long __nv_float2ll_rn(float __a);
+__DEVICE__ long long __nv_float2ll_ru(float __a);
+__DEVICE__ long long __nv_float2ll_rz(float __a);
+__DEVICE__ unsigned int __nv_float2uint_rd(float __a);
+__DEVICE__ unsigned int __nv_float2uint_rn(float __a);
+__DEVICE__ unsigned int __nv_float2uint_ru(float __a);
+__DEVICE__ unsigned int __nv_float2uint_rz(float __a);
+__DEVICE__ unsigned long long __nv_float2ull_rd(float __a);
+__DEVICE__ unsigned long long __nv_float2ull_rn(float __a);
+__DEVICE__ unsigned long long __nv_float2ull_ru(float __a);
+__DEVICE__ unsigned long long __nv_float2ull_rz(float __a);
+__DEVICE__ int __nv_float_as_int(float __a);
+__DEVICE__ unsigned int __nv_float_as_uint(float __a);
+__DEVICE__ double __nv_floor(double __a);
+__DEVICE__ float __nv_floorf(float __a);
+__DEVICE__ double __nv_fma(double __a, double __b, double __c);
+__DEVICE__ float __nv_fmaf(float __a, float __b, float __c);
+__DEVICE__ float __nv_fmaf_ieee_rd(float __a, float __b, float __c);
+__DEVICE__ float __nv_fmaf_ieee_rn(float __a, float __b, float __c);
+__DEVICE__ float __nv_fmaf_ieee_ru(float __a, float __b, float __c);
+__DEVICE__ float __nv_fmaf_ieee_rz(float __a, float __b, float __c);
+__DEVICE__ float __nv_fmaf_rd(float __a, float __b, float __c);
+__DEVICE__ float __nv_fmaf_rn(float __a, float __b, float __c);
+__DEVICE__ float __nv_fmaf_ru(float __a, float __b, float __c);
+__DEVICE__ float __nv_fmaf_rz(float __a, float __b, float __c);
+__DEVICE__ double __nv_fma_rd(double __a, double __b, double __c);
+__DEVICE__ double __nv_fma_rn(double __a, double __b, double __c);
+__DEVICE__ double __nv_fma_ru(double __a, double __b, double __c);
+__DEVICE__ double __nv_fma_rz(double __a, double __b, double __c);
+__DEVICE__ double __nv_fmax(double __a, double __b);
+__DEVICE__ float __nv_fmaxf(float __a, float __b);
+__DEVICE__ double __nv_fmin(double __a, double __b);
+__DEVICE__ float __nv_fminf(float __a, float __b);
+__DEVICE__ double __nv_fmod(double __a, double __b);
+__DEVICE__ float __nv_fmodf(float __a, float __b);
+__DEVICE__ float __nv_fmul_rd(float __a, float __b);
+__DEVICE__ float __nv_fmul_rn(float __a, float __b);
+__DEVICE__ float __nv_fmul_ru(float __a, float __b);
+__DEVICE__ float __nv_fmul_rz(float __a, float __b);
+__DEVICE__ float __nv_frcp_rd(float __a);
+__DEVICE__ float __nv_frcp_rn(float __a);
+__DEVICE__ float __nv_frcp_ru(float __a);
+__DEVICE__ float __nv_frcp_rz(float __a);
+__DEVICE__ double __nv_frexp(double __a, int *__b);
+__DEVICE__ float __nv_frexpf(float __a, int *__b);
+__DEVICE__ float __nv_frsqrt_rn(float __a);
+__DEVICE__ float __nv_fsqrt_rd(float __a);
+__DEVICE__ float __nv_fsqrt_rn(float __a);
+__DEVICE__ float __nv_fsqrt_ru(float __a);
+__DEVICE__ float __nv_fsqrt_rz(float __a);
+__DEVICE__ float __nv_fsub_rd(float __a, float __b);
+__DEVICE__ float __nv_fsub_rn(float __a, float __b);
+__DEVICE__ float __nv_fsub_ru(float __a, float __b);
+__DEVICE__ float __nv_fsub_rz(float __a, float __b);
+__DEVICE__ int __nv_hadd(int __a, int __b);
+__DEVICE__ float __nv_half2float(unsigned short __h);
+__DEVICE__ double __nv_hiloint2double(int __a, int __b);
+__DEVICE__ double __nv_hypot(double __a, double __b);
+__DEVICE__ float __nv_hypotf(float __a, float __b);
+__DEVICE__ int __nv_ilogb(double __a);
+__DEVICE__ int __nv_ilogbf(float __a);
+__DEVICE__ double __nv_int2double_rn(int __a);
+__DEVICE__ float __nv_int2float_rd(int __a);
+__DEVICE__ float __nv_int2float_rn(int __a);
+__DEVICE__ float __nv_int2float_ru(int __a);
+__DEVICE__ float __nv_int2float_rz(int __a);
+__DEVICE__ float __nv_int_as_float(int __a);
+__DEVICE__ int __nv_isfinited(double __a);
+__DEVICE__ int __nv_isinfd(double __a);
+__DEVICE__ int __nv_isinff(float __a);
+__DEVICE__ int __nv_isnand(double __a);
+__DEVICE__ int __nv_isnanf(float __a);
+__DEVICE__ double __nv_j0(double __a);
+__DEVICE__ float __nv_j0f(float __a);
+__DEVICE__ double __nv_j1(double __a);
+__DEVICE__ float __nv_j1f(float __a);
+__DEVICE__ float __nv_jnf(int __a, float __b);
+__DEVICE__ double __nv_jn(int __a, double __b);
+__DEVICE__ double __nv_ldexp(double __a, int __b);
+__DEVICE__ float __nv_ldexpf(float __a, int __b);
+__DEVICE__ double __nv_lgamma(double __a);
+__DEVICE__ float __nv_lgammaf(float __a);
+__DEVICE__ double __nv_ll2double_rd(long long __a);
+__DEVICE__ double __nv_ll2double_rn(long long __a);
+__DEVICE__ double __nv_ll2double_ru(long long __a);
+__DEVICE__ double __nv_ll2double_rz(long long __a);
+__DEVICE__ float __nv_ll2float_rd(long long __a);
+__DEVICE__ float __nv_ll2float_rn(long long __a);
+__DEVICE__ float __nv_ll2float_ru(long long __a);
+__DEVICE__ float __nv_ll2float_rz(long long __a);
+__DEVICE__ long long __nv_llabs(long long __a);
+__DEVICE__ long long __nv_llmax(long long __a, long long __b);
+__DEVICE__ long long __nv_llmin(long long __a, long long __b);
+__DEVICE__ long long __nv_llrint(double __a);
+__DEVICE__ long long __nv_llrintf(float __a);
+__DEVICE__ long long __nv_llround(double __a);
+__DEVICE__ long long __nv_llroundf(float __a);
+__DEVICE__ double __nv_log10(double __a);
+__DEVICE__ float __nv_log10f(float __a);
+__DEVICE__ double __nv_log1p(double __a);
+__DEVICE__ float __nv_log1pf(float __a);
+__DEVICE__ double __nv_log2(double __a);
+__DEVICE__ float __nv_log2f(float __a);
+__DEVICE__ double __nv_logb(double __a);
+__DEVICE__ float __nv_logbf(float __a);
+__DEVICE__ double __nv_log(double __a);
+__DEVICE__ float __nv_logf(float __a);
+__DEVICE__ double __nv_longlong_as_double(long long __a);
+__DEVICE__ int __nv_max(int __a, int __b);
+__DEVICE__ int __nv_min(int __a, int __b);
+__DEVICE__ double __nv_modf(double __a, double *__b);
+__DEVICE__ float __nv_modff(float __a, float *__b);
+__DEVICE__ int __nv_mul24(int __a, int __b);
+__DEVICE__ long long __nv_mul64hi(long long __a, long long __b);
+__DEVICE__ int __nv_mulhi(int __a, int __b);
+__DEVICE__ double __nv_nan(const signed char *__a);
+__DEVICE__ float __nv_nanf(const signed char *__a);
+__DEVICE__ double __nv_nearbyint(double __a);
+__DEVICE__ float __nv_nearbyintf(float __a);
+__DEVICE__ double __nv_nextafter(double __a, double __b);
+__DEVICE__ float __nv_nextafterf(float __a, float __b);
+__DEVICE__ double __nv_norm3d(double __a, double __b, double __c);
+__DEVICE__ float __nv_norm3df(float __a, float __b, float __c);
+__DEVICE__ double __nv_norm4d(double __a, double __b, double __c, double __d);
+__DEVICE__ float __nv_norm4df(float __a, float __b, float __c, float __d);
+__DEVICE__ double __nv_normcdf(double __a);
+__DEVICE__ float __nv_normcdff(float __a);
+__DEVICE__ double __nv_normcdfinv(double __a);
+__DEVICE__ float __nv_normcdfinvf(float __a);
+__DEVICE__ float __nv_normf(int __a, const float *__b);
+__DEVICE__ double __nv_norm(int __a, const double *__b);
+__DEVICE__ int __nv_popc(int __a);
+__DEVICE__ int __nv_popcll(long long __a);
+__DEVICE__ double __nv_pow(double __a, double __b);
+__DEVICE__ float __nv_powf(float __a, float __b);
+__DEVICE__ double __nv_powi(double __a, int __b);
+__DEVICE__ float __nv_powif(float __a, int __b);
+__DEVICE__ double __nv_rcbrt(double __a);
+__DEVICE__ float __nv_rcbrtf(float __a);
+__DEVICE__ double __nv_rcp64h(double __a);
+__DEVICE__ double __nv_remainder(double __a, double __b);
+__DEVICE__ float __nv_remainderf(float __a, float __b);
+__DEVICE__ double __nv_remquo(double __a, double __b, int *__c);
+__DEVICE__ float __nv_remquof(float __a, float __b, int *__c);
+__DEVICE__ int __nv_rhadd(int __a, int __b);
+__DEVICE__ double __nv_rhypot(double __a, double __b);
+__DEVICE__ float __nv_rhypotf(float __a, float __b);
+__DEVICE__ double __nv_rint(double __a);
+__DEVICE__ float __nv_rintf(float __a);
+__DEVICE__ double __nv_rnorm3d(double __a, double __b, double __c);
+__DEVICE__ float __nv_rnorm3df(float __a, float __b, float __c);
+__DEVICE__ double __nv_rnorm4d(double __a, double __b, double __c, double __d);
+__DEVICE__ float __nv_rnorm4df(float __a, float __b, float __c, float __d);
+__DEVICE__ float __nv_rnormf(int __a, const float *__b);
+__DEVICE__ double __nv_rnorm(int __a, const double *__b);
+__DEVICE__ double __nv_round(double __a);
+__DEVICE__ float __nv_roundf(float __a);
+__DEVICE__ double __nv_rsqrt(double __a);
+__DEVICE__ float __nv_rsqrtf(float __a);
+__DEVICE__ int __nv_sad(int __a, int __b, int __c);
+__DEVICE__ float __nv_saturatef(float __a);
+__DEVICE__ double __nv_scalbn(double __a, int __b);
+__DEVICE__ float __nv_scalbnf(float __a, int __b);
+__DEVICE__ int __nv_signbitd(double __a);
+__DEVICE__ int __nv_signbitf(float __a);
+__DEVICE__ void __nv_sincos(double __a, double *__b, double *__c);
+__DEVICE__ void __nv_sincosf(float __a, float *__b, float *__c);
+__DEVICE__ void __nv_sincospi(double __a, double *__b, double *__c);
+__DEVICE__ void __nv_sincospif(float __a, float *__b, float *__c);
+__DEVICE__ double __nv_sin(double __a);
+__DEVICE__ float __nv_sinf(float __a);
+__DEVICE__ double __nv_sinh(double __a);
+__DEVICE__ float __nv_sinhf(float __a);
+__DEVICE__ double __nv_sinpi(double __a);
+__DEVICE__ float __nv_sinpif(float __a);
+__DEVICE__ double __nv_sqrt(double __a);
+__DEVICE__ float __nv_sqrtf(float __a);
+__DEVICE__ double __nv_tan(double __a);
+__DEVICE__ float __nv_tanf(float __a);
+__DEVICE__ double __nv_tanh(double __a);
+__DEVICE__ float __nv_tanhf(float __a);
+__DEVICE__ double __nv_tgamma(double __a);
+__DEVICE__ float __nv_tgammaf(float __a);
+__DEVICE__ double __nv_trunc(double __a);
+__DEVICE__ float __nv_truncf(float __a);
+__DEVICE__ int __nv_uhadd(unsigned int __a, unsigned int __b);
+__DEVICE__ double __nv_uint2double_rn(unsigned int __i);
+__DEVICE__ float __nv_uint2float_rd(unsigned int __a);
+__DEVICE__ float __nv_uint2float_rn(unsigned int __a);
+__DEVICE__ float __nv_uint2float_ru(unsigned int __a);
+__DEVICE__ float __nv_uint2float_rz(unsigned int __a);
+__DEVICE__ float __nv_uint_as_float(unsigned int __a);
+__DEVICE__ double __nv_ull2double_rd(unsigned long long __a);
+__DEVICE__ double __nv_ull2double_rn(unsigned long long __a);
+__DEVICE__ double __nv_ull2double_ru(unsigned long long __a);
+__DEVICE__ double __nv_ull2double_rz(unsigned long long __a);
+__DEVICE__ float __nv_ull2float_rd(unsigned long long __a);
+__DEVICE__ float __nv_ull2float_rn(unsigned long long __a);
+__DEVICE__ float __nv_ull2float_ru(unsigned long long __a);
+__DEVICE__ float __nv_ull2float_rz(unsigned long long __a);
+__DEVICE__ unsigned long long __nv_ullmax(unsigned long long __a,
                                          unsigned long long __b);
-__device__ unsigned long long __nv_ullmin(unsigned long long __a,
+__DEVICE__ unsigned long long __nv_ullmin(unsigned long long __a,
                                          unsigned long long __b);
-__device__ unsigned int __nv_umax(unsigned int __a, unsigned int __b);
-__device__ unsigned int __nv_umin(unsigned int __a, unsigned int __b);
-__device__ unsigned int __nv_umul24(unsigned int __a, unsigned int __b);
-__device__ unsigned long long __nv_umul64hi(unsigned long long __a,
+__DEVICE__ unsigned int __nv_umax(unsigned int __a, unsigned int __b);
+__DEVICE__ unsigned int __nv_umin(unsigned int __a, unsigned int __b);
+__DEVICE__ unsigned int __nv_umul24(unsigned int __a, unsigned int __b);
+__DEVICE__ unsigned long long __nv_umul64hi(unsigned long long __a,
                                            unsigned long long __b);
-__device__ unsigned int __nv_umulhi(unsigned int __a, unsigned int __b);
-__device__ unsigned int __nv_urhadd(unsigned int __a, unsigned int __b);
-__device__ unsigned int __nv_usad(unsigned int __a, unsigned int __b,
+__DEVICE__ unsigned int __nv_umulhi(unsigned int __a, unsigned int __b);
+__DEVICE__ unsigned int __nv_urhadd(unsigned int __a, unsigned int __b);
+__DEVICE__ unsigned int __nv_usad(unsigned int __a, unsigned int __b,
                                  unsigned int __c);
 #if CUDA_VERSION >= 9000 && CUDA_VERSION < 9020
-__device__ int __nv_vabs2(int __a);
-__device__ int __nv_vabs4(int __a);
-__device__ int __nv_vabsdiffs2(int __a, int __b);
-__device__ int __nv_vabsdiffs4(int __a, int __b);
-__device__ int __nv_vabsdiffu2(int __a, int __b);
-__device__ int __nv_vabsdiffu4(int __a, int __b);
-__device__ int __nv_vabsss2(int __a);
-__device__ int __nv_vabsss4(int __a);
-__device__ int __nv_vadd2(int __a, int __b);
-__device__ int __nv_vadd4(int __a, int __b);
-__device__ int __nv_vaddss2(int __a, int __b);
-__device__ int __nv_vaddss4(int __a, int __b);
-__device__ int __nv_vaddus2(int __a, int __b);
-__device__ int __nv_vaddus4(int __a, int __b);
-__device__ int __nv_vavgs2(int __a, int __b);
-__device__ int __nv_vavgs4(int __a, int __b);
-__device__ int __nv_vavgu2(int __a, int __b);
-__device__ int __nv_vavgu4(int __a, int __b);
-__device__ int __nv_vcmpeq2(int __a, int __b);
-__device__ int __nv_vcmpeq4(int __a, int __b);
-__device__ int __nv_vcmpges2(int __a, int __b);
-__device__ int __nv_vcmpges4(int __a, int __b);
-__device__ int __nv_vcmpgeu2(int __a, int __b);
-__device__ int __nv_vcmpgeu4(int __a, int __b);
-__device__ int __nv_vcmpgts2(int __a, int __b);
-__device__ int __nv_vcmpgts4(int __a, int __b);
-__device__ int __nv_vcmpgtu2(int __a, int __b);
-__device__ int __nv_vcmpgtu4(int __a, int __b);
-__device__ int __nv_vcmples2(int __a, int __b);
-__device__ int __nv_vcmples4(int __a, int __b);
-__device__ int __nv_vcmpleu2(int __a, int __b);
-__device__ int __nv_vcmpleu4(int __a, int __b);
-__device__ int __nv_vcmplts2(int __a, int __b);
-__device__ int __nv_vcmplts4(int __a, int __b);
-__device__ int __nv_vcmpltu2(int __a, int __b);
-__device__ int __nv_vcmpltu4(int __a, int __b);
-__device__ int __nv_vcmpne2(int __a, int __b);
-__device__ int __nv_vcmpne4(int __a, int __b);
-__device__ int __nv_vhaddu2(int __a, int __b);
-__device__ int __nv_vhaddu4(int __a, int __b);
-__device__ int __nv_vmaxs2(int __a, int __b);
-__device__ int __nv_vmaxs4(int __a, int __b);
-__device__ int __nv_vmaxu2(int __a, int __b);
-__device__ int __nv_vmaxu4(int __a, int __b);
-__device__ int __nv_vmins2(int __a, int __b);
-__device__ int __nv_vmins4(int __a, int __b);
-__device__ int __nv_vminu2(int __a, int __b);
-__device__ int __nv_vminu4(int __a, int __b);
-__device__ int __nv_vneg2(int __a);
-__device__ int __nv_vneg4(int __a);
-__device__ int __nv_vnegss2(int __a);
-__device__ int __nv_vnegss4(int __a);
-__device__ int __nv_vsads2(int __a, int __b);
-__device__ int __nv_vsads4(int __a, int __b);
-__device__ int __nv_vsadu2(int __a, int __b);
-__device__ int __nv_vsadu4(int __a, int __b);
-__device__ int __nv_vseteq2(int __a, int __b);
-__device__ int __nv_vseteq4(int __a, int __b);
-__device__ int __nv_vsetges2(int __a, int __b);
-__device__ int __nv_vsetges4(int __a, int __b);
-__device__ int __nv_vsetgeu2(int __a, int __b);
-__device__ int __nv_vsetgeu4(int __a, int __b);
-__device__ int __nv_vsetgts2(int __a, int __b);
-__device__ int __nv_vsetgts4(int __a, int __b);
-__device__ int __nv_vsetgtu2(int __a, int __b);
-__device__ int __nv_vsetgtu4(int __a, int __b);
-__device__ int __nv_vsetles2(int __a, int __b);
-__device__ int __nv_vsetles4(int __a, int __b);
-__device__ int __nv_vsetleu2(int __a, int __b);
-__device__ int __nv_vsetleu4(int __a, int __b);
-__device__ int __nv_vsetlts2(int __a, int __b);
-__device__ int __nv_vsetlts4(int __a, int __b);
-__device__ int __nv_vsetltu2(int __a, int __b);
-__device__ int __nv_vsetltu4(int __a, int __b);
-__device__ int __nv_vsetne2(int __a, int __b);
-__device__ int __nv_vsetne4(int __a, int __b);
-__device__ int __nv_vsub2(int __a, int __b);
-__device__ int __nv_vsub4(int __a, int __b);
-__device__ int __nv_vsubss2(int __a, int __b);
-__device__ int __nv_vsubss4(int __a, int __b);
-__device__ int __nv_vsubus2(int __a, int __b);
-__device__ int __nv_vsubus4(int __a, int __b);
+__DEVICE__ int __nv_vabs2(int __a);
+__DEVICE__ int __nv_vabs4(int __a);
+__DEVICE__ int __nv_vabsdiffs2(int __a, int __b);
+__DEVICE__ int __nv_vabsdiffs4(int __a, int __b);
+__DEVICE__ int __nv_vabsdiffu2(int __a, int __b);
+__DEVICE__ int __nv_vabsdiffu4(int __a, int __b);
+__DEVICE__ int __nv_vabsss2(int __a);
+__DEVICE__ int __nv_vabsss4(int __a);
+__DEVICE__ int __nv_vadd2(int __a, int __b);
+__DEVICE__ int __nv_vadd4(int __a, int __b);
+__DEVICE__ int __nv_vaddss2(int __a, int __b);
+__DEVICE__ int __nv_vaddss4(int __a, int __b);
+__DEVICE__ int __nv_vaddus2(int __a, int __b);
+__DEVICE__ int __nv_vaddus4(int __a, int __b);
+__DEVICE__ int __nv_vavgs2(int __a, int __b);
+__DEVICE__ int __nv_vavgs4(int __a, int __b);
+__DEVICE__ int __nv_vavgu2(int __a, int __b);
+__DEVICE__ int __nv_vavgu4(int __a, int __b);
+__DEVICE__ int __nv_vcmpeq2(int __a, int __b);
+__DEVICE__ int __nv_vcmpeq4(int __a, int __b);
+__DEVICE__ int __nv_vcmpges2(int __a, int __b);
+__DEVICE__ int __nv_vcmpges4(int __a, int __b);
+__DEVICE__ int __nv_vcmpgeu2(int __a, int __b);
+__DEVICE__ int __nv_vcmpgeu4(int __a, int __b);
+__DEVICE__ int __nv_vcmpgts2(int __a, int __b);
+__DEVICE__ int __nv_vcmpgts4(int __a, int __b);
+__DEVICE__ int __nv_vcmpgtu2(int __a, int __b);
+__DEVICE__ int __nv_vcmpgtu4(int __a, int __b);
+__DEVICE__ int __nv_vcmples2(int __a, int __b);
+__DEVICE__ int __nv_vcmples4(int __a, int __b);
+__DEVICE__ int __nv_vcmpleu2(int __a, int __b);
+__DEVICE__ int __nv_vcmpleu4(int __a, int __b);
+__DEVICE__ int __nv_vcmplts2(int __a, int __b);
+__DEVICE__ int __nv_vcmplts4(int __a, int __b);
+__DEVICE__ int __nv_vcmpltu2(int __a, int __b);
+__DEVICE__ int __nv_vcmpltu4(int __a, int __b);
+__DEVICE__ int __nv_vcmpne2(int __a, int __b);
+__DEVICE__ int __nv_vcmpne4(int __a, int __b);
+__DEVICE__ int __nv_vhaddu2(int __a, int __b);
+__DEVICE__ int __nv_vhaddu4(int __a, int __b);
+__DEVICE__ int __nv_vmaxs2(int __a, int __b);
+__DEVICE__ int __nv_vmaxs4(int __a, int __b);
+__DEVICE__ int __nv_vmaxu2(int __a, int __b);
+__DEVICE__ int __nv_vmaxu4(int __a, int __b);
+__DEVICE__ int __nv_vmins2(int __a, int __b);
+__DEVICE__ int __nv_vmins4(int __a, int __b);
+__DEVICE__ int __nv_vminu2(int __a, int __b);
+__DEVICE__ int __nv_vminu4(int __a, int __b);
+__DEVICE__ int __nv_vneg2(int __a);
+__DEVICE__ int __nv_vneg4(int __a);
+__DEVICE__ int __nv_vnegss2(int __a);
+__DEVICE__ int __nv_vnegss4(int __a);
+__DEVICE__ int __nv_vsads2(int __a, int __b);
+__DEVICE__ int __nv_vsads4(int __a, int __b);
+__DEVICE__ int __nv_vsadu2(int __a, int __b);
+__DEVICE__ int __nv_vsadu4(int __a, int __b);
+__DEVICE__ int __nv_vseteq2(int __a, int __b);
+__DEVICE__ int __nv_vseteq4(int __a, int __b);
+__DEVICE__ int __nv_vsetges2(int __a, int __b);
+__DEVICE__ int __nv_vsetges4(int __a, int __b);
+__DEVICE__ int __nv_vsetgeu2(int __a, int __b);
+__DEVICE__ int __nv_vsetgeu4(int __a, int __b);
+__DEVICE__ int __nv_vsetgts2(int __a, int __b);
+__DEVICE__ int __nv_vsetgts4(int __a, int __b);
+__DEVICE__ int __nv_vsetgtu2(int __a, int __b);
+__DEVICE__ int __nv_vsetgtu4(int __a, int __b);
+__DEVICE__ int __nv_vsetles2(int __a, int __b);
+__DEVICE__ int __nv_vsetles4(int __a, int __b);
+__DEVICE__ int __nv_vsetleu2(int __a, int __b);
+__DEVICE__ int __nv_vsetleu4(int __a, int __b);
+__DEVICE__ int __nv_vsetlts2(int __a, int __b);
+__DEVICE__ int __nv_vsetlts4(int __a, int __b);
+__DEVICE__ int __nv_vsetltu2(int __a, int __b);
+__DEVICE__ int __nv_vsetltu4(int __a, int __b);
+__DEVICE__ int __nv_vsetne2(int __a, int __b);
+__DEVICE__ int __nv_vsetne4(int __a, int __b);
+__DEVICE__ int __nv_vsub2(int __a, int __b);
+__DEVICE__ int __nv_vsub4(int __a, int __b);
+__DEVICE__ int __nv_vsubss2(int __a, int __b);
+__DEVICE__ int __nv_vsubss4(int __a, int __b);
+__DEVICE__ int __nv_vsubus2(int __a, int __b);
+__DEVICE__ int __nv_vsubus4(int __a, int __b);
 #endif  // CUDA_VERSION
-__device__ double __nv_y0(double __a);
-__device__ float __nv_y0f(float __a);
-__device__ double __nv_y1(double __a);
-__device__ float __nv_y1f(float __a);
-__device__ float __nv_ynf(int __a, float __b);
-__device__ double __nv_yn(int __a, double __b);
+__DEVICE__ double __nv_y0(double __a);
+__DEVICE__ float __nv_y0f(float __a);
+__DEVICE__ double __nv_y1(double __a);
+__DEVICE__ float __nv_y1f(float __a);
+__DEVICE__ float __nv_ynf(int __a, float __b);
+__DEVICE__ double __nv_yn(int __a, double __b);
+#if defined(__cplusplus)
 } // extern "C"
+#endif
 #endif // __CLANG_CUDA_LIBDEVICE_DECLARES_H__
@@ -1,22 +1,8 @@
 /*===- __clang_math_forward_declares.h - Prototypes of __device__ math fns --===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -34,14 +20,37 @@
 // would preclude the use of our own __device__ overloads for these functions.

 #pragma push_macro("__DEVICE__")
+#ifdef _OPENMP
+#define __DEVICE__ static __inline__ __attribute__((always_inline))
+#else
 #define __DEVICE__                                                             \
  static __inline__ __attribute__((always_inline)) __attribute__((device))
+#endif

-__DEVICE__ double abs(double);
-__DEVICE__ float abs(float);
-__DEVICE__ int abs(int);
+// For C++ 17 we need to include noexcept attribute to be compatible
+// with the header-defined version. This may be removed once
+// variant is supported.
+#if defined(_OPENMP) && defined(__cplusplus) && __cplusplus >= 201703L
+#define __NOEXCEPT noexcept
+#else
+#define __NOEXCEPT
+#endif
+
+#if !(defined(_OPENMP) && defined(__cplusplus))
 __DEVICE__ long abs(long);
 __DEVICE__ long long abs(long long);
+__DEVICE__ double abs(double);
+__DEVICE__ float abs(float);
+#endif
+// While providing the CUDA declarations and definitions for math functions,
+// we may manually define additional functions.
+// TODO: Once variant is supported the additional functions will have
+// to be removed.
+#if defined(_OPENMP) && defined(__cplusplus)
+__DEVICE__ const double abs(const double);
+__DEVICE__ const float abs(const float);
+#endif
+__DEVICE__ int abs(int) __NOEXCEPT;
 __DEVICE__ double acos(double);
 __DEVICE__ float acos(float);
 __DEVICE__ double acosh(double);
@@ -76,8 +85,8 @@ __DEVICE__ double exp(double);
 __DEVICE__ float exp(float);
 __DEVICE__ double expm1(double);
 __DEVICE__ float expm1(float);
-__DEVICE__ double fabs(double);
-__DEVICE__ float fabs(float);
+__DEVICE__ double fabs(double) __NOEXCEPT;
+__DEVICE__ float fabs(float) __NOEXCEPT;
 __DEVICE__ double fdim(double, double);
 __DEVICE__ float fdim(float, float);
 __DEVICE__ double floor(double);
@@ -98,12 +107,18 @@ __DEVICE__ double hypot(double, double);
 __DEVICE__ float hypot(float, float);
 __DEVICE__ int ilogb(double);
 __DEVICE__ int ilogb(float);
+#ifdef _MSC_VER
+__DEVICE__ bool isfinite(long double);
+#endif
 __DEVICE__ bool isfinite(double);
 __DEVICE__ bool isfinite(float);
 __DEVICE__ bool isgreater(double, double);
 __DEVICE__ bool isgreaterequal(double, double);
 __DEVICE__ bool isgreaterequal(float, float);
 __DEVICE__ bool isgreater(float, float);
+#ifdef _MSC_VER
+__DEVICE__ bool isinf(long double);
+#endif
 __DEVICE__ bool isinf(double);
 __DEVICE__ bool isinf(float);
 __DEVICE__ bool isless(double, double);
@@ -112,18 +127,21 @@ __DEVICE__ bool islessequal(float, float);
 __DEVICE__ bool isless(float, float);
 __DEVICE__ bool islessgreater(double, double);
 __DEVICE__ bool islessgreater(float, float);
+#ifdef _MSC_VER
+__DEVICE__ bool isnan(long double);
+#endif
 __DEVICE__ bool isnan(double);
 __DEVICE__ bool isnan(float);
 __DEVICE__ bool isnormal(double);
 __DEVICE__ bool isnormal(float);
 __DEVICE__ bool isunordered(double, double);
 __DEVICE__ bool isunordered(float, float);
-__DEVICE__ long labs(long);
+__DEVICE__ long labs(long) __NOEXCEPT;
 __DEVICE__ double ldexp(double, int);
 __DEVICE__ float ldexp(float, int);
 __DEVICE__ double lgamma(double);
 __DEVICE__ float lgamma(float);
-__DEVICE__ long long llabs(long long);
+__DEVICE__ long long llabs(long long) __NOEXCEPT;
 __DEVICE__ long long llrint(double);
 __DEVICE__ long long llrint(float);
 __DEVICE__ double log10(double);
@@ -134,6 +152,9 @@ __DEVICE__ double log2(double);
 __DEVICE__ float log2(float);
 __DEVICE__ double logb(double);
 __DEVICE__ float logb(float);
+#if defined(_OPENMP) && defined(__cplusplus)
+__DEVICE__ long double log(long double);
+#endif
 __DEVICE__ double log(double);
 __DEVICE__ float log(float);
 __DEVICE__ long lrint(double);
@@ -281,6 +302,7 @@ _GLIBCXX_END_NAMESPACE_VERSION
 } // namespace std
 #endif

+#undef __NOEXCEPT
 #pragma pop_macro("__DEVICE__")

 #endif
@@ -1,22 +1,8 @@
 /*===---- __clang_cuda_runtime_wrapper.h - CUDA runtime support -------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -62,7 +48,7 @@
 #include "cuda.h"
 #if !defined(CUDA_VERSION)
 #error "cuda.h did not define CUDA_VERSION"
-#elif CUDA_VERSION < 7000 || CUDA_VERSION > 10000
+#elif CUDA_VERSION < 7000 || CUDA_VERSION > 10010
 #error "Unsupported CUDA version!"
 #endif

@@ -426,5 +412,15 @@ __device__ inline __cuda_builtin_gridDim_t::operator dim3() const {
 #pragma pop_macro("__USE_FAST_MATH__")
 #pragma pop_macro("__CUDA_INCLUDE_COMPILER_INTERNAL_HEADERS__")

+// CUDA runtime uses this undocumented function to access kernel launch
+// configuration. The declaration is in crt/device_functions.h but that file
+// includes a lot of other stuff we don't want. Instead, we'll provide our own
+// declaration for it here.
+#if CUDA_VERSION >= 9020
+extern "C" unsigned __cudaPushCallConfiguration(dim3 gridDim, dim3 blockDim,
+                                                size_t sharedMem = 0,
+                                                void *stream = 0);
+#endif
+
 #endif // __CUDA__
 #endif // __CLANG_CUDA_RUNTIME_WRAPPER_H__
@@ -1,24 +1,8 @@
 /*===---- __stddef_max_align_t.h - Definition of max_align_t for modules ---===
 *
- * Copyright (c) 2014 Chandler Carruth
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- __wmmintrin_aes.h - AES intrinsics -------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- __wmmintrin_pclmul.h - PCMUL intrinsics ---------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- adxintrin.h - ADX intrinsics -------------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- altivec.h - Standard header for type generic math ---------------===*\
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 \*===----------------------------------------------------------------------===*/

@@ -1,22 +1,8 @@
 /*===---- ammintrin.h - SSE4a intrinsics -----------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- arm64intr.h - ARM64 Windows intrinsics -------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- arm_acle.h - ARM Non-Neon intrinsics -----------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -611,6 +597,14 @@ __crc32cd(uint32_t __a, uint64_t __b) {
 }
 #endif

+/* Armv8.3-A Javascript conversion intrinsic */
+#if __ARM_64BIT_STATE && defined(__ARM_FEATURE_JCVT)
+static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
+__jcvt(double __a) {
+  return __builtin_arm_jcvt(__a);
+}
+#endif
+
 /* 10.1 Special register intrinsics */
 #define __arm_rsr(sysreg) __builtin_arm_rsr(sysreg)
 #define __arm_rsr64(sysreg) __builtin_arm_rsr64(sysreg)
@@ -619,6 +613,16 @@ __crc32cd(uint32_t __a, uint64_t __b) {
 #define __arm_wsr64(sysreg, v) __builtin_arm_wsr64(sysreg, v)
 #define __arm_wsrp(sysreg, v) __builtin_arm_wsrp(sysreg, v)

+// Memory Tagging Extensions (MTE) Intrinsics
+#if __ARM_FEATURE_MEMORY_TAGGING
+#define __arm_mte_create_random_tag(__ptr, __mask)  __builtin_arm_irg(__ptr, __mask)
+#define __arm_mte_increment_tag(__ptr, __tag_offset)  __builtin_arm_addg(__ptr, __tag_offset)
+#define __arm_mte_exclude_tag(__ptr, __excluded)  __builtin_arm_gmi(__ptr, __excluded)
+#define __arm_mte_get_tag(__ptr) __builtin_arm_ldg(__ptr)
+#define __arm_mte_set_tag(__ptr) __builtin_arm_stg(__ptr)
+#define __arm_mte_ptrdiff(__ptra, __ptrb) __builtin_arm_subp(__ptra, __ptrb)
+#endif
+
 #if defined(__cplusplus)
 }
 #endif
@@ -1,22 +1,8 @@
 /*===---- armintr.h - ARM Windows intrinsics -------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- avx2intrin.h - AVX2 intrinsics -----------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -146,21 +132,13 @@ _mm256_andnot_si256(__m256i __a, __m256i __b)
 static __inline__ __m256i __DEFAULT_FN_ATTRS256
 _mm256_avg_epu8(__m256i __a, __m256i __b)
 {
-  typedef unsigned short __v32hu __attribute__((__vector_size__(64)));
-  return (__m256i)__builtin_convertvector(
-               ((__builtin_convertvector((__v32qu)__a, __v32hu) +
-                 __builtin_convertvector((__v32qu)__b, __v32hu)) + 1)
-                 >> 1, __v32qu);
+  return (__m256i)__builtin_ia32_pavgb256((__v32qi)__a, (__v32qi)__b);
 }

 static __inline__ __m256i __DEFAULT_FN_ATTRS256
 _mm256_avg_epu16(__m256i __a, __m256i __b)
 {
-  typedef unsigned int __v16su __attribute__((__vector_size__(64)));
-  return (__m256i)__builtin_convertvector(
-               ((__builtin_convertvector((__v16hu)__a, __v16su) +
-                 __builtin_convertvector((__v16hu)__b, __v16su)) + 1)
-                 >> 1, __v16hu);
+  return (__m256i)__builtin_ia32_pavgw256((__v16hi)__a, (__v16hi)__b);
 }

 static __inline__ __m256i __DEFAULT_FN_ATTRS256
@@ -0,0 +1,279 @@
+/*===------------ avx512bf16intrin.h - AVX512_BF16 intrinsics --------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+#ifndef __IMMINTRIN_H
+#error "Never use <avx512bf16intrin.h> directly; include <immintrin.h> instead."
+#endif
+
+#ifndef __AVX512BF16INTRIN_H
+#define __AVX512BF16INTRIN_H
+
+typedef short __m512bh __attribute__((__vector_size__(64), __aligned__(64)));
+typedef short __m256bh __attribute__((__vector_size__(32), __aligned__(32)));
+typedef unsigned short __bfloat16;
+
+#define __DEFAULT_FN_ATTRS512 \
+  __attribute__((__always_inline__, __nodebug__, __target__("avx512bf16"), \
+                 __min_vector_width__(512)))
+#define __DEFAULT_FN_ATTRS                                                     \
+  __attribute__((__always_inline__, __nodebug__, __target__("avx512bf16")))
+
+/// Convert One BF16 Data to One Single Float Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic does not correspond to a specific instruction.
+///
+/// \param __A
+///    A bfloat data.
+/// \returns A float data whose sign field and exponent field keep unchanged,
+///    and fraction field is extended to 23 bits.
+static __inline__ float __DEFAULT_FN_ATTRS _mm_cvtsbh_ss(__bfloat16 __A) {
+  return __builtin_ia32_cvtsbf162ss_32(__A);
+}
+
+/// Convert Two Packed Single Data to One Packed BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNE2PS2BF16 </c> instructions.
+///
+/// \param __A
+///    A 512-bit vector of [16 x float].
+/// \param __B
+///    A 512-bit vector of [16 x float].
+/// \returns A 512-bit vector of [32 x bfloat] whose lower 256 bits come from
+///    conversion of __B, and higher 256 bits come from conversion of __A.
+static __inline__ __m512bh __DEFAULT_FN_ATTRS512
+_mm512_cvtne2ps_pbh(__m512 __A, __m512 __B) {
+  return (__m512bh)__builtin_ia32_cvtne2ps2bf16_512((__v16sf) __A,
+                                                    (__v16sf) __B);
+}
+
+/// Convert Two Packed Single Data to One Packed BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNE2PS2BF16 </c> instructions.
+///
+/// \param __A
+///    A 512-bit vector of [16 x float].
+/// \param __B
+///    A 512-bit vector of [16 x float].
+/// \param __W
+///    A 512-bit vector of [32 x bfloat].
+/// \param __U
+///    A 32-bit mask value specifying what is chosen for each element.
+///    A 1 means conversion of __A or __B. A 0 means element from __W.
+/// \returns A 512-bit vector of [32 x bfloat] whose lower 256 bits come from
+///    conversion of __B, and higher 256 bits come from conversion of __A.
+static __inline__ __m512bh __DEFAULT_FN_ATTRS512
+_mm512_mask_cvtne2ps_pbh(__m512bh __W, __mmask32 __U, __m512 __A, __m512 __B) {
+  return (__m512bh)__builtin_ia32_selectw_512((__mmask32)__U,
+                                        (__v32hi)_mm512_cvtne2ps_pbh(__A, __B),
+                                        (__v32hi)__W);
+}
+
+/// Convert Two Packed Single Data to One Packed BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNE2PS2BF16 </c> instructions.
+///
+/// \param __A
+///    A 512-bit vector of [16 x float].
+/// \param __B
+///    A 512-bit vector of [16 x float].
+/// \param __U
+///    A 32-bit mask value specifying what is chosen for each element.
+///    A 1 means conversion of __A or __B. A 0 means element is zero.
+/// \returns A 512-bit vector of [32 x bfloat] whose lower 256 bits come from
+///    conversion of __B, and higher 256 bits come from conversion of __A.
+static __inline__ __m512bh __DEFAULT_FN_ATTRS512
+_mm512_maskz_cvtne2ps_pbh(__mmask32 __U, __m512 __A, __m512 __B) {
+  return (__m512bh)__builtin_ia32_selectw_512((__mmask32)__U,
+                                        (__v32hi)_mm512_cvtne2ps_pbh(__A, __B),
+                                        (__v32hi)_mm512_setzero_si512());
+}
+
+/// Convert Packed Single Data to Packed BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNEPS2BF16 </c> instructions.
+///
+/// \param __A
+///    A 512-bit vector of [16 x float].
+/// \returns A 256-bit vector of [16 x bfloat] come from conversion of __A.
+static __inline__ __m256bh __DEFAULT_FN_ATTRS512
+_mm512_cvtneps_pbh(__m512 __A) {
+  return (__m256bh)__builtin_ia32_cvtneps2bf16_512_mask((__v16sf)__A,
+                                              (__v16hi)_mm256_undefined_si256(),
+                                              (__mmask16)-1);
+}
+
+/// Convert Packed Single Data to Packed BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNEPS2BF16 </c> instructions.
+///
+/// \param __A
+///    A 512-bit vector of [16 x float].
+/// \param __W
+///    A 256-bit vector of [16 x bfloat].
+/// \param __U
+///    A 16-bit mask value specifying what is chosen for each element.
+///    A 1 means conversion of __A. A 0 means element from __W.
+/// \returns A 256-bit vector of [16 x bfloat] come from conversion of __A.
+static __inline__ __m256bh __DEFAULT_FN_ATTRS512
+_mm512_mask_cvtneps_pbh(__m256bh __W, __mmask16 __U, __m512 __A) {
+  return (__m256bh)__builtin_ia32_cvtneps2bf16_512_mask((__v16sf)__A,
+                                                        (__v16hi)__W,
+                                                        (__mmask16)__U);
+}
+
+/// Convert Packed Single Data to Packed BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNEPS2BF16 </c> instructions.
+///
+/// \param __A
+///    A 512-bit vector of [16 x float].
+/// \param __U
+///    A 16-bit mask value specifying what is chosen for each element.
+///    A 1 means conversion of __A. A 0 means element is zero.
+/// \returns A 256-bit vector of [16 x bfloat] come from conversion of __A.
+static __inline__ __m256bh __DEFAULT_FN_ATTRS512
+_mm512_maskz_cvtneps_pbh(__mmask16 __U, __m512 __A) {
+  return (__m256bh)__builtin_ia32_cvtneps2bf16_512_mask((__v16sf)__A,
+                                                (__v16hi)_mm256_setzero_si256(),
+                                                (__mmask16)__U);
+}
+
+/// Dot Product of BF16 Pairs Accumulated into Packed Single Precision.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VDPBF16PS </c> instructions.
+///
+/// \param __A
+///    A 512-bit vector of [32 x bfloat].
+/// \param __B
+///    A 512-bit vector of [32 x bfloat].
+/// \param __D
+///    A 512-bit vector of [16 x float].
+/// \returns A 512-bit vector of [16 x float] comes from  Dot Product of
+///  __A, __B and __D
+static __inline__ __m512 __DEFAULT_FN_ATTRS512
+_mm512_dpbf16_ps(__m512 __D, __m512bh __A, __m512bh __B) {
+  return (__m512)__builtin_ia32_dpbf16ps_512((__v16sf) __D,
+                                             (__v16si) __A,
+                                             (__v16si) __B);
+}
+
+/// Dot Product of BF16 Pairs Accumulated into Packed Single Precision.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VDPBF16PS </c> instructions.
+///
+/// \param __A
+///    A 512-bit vector of [32 x bfloat].
+/// \param __B
+///    A 512-bit vector of [32 x bfloat].
+/// \param __D
+///    A 512-bit vector of [16 x float].
+/// \param __U
+///    A 16-bit mask value specifying what is chosen for each element.
+///    A 1 means __A and __B's dot product accumulated with __D. A 0 means __D.
+/// \returns A 512-bit vector of [16 x float] comes from  Dot Product of
+///  __A, __B and __D
+static __inline__ __m512 __DEFAULT_FN_ATTRS512
+_mm512_mask_dpbf16_ps(__m512 __D, __mmask16 __U, __m512bh __A, __m512bh __B) {
+  return (__m512)__builtin_ia32_selectps_512((__mmask16)__U,
+                                       (__v16sf)_mm512_dpbf16_ps(__D, __A, __B),
+                                       (__v16sf)__D);
+}
+
+/// Dot Product of BF16 Pairs Accumulated into Packed Single Precision.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VDPBF16PS </c> instructions.
+///
+/// \param __A
+///    A 512-bit vector of [32 x bfloat].
+/// \param __B
+///    A 512-bit vector of [32 x bfloat].
+/// \param __D
+///    A 512-bit vector of [16 x float].
+/// \param __U
+///    A 16-bit mask value specifying what is chosen for each element.
+///    A 1 means __A and __B's dot product accumulated with __D. A 0 means 0.
+/// \returns A 512-bit vector of [16 x float] comes from  Dot Product of
+///  __A, __B and __D
+static __inline__ __m512 __DEFAULT_FN_ATTRS512
+_mm512_maskz_dpbf16_ps(__mmask16 __U, __m512 __D, __m512bh __A, __m512bh __B) {
+  return (__m512)__builtin_ia32_selectps_512((__mmask16)__U,
+                                       (__v16sf)_mm512_dpbf16_ps(__D, __A, __B),
+                                       (__v16sf)_mm512_setzero_si512());
+}
+
+/// Convert Packed BF16 Data to Packed float Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \param __A
+///    A 256-bit vector of [16 x bfloat].
+/// \returns A 512-bit vector of [16 x float] come from convertion of __A
+static __inline__ __m512 __DEFAULT_FN_ATTRS512 _mm512_cvtpbh_ps(__m256bh __A) {
+  return _mm512_castsi512_ps((__m512i)_mm512_slli_epi32(
+      (__m512i)_mm512_cvtepi16_epi32((__m256i)__A), 16));
+}
+
+/// Convert Packed BF16 Data to Packed float Data using zeroing mask.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \param __U
+///    A 16-bit mask. Elements are zeroed out when the corresponding mask
+///    bit is not set.
+/// \param __A
+///    A 256-bit vector of [16 x bfloat].
+/// \returns A 512-bit vector of [16 x float] come from convertion of __A
+static __inline__ __m512 __DEFAULT_FN_ATTRS512
+_mm512_maskz_cvtpbh_ps(__mmask16 __U, __m256bh __A) {
+  return _mm512_castsi512_ps((__m512i)_mm512_slli_epi32(
+      (__m512i)_mm512_maskz_cvtepi16_epi32((__mmask16)__U, (__m256i)__A), 16));
+}
+
+/// Convert Packed BF16 Data to Packed float Data using merging mask.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \param __S
+///    A 512-bit vector of [16 x float]. Elements are copied from __S when
+///     the corresponding mask bit is not set.
+/// \param __U
+///    A 16-bit mask.
+/// \param __A
+///    A 256-bit vector of [16 x bfloat].
+/// \returns A 512-bit vector of [16 x float] come from convertion of __A
+static __inline__ __m512 __DEFAULT_FN_ATTRS512
+_mm512_mask_cvtpbh_ps(__m512 __S, __mmask16 __U, __m256bh __A) {
+  return _mm512_castsi512_ps((__m512i)_mm512_mask_slli_epi32(
+      (__m512i)__S, (__mmask16)__U,
+      (__m512i)_mm512_cvtepi16_epi32((__m256i)__A), 16));
+}
+
+#undef __DEFAULT_FN_ATTRS
+#undef __DEFAULT_FN_ATTRS512
+
+#endif
@@ -1,23 +1,9 @@
 /*===------------- avx512bitalgintrin.h - BITALG intrinsics ------------------===
 *
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,23 +1,9 @@
 /*===------------- avx512bwintrin.h - AVX512BW intrinsics ------------------===
 *
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -719,11 +705,7 @@ _mm512_maskz_adds_epu16 (__mmask32 __U, __m512i __A, __m512i __B)
 static __inline__ __m512i __DEFAULT_FN_ATTRS512
 _mm512_avg_epu8 (__m512i __A, __m512i __B)
 {
-  typedef unsigned short __v64hu __attribute__((__vector_size__(128)));
-  return (__m512i)__builtin_convertvector(
-              ((__builtin_convertvector((__v64qu) __A, __v64hu) +
-                __builtin_convertvector((__v64qu) __B, __v64hu)) + 1)
-                >> 1, __v64qu);
+  return (__m512i)__builtin_ia32_pavgb512((__v64qi)__A, (__v64qi)__B);
 }

 static __inline__ __m512i __DEFAULT_FN_ATTRS512
@@ -746,11 +728,7 @@ _mm512_maskz_avg_epu8 (__mmask64 __U, __m512i __A, __m512i __B)
 static __inline__ __m512i __DEFAULT_FN_ATTRS512
 _mm512_avg_epu16 (__m512i __A, __m512i __B)
 {
-  typedef unsigned int __v32su __attribute__((__vector_size__(128)));
-  return (__m512i)__builtin_convertvector(
-              ((__builtin_convertvector((__v32hu) __A, __v32su) +
-                __builtin_convertvector((__v32hu) __B, __v32su)) + 1)
-                >> 1, __v32hu);
+  return (__m512i)__builtin_ia32_pavgw512((__v32hi)__A, (__v32hi)__B);
 }

 static __inline__ __m512i __DEFAULT_FN_ATTRS512
@@ -1733,14 +1711,14 @@ _mm512_maskz_set1_epi8 (__mmask64 __M, char __A)
                                              (__v64qi) _mm512_setzero_si512());
 }

-static __inline__ __mmask64 __DEFAULT_FN_ATTRS512
+static __inline__ __mmask64 __DEFAULT_FN_ATTRS
 _mm512_kunpackd (__mmask64 __A, __mmask64 __B)
 {
  return (__mmask64) __builtin_ia32_kunpckdi ((__mmask64) __A,
                (__mmask64) __B);
 }

-static __inline__ __mmask32 __DEFAULT_FN_ATTRS512
+static __inline__ __mmask32 __DEFAULT_FN_ATTRS
 _mm512_kunpackw (__mmask32 __A, __mmask32 __B)
 {
  return (__mmask32) __builtin_ia32_kunpcksi ((__mmask32) __A,
@@ -1751,7 +1729,7 @@ static __inline __m512i __DEFAULT_FN_ATTRS512
 _mm512_loadu_epi16 (void const *__P)
 {
  struct __loadu_epi16 {
-    __m512i __v;
+    __m512i_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_epi16*)__P)->__v;
 }
@@ -1777,7 +1755,7 @@ static __inline __m512i __DEFAULT_FN_ATTRS512
 _mm512_loadu_epi8 (void const *__P)
 {
  struct __loadu_epi8 {
-    __m512i __v;
+    __m512i_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_epi8*)__P)->__v;
 }
@@ -1803,7 +1781,7 @@ static __inline void __DEFAULT_FN_ATTRS512
 _mm512_storeu_epi16 (void *__P, __m512i __A)
 {
  struct __storeu_epi16 {
-    __m512i __v;
+    __m512i_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_epi16*)__P)->__v = __A;
 }
@@ -1820,7 +1798,7 @@ static __inline void __DEFAULT_FN_ATTRS512
 _mm512_storeu_epi8 (void *__P, __m512i __A)
 {
  struct __storeu_epi8 {
-    __m512i __v;
+    __m512i_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_epi8*)__P)->__v = __A;
 }
@@ -1,23 +1,9 @@
 /*===------------- avx512cdintrin.h - AVX512CD intrinsics ------------------===
 *
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -34,49 +20,45 @@
 static __inline__ __m512i __DEFAULT_FN_ATTRS
 _mm512_conflict_epi64 (__m512i __A)
 {
-  return (__m512i) __builtin_ia32_vpconflictdi_512_mask ((__v8di) __A,
-                 (__v8di) _mm512_setzero_si512 (),
-                 (__mmask8) -1);
+  return (__m512i) __builtin_ia32_vpconflictdi_512 ((__v8di) __A);
 }

 static __inline__ __m512i __DEFAULT_FN_ATTRS
 _mm512_mask_conflict_epi64 (__m512i __W, __mmask8 __U, __m512i __A)
 {
-  return (__m512i) __builtin_ia32_vpconflictdi_512_mask ((__v8di) __A,
-               (__v8di) __W,
-               (__mmask8) __U);
+  return (__m512i)__builtin_ia32_selectq_512((__mmask8)__U,
+                                             (__v8di)_mm512_conflict_epi64(__A),
+                                             (__v8di)__W);
 }

 static __inline__ __m512i __DEFAULT_FN_ATTRS
 _mm512_maskz_conflict_epi64 (__mmask8 __U, __m512i __A)
 {
-  return (__m512i) __builtin_ia32_vpconflictdi_512_mask ((__v8di) __A,
-                 (__v8di) _mm512_setzero_si512 (),
-                 (__mmask8) __U);
+  return (__m512i)__builtin_ia32_selectq_512((__mmask8)__U,
+                                             (__v8di)_mm512_conflict_epi64(__A),
+                                             (__v8di)_mm512_setzero_si512 ());
 }

 static __inline__ __m512i __DEFAULT_FN_ATTRS
 _mm512_conflict_epi32 (__m512i __A)
 {
-  return (__m512i) __builtin_ia32_vpconflictsi_512_mask ((__v16si) __A,
-                 (__v16si) _mm512_setzero_si512 (),
-                 (__mmask16) -1);
+  return (__m512i) __builtin_ia32_vpconflictsi_512 ((__v16si) __A);
 }

 static __inline__ __m512i __DEFAULT_FN_ATTRS
 _mm512_mask_conflict_epi32 (__m512i __W, __mmask16 __U, __m512i __A)
 {
-  return (__m512i) __builtin_ia32_vpconflictsi_512_mask ((__v16si) __A,
-               (__v16si) __W,
-               (__mmask16) __U);
+  return (__m512i)__builtin_ia32_selectd_512((__mmask16)__U,
+                                            (__v16si)_mm512_conflict_epi32(__A),
+                                            (__v16si)__W);
 }

 static __inline__ __m512i __DEFAULT_FN_ATTRS
 _mm512_maskz_conflict_epi32 (__mmask16 __U, __m512i __A)
 {
-  return (__m512i) __builtin_ia32_vpconflictsi_512_mask ((__v16si) __A,
-                 (__v16si) _mm512_setzero_si512 (),
-                 (__mmask16) __U);
+  return (__m512i)__builtin_ia32_selectd_512((__mmask16)__U,
+                                            (__v16si)_mm512_conflict_epi32(__A),
+                                            (__v16si)_mm512_setzero_si512());
 }

 static __inline__ __m512i __DEFAULT_FN_ATTRS
@@ -1,22 +1,8 @@
 /*===---- avx512dqintrin.h - AVX512DQ intrinsics ---------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- avx512erintrin.h - AVX512ER intrinsics ---------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- avx512fintrin.h - AVX512F intrinsics -----------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -40,9 +26,13 @@ typedef unsigned short __v32hu __attribute__((__vector_size__(64)));
 typedef unsigned long long __v8du __attribute__((__vector_size__(64)));
 typedef unsigned int __v16su __attribute__((__vector_size__(64)));

-typedef float __m512 __attribute__((__vector_size__(64)));
-typedef double __m512d __attribute__((__vector_size__(64)));
-typedef long long __m512i __attribute__((__vector_size__(64)));
+typedef float __m512 __attribute__((__vector_size__(64), __aligned__(64)));
+typedef double __m512d __attribute__((__vector_size__(64), __aligned__(64)));
+typedef long long __m512i __attribute__((__vector_size__(64), __aligned__(64)));
+
+typedef float __m512_u __attribute__((__vector_size__(64), __aligned__(1)));
+typedef double __m512d_u __attribute__((__vector_size__(64), __aligned__(1)));
+typedef long long __m512i_u __attribute__((__vector_size__(64), __aligned__(1)));

 typedef unsigned char __mmask8;
 typedef unsigned short __mmask16;
@@ -1991,12 +1981,12 @@ _mm512_maskz_add_ps(__mmask16 __U, __m512 __A, __m512 __B) {
 #define _mm512_mask_add_round_pd(W, U, A, B, R) \
  (__m512d)__builtin_ia32_selectpd_512((__mmask8)(U), \
                                   (__v8df)_mm512_add_round_pd((A), (B), (R)), \
-                                   (__v8df)(__m512d)(W));
+                                   (__v8df)(__m512d)(W))

 #define _mm512_maskz_add_round_pd(U, A, B, R) \
  (__m512d)__builtin_ia32_selectpd_512((__mmask8)(U), \
                                   (__v8df)_mm512_add_round_pd((A), (B), (R)), \
-                                   (__v8df)_mm512_setzero_pd());
+                                   (__v8df)_mm512_setzero_pd())

 #define _mm512_add_round_ps(A, B, R) \
  (__m512)__builtin_ia32_addps512((__v16sf)(__m512)(A), \
@@ -2005,12 +1995,12 @@ _mm512_maskz_add_ps(__mmask16 __U, __m512 __A, __m512 __B) {
 #define _mm512_mask_add_round_ps(W, U, A, B, R) \
  (__m512)__builtin_ia32_selectps_512((__mmask16)(U), \
                                  (__v16sf)_mm512_add_round_ps((A), (B), (R)), \
-                                  (__v16sf)(__m512)(W));
+                                  (__v16sf)(__m512)(W))

 #define _mm512_maskz_add_round_ps(U, A, B, R) \
  (__m512)__builtin_ia32_selectps_512((__mmask16)(U), \
                                  (__v16sf)_mm512_add_round_ps((A), (B), (R)), \
-                                  (__v16sf)_mm512_setzero_ps());
+                                  (__v16sf)_mm512_setzero_ps())

 static __inline__ __m128 __DEFAULT_FN_ATTRS128
 _mm_mask_sub_ss(__m128 __W, __mmask8 __U,__m128 __A, __m128 __B) {
@@ -2106,12 +2096,12 @@ _mm512_maskz_sub_ps(__mmask16 __U, __m512 __A, __m512 __B) {
 #define _mm512_mask_sub_round_pd(W, U, A, B, R) \
  (__m512d)__builtin_ia32_selectpd_512((__mmask8)(U), \
                                   (__v8df)_mm512_sub_round_pd((A), (B), (R)), \
-                                   (__v8df)(__m512d)(W));
+                                   (__v8df)(__m512d)(W))

 #define _mm512_maskz_sub_round_pd(U, A, B, R) \
  (__m512d)__builtin_ia32_selectpd_512((__mmask8)(U), \
                                   (__v8df)_mm512_sub_round_pd((A), (B), (R)), \
-                                   (__v8df)_mm512_setzero_pd());
+                                   (__v8df)_mm512_setzero_pd())

 #define _mm512_sub_round_ps(A, B, R) \
  (__m512)__builtin_ia32_subps512((__v16sf)(__m512)(A), \
@@ -2120,12 +2110,12 @@ _mm512_maskz_sub_ps(__mmask16 __U, __m512 __A, __m512 __B) {
 #define _mm512_mask_sub_round_ps(W, U, A, B, R) \
  (__m512)__builtin_ia32_selectps_512((__mmask16)(U), \
                                  (__v16sf)_mm512_sub_round_ps((A), (B), (R)), \
-                                  (__v16sf)(__m512)(W));
+                                  (__v16sf)(__m512)(W))

 #define _mm512_maskz_sub_round_ps(U, A, B, R) \
  (__m512)__builtin_ia32_selectps_512((__mmask16)(U), \
                                  (__v16sf)_mm512_sub_round_ps((A), (B), (R)), \
-                                  (__v16sf)_mm512_setzero_ps());
+                                  (__v16sf)_mm512_setzero_ps())

 static __inline__ __m128 __DEFAULT_FN_ATTRS128
 _mm_mask_mul_ss(__m128 __W, __mmask8 __U,__m128 __A, __m128 __B) {
@@ -2221,12 +2211,12 @@ _mm512_maskz_mul_ps(__mmask16 __U, __m512 __A, __m512 __B) {
 #define _mm512_mask_mul_round_pd(W, U, A, B, R) \
  (__m512d)__builtin_ia32_selectpd_512((__mmask8)(U), \
                                   (__v8df)_mm512_mul_round_pd((A), (B), (R)), \
-                                   (__v8df)(__m512d)(W));
+                                   (__v8df)(__m512d)(W))

 #define _mm512_maskz_mul_round_pd(U, A, B, R) \
  (__m512d)__builtin_ia32_selectpd_512((__mmask8)(U), \
                                   (__v8df)_mm512_mul_round_pd((A), (B), (R)), \
-                                   (__v8df)_mm512_setzero_pd());
+                                   (__v8df)_mm512_setzero_pd())

 #define _mm512_mul_round_ps(A, B, R) \
  (__m512)__builtin_ia32_mulps512((__v16sf)(__m512)(A), \
@@ -2235,12 +2225,12 @@ _mm512_maskz_mul_ps(__mmask16 __U, __m512 __A, __m512 __B) {
 #define _mm512_mask_mul_round_ps(W, U, A, B, R) \
  (__m512)__builtin_ia32_selectps_512((__mmask16)(U), \
                                  (__v16sf)_mm512_mul_round_ps((A), (B), (R)), \
-                                  (__v16sf)(__m512)(W));
+                                  (__v16sf)(__m512)(W))

 #define _mm512_maskz_mul_round_ps(U, A, B, R) \
  (__m512)__builtin_ia32_selectps_512((__mmask16)(U), \
                                  (__v16sf)_mm512_mul_round_ps((A), (B), (R)), \
-                                  (__v16sf)_mm512_setzero_ps());
+                                  (__v16sf)_mm512_setzero_ps())

 static __inline__ __m128 __DEFAULT_FN_ATTRS128
 _mm_mask_div_ss(__m128 __W, __mmask8 __U,__m128 __A, __m128 __B) {
@@ -2349,12 +2339,12 @@ _mm512_maskz_div_ps(__mmask16 __U, __m512 __A, __m512 __B) {
 #define _mm512_mask_div_round_pd(W, U, A, B, R) \
  (__m512d)__builtin_ia32_selectpd_512((__mmask8)(U), \
                                   (__v8df)_mm512_div_round_pd((A), (B), (R)), \
-                                   (__v8df)(__m512d)(W));
+                                   (__v8df)(__m512d)(W))

 #define _mm512_maskz_div_round_pd(U, A, B, R) \
  (__m512d)__builtin_ia32_selectpd_512((__mmask8)(U), \
                                   (__v8df)_mm512_div_round_pd((A), (B), (R)), \
-                                   (__v8df)_mm512_setzero_pd());
+                                   (__v8df)_mm512_setzero_pd())

 #define _mm512_div_round_ps(A, B, R) \
  (__m512)__builtin_ia32_divps512((__v16sf)(__m512)(A), \
@@ -2363,12 +2353,12 @@ _mm512_maskz_div_ps(__mmask16 __U, __m512 __A, __m512 __B) {
 #define _mm512_mask_div_round_ps(W, U, A, B, R) \
  (__m512)__builtin_ia32_selectps_512((__mmask16)(U), \
                                  (__v16sf)_mm512_div_round_ps((A), (B), (R)), \
-                                  (__v16sf)(__m512)(W));
+                                  (__v16sf)(__m512)(W))

 #define _mm512_maskz_div_round_ps(U, A, B, R) \
  (__m512)__builtin_ia32_selectps_512((__mmask16)(U), \
                                  (__v16sf)_mm512_div_round_ps((A), (B), (R)), \
-                                  (__v16sf)_mm512_setzero_ps());
+                                  (__v16sf)_mm512_setzero_ps())

 #define _mm512_roundscale_ps(A, B) \
  (__m512)__builtin_ia32_rndscaleps_mask((__v16sf)(__m512)(A), (int)(B), \
@@ -3789,20 +3779,9 @@ _mm512_mask_cvtpd_pslo (__m512 __W, __mmask8 __U,__m512d __A)
                                            (__v16hi)_mm256_setzero_si256(), \
                                            (__mmask16)(W))

-#define _mm512_cvtps_ph(A, I) \
-  (__m256i)__builtin_ia32_vcvtps2ph512_mask((__v16sf)(__m512)(A), (int)(I), \
-                                            (__v16hi)_mm256_setzero_si256(), \
-                                            (__mmask16)-1)
-
-#define _mm512_mask_cvtps_ph(U, W, A, I) \
-  (__m256i)__builtin_ia32_vcvtps2ph512_mask((__v16sf)(__m512)(A), (int)(I), \
-                                            (__v16hi)(__m256i)(U), \
-                                            (__mmask16)(W))
-
-#define _mm512_maskz_cvtps_ph(W, A, I) \
-  (__m256i)__builtin_ia32_vcvtps2ph512_mask((__v16sf)(__m512)(A), (int)(I), \
-                                            (__v16hi)_mm256_setzero_si256(), \
-                                            (__mmask16)(W))
+#define _mm512_cvtps_ph       _mm512_cvt_roundps_ph
+#define _mm512_mask_cvtps_ph  _mm512_mask_cvt_roundps_ph
+#define _mm512_maskz_cvtps_ph _mm512_maskz_cvt_roundps_ph

 #define _mm512_cvt_roundph_ps(A, R) \
  (__m512)__builtin_ia32_vcvtph2ps512_mask((__v16hi)(__m256i)(A), \
@@ -4324,7 +4303,7 @@ static __inline __m512i __DEFAULT_FN_ATTRS512
 _mm512_loadu_si512 (void const *__P)
 {
  struct __loadu_si512 {
-    __m512i __v;
+    __m512i_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_si512*)__P)->__v;
 }
@@ -4333,7 +4312,7 @@ static __inline __m512i __DEFAULT_FN_ATTRS512
 _mm512_loadu_epi32 (void const *__P)
 {
  struct __loadu_epi32 {
-    __m512i __v;
+    __m512i_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_epi32*)__P)->__v;
 }
@@ -4360,7 +4339,7 @@ static __inline __m512i __DEFAULT_FN_ATTRS512
 _mm512_loadu_epi64 (void const *__P)
 {
  struct __loadu_epi64 {
-    __m512i __v;
+    __m512i_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_epi64*)__P)->__v;
 }
@@ -4420,7 +4399,7 @@ static __inline __m512d __DEFAULT_FN_ATTRS512
 _mm512_loadu_pd(void const *__p)
 {
  struct __loadu_pd {
-    __m512d __v;
+    __m512d_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_pd*)__p)->__v;
 }
@@ -4429,7 +4408,7 @@ static __inline __m512 __DEFAULT_FN_ATTRS512
 _mm512_loadu_ps(void const *__p)
 {
  struct __loadu_ps {
-    __m512 __v;
+    __m512_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_ps*)__p)->__v;
 }
@@ -4504,7 +4483,7 @@ static __inline void __DEFAULT_FN_ATTRS512
 _mm512_storeu_epi64 (void *__P, __m512i __A)
 {
  struct __storeu_epi64 {
-    __m512i __v;
+    __m512i_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_epi64*)__P)->__v = __A;
 }
@@ -4520,7 +4499,7 @@ static __inline void __DEFAULT_FN_ATTRS512
 _mm512_storeu_si512 (void *__P, __m512i __A)
 {
  struct __storeu_si512 {
-    __m512i __v;
+    __m512i_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_si512*)__P)->__v = __A;
 }
@@ -4529,7 +4508,7 @@ static __inline void __DEFAULT_FN_ATTRS512
 _mm512_storeu_epi32 (void *__P, __m512i __A)
 {
  struct __storeu_epi32 {
-    __m512i __v;
+    __m512i_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_epi32*)__P)->__v = __A;
 }
@@ -4551,7 +4530,7 @@ static __inline void __DEFAULT_FN_ATTRS512
 _mm512_storeu_pd(void *__P, __m512d __A)
 {
  struct __storeu_pd {
-    __m512d __v;
+    __m512d_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_pd*)__P)->__v = __A;
 }
@@ -4567,7 +4546,7 @@ static __inline void __DEFAULT_FN_ATTRS512
 _mm512_storeu_ps(void *__P, __m512 __A)
 {
  struct __storeu_ps {
-    __m512 __v;
+    __m512_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_ps*)__P)->__v = __A;
 }
@@ -9329,7 +9308,7 @@ _mm512_mask_abs_pd(__m512d __W, __mmask8 __K, __m512d __A)
  __v2du __t6 = __t4 op __t5; \
  __v2du __t7 = __builtin_shufflevector(__t6, __t6, 1, 0); \
  __v2du __t8 = __t6 op __t7; \
-  return __t8[0];
+  return __t8[0]

 static __inline__ long long __DEFAULT_FN_ATTRS512 _mm512_reduce_add_epi64(__m512i __W) {
  _mm512_mask_reduce_operator(+);
@@ -9381,7 +9360,7 @@ _mm512_mask_reduce_or_epi64(__mmask8 __M, __m512i __W) {
  __m128d __t6 = __t4 op __t5; \
  __m128d __t7 = __builtin_shufflevector(__t6, __t6, 1, 0); \
  __m128d __t8 = __t6 op __t7; \
-  return __t8[0];
+  return __t8[0]

 static __inline__ double __DEFAULT_FN_ATTRS512 _mm512_reduce_add_pd(__m512d __W) {
  _mm512_mask_reduce_operator(+);
@@ -9415,7 +9394,7 @@ _mm512_mask_reduce_mul_pd(__mmask8 __M, __m512d __W) {
  __v4su __t8 = __t6 op __t7; \
  __v4su __t9 = __builtin_shufflevector(__t8, __t8, 1, 0, 3, 2); \
  __v4su __t10 = __t8 op __t9; \
-  return __t10[0];
+  return __t10[0]

 static __inline__ int __DEFAULT_FN_ATTRS512
 _mm512_reduce_add_epi32(__m512i __W) {
@@ -9473,7 +9452,7 @@ _mm512_mask_reduce_or_epi32(__mmask16 __M, __m512i __W) {
  __m128 __t8 = __t6 op __t7; \
  __m128 __t9 = __builtin_shufflevector(__t8, __t8, 1, 0, 3, 2); \
  __m128 __t10 = __t8 op __t9; \
-  return __t10[0];
+  return __t10[0]

 static __inline__ float __DEFAULT_FN_ATTRS512
 _mm512_reduce_add_ps(__m512 __W) {
@@ -9505,7 +9484,7 @@ _mm512_mask_reduce_mul_ps(__mmask16 __M, __m512 __W) {
  __m512i __t4 = _mm512_##op(__t2, __t3); \
  __m512i __t5 = (__m512i)__builtin_shufflevector((__v8di)__t4, (__v8di)__t4, 1, 0, 3, 2, 5, 4, 7, 6); \
  __v8di __t6 = (__v8di)_mm512_##op(__t4, __t5); \
-  return __t6[0];
+  return __t6[0]

 static __inline__ long long __DEFAULT_FN_ATTRS512
 _mm512_reduce_max_epi64(__m512i __V) {
@@ -9563,7 +9542,7 @@ _mm512_mask_reduce_min_epu64(__mmask8 __M, __m512i __V) {
  __m128i __t8 = _mm_##op(__t6, __t7); \
  __m128i __t9 = (__m128i)__builtin_shufflevector((__v4si)__t8, (__v4si)__t8, 1, 0, 3, 2); \
  __v4si __t10 = (__v4si)_mm_##op(__t8, __t9); \
-  return __t10[0];
+  return __t10[0]

 static __inline__ int __DEFAULT_FN_ATTRS512
 _mm512_reduce_max_epi32(__m512i __V) {
@@ -9619,7 +9598,7 @@ _mm512_mask_reduce_min_epu32(__mmask16 __M, __m512i __V) {
  __m128d __t6 = _mm_##op(__t4, __t5); \
  __m128d __t7 = __builtin_shufflevector(__t6, __t6, 1, 0); \
  __m128d __t8 = _mm_##op(__t6, __t7); \
-  return __t8[0];
+  return __t8[0]

 static __inline__ double __DEFAULT_FN_ATTRS512
 _mm512_reduce_max_pd(__m512d __V) {
@@ -9655,7 +9634,7 @@ _mm512_mask_reduce_min_pd(__mmask8 __M, __m512d __V) {
  __m128 __t8 = _mm_##op(__t6, __t7); \
  __m128 __t9 = __builtin_shufflevector(__t8, __t8, 1, 0, 3, 2); \
  __m128 __t10 = _mm_##op(__t8, __t9); \
-  return __t10[0];
+  return __t10[0]

 static __inline__ float __DEFAULT_FN_ATTRS512
 _mm512_reduce_max_ps(__m512 __V) {
@@ -1,23 +1,9 @@
 /*===------------- avx512ifmaintrin.h - IFMA intrinsics ------------------===
 *
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,23 +1,9 @@
 /*===------------- avx512ifmavlintrin.h - IFMA intrinsics ------------------===
 *
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,23 +1,9 @@
 /*===------------- avx512pfintrin.h - PF intrinsics ------------------------===
 *
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,23 +1,9 @@
 /*===------------- avx512vbmi2intrin.h - VBMI2 intrinsics ------------------===
 *
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,23 +1,9 @@
 /*===------------- avx512vbmiintrin.h - VBMI intrinsics ------------------===
 *
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,23 +1,9 @@
 /*===------------- avx512vbmivlintrin.h - VBMI intrinsics ------------------===
 *
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -0,0 +1,474 @@
+/*===--------- avx512vlbf16intrin.h - AVX512_BF16 intrinsics ---------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+#ifndef __IMMINTRIN_H
+#error "Never use <avx512vlbf16intrin.h> directly; include <immintrin.h> instead."
+#endif
+
+#ifndef __AVX512VLBF16INTRIN_H
+#define __AVX512VLBF16INTRIN_H
+
+typedef short __m128bh __attribute__((__vector_size__(16), __aligned__(16)));
+
+#define __DEFAULT_FN_ATTRS128 \
+  __attribute__((__always_inline__, __nodebug__, \
+                 __target__("avx512vl, avx512bf16"), __min_vector_width__(128)))
+#define __DEFAULT_FN_ATTRS256 \
+  __attribute__((__always_inline__, __nodebug__, \
+                 __target__("avx512vl, avx512bf16"), __min_vector_width__(256)))
+
+/// Convert Two Packed Single Data to One Packed BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNE2PS2BF16 </c> instructions.
+///
+/// \param __A
+///    A 128-bit vector of [4 x float].
+/// \param __B
+///    A 128-bit vector of [4 x float].
+/// \returns A 128-bit vector of [8 x bfloat] whose lower 64 bits come from
+///    conversion of __B, and higher 64 bits come from conversion of __A.
+static __inline__ __m128bh __DEFAULT_FN_ATTRS128
+_mm_cvtne2ps_pbh(__m128 __A, __m128 __B) {
+  return (__m128bh)__builtin_ia32_cvtne2ps2bf16_128((__v4sf) __A,
+                                                    (__v4sf) __B);
+}
+
+/// Convert Two Packed Single Data to One Packed BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNE2PS2BF16 </c> instructions.
+///
+/// \param __A
+///    A 128-bit vector of [4 x float].
+/// \param __B
+///    A 128-bit vector of [4 x float].
+/// \param __W
+///    A 128-bit vector of [8 x bfloat].
+/// \param __U
+///    A 8-bit mask value specifying what is chosen for each element.
+///    A 1 means conversion of __A or __B. A 0 means element from __W.
+/// \returns A 128-bit vector of [8 x bfloat] whose lower 64 bits come from
+///    conversion of __B, and higher 64 bits come from conversion of __A.
+static __inline__ __m128bh __DEFAULT_FN_ATTRS128
+_mm_mask_cvtne2ps_pbh(__m128bh __W, __mmask8 __U, __m128 __A, __m128 __B) {
+  return (__m128bh)__builtin_ia32_selectw_128((__mmask8)__U,
+                                             (__v8hi)_mm_cvtne2ps_pbh(__A, __B),
+                                             (__v8hi)__W);
+}
+
+/// Convert Two Packed Single Data to One Packed BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNE2PS2BF16 </c> instructions.
+///
+/// \param __A
+///    A 128-bit vector of [4 x float].
+/// \param __B
+///    A 128-bit vector of [4 x float].
+/// \param __U
+///    A 8-bit mask value specifying what is chosen for each element.
+///    A 1 means conversion of __A or __B. A 0 means element is zero.
+/// \returns A 128-bit vector of [8 x bfloat] whose lower 64 bits come from
+///    conversion of __B, and higher 64 bits come from conversion of __A.
+static __inline__ __m128bh __DEFAULT_FN_ATTRS128
+_mm_maskz_cvtne2ps_pbh(__mmask8 __U, __m128 __A, __m128 __B) {
+  return (__m128bh)__builtin_ia32_selectw_128((__mmask8)__U,
+                                             (__v8hi)_mm_cvtne2ps_pbh(__A, __B),
+                                             (__v8hi)_mm_setzero_si128());
+}
+
+/// Convert Two Packed Single Data to One Packed BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNE2PS2BF16 </c> instructions.
+///
+/// \param __A
+///    A 256-bit vector of [8 x float].
+/// \param __B
+///    A 256-bit vector of [8 x float].
+/// \returns A 256-bit vector of [16 x bfloat] whose lower 128 bits come from
+///    conversion of __B, and higher 128 bits come from conversion of __A.
+static __inline__ __m256bh __DEFAULT_FN_ATTRS256
+_mm256_cvtne2ps_pbh(__m256 __A, __m256 __B) {
+  return (__m256bh)__builtin_ia32_cvtne2ps2bf16_256((__v8sf) __A,
+                                                    (__v8sf) __B);
+}
+
+/// Convert Two Packed Single Data to One Packed BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNE2PS2BF16 </c> instructions.
+///
+/// \param __A
+///    A 256-bit vector of [8 x float].
+/// \param __B
+///    A 256-bit vector of [8 x float].
+/// \param __W
+///    A 256-bit vector of [16 x bfloat].
+/// \param __U
+///    A 16-bit mask value specifying what is chosen for each element.
+///    A 1 means conversion of __A or __B. A 0 means element from __W.
+/// \returns A 256-bit vector of [16 x bfloat] whose lower 128 bits come from
+///    conversion of __B, and higher 128 bits come from conversion of __A.
+static __inline__ __m256bh __DEFAULT_FN_ATTRS256
+_mm256_mask_cvtne2ps_pbh(__m256bh __W, __mmask16 __U, __m256 __A, __m256 __B) {
+  return (__m256bh)__builtin_ia32_selectw_256((__mmask16)__U,
+                                         (__v16hi)_mm256_cvtne2ps_pbh(__A, __B),
+                                         (__v16hi)__W);
+}
+
+/// Convert Two Packed Single Data to One Packed BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNE2PS2BF16 </c> instructions.
+///
+/// \param __A
+///    A 256-bit vector of [8 x float].
+/// \param __B
+///    A 256-bit vector of [8 x float].
+/// \param __U
+///    A 16-bit mask value specifying what is chosen for each element.
+///    A 1 means conversion of __A or __B. A 0 means element is zero.
+/// \returns A 256-bit vector of [16 x bfloat] whose lower 128 bits come from
+///    conversion of __B, and higher 128 bits come from conversion of __A.
+static __inline__ __m256bh __DEFAULT_FN_ATTRS256
+_mm256_maskz_cvtne2ps_pbh(__mmask16 __U, __m256 __A, __m256 __B) {
+  return (__m256bh)__builtin_ia32_selectw_256((__mmask16)__U,
+                                         (__v16hi)_mm256_cvtne2ps_pbh(__A, __B),
+                                         (__v16hi)_mm256_setzero_si256());
+}
+
+/// Convert Packed Single Data to Packed BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNEPS2BF16 </c> instructions.
+///
+/// \param __A
+///    A 128-bit vector of [4 x float].
+/// \returns A 128-bit vector of [8 x bfloat] whose lower 64 bits come from
+///    conversion of __A, and higher 64 bits are 0.
+static __inline__ __m128bh __DEFAULT_FN_ATTRS128
+_mm_cvtneps_pbh(__m128 __A) {
+  return (__m128bh)__builtin_ia32_cvtneps2bf16_128_mask((__v4sf) __A,
+                                                  (__v8hi)_mm_undefined_si128(),
+                                                  (__mmask8)-1);
+}
+
+/// Convert Packed Single Data to Packed BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNEPS2BF16 </c> instructions.
+///
+/// \param __A
+///    A 128-bit vector of [4 x float].
+/// \param __W
+///    A 128-bit vector of [8 x bfloat].
+/// \param __U
+///    A 4-bit mask value specifying what is chosen for each element.
+///    A 1 means conversion of __A. A 0 means element from __W.
+/// \returns A 128-bit vector of [8 x bfloat] whose lower 64 bits come from
+///    conversion of __A, and higher 64 bits are 0.
+static __inline__ __m128bh __DEFAULT_FN_ATTRS128
+_mm_mask_cvtneps_pbh(__m128bh __W, __mmask8 __U, __m128 __A) {
+  return (__m128bh)__builtin_ia32_cvtneps2bf16_128_mask((__v4sf) __A,
+                                                        (__v8hi)__W,
+                                                        (__mmask8)__U);
+}
+
+/// Convert Packed Single Data to Packed BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNEPS2BF16 </c> instructions.
+///
+/// \param __A
+///    A 128-bit vector of [4 x float].
+/// \param __U
+///    A 4-bit mask value specifying what is chosen for each element.
+///    A 1 means conversion of __A. A 0 means element is zero.
+/// \returns A 128-bit vector of [8 x bfloat] whose lower 64 bits come from
+///    conversion of __A, and higher 64 bits are 0.
+static __inline__ __m128bh __DEFAULT_FN_ATTRS128
+_mm_maskz_cvtneps_pbh(__mmask8 __U, __m128 __A) {
+  return (__m128bh)__builtin_ia32_cvtneps2bf16_128_mask((__v4sf) __A,
+                                                    (__v8hi)_mm_setzero_si128(),
+                                                    (__mmask8)__U);
+}
+
+/// Convert Packed Single Data to Packed BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNEPS2BF16 </c> instructions.
+///
+/// \param __A
+///    A 256-bit vector of [8 x float].
+/// \returns A 128-bit vector of [8 x bfloat] comes from conversion of __A.
+static __inline__ __m128bh __DEFAULT_FN_ATTRS256
+_mm256_cvtneps_pbh(__m256 __A) {
+  return (__m128bh)__builtin_ia32_cvtneps2bf16_256_mask((__v8sf)__A,
+                                                  (__v8hi)_mm_undefined_si128(),
+                                                  (__mmask8)-1);
+}
+
+/// Convert Packed Single Data to Packed BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNEPS2BF16 </c> instructions.
+///
+/// \param __A
+///    A 256-bit vector of [8 x float].
+/// \param __W
+///    A 256-bit vector of [8 x bfloat].
+/// \param __U
+///    A 8-bit mask value specifying what is chosen for each element.
+///    A 1 means conversion of __A. A 0 means element from __W.
+/// \returns A 128-bit vector of [8 x bfloat] comes from conversion of __A.
+static __inline__ __m128bh __DEFAULT_FN_ATTRS256
+_mm256_mask_cvtneps_pbh(__m128bh __W, __mmask8 __U, __m256 __A) {
+  return (__m128bh)__builtin_ia32_cvtneps2bf16_256_mask((__v8sf)__A,
+                                                        (__v8hi)__W,
+                                                        (__mmask8)__U);
+}
+
+/// Convert Packed Single Data to Packed BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNEPS2BF16 </c> instructions.
+///
+/// \param __A
+///    A 256-bit vector of [8 x float].
+/// \param __U
+///    A 8-bit mask value specifying what is chosen for each element.
+///    A 1 means conversion of __A. A 0 means element is zero.
+/// \returns A 128-bit vector of [8 x bfloat] comes from conversion of __A.
+static __inline__ __m128bh __DEFAULT_FN_ATTRS256
+_mm256_maskz_cvtneps_pbh(__mmask8 __U, __m256 __A) {
+  return (__m128bh)__builtin_ia32_cvtneps2bf16_256_mask((__v8sf)__A,
+                                                    (__v8hi)_mm_setzero_si128(),
+                                                    (__mmask8)__U);
+}
+
+/// Dot Product of BF16 Pairs Accumulated into Packed Single Precision.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VDPBF16PS </c> instructions.
+///
+/// \param __A
+///    A 128-bit vector of [8 x bfloat].
+/// \param __B
+///    A 128-bit vector of [8 x bfloat].
+/// \param __D
+///    A 128-bit vector of [4 x float].
+/// \returns A 128-bit vector of [4 x float] comes from  Dot Product of
+///  __A, __B and __D
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_dpbf16_ps(__m128 __D, __m128bh __A, __m128bh __B) {
+  return (__m128)__builtin_ia32_dpbf16ps_128((__v4sf)__D,
+                                             (__v4si)__A,
+                                             (__v4si)__B);
+}
+
+/// Dot Product of BF16 Pairs Accumulated into Packed Single Precision.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VDPBF16PS </c> instructions.
+///
+/// \param __A
+///    A 128-bit vector of [8 x bfloat].
+/// \param __B
+///    A 128-bit vector of [8 x bfloat].
+/// \param __D
+///    A 128-bit vector of [4 x float].
+/// \param __U
+///    A 8-bit mask value specifying what is chosen for each element.
+///    A 1 means __A and __B's dot product accumulated with __D. A 0 means __D.
+/// \returns A 128-bit vector of [4 x float] comes from  Dot Product of
+///  __A, __B and __D
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_mask_dpbf16_ps(__m128 __D, __mmask8 __U, __m128bh __A, __m128bh __B) {
+  return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
+                                           (__v4sf)_mm_dpbf16_ps(__D, __A, __B),
+                                           (__v4sf)__D);
+}
+
+/// Dot Product of BF16 Pairs Accumulated into Packed Single Precision.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VDPBF16PS </c> instructions.
+///
+/// \param __A
+///    A 128-bit vector of [8 x bfloat].
+/// \param __B
+///    A 128-bit vector of [8 x bfloat].
+/// \param __D
+///    A 128-bit vector of [4 x float].
+/// \param __U
+///    A 8-bit mask value specifying what is chosen for each element.
+///    A 1 means __A and __B's dot product accumulated with __D. A 0 means 0.
+/// \returns A 128-bit vector of [4 x float] comes from  Dot Product of
+///  __A, __B and __D
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_maskz_dpbf16_ps(__mmask8 __U, __m128 __D, __m128bh __A, __m128bh __B) {
+  return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
+                                           (__v4sf)_mm_dpbf16_ps(__D, __A, __B),
+                                           (__v4sf)_mm_setzero_si128());
+}
+
+/// Dot Product of BF16 Pairs Accumulated into Packed Single Precision.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VDPBF16PS </c> instructions.
+///
+/// \param __A
+///    A 256-bit vector of [16 x bfloat].
+/// \param __B
+///    A 256-bit vector of [16 x bfloat].
+/// \param __D
+///    A 256-bit vector of [8 x float].
+/// \returns A 256-bit vector of [8 x float] comes from  Dot Product of
+///  __A, __B and __D
+static __inline__ __m256 __DEFAULT_FN_ATTRS256
+_mm256_dpbf16_ps(__m256 __D, __m256bh __A, __m256bh __B) {
+  return (__m256)__builtin_ia32_dpbf16ps_256((__v8sf)__D,
+                                             (__v8si)__A,
+                                             (__v8si)__B);
+}
+
+/// Dot Product of BF16 Pairs Accumulated into Packed Single Precision.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VDPBF16PS </c> instructions.
+///
+/// \param __A
+///    A 256-bit vector of [16 x bfloat].
+/// \param __B
+///    A 256-bit vector of [16 x bfloat].
+/// \param __D
+///    A 256-bit vector of [8 x float].
+/// \param __U
+///    A 16-bit mask value specifying what is chosen for each element.
+///    A 1 means __A and __B's dot product accumulated with __D. A 0 means __D.
+/// \returns A 256-bit vector of [8 x float] comes from  Dot Product of
+///  __A, __B and __D
+static __inline__ __m256 __DEFAULT_FN_ATTRS256
+_mm256_mask_dpbf16_ps(__m256 __D, __mmask8 __U, __m256bh __A, __m256bh __B) {
+  return (__m256)__builtin_ia32_selectps_256((__mmask8)__U,
+                                        (__v8sf)_mm256_dpbf16_ps(__D, __A, __B),
+                                        (__v8sf)__D);
+}
+
+/// Dot Product of BF16 Pairs Accumulated into Packed Single Precision.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VDPBF16PS </c> instructions.
+///
+/// \param __A
+///    A 256-bit vector of [16 x bfloat].
+/// \param __B
+///    A 256-bit vector of [16 x bfloat].
+/// \param __D
+///    A 256-bit vector of [8 x float].
+/// \param __U
+///    A 8-bit mask value specifying what is chosen for each element.
+///    A 1 means __A and __B's dot product accumulated with __D. A 0 means 0.
+/// \returns A 256-bit vector of [8 x float] comes from  Dot Product of
+///  __A, __B and __D
+static __inline__ __m256 __DEFAULT_FN_ATTRS256
+_mm256_maskz_dpbf16_ps(__mmask8 __U, __m256 __D, __m256bh __A, __m256bh __B) {
+  return (__m256)__builtin_ia32_selectps_256((__mmask8)__U,
+                                        (__v8sf)_mm256_dpbf16_ps(__D, __A, __B),
+                                        (__v8sf)_mm256_setzero_si256());
+}
+
+/// Convert One Single float Data to One BF16 Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTNEPS2BF16 </c> instructions.
+///
+/// \param __A
+///    A float data.
+/// \returns A bf16 data whose sign field and exponent field keep unchanged,
+///    and fraction field is truncated to 7 bits.
+static __inline__ __bfloat16 __DEFAULT_FN_ATTRS128 _mm_cvtness_sbh(float __A) {
+  __v4sf __V = {__A, 0, 0, 0};
+  __v8hi __R = __builtin_ia32_cvtneps2bf16_128_mask(
+      (__v4sf)__V, (__v8hi)_mm_undefined_si128(), (__mmask8)-1);
+  return __R[0];
+}
+
+/// Convert Packed BF16 Data to Packed float Data.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \param __A
+///    A 128-bit vector of [8 x bfloat].
+/// \returns A 256-bit vector of [8 x float] come from convertion of __A
+static __inline__ __m256 __DEFAULT_FN_ATTRS256 _mm256_cvtpbh_ps(__m128bh __A) {
+  return _mm256_castsi256_ps((__m256i)_mm256_slli_epi32(
+      (__m256i)_mm256_cvtepi16_epi32((__m128i)__A), 16));
+}
+
+/// Convert Packed BF16 Data to Packed float Data using zeroing mask.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \param __U
+///    A 8-bit mask. Elements are zeroed out when the corresponding mask
+///    bit is not set.
+/// \param __A
+///    A 128-bit vector of [8 x bfloat].
+/// \returns A 256-bit vector of [8 x float] come from convertion of __A
+static __inline__ __m256 __DEFAULT_FN_ATTRS256
+_mm256_maskz_cvtpbh_ps(__mmask8 __U, __m128bh __A) {
+  return _mm256_castsi256_ps((__m256i)_mm256_slli_epi32(
+      (__m256i)_mm256_maskz_cvtepi16_epi32((__mmask8)__U, (__m128i)__A), 16));
+}
+
+/// Convert Packed BF16 Data to Packed float Data using merging mask.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \param __S
+///    A 256-bit vector of [8 x float]. Elements are copied from __S when
+///     the corresponding mask bit is not set.
+/// \param __U
+///    A 8-bit mask. Elements are zeroed out when the corresponding mask
+///    bit is not set.
+/// \param __A
+///    A 128-bit vector of [8 x bfloat].
+/// \returns A 256-bit vector of [8 x float] come from convertion of __A
+static __inline__ __m256 __DEFAULT_FN_ATTRS256
+_mm256_mask_cvtpbh_ps(__m256 __S, __mmask8 __U, __m128bh __A) {
+  return _mm256_castsi256_ps((__m256i)_mm256_mask_slli_epi32(
+      (__m256i)__S, (__mmask8)__U, (__m256i)_mm256_cvtepi16_epi32((__m128i)__A),
+      16));
+}
+
+#undef __DEFAULT_FN_ATTRS128
+#undef __DEFAULT_FN_ATTRS256
+
+#endif
@@ -1,23 +1,9 @@
 /*===---- avx512vlbitalgintrin.h - BITALG intrinsics -----------------------===
 *
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- avx512vlbwintrin.h - AVX512VL and AVX512BW intrinsics ------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -2301,7 +2287,7 @@ static __inline __m128i __DEFAULT_FN_ATTRS128
 _mm_loadu_epi16 (void const *__P)
 {
  struct __loadu_epi16 {
-    __m128i __v;
+    __m128i_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_epi16*)__P)->__v;
 }
@@ -2327,7 +2313,7 @@ static __inline __m256i __DEFAULT_FN_ATTRS256
 _mm256_loadu_epi16 (void const *__P)
 {
  struct __loadu_epi16 {
-    __m256i __v;
+    __m256i_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_epi16*)__P)->__v;
 }
@@ -2353,7 +2339,7 @@ static __inline __m128i __DEFAULT_FN_ATTRS128
 _mm_loadu_epi8 (void const *__P)
 {
  struct __loadu_epi8 {
-    __m128i __v;
+    __m128i_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_epi8*)__P)->__v;
 }
@@ -2379,7 +2365,7 @@ static __inline __m256i __DEFAULT_FN_ATTRS256
 _mm256_loadu_epi8 (void const *__P)
 {
  struct __loadu_epi8 {
-    __m256i __v;
+    __m256i_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_epi8*)__P)->__v;
 }
@@ -2405,7 +2391,7 @@ static __inline void __DEFAULT_FN_ATTRS128
 _mm_storeu_epi16 (void *__P, __m128i __A)
 {
  struct __storeu_epi16 {
-    __m128i __v;
+    __m128i_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_epi16*)__P)->__v = __A;
 }
@@ -2422,7 +2408,7 @@ static __inline void __DEFAULT_FN_ATTRS256
 _mm256_storeu_epi16 (void *__P, __m256i __A)
 {
  struct __storeu_epi16 {
-    __m256i __v;
+    __m256i_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_epi16*)__P)->__v = __A;
 }
@@ -2439,7 +2425,7 @@ static __inline void __DEFAULT_FN_ATTRS128
 _mm_storeu_epi8 (void *__P, __m128i __A)
 {
  struct __storeu_epi8 {
-    __m128i __v;
+    __m128i_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_epi8*)__P)->__v = __A;
 }
@@ -2456,7 +2442,7 @@ static __inline void __DEFAULT_FN_ATTRS256
 _mm256_storeu_epi8 (void *__P, __m256i __A)
 {
  struct __storeu_epi8 {
-    __m256i __v;
+    __m256i_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_epi8*)__P)->__v = __A;
 }
@@ -1,22 +1,8 @@
 /*===---- avx512vlcdintrin.h - AVX512VL and AVX512CD intrinsics ------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -60,99 +46,89 @@ _mm256_broadcastmw_epi32 (__mmask16 __A)
 static __inline__ __m128i __DEFAULT_FN_ATTRS128
 _mm_conflict_epi64 (__m128i __A)
 {
-  return (__m128i) __builtin_ia32_vpconflictdi_128_mask ((__v2di) __A,
-               (__v2di) _mm_undefined_si128 (),
-               (__mmask8) -1);
+  return (__m128i) __builtin_ia32_vpconflictdi_128 ((__v2di) __A);
 }

 static __inline__ __m128i __DEFAULT_FN_ATTRS128
 _mm_mask_conflict_epi64 (__m128i __W, __mmask8 __U, __m128i __A)
 {
-  return (__m128i) __builtin_ia32_vpconflictdi_128_mask ((__v2di) __A,
-               (__v2di) __W,
-               (__mmask8) __U);
+  return (__m128i)__builtin_ia32_selectq_128((__mmask8)__U,
+                                             (__v2di)_mm_conflict_epi64(__A),
+                                             (__v2di)__W);
 }

 static __inline__ __m128i __DEFAULT_FN_ATTRS128
 _mm_maskz_conflict_epi64 (__mmask8 __U, __m128i __A)
 {
-  return (__m128i) __builtin_ia32_vpconflictdi_128_mask ((__v2di) __A,
-               (__v2di)
-               _mm_setzero_si128 (),
-               (__mmask8) __U);
+  return (__m128i)__builtin_ia32_selectq_128((__mmask8)__U,
+                                             (__v2di)_mm_conflict_epi64(__A),
+                                             (__v2di)_mm_setzero_si128());
 }

 static __inline__ __m256i __DEFAULT_FN_ATTRS256
 _mm256_conflict_epi64 (__m256i __A)
 {
-  return (__m256i) __builtin_ia32_vpconflictdi_256_mask ((__v4di) __A,
-               (__v4di)  _mm256_undefined_si256 (),
-               (__mmask8) -1);
+  return (__m256i) __builtin_ia32_vpconflictdi_256 ((__v4di) __A);
 }

 static __inline__ __m256i __DEFAULT_FN_ATTRS256
 _mm256_mask_conflict_epi64 (__m256i __W, __mmask8 __U, __m256i __A)
 {
-  return (__m256i) __builtin_ia32_vpconflictdi_256_mask ((__v4di) __A,
-               (__v4di) __W,
-               (__mmask8) __U);
+  return (__m256i)__builtin_ia32_selectq_256((__mmask8)__U,
+                                             (__v4di)_mm256_conflict_epi64(__A),
+                                             (__v4di)__W);
 }

 static __inline__ __m256i __DEFAULT_FN_ATTRS256
 _mm256_maskz_conflict_epi64 (__mmask8 __U, __m256i __A)
 {
-  return (__m256i) __builtin_ia32_vpconflictdi_256_mask ((__v4di) __A,
-               (__v4di) _mm256_setzero_si256 (),
-               (__mmask8) __U);
+  return (__m256i)__builtin_ia32_selectq_256((__mmask8)__U,
+                                             (__v4di)_mm256_conflict_epi64(__A),
+                                             (__v4di)_mm256_setzero_si256());
 }

 static __inline__ __m128i __DEFAULT_FN_ATTRS128
 _mm_conflict_epi32 (__m128i __A)
 {
-  return (__m128i) __builtin_ia32_vpconflictsi_128_mask ((__v4si) __A,
-               (__v4si) _mm_undefined_si128 (),
-               (__mmask8) -1);
+  return (__m128i) __builtin_ia32_vpconflictsi_128 ((__v4si) __A);
 }

 static __inline__ __m128i __DEFAULT_FN_ATTRS128
 _mm_mask_conflict_epi32 (__m128i __W, __mmask8 __U, __m128i __A)
 {
-  return (__m128i) __builtin_ia32_vpconflictsi_128_mask ((__v4si) __A,
-               (__v4si) __W,
-               (__mmask8) __U);
+  return (__m128i)__builtin_ia32_selectd_128((__mmask8)__U,
+                                             (__v4si)_mm_conflict_epi32(__A),
+                                             (__v4si)__W);
 }

 static __inline__ __m128i __DEFAULT_FN_ATTRS128
 _mm_maskz_conflict_epi32 (__mmask8 __U, __m128i __A)
 {
-  return (__m128i) __builtin_ia32_vpconflictsi_128_mask ((__v4si) __A,
-               (__v4si) _mm_setzero_si128 (),
-               (__mmask8) __U);
+  return (__m128i)__builtin_ia32_selectd_128((__mmask8)__U,
+                                             (__v4si)_mm_conflict_epi32(__A),
+                                             (__v4si)_mm_setzero_si128());
 }

 static __inline__ __m256i __DEFAULT_FN_ATTRS256
 _mm256_conflict_epi32 (__m256i __A)
 {
-  return (__m256i) __builtin_ia32_vpconflictsi_256_mask ((__v8si) __A,
-               (__v8si) _mm256_undefined_si256 (),
-               (__mmask8) -1);
+  return (__m256i) __builtin_ia32_vpconflictsi_256 ((__v8si) __A);
 }

 static __inline__ __m256i __DEFAULT_FN_ATTRS256
 _mm256_mask_conflict_epi32 (__m256i __W, __mmask8 __U, __m256i __A)
 {
-  return (__m256i) __builtin_ia32_vpconflictsi_256_mask ((__v8si) __A,
-               (__v8si) __W,
-               (__mmask8) __U);
+  return (__m256i)__builtin_ia32_selectd_256((__mmask8)__U,
+                                             (__v8si)_mm256_conflict_epi32(__A),
+                                             (__v8si)__W);
 }

 static __inline__ __m256i __DEFAULT_FN_ATTRS256
 _mm256_maskz_conflict_epi32 (__mmask8 __U, __m256i __A)
 {
-  return (__m256i) __builtin_ia32_vpconflictsi_256_mask ((__v8si) __A,
-               (__v8si)
-               _mm256_setzero_si256 (),
-               (__mmask8) __U);
+  return (__m256i)__builtin_ia32_selectd_256((__mmask8)__U,
+                                             (__v8si)_mm256_conflict_epi32(__A),
+                                             (__v8si)_mm256_setzero_si256());
 }

 static __inline__ __m128i __DEFAULT_FN_ATTRS128
@@ -1,22 +1,8 @@
 /*===---- avx512vldqintrin.h - AVX512VL and AVX512DQ intrinsics ------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -523,23 +509,21 @@ _mm_maskz_cvtepi64_ps (__mmask8 __U, __m128i __A) {

 static __inline__ __m128 __DEFAULT_FN_ATTRS256
 _mm256_cvtepi64_ps (__m256i __A) {
-  return (__m128) __builtin_ia32_cvtqq2ps256_mask ((__v4di) __A,
-                (__v4sf) _mm_setzero_ps(),
-                (__mmask8) -1);
+  return (__m128)__builtin_convertvector((__v4di)__A, __v4sf);
 }

 static __inline__ __m128 __DEFAULT_FN_ATTRS256
 _mm256_mask_cvtepi64_ps (__m128 __W, __mmask8 __U, __m256i __A) {
-  return (__m128) __builtin_ia32_cvtqq2ps256_mask ((__v4di) __A,
-                (__v4sf) __W,
-                (__mmask8) __U);
+  return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
+                                             (__v4sf)_mm256_cvtepi64_ps(__A),
+                                             (__v4sf)__W);
 }

 static __inline__ __m128 __DEFAULT_FN_ATTRS256
 _mm256_maskz_cvtepi64_ps (__mmask8 __U, __m256i __A) {
-  return (__m128) __builtin_ia32_cvtqq2ps256_mask ((__v4di) __A,
-                (__v4sf) _mm_setzero_ps(),
-                (__mmask8) __U);
+  return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
+                                             (__v4sf)_mm256_cvtepi64_ps(__A),
+                                             (__v4sf)_mm_setzero_ps());
 }

 static __inline__ __m128i __DEFAULT_FN_ATTRS128
@@ -771,23 +755,21 @@ _mm_maskz_cvtepu64_ps (__mmask8 __U, __m128i __A) {

 static __inline__ __m128 __DEFAULT_FN_ATTRS256
 _mm256_cvtepu64_ps (__m256i __A) {
-  return (__m128) __builtin_ia32_cvtuqq2ps256_mask ((__v4di) __A,
-                (__v4sf) _mm_setzero_ps(),
-                (__mmask8) -1);
+  return (__m128)__builtin_convertvector((__v4du)__A, __v4sf);
 }

 static __inline__ __m128 __DEFAULT_FN_ATTRS256
 _mm256_mask_cvtepu64_ps (__m128 __W, __mmask8 __U, __m256i __A) {
-  return (__m128) __builtin_ia32_cvtuqq2ps256_mask ((__v4di) __A,
-                (__v4sf) __W,
-                (__mmask8) __U);
+  return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
+                                             (__v4sf)_mm256_cvtepu64_ps(__A),
+                                             (__v4sf)__W);
 }

 static __inline__ __m128 __DEFAULT_FN_ATTRS256
 _mm256_maskz_cvtepu64_ps (__mmask8 __U, __m256i __A) {
-  return (__m128) __builtin_ia32_cvtuqq2ps256_mask ((__v4di) __A,
-                (__v4sf) _mm_setzero_ps(),
-                (__mmask8) __U);
+  return (__m128)__builtin_ia32_selectps_128((__mmask8)__U,
+                                             (__v4sf)_mm256_cvtepu64_ps(__A),
+                                             (__v4sf)_mm_setzero_ps());
 }

 #define _mm_range_pd(A, B, C) \
@@ -1,22 +1,8 @@
 /*===---- avx512vlintrin.h - AVX512VL intrinsics ---------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -5513,7 +5499,7 @@ static __inline __m128i __DEFAULT_FN_ATTRS128
 _mm_loadu_epi64 (void const *__P)
 {
  struct __loadu_epi64 {
-    __m128i __v;
+    __m128i_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_epi64*)__P)->__v;
 }
@@ -5539,7 +5525,7 @@ static __inline __m256i __DEFAULT_FN_ATTRS256
 _mm256_loadu_epi64 (void const *__P)
 {
  struct __loadu_epi64 {
-    __m256i __v;
+    __m256i_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_epi64*)__P)->__v;
 }
@@ -5565,7 +5551,7 @@ static __inline __m128i __DEFAULT_FN_ATTRS128
 _mm_loadu_epi32 (void const *__P)
 {
  struct __loadu_epi32 {
-    __m128i __v;
+    __m128i_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_epi32*)__P)->__v;
 }
@@ -5591,7 +5577,7 @@ static __inline __m256i __DEFAULT_FN_ATTRS256
 _mm256_loadu_epi32 (void const *__P)
 {
  struct __loadu_epi32 {
-    __m256i __v;
+    __m256i_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_epi32*)__P)->__v;
 }
@@ -5717,7 +5703,7 @@ static __inline void __DEFAULT_FN_ATTRS128
 _mm_storeu_epi64 (void *__P, __m128i __A)
 {
  struct __storeu_epi64 {
-    __m128i __v;
+    __m128i_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_epi64*)__P)->__v = __A;
 }
@@ -5734,7 +5720,7 @@ static __inline void __DEFAULT_FN_ATTRS256
 _mm256_storeu_epi64 (void *__P, __m256i __A)
 {
  struct __storeu_epi64 {
-    __m256i __v;
+    __m256i_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_epi64*)__P)->__v = __A;
 }
@@ -5751,7 +5737,7 @@ static __inline void __DEFAULT_FN_ATTRS128
 _mm_storeu_epi32 (void *__P, __m128i __A)
 {
  struct __storeu_epi32 {
-    __m128i __v;
+    __m128i_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_epi32*)__P)->__v = __A;
 }
@@ -5768,7 +5754,7 @@ static __inline void __DEFAULT_FN_ATTRS256
 _mm256_storeu_epi32 (void *__P, __m256i __A)
 {
  struct __storeu_epi32 {
-    __m256i __v;
+    __m256i_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_epi32*)__P)->__v = __A;
 }
@@ -7000,7 +6986,7 @@ _mm_mask_cvtsepi32_storeu_epi8 (void * __P, __mmask8 __M, __m128i __A)
  __builtin_ia32_pmovsdb128mem_mask ((__v16qi *) __P, (__v4si) __A, __M);
 }

-static __inline__ __m128i __DEFAULT_FN_ATTRS128
+static __inline__ __m128i __DEFAULT_FN_ATTRS256
 _mm256_cvtsepi32_epi8 (__m256i __A)
 {
  return (__m128i) __builtin_ia32_pmovsdb256_mask ((__v8si) __A,
@@ -7023,7 +7009,7 @@ _mm256_maskz_cvtsepi32_epi8 (__mmask8 __M, __m256i __A)
               __M);
 }

-static __inline__ void __DEFAULT_FN_ATTRS128
+static __inline__ void __DEFAULT_FN_ATTRS256
 _mm256_mask_cvtsepi32_storeu_epi8 (void * __P, __mmask8 __M, __m256i __A)
 {
  __builtin_ia32_pmovsdb256mem_mask ((__v16qi *) __P, (__v8si) __A, __M);
@@ -7581,7 +7567,7 @@ _mm_maskz_cvtepi32_epi8 (__mmask8 __M, __m128i __A)
              __M);
 }

-static __inline__ void __DEFAULT_FN_ATTRS256
+static __inline__ void __DEFAULT_FN_ATTRS128
 _mm_mask_cvtepi32_storeu_epi8 (void * __P, __mmask8 __M, __m128i __A)
 {
  __builtin_ia32_pmovdb128mem_mask ((__v16qi *) __P, (__v4si) __A, __M);
@@ -8425,22 +8411,6 @@ _mm256_maskz_cvtph_ps (__mmask8 __U, __m128i __A)
                (__mmask8) __U);
 }

-static __inline __m128i __DEFAULT_FN_ATTRS128
-_mm_mask_cvtps_ph (__m128i __W, __mmask8 __U, __m128 __A)
-{
-  return (__m128i) __builtin_ia32_vcvtps2ph_mask ((__v4sf) __A, _MM_FROUND_CUR_DIRECTION,
-                                                  (__v8hi) __W,
-                                                  (__mmask8) __U);
-}
-
-static __inline __m128i __DEFAULT_FN_ATTRS128
-_mm_maskz_cvtps_ph (__mmask8 __U, __m128 __A)
-{
-  return (__m128i) __builtin_ia32_vcvtps2ph_mask ((__v4sf) __A, _MM_FROUND_CUR_DIRECTION,
-                                                  (__v8hi) _mm_setzero_si128 (),
-                                                  (__mmask8) __U);
-}
-
 #define _mm_mask_cvt_roundps_ph(W, U, A, I) \
  (__m128i)__builtin_ia32_vcvtps2ph_mask((__v4sf)(__m128)(A), (int)(I), \
                                         (__v8hi)(__m128i)(W), \
@@ -8451,21 +8421,9 @@ _mm_maskz_cvtps_ph (__mmask8 __U, __m128 __A)
                                         (__v8hi)_mm_setzero_si128(), \
                                         (__mmask8)(U))

-static __inline __m128i __DEFAULT_FN_ATTRS256
-_mm256_mask_cvtps_ph (__m128i __W, __mmask8 __U, __m256 __A)
-{
-  return (__m128i) __builtin_ia32_vcvtps2ph256_mask ((__v8sf) __A, _MM_FROUND_CUR_DIRECTION,
-                                                      (__v8hi) __W,
-                                                      (__mmask8) __U);
-}
+#define _mm_mask_cvtps_ph  _mm_mask_cvt_roundps_ph
+#define _mm_maskz_cvtps_ph _mm_maskz_cvt_roundps_ph

-static __inline __m128i __DEFAULT_FN_ATTRS256
-_mm256_maskz_cvtps_ph ( __mmask8 __U, __m256 __A)
-{
-  return (__m128i) __builtin_ia32_vcvtps2ph256_mask ((__v8sf) __A, _MM_FROUND_CUR_DIRECTION,
-                                                      (__v8hi) _mm_setzero_si128(),
-                                                      (__mmask8) __U);
-}
 #define _mm256_mask_cvt_roundps_ph(W, U, A, I) \
  (__m128i)__builtin_ia32_vcvtps2ph256_mask((__v8sf)(__m256)(A), (int)(I), \
                                            (__v8hi)(__m128i)(W), \
@@ -8476,6 +8434,9 @@ _mm256_maskz_cvtps_ph ( __mmask8 __U, __m256 __A)
                                            (__v8hi)_mm_setzero_si128(), \
                                            (__mmask8)(U))

+#define _mm256_mask_cvtps_ph  _mm256_mask_cvt_roundps_ph
+#define _mm256_maskz_cvtps_ph _mm256_maskz_cvt_roundps_ph
+

 #undef __DEFAULT_FN_ATTRS128
 #undef __DEFAULT_FN_ATTRS256
@@ -1,23 +1,9 @@
 /*===------------- avx512vlvbmi2intrin.h - VBMI2 intrinsics -----------------===
 *
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,23 +1,9 @@
 /*===------------- avx512vlvnniintrin.h - VNNI intrinsics ------------------===
 *
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -0,0 +1,121 @@
+/*===------ avx512vlvp2intersectintrin.h - VL VP2INTERSECT intrinsics ------===
+ *
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ *
+ *===-----------------------------------------------------------------------===
+ */
+#ifndef __IMMINTRIN_H
+#error "Never use <avx512vlvp2intersectintrin.h> directly; include <immintrin.h> instead."
+#endif
+
+#ifndef _AVX512VLVP2INTERSECT_H
+#define _AVX512VLVP2INTERSECT_H
+
+#define __DEFAULT_FN_ATTRS128 \
+  __attribute__((__always_inline__, __nodebug__,  __target__("avx512vl,avx512vp2intersect"), \
+                 __min_vector_width__(128)))
+
+#define __DEFAULT_FN_ATTRS256 \
+  __attribute__((__always_inline__, __nodebug__,  __target__("avx512vl,avx512vp2intersect"), \
+                 __min_vector_width__(256)))
+/// Store, in an even/odd pair of mask registers, the indicators of the
+/// locations of value matches between dwords in operands __a and __b.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VP2INTERSECTD </c> instruction.
+///
+/// \param __a
+///    A 256-bit vector of [8 x i32].
+/// \param __b
+///    A 256-bit vector of [8 x i32]
+/// \param __m0
+///    A pointer point to 8-bit mask
+/// \param __m1
+///    A pointer point to 8-bit mask
+static __inline__ void __DEFAULT_FN_ATTRS256
+_mm256_2intersect_epi32(__m256i __a, __m256i __b, __mmask8 *__m0, __mmask8 *__m1) {
+  __builtin_ia32_vp2intersect_d_256((__v8si)__a, (__v8si)__b, __m0, __m1);
+}
+
+/// Store, in an even/odd pair of mask registers, the indicators of the
+/// locations of value matches between quadwords in operands __a and __b.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VP2INTERSECTQ </c> instruction.
+///
+/// \param __a
+///    A 256-bit vector of [4 x i64].
+/// \param __b
+///    A 256-bit vector of [4 x i64]
+/// \param __m0
+///    A pointer point to 8-bit mask
+/// \param __m1
+///    A pointer point to 8-bit mask
+static __inline__ void __DEFAULT_FN_ATTRS256
+_mm256_2intersect_epi64(__m256i __a, __m256i __b, __mmask8 *__m0, __mmask8 *__m1) {
+  __builtin_ia32_vp2intersect_q_256((__v4di)__a, (__v4di)__b, __m0, __m1);
+}
+
+/// Store, in an even/odd pair of mask registers, the indicators of the
+/// locations of value matches between dwords in operands __a and __b.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VP2INTERSECTD </c> instruction.
+///
+/// \param __a
+///    A 128-bit vector of [4 x i32].
+/// \param __b
+///    A 128-bit vector of [4 x i32]
+/// \param __m0
+///    A pointer point to 8-bit mask
+/// \param __m1
+///    A pointer point to 8-bit mask
+static __inline__ void __DEFAULT_FN_ATTRS128
+_mm_2intersect_epi32(__m128i __a, __m128i __b, __mmask8 *__m0, __mmask8 *__m1) {
+  __builtin_ia32_vp2intersect_d_128((__v4si)__a, (__v4si)__b, __m0, __m1);
+}
+
+/// Store, in an even/odd pair of mask registers, the indicators of the
+/// locations of value matches between quadwords in operands __a and __b.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VP2INTERSECTQ </c> instruction.
+///
+/// \param __a
+///    A 128-bit vector of [2 x i64].
+/// \param __b
+///    A 128-bit vector of [2 x i64]
+/// \param __m0
+///    A pointer point to 8-bit mask
+/// \param __m1
+///    A pointer point to 8-bit mask
+static __inline__ void __DEFAULT_FN_ATTRS128
+_mm_2intersect_epi64(__m128i __a, __m128i __b, __mmask8 *__m0, __mmask8 *__m1) {
+  __builtin_ia32_vp2intersect_q_128((__v2di)__a, (__v2di)__b, __m0, __m1);
+}
+
+#undef __DEFAULT_FN_ATTRS128
+#undef __DEFAULT_FN_ATTRS256
+
+#endif
@@ -1,23 +1,9 @@
 /*===------------- avx512vnniintrin.h - VNNI intrinsics ------------------===
 *
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -0,0 +1,77 @@
+/*===------- avx512vpintersectintrin.h - VP2INTERSECT intrinsics ------------===
+ *
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ *
+ *===-----------------------------------------------------------------------===
+ */
+#ifndef __IMMINTRIN_H
+#error "Never use <avx512vp2intersect.h> directly; include <immintrin.h> instead."
+#endif
+
+#ifndef _AVX512VP2INTERSECT_H
+#define _AVX512VP2INTERSECT_H
+
+#define __DEFAULT_FN_ATTRS \
+  __attribute__((__always_inline__, __nodebug__,  __target__("avx512vp2intersect"), \
+                 __min_vector_width__(512)))
+
+/// Store, in an even/odd pair of mask registers, the indicators of the
+/// locations of value matches between dwords in operands __a and __b.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VP2INTERSECTD </c> instruction.
+///
+/// \param __a
+///    A 512-bit vector of [16 x i32].
+/// \param __b
+///    A 512-bit vector of [16 x i32]
+/// \param __m0
+///    A pointer point to 16-bit mask
+/// \param __m1
+///    A pointer point to 16-bit mask
+static __inline__ void __DEFAULT_FN_ATTRS
+_mm512_2intersect_epi32(__m512i __a, __m512i __b, __mmask16 *__m0, __mmask16 *__m1) {
+  __builtin_ia32_vp2intersect_d_512((__v16si)__a, (__v16si)__b, __m0, __m1);
+}
+
+/// Store, in an even/odd pair of mask registers, the indicators of the
+/// locations of value matches between quadwords in operands __a and __b.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VP2INTERSECTQ </c> instruction.
+///
+/// \param __a
+///    A 512-bit vector of [8 x i64].
+/// \param __b
+///    A 512-bit vector of [8 x i64]
+/// \param __m0
+///    A pointer point to 8-bit mask
+/// \param __m1
+///    A pointer point to 8-bit mask
+static __inline__ void __DEFAULT_FN_ATTRS
+_mm512_2intersect_epi64(__m512i __a, __m512i __b, __mmask8 *__m0, __mmask8 *__m1) {
+  __builtin_ia32_vp2intersect_q_512((__v8di)__a, (__v8di)__b, __m0, __m1);
+}
+
+#undef __DEFAULT_FN_ATTRS
+
+#endif
@@ -1,23 +1,9 @@
 /*===----- avx512vpopcntdqintrin.h - AVX512VPOPCNTDQ intrinsics-------------===
 *
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,23 +1,9 @@
 /*===---- avx512vpopcntdqintrin.h - AVX512VPOPCNTDQ intrinsics -------------===
 *
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- avxintrin.h - AVX intrinsics -------------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -45,9 +31,13 @@ typedef unsigned char __v32qu __attribute__ ((__vector_size__ (32)));
 * appear in the interface though. */
 typedef signed char __v32qs __attribute__((__vector_size__(32)));

-typedef float __m256 __attribute__ ((__vector_size__ (32)));
-typedef double __m256d __attribute__((__vector_size__(32)));
-typedef long long __m256i __attribute__((__vector_size__(32)));
+typedef float __m256 __attribute__ ((__vector_size__ (32), __aligned__(32)));
+typedef double __m256d __attribute__((__vector_size__(32), __aligned__(32)));
+typedef long long __m256i __attribute__((__vector_size__(32), __aligned__(32)));
+
+typedef float __m256_u __attribute__ ((__vector_size__ (32), __aligned__(1)));
+typedef double __m256d_u __attribute__((__vector_size__(32), __aligned__(1)));
+typedef long long __m256i_u __attribute__((__vector_size__(32), __aligned__(1)));

 /* Define the default attributes for the functions in this file. */
 #define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("avx"), __min_vector_width__(256)))
@@ -3113,7 +3103,7 @@ static __inline __m256d __DEFAULT_FN_ATTRS
 _mm256_loadu_pd(double const *__p)
 {
  struct __loadu_pd {
-    __m256d __v;
+    __m256d_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_pd*)__p)->__v;
 }
@@ -3133,7 +3123,7 @@ static __inline __m256 __DEFAULT_FN_ATTRS
 _mm256_loadu_ps(float const *__p)
 {
  struct __loadu_ps {
-    __m256 __v;
+    __m256_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_ps*)__p)->__v;
 }
@@ -3166,10 +3156,10 @@ _mm256_load_si256(__m256i const *__p)
 ///    A pointer to a 256-bit integer vector containing integer values.
 /// \returns A 256-bit integer vector containing the moved values.
 static __inline __m256i __DEFAULT_FN_ATTRS
-_mm256_loadu_si256(__m256i const *__p)
+_mm256_loadu_si256(__m256i_u const *__p)
 {
  struct __loadu_si256 {
-    __m256i __v;
+    __m256i_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_si256*)__p)->__v;
 }
@@ -3246,7 +3236,7 @@ static __inline void __DEFAULT_FN_ATTRS
 _mm256_storeu_pd(double *__p, __m256d __a)
 {
  struct __storeu_pd {
-    __m256d __v;
+    __m256d_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_pd*)__p)->__v = __a;
 }
@@ -3266,7 +3256,7 @@ static __inline void __DEFAULT_FN_ATTRS
 _mm256_storeu_ps(float *__p, __m256 __a)
 {
  struct __storeu_ps {
-    __m256 __v;
+    __m256_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_ps*)__p)->__v = __a;
 }
@@ -3301,10 +3291,10 @@ _mm256_store_si256(__m256i *__p, __m256i __a)
 /// \param __a
 ///    A 256-bit integer vector containing the values to be moved.
 static __inline void __DEFAULT_FN_ATTRS
-_mm256_storeu_si256(__m256i *__p, __m256i __a)
+_mm256_storeu_si256(__m256i_u *__p, __m256i __a)
 {
  struct __storeu_si256 {
-    __m256i __v;
+    __m256i_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_si256*)__p)->__v = __a;
 }
@@ -4834,7 +4824,7 @@ _mm256_loadu2_m128d(double const *__addr_hi, double const *__addr_lo)
 ///    address of the memory location does not have to be aligned.
 /// \returns A 256-bit integer vector containing the concatenated result.
 static __inline __m256i __DEFAULT_FN_ATTRS
-_mm256_loadu2_m128i(__m128i const *__addr_hi, __m128i const *__addr_lo)
+_mm256_loadu2_m128i(__m128i_u const *__addr_hi, __m128i_u const *__addr_lo)
 {
  __m256i __v256 = _mm256_castsi128_si256(_mm_loadu_si128(__addr_lo));
  return _mm256_insertf128_si256(__v256, _mm_loadu_si128(__addr_hi), 1);
@@ -4918,7 +4908,7 @@ _mm256_storeu2_m128d(double *__addr_hi, double *__addr_lo, __m256d __a)
 /// \param __a
 ///    A 256-bit integer vector.
 static __inline void __DEFAULT_FN_ATTRS
-_mm256_storeu2_m128i(__m128i *__addr_hi, __m128i *__addr_lo, __m256i __a)
+_mm256_storeu2_m128i(__m128i_u *__addr_hi, __m128i_u *__addr_lo, __m256i __a)
 {
  __m128i __v128;

@@ -1,22 +1,8 @@
 /*===---- bmi2intrin.h - BMI2 intrinsics -----------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- bmiintrin.h - BMI intrinsics -------------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- cetintrin.h - CET intrinsic --------------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- cldemoteintrin.h - CLDEMOTE intrinsic ----------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- clflushoptintrin.h - CLFLUSHOPT intrinsic ------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- clwbintrin.h - CLWB intrinsic ------------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===----------------------- clzerointrin.h - CLZERO ----------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- cpuid.h - X86 cpu model detection --------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -191,6 +177,7 @@
 #define bit_CLDEMOTE         0x02000000
 #define bit_MOVDIRI          0x08000000
 #define bit_MOVDIR64B        0x10000000
+#define bit_ENQCMD           0x20000000

 /* Features in %edx for leaf 7 sub-leaf 0 */
 #define bit_AVX5124VNNIW  0x00000004
@@ -198,6 +185,9 @@
 #define bit_PCONFIG       0x00040000
 #define bit_IBT           0x00100000

+/* Features in %eax for leaf 7 sub-leaf 1 */
+#define bit_AVX512BF16    0x00000020
+
 /* Features in %eax for leaf 13 sub-leaf 1 */
 #define bit_XSAVEOPT    0x00000001
 #define bit_XSAVEC      0x00000002
@@ -1,22 +1,8 @@
 /*===---- emmintrin.h - SSE2 intrinsics ------------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -26,8 +12,11 @@

 #include <xmmintrin.h>

-typedef double __m128d __attribute__((__vector_size__(16)));
-typedef long long __m128i __attribute__((__vector_size__(16)));
+typedef double __m128d __attribute__((__vector_size__(16), __aligned__(16)));
+typedef long long __m128i __attribute__((__vector_size__(16), __aligned__(16)));
+
+typedef double __m128d_u __attribute__((__vector_size__(16), __aligned__(1)));
+typedef long long __m128i_u __attribute__((__vector_size__(16), __aligned__(1)));

 /* Type defines.  */
 typedef double __v2df __attribute__ ((__vector_size__ (16)));
@@ -1652,7 +1641,7 @@ static __inline__ __m128d __DEFAULT_FN_ATTRS
 _mm_loadu_pd(double const *__dp)
 {
  struct __loadu_pd {
-    __m128d __v;
+    __m128d_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_pd*)__dp)->__v;
 }
@@ -2042,7 +2031,7 @@ static __inline__ void __DEFAULT_FN_ATTRS
 _mm_storeu_pd(double *__dp, __m128d __a)
 {
  struct __storeu_pd {
-    __m128d __v;
+    __m128d_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_pd*)__dp)->__v = __a;
 }
@@ -2316,11 +2305,7 @@ _mm_adds_epu16(__m128i __a, __m128i __b)
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_avg_epu8(__m128i __a, __m128i __b)
 {
-  typedef unsigned short __v16hu __attribute__ ((__vector_size__ (32)));
-  return (__m128i)__builtin_convertvector(
-               ((__builtin_convertvector((__v16qu)__a, __v16hu) +
-                 __builtin_convertvector((__v16qu)__b, __v16hu)) + 1)
-                 >> 1, __v16qu);
+  return (__m128i)__builtin_ia32_pavgb128((__v16qi)__a, (__v16qi)__b);
 }

 /// Computes the rounded avarages of corresponding elements of two
@@ -2340,11 +2325,7 @@ _mm_avg_epu8(__m128i __a, __m128i __b)
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_avg_epu16(__m128i __a, __m128i __b)
 {
-  typedef unsigned int __v8su __attribute__ ((__vector_size__ (32)));
-  return (__m128i)__builtin_convertvector(
-               ((__builtin_convertvector((__v8hu)__a, __v8su) +
-                 __builtin_convertvector((__v8hu)__b, __v8su)) + 1)
-                 >> 1, __v8hu);
+  return (__m128i)__builtin_ia32_pavgw128((__v8hi)__a, (__v8hi)__b);
 }

 /// Multiplies the corresponding elements of two 128-bit signed [8 x i16]
@@ -3564,10 +3545,10 @@ _mm_load_si128(__m128i const *__p)
 ///    A pointer to a memory location containing integer values.
 /// \returns A 128-bit integer vector containing the moved values.
 static __inline__ __m128i __DEFAULT_FN_ATTRS
-_mm_loadu_si128(__m128i const *__p)
+_mm_loadu_si128(__m128i_u const *__p)
 {
  struct __loadu_si128 {
-    __m128i __v;
+    __m128i_u __v;
  } __attribute__((__packed__, __may_alias__));
  return ((struct __loadu_si128*)__p)->__v;
 }
@@ -3585,7 +3566,7 @@ _mm_loadu_si128(__m128i const *__p)
 /// \returns A 128-bit vector of [2 x i64]. The lower order bits contain the
 ///    moved value. The higher order bits are cleared.
 static __inline__ __m128i __DEFAULT_FN_ATTRS
-_mm_loadl_epi64(__m128i const *__p)
+_mm_loadl_epi64(__m128i_u const *__p)
 {
  struct __mm_loadl_epi64_struct {
    long long __u;
@@ -4027,10 +4008,10 @@ _mm_store_si128(__m128i *__p, __m128i __b)
 /// \param __b
 ///    A 128-bit integer vector containing the values to be moved.
 static __inline__ void __DEFAULT_FN_ATTRS
-_mm_storeu_si128(__m128i *__p, __m128i __b)
+_mm_storeu_si128(__m128i_u *__p, __m128i __b)
 {
  struct __storeu_si128 {
-    __m128i __v;
+    __m128i_u __v;
  } __attribute__((__packed__, __may_alias__));
  ((struct __storeu_si128*)__p)->__v = __b;
 }
@@ -4048,7 +4029,7 @@ _mm_storeu_si128(__m128i *__p, __m128i __b)
 /// \param __b
 ///    A 128-bit integer vector containing the value to be stored.
 static __inline__ void __DEFAULT_FN_ATTRS
-_mm_storeu_si64(void const *__p, __m128i __b)
+_mm_storeu_si64(void *__p, __m128i __b)
 {
  struct __storeu_si64 {
    long long __v;
@@ -4069,7 +4050,7 @@ _mm_storeu_si64(void const *__p, __m128i __b)
 /// \param __b
 ///    A 128-bit integer vector containing the value to be stored.
 static __inline__ void __DEFAULT_FN_ATTRS
-_mm_storeu_si32(void const *__p, __m128i __b)
+_mm_storeu_si32(void *__p, __m128i __b)
 {
  struct __storeu_si32 {
    int __v;
@@ -4090,7 +4071,7 @@ _mm_storeu_si32(void const *__p, __m128i __b)
 /// \param __b
 ///    A 128-bit integer vector containing the value to be stored.
 static __inline__ void __DEFAULT_FN_ATTRS
-_mm_storeu_si16(void const *__p, __m128i __b)
+_mm_storeu_si16(void *__p, __m128i __b)
 {
  struct __storeu_si16 {
    short __v;
@@ -4139,7 +4120,7 @@ _mm_maskmoveu_si128(__m128i __d, __m128i __n, char *__p)
 ///    A 128-bit integer vector of [2 x i64]. The lower 64 bits contain the
 ///    value to be stored.
 static __inline__ void __DEFAULT_FN_ATTRS
-_mm_storel_epi64(__m128i *__p, __m128i __a)
+_mm_storel_epi64(__m128i_u *__p, __m128i __a)
 {
  struct __mm_storel_epi64_struct {
    long long __u;
@@ -0,0 +1,63 @@
+/*===------------------ enqcmdintrin.h - enqcmd intrinsics -----------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#ifndef __IMMINTRIN_H
+#error "Never use <enqcmdintrin.h> directly; include <immintrin.h> instead."
+#endif
+
+#ifndef __ENQCMDINTRIN_H
+#define __ENQCMDINTRIN_H
+
+/* Define the default attributes for the functions in this file */
+#define _DEFAULT_FN_ATTRS \
+  __attribute__((__always_inline__, __nodebug__, __target__("enqcmd")))
+
+/// Reads 64-byte command pointed by \a __src, formats 64-byte enqueue store
+///    data, and performs 64-byte enqueue store to memory pointed by \a __dst.
+///    This intrinsics may only be used in User mode.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsics corresponds to the <c> ENQCMD </c> instruction.
+///
+/// \param __dst
+///    Pointer to the destination of the enqueue store.
+/// \param __src
+///    Pointer to 64-byte command data.
+/// \returns If the command data is successfully written to \a __dst then 0 is
+///    returned. Otherwise 1 is returned.
+static __inline__ int _DEFAULT_FN_ATTRS
+_enqcmd (void *__dst, const void *__src)
+{
+  return __builtin_ia32_enqcmd(__dst, __src);
+}
+
+/// Reads 64-byte command pointed by \a __src, formats 64-byte enqueue store
+///    data, and performs 64-byte enqueue store to memory pointed by \a __dst
+///    This intrinsic may only be used in Privileged mode.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsics corresponds to the <c> ENQCMDS </c> instruction.
+///
+/// \param __dst
+///    Pointer to the destination of the enqueue store.
+/// \param __src
+///    Pointer to 64-byte command data.
+/// \returns If the command data is successfully written to \a __dst then 0 is
+///    returned. Otherwise 1 is returned.
+static __inline__ int _DEFAULT_FN_ATTRS
+_enqcmds (void *__dst, const void *__src)
+{
+  return __builtin_ia32_enqcmds(__dst, __src);
+}
+
+#undef _DEFAULT_FN_ATTRS
+
+#endif /* __ENQCMDINTRIN_H */
@@ -1,22 +1,8 @@
 /*===---- f16cintrin.h - F16C intrinsics -----------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -52,9 +38,9 @@
 static __inline float __DEFAULT_FN_ATTRS128
 _cvtsh_ss(unsigned short __a)
 {
-  __v8hi v = {(short)__a, 0, 0, 0, 0, 0, 0, 0};
-  __v4sf r = __builtin_ia32_vcvtph2ps(v);
-  return r[0];
+  __v8hi __v = {(short)__a, 0, 0, 0, 0, 0, 0, 0};
+  __v4sf __r = __builtin_ia32_vcvtph2ps(__v);
+  return __r[0];
 }

 /// Converts a 32-bit single-precision float value to a 16-bit
@@ -1,22 +1,8 @@
 /*===---- float.h - Characteristics of floating point types ----------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -51,7 +37,7 @@
 #  undef FLT_MANT_DIG
 #  undef DBL_MANT_DIG
 #  undef LDBL_MANT_DIG
-#  if __STDC_VERSION__ >= 199901L || !defined(__STRICT_ANSI__)
+#  if __STDC_VERSION__ >= 199901L || !defined(__STRICT_ANSI__) || __cplusplus >= 201103L
 #    undef DECIMAL_DIG
 #  endif
 #  undef FLT_DIG
@@ -78,7 +64,7 @@
 #  undef FLT_MIN
 #  undef DBL_MIN
 #  undef LDBL_MIN
-#  if __STDC_VERSION__ >= 201112L || !defined(__STRICT_ANSI__)
+#  if __STDC_VERSION__ >= 201112L || !defined(__STRICT_ANSI__) || __cplusplus >= 201703L
 #    undef FLT_TRUE_MIN
 #    undef DBL_TRUE_MIN
 #    undef LDBL_TRUE_MIN
@@ -101,7 +87,7 @@
 #define DBL_MANT_DIG __DBL_MANT_DIG__
 #define LDBL_MANT_DIG __LDBL_MANT_DIG__

-#if __STDC_VERSION__ >= 199901L || !defined(__STRICT_ANSI__)
+#if __STDC_VERSION__ >= 199901L || !defined(__STRICT_ANSI__) || __cplusplus >= 201103L
 #  define DECIMAL_DIG __DECIMAL_DIG__
 #endif

@@ -137,7 +123,7 @@
 #define DBL_MIN __DBL_MIN__
 #define LDBL_MIN __LDBL_MIN__

-#if __STDC_VERSION__ >= 201112L || !defined(__STRICT_ANSI__)
+#if __STDC_VERSION__ >= 201112L || !defined(__STRICT_ANSI__) || __cplusplus >= 201703L
 #  define FLT_TRUE_MIN __FLT_DENORM_MIN__
 #  define DBL_TRUE_MIN __DBL_DENORM_MIN__
 #  define LDBL_TRUE_MIN __LDBL_DENORM_MIN__
@@ -1,22 +1,8 @@
 /*===---- fma4intrin.h - FMA4 intrinsics -----------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- fmaintrin.h - FMA intrinsics -------------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- fxsrintrin.h - FXSR intrinsic ------------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,23 +1,9 @@
 /*===----------------- gfniintrin.h - GFNI intrinsics ----------------------===
 *
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- htmintrin.h - Standard header for PowerPC HTM ---------------===*\
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 \*===----------------------------------------------------------------------===*/

@@ -1,22 +1,8 @@
 /*===---- htmxlintrin.h - XL compiler HTM execution intrinsics-------------===*\
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 \*===----------------------------------------------------------------------===*/

@@ -1,22 +1,8 @@
 /* ===-------- ia32intrin.h ---------------------------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -28,6 +14,160 @@
 #ifndef __IA32INTRIN_H
 #define __IA32INTRIN_H

+/** Find the first set bit starting from the lsb. Result is undefined if
+ *  input is 0.
+ *
+ *  \headerfile <x86intrin.h>
+ *
+ *  This intrinsic corresponds to the <c> BSF </c> instruction or the
+ *  <c> TZCNT </c> instruction.
+ *
+ *  \param __A
+ *     A 32-bit integer operand.
+ *  \returns A 32-bit integer containing the bit number.
+ */
+static __inline__ int __attribute__((__always_inline__, __nodebug__))
+__bsfd(int __A) {
+  return __builtin_ctz(__A);
+}
+
+/** Find the first set bit starting from the msb. Result is undefined if
+ *  input is 0.
+ *
+ *  \headerfile <x86intrin.h>
+ *
+ *  This intrinsic corresponds to the <c> BSR </c> instruction or the
+ *  <c> LZCNT </c> instruction and an <c> XOR </c>.
+ *
+ *  \param __A
+ *     A 32-bit integer operand.
+ *  \returns A 32-bit integer containing the bit number.
+ */
+static __inline__ int __attribute__((__always_inline__, __nodebug__))
+__bsrd(int __A) {
+  return 31 - __builtin_clz(__A);
+}
+
+/** Swaps the bytes in the input. Converting little endian to big endian or
+ *  vice versa.
+ *
+ *  \headerfile <x86intrin.h>
+ *
+ *  This intrinsic corresponds to the <c> BSWAP </c> instruction.
+ *
+ *  \param __A
+ *     A 32-bit integer operand.
+ *  \returns A 32-bit integer containing the swapped bytes.
+ */
+static __inline__ int __attribute__((__always_inline__, __nodebug__))
+__bswapd(int __A) {
+  return __builtin_bswap32(__A);
+}
+
+static __inline__ int __attribute__((__always_inline__, __nodebug__))
+_bswap(int __A) {
+  return __builtin_bswap32(__A);
+}
+
+#define _bit_scan_forward(A) __bsfd((A))
+#define _bit_scan_reverse(A) __bsrd((A))
+
+#ifdef __x86_64__
+/** Find the first set bit starting from the lsb. Result is undefined if
+ *  input is 0.
+ *
+ *  \headerfile <x86intrin.h>
+ *
+ *  This intrinsic corresponds to the <c> BSF </c> instruction or the
+ *  <c> TZCNT </c> instruction.
+ *
+ *  \param __A
+ *     A 64-bit integer operand.
+ *  \returns A 32-bit integer containing the bit number.
+ */
+static __inline__ int __attribute__((__always_inline__, __nodebug__))
+__bsfq(long long __A) {
+  return __builtin_ctzll(__A);
+}
+
+/** Find the first set bit starting from the msb. Result is undefined if
+ *  input is 0.
+ *
+ *  \headerfile <x86intrin.h>
+ *
+ *  This intrinsic corresponds to the <c> BSR </c> instruction or the
+ *  <c> LZCNT </c> instruction and an <c> XOR </c>.
+ *
+ *  \param __A
+ *     A 64-bit integer operand.
+ *  \returns A 32-bit integer containing the bit number.
+ */
+static __inline__ int __attribute__((__always_inline__, __nodebug__))
+__bsrq(long long __A) {
+  return 63 - __builtin_clzll(__A);
+}
+
+/** Swaps the bytes in the input. Converting little endian to big endian or
+ *  vice versa.
+ *
+ *  \headerfile <x86intrin.h>
+ *
+ *  This intrinsic corresponds to the <c> BSWAP </c> instruction.
+ *
+ *  \param __A
+ *     A 64-bit integer operand.
+ *  \returns A 64-bit integer containing the swapped bytes.
+ */
+static __inline__ long long __attribute__((__always_inline__, __nodebug__))
+__bswapq(long long __A) {
+  return __builtin_bswap64(__A);
+}
+
+#define _bswap64(A) __bswapq((A))
+#endif
+
+/** Counts the number of bits in the source operand having a value of 1.
+ *
+ *  \headerfile <x86intrin.h>
+ *
+ *  This intrinsic corresponds to the <c> POPCNT </c> instruction or a
+ *  a sequence of arithmetic and logic ops to calculate it.
+ *
+ *  \param __A
+ *     An unsigned 32-bit integer operand.
+ *  \returns A 32-bit integer containing the number of bits with value 1 in the
+ *     source operand.
+ */
+static __inline__ int __attribute__((__always_inline__, __nodebug__))
+__popcntd(unsigned int __A)
+{
+  return __builtin_popcount(__A);
+}
+
+#define _popcnt32(A) __popcntd((A))
+
+#ifdef __x86_64__
+/** Counts the number of bits in the source operand having a value of 1.
+ *
+ *  \headerfile <x86intrin.h>
+ *
+ *  This intrinsic corresponds to the <c> POPCNT </c> instruction or a
+ *  a sequence of arithmetic and logic ops to calculate it.
+ *
+ *  \param __A
+ *     An unsigned 64-bit integer operand.
+ *  \returns A 64-bit integer containing the number of bits with value 1 in the
+ *     source operand.
+ */
+static __inline__ long long __attribute__((__always_inline__, __nodebug__))
+__popcntq(unsigned long long __A)
+{
+  return __builtin_popcountll(__A);
+}
+
+#define _popcnt64(A) __popcntq((A))
+#endif /* __x86_64__ */
+
 #ifdef __x86_64__
 static __inline__ unsigned long long __attribute__((__always_inline__, __nodebug__))
 __readeflags(void)
@@ -55,6 +195,92 @@ __writeeflags(unsigned int __f)
 }
 #endif /* !__x86_64__ */

+/** Adds the unsigned integer operand to the CRC-32C checksum of the
+ *     unsigned char operand.
+ *
+ *  \headerfile <x86intrin.h>
+ *
+ *  This intrinsic corresponds to the <c> CRC32B </c> instruction.
+ *
+ *  \param __C
+ *     An unsigned integer operand to add to the CRC-32C checksum of operand
+ *     \a  __D.
+ *  \param __D
+ *     An unsigned 8-bit integer operand used to compute the CRC-32C checksum.
+ *  \returns The result of adding operand \a __C to the CRC-32C checksum of
+ *     operand \a __D.
+ */
+static __inline__ unsigned int __attribute__((__always_inline__, __nodebug__, __target__("sse4.2")))
+__crc32b(unsigned int __C, unsigned char __D)
+{
+  return __builtin_ia32_crc32qi(__C, __D);
+}
+
+/** Adds the unsigned integer operand to the CRC-32C checksum of the
+ *     unsigned short operand.
+ *
+ *  \headerfile <x86intrin.h>
+ *
+ *  This intrinsic corresponds to the <c> CRC32W </c> instruction.
+ *
+ *  \param __C
+ *     An unsigned integer operand to add to the CRC-32C checksum of operand
+ *     \a  __D.
+ *  \param __D
+ *     An unsigned 16-bit integer operand used to compute the CRC-32C checksum.
+ *  \returns The result of adding operand \a __C to the CRC-32C checksum of
+ *     operand \a __D.
+ */
+static __inline__ unsigned int __attribute__((__always_inline__, __nodebug__, __target__("sse4.2")))
+__crc32w(unsigned int __C, unsigned short __D)
+{
+  return __builtin_ia32_crc32hi(__C, __D);
+}
+
+/** Adds the unsigned integer operand to the CRC-32C checksum of the
+ *     second unsigned integer operand.
+ *
+ *  \headerfile <x86intrin.h>
+ *
+ *  This intrinsic corresponds to the <c> CRC32D </c> instruction.
+ *
+ *  \param __C
+ *     An unsigned integer operand to add to the CRC-32C checksum of operand
+ *     \a  __D.
+ *  \param __D
+ *     An unsigned 32-bit integer operand used to compute the CRC-32C checksum.
+ *  \returns The result of adding operand \a __C to the CRC-32C checksum of
+ *     operand \a __D.
+ */
+static __inline__ unsigned int __attribute__((__always_inline__, __nodebug__, __target__("sse4.2")))
+__crc32d(unsigned int __C, unsigned int __D)
+{
+  return __builtin_ia32_crc32si(__C, __D);
+}
+
+#ifdef __x86_64__
+/** Adds the unsigned integer operand to the CRC-32C checksum of the
+ *     unsigned 64-bit integer operand.
+ *
+ *  \headerfile <x86intrin.h>
+ *
+ *  This intrinsic corresponds to the <c> CRC32Q </c> instruction.
+ *
+ *  \param __C
+ *     An unsigned integer operand to add to the CRC-32C checksum of operand
+ *     \a  __D.
+ *  \param __D
+ *     An unsigned 64-bit integer operand used to compute the CRC-32C checksum.
+ *  \returns The result of adding operand \a __C to the CRC-32C checksum of
+ *     operand \a __D.
+ */
+static __inline__ unsigned long long __attribute__((__always_inline__, __nodebug__, __target__("sse4.2")))
+__crc32q(unsigned long long __C, unsigned long long __D)
+{
+  return __builtin_ia32_crc32di(__C, __D);
+}
+#endif /* __x86_64__ */
+
 static __inline__ unsigned long long __attribute__((__always_inline__, __nodebug__))
 __rdpmc(int __A) {
  return __builtin_ia32_rdpmc(__A);
@@ -75,4 +301,64 @@ _wbinvd(void) {
  __builtin_ia32_wbinvd();
 }

+static __inline__ unsigned char __attribute__((__always_inline__, __nodebug__))
+__rolb(unsigned char __X, int __C) {
+  return __builtin_rotateleft8(__X, __C);
+}
+
+static __inline__ unsigned char __attribute__((__always_inline__, __nodebug__))
+__rorb(unsigned char __X, int __C) {
+  return __builtin_rotateright8(__X, __C);
+}
+
+static __inline__ unsigned short __attribute__((__always_inline__, __nodebug__))
+__rolw(unsigned short __X, int __C) {
+  return __builtin_rotateleft16(__X, __C);
+}
+
+static __inline__ unsigned short __attribute__((__always_inline__, __nodebug__))
+__rorw(unsigned short __X, int __C) {
+  return __builtin_rotateright16(__X, __C);
+}
+
+static __inline__ unsigned int __attribute__((__always_inline__, __nodebug__))
+__rold(unsigned int __X, int __C) {
+  return __builtin_rotateleft32(__X, __C);
+}
+
+static __inline__ unsigned int __attribute__((__always_inline__, __nodebug__))
+__rord(unsigned int __X, int __C) {
+  return __builtin_rotateright32(__X, __C);
+}
+
+#ifdef __x86_64__
+static __inline__ unsigned long long __attribute__((__always_inline__, __nodebug__))
+__rolq(unsigned long long __X, int __C) {
+  return __builtin_rotateleft64(__X, __C);
+}
+
+static __inline__ unsigned long long __attribute__((__always_inline__, __nodebug__))
+__rorq(unsigned long long __X, int __C) {
+  return __builtin_rotateright64(__X, __C);
+}
+#endif /* __x86_64__ */
+
+#ifndef _MSC_VER
+/* These are already provided as builtins for MSVC. */
+/* Select the correct function based on the size of long. */
+#ifdef __LP64__
+#define _lrotl(a,b) __rolq((a), (b))
+#define _lrotr(a,b) __rorq((a), (b))
+#else
+#define _lrotl(a,b) __rold((a), (b))
+#define _lrotr(a,b) __rord((a), (b))
+#endif
+#define _rotl(a,b) __rold((a), (b))
+#define _rotr(a,b) __rord((a), (b))
+#endif // _MSC_VER
+
+/* These are not builtins so need to be provided in all modes. */
+#define _rotwl(a,b) __rolw((a), (b))
+#define _rotwr(a,b) __rorw((a), (b))
+
 #endif /* __IA32INTRIN_H */
@@ -1,22 +1,8 @@
 /*===---- immintrin.h - Intel intrinsics -----------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -195,6 +181,15 @@
 #include <avx512pfintrin.h>
 #endif

+#if !defined(_MSC_VER) || __has_feature(modules) || defined(__AVX512BF16__)
+#include <avx512bf16intrin.h>
+#endif
+
+#if !defined(_MSC_VER) || __has_feature(modules) || \
+    (defined(__AVX512VL__) && defined(__AVX512BF16__))
+#include <avx512vlbf16intrin.h>
+#endif
+
 #if !defined(_MSC_VER) || __has_feature(modules) || defined(__PKU__)
 #include <pkuintrin.h>
 #endif
@@ -241,18 +236,6 @@ _rdrand64_step(unsigned long long *__p)
 #endif
 #endif /* __RDRND__ */

-/* __bit_scan_forward */
-static __inline__ int __attribute__((__always_inline__, __nodebug__))
-_bit_scan_forward(int __A) {
-  return __builtin_ctz(__A);
-}
-
-/* __bit_scan_reverse */
-static __inline__ int __attribute__((__always_inline__, __nodebug__))
-_bit_scan_reverse(int __A) {
-  return 31 - __builtin_clz(__A);
-}
-
 #if !defined(_MSC_VER) || __has_feature(modules) || defined(__FSGSBASE__)
 #ifdef __x86_64__
 static __inline__ unsigned int __attribute__((__always_inline__, __nodebug__, __target__("fsgsbase")))
@@ -378,9 +361,8 @@ _storebe_i64(void * __P, long long __D) {
 #include <fxsrintrin.h>
 #endif

-#if !defined(_MSC_VER) || __has_feature(modules) || defined(__XSAVE__)
+/* No feature check desired due to internal MSC_VER checks */
 #include <xsaveintrin.h>
-#endif

 #if !defined(_MSC_VER) || __has_feature(modules) || defined(__XSAVEOPT__)
 #include <xsaveoptintrin.h>
@@ -439,7 +421,21 @@ _storebe_i64(void * __P, long long __D) {
 #include <invpcidintrin.h>
 #endif

-#ifdef _MSC_VER
+#if !defined(_MSC_VER) || __has_feature(modules) || \
+  defined(__AVX512VP2INTERSECT__)
+#include <avx512vp2intersectintrin.h>
+#endif
+
+#if !defined(_MSC_VER) || __has_feature(modules) || \
+  (defined(__AVX512VL__) && defined(__AVX512VP2INTERSECT__))
+#include <avx512vlvp2intersectintrin.h>
+#endif
+
+#if !defined(_MSC_VER) || __has_feature(modules) || defined(__ENQCMD__)
+#include <enqcmdintrin.h>
+#endif
+
+#if defined(_MSC_VER) && __has_extension(gnu_asm)
 /* Define the default attributes for these intrinsics */
 #define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__))
 #ifdef __cplusplus
@@ -521,6 +517,6 @@ _InterlockedCompareExchange64_HLERelease(__int64 volatile *_Destination,

 #undef __DEFAULT_FN_ATTRS

-#endif /* _MSC_VER */
+#endif /* defined(_MSC_VER) && __has_extension(gnu_asm) */

 #endif /* __IMMINTRIN_H */
@@ -1,22 +1,8 @@
 /* ===-------- intrin.h ---------------------------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -200,10 +186,6 @@ __attribute__((__deprecated__("use other intrinsics or C++11 atomics instead")))
 _WriteBarrier(void);
 unsigned __int32 xbegin(void);
 void _xend(void);
-static __inline__
-#define _XCR_XFEATURE_ENABLED_MASK 0
-unsigned __int64 __cdecl _xgetbv(unsigned int);
-void __cdecl _xsetbv(unsigned int, unsigned __int64);

 /* These additional intrinsics are turned on in x64/amd64/x86_64 mode. */
 #ifdef __x86_64__
@@ -539,12 +521,6 @@ __cpuidex(int __info[4], int __level, int __ecx) {
  __asm__ ("cpuid" : "=a"(__info[0]), "=b" (__info[1]), "=c"(__info[2]), "=d"(__info[3])
                   : "a"(__level), "c"(__ecx));
 }
-static __inline__ unsigned __int64 __cdecl __DEFAULT_FN_ATTRS
-_xgetbv(unsigned int __xcr_no) {
-  unsigned int __eax, __edx;
-  __asm__ ("xgetbv" : "=a" (__eax), "=d" (__edx) : "c" (__xcr_no));
-  return ((unsigned __int64)__edx << 32) | __eax;
-}
 static __inline__ void __DEFAULT_FN_ATTRS
 __halt(void) {
  __asm__ volatile ("hlt");
@@ -567,15 +543,9 @@ long _InterlockedAdd(long volatile *Addend, long Value);
 __int64 _ReadStatusReg(int);
 void _WriteStatusReg(int, __int64);

-static inline unsigned short _byteswap_ushort (unsigned short val) {
-  return __builtin_bswap16(val);
-}
-static inline unsigned long _byteswap_ulong (unsigned long val) {
-  return __builtin_bswap32(val);
-}
-static inline unsigned __int64 _byteswap_uint64 (unsigned __int64 val) {
-  return __builtin_bswap64(val);
-}
+unsigned short __cdecl _byteswap_ushort(unsigned short val);
+unsigned long __cdecl _byteswap_ulong (unsigned long val);
+unsigned __int64 __cdecl _byteswap_uint64(unsigned __int64 val);
 #endif

 /*----------------------------------------------------------------------------*\
@@ -1,27 +1,18 @@
 /*===---- inttypes.h - Standard header for integer printf macros ----------===*\
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 \*===----------------------------------------------------------------------===*/

 #ifndef __CLANG_INTTYPES_H
+// AIX system headers need inttypes.h to be re-enterable while _STD_TYPES_T
+// is defined until an inclusion of it without _STD_TYPES_T occurs, in which
+// case the header guard macro is defined.
+#if !defined(_AIX) || !defined(_STD_TYPES_T)
 #define __CLANG_INTTYPES_H
+#endif

 #if defined(_MSC_VER) && _MSC_VER < 1800
 #error MSVC does not have inttypes.h prior to Visual Studio 2013
@@ -1,22 +1,8 @@
 /*===------------- invpcidintrin.h - INVPCID intrinsic ---------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,24 +1,8 @@
 /*===---- iso646.h - Standard header for alternate spellings of operators---===
 *
- * Copyright (c) 2008 Eli Friedman
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,24 +1,8 @@
 /*===---- limits.h - Standard header for integer sizes --------------------===*\
 *
- * Copyright (c) 2009 Chris Lattner
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 \*===----------------------------------------------------------------------===*/

@@ -1,22 +1,8 @@
 /*===---- lwpintrin.h - LWP intrinsics -------------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- lzcntintrin.h - LZCNT intrinsics ---------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- mm3dnow.h - 3DNow! intrinsics ------------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- mm_malloc.h - Allocating and Freeing Aligned Memory Blocks -------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- mmintrin.h - MMX intrinsics --------------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -24,7 +10,7 @@
 #ifndef __MMINTRIN_H
 #define __MMINTRIN_H

-typedef long long __m64 __attribute__((__vector_size__(8)));
+typedef long long __m64 __attribute__((__vector_size__(8), __aligned__(8)));

 typedef long long __v1di __attribute__((__vector_size__(8)));
 typedef int __v2si __attribute__((__vector_size__(8)));
@@ -1,22 +1,8 @@
 /*===---- module.modulemap - intrinsics module map -------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -168,4 +154,5 @@ module _Builtin_stddef_max_align_t [system] [extern_c] {
 module opencl_c {
  requires opencl
  header "opencl-c.h"
+  header "opencl-c-base.h"
 }
@@ -1,22 +1,8 @@
 /*===------------------------- movdirintrin.h ------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- msa.h - MIPS MSA intrinsics --------------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- mwaitxintrin.h - MONITORX/MWAITX intrinsics ----------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- nmmintrin.h - SSE4 intrinsics ------------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -0,0 +1,571 @@
+//===----- opencl-c-base.h - OpenCL C language base definitions -----------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef _OPENCL_BASE_H_
+#define _OPENCL_BASE_H_
+
+// built-in scalar data types:
+
+/**
+ * An unsigned 8-bit integer.
+ */
+typedef unsigned char uchar;
+
+/**
+ * An unsigned 16-bit integer.
+ */
+typedef unsigned short ushort;
+
+/**
+ * An unsigned 32-bit integer.
+ */
+typedef unsigned int uint;
+
+/**
+ * An unsigned 64-bit integer.
+ */
+typedef unsigned long ulong;
+
+/**
+ * The unsigned integer type of the result of the sizeof operator. This
+ * is a 32-bit unsigned integer if CL_DEVICE_ADDRESS_BITS
+ * defined in table 4.3 is 32-bits and is a 64-bit unsigned integer if
+ * CL_DEVICE_ADDRESS_BITS is 64-bits.
+ */
+typedef __SIZE_TYPE__ size_t;
+
+/**
+ * A signed integer type that is the result of subtracting two pointers.
+ * This is a 32-bit signed integer if CL_DEVICE_ADDRESS_BITS
+ * defined in table 4.3 is 32-bits and is a 64-bit signed integer if
+ * CL_DEVICE_ADDRESS_BITS is 64-bits.
+ */
+typedef __PTRDIFF_TYPE__ ptrdiff_t;
+
+/**
+ * A signed integer type with the property that any valid pointer to
+ * void can be converted to this type, then converted back to pointer
+ * to void, and the result will compare equal to the original pointer.
+ */
+typedef __INTPTR_TYPE__ intptr_t;
+
+/**
+ * An unsigned integer type with the property that any valid pointer to
+ * void can be converted to this type, then converted back to pointer
+ * to void, and the result will compare equal to the original pointer.
+ */
+typedef __UINTPTR_TYPE__ uintptr_t;
+
+// built-in vector data types:
+typedef char char2 __attribute__((ext_vector_type(2)));
+typedef char char3 __attribute__((ext_vector_type(3)));
+typedef char char4 __attribute__((ext_vector_type(4)));
+typedef char char8 __attribute__((ext_vector_type(8)));
+typedef char char16 __attribute__((ext_vector_type(16)));
+typedef uchar uchar2 __attribute__((ext_vector_type(2)));
+typedef uchar uchar3 __attribute__((ext_vector_type(3)));
+typedef uchar uchar4 __attribute__((ext_vector_type(4)));
+typedef uchar uchar8 __attribute__((ext_vector_type(8)));
+typedef uchar uchar16 __attribute__((ext_vector_type(16)));
+typedef short short2 __attribute__((ext_vector_type(2)));
+typedef short short3 __attribute__((ext_vector_type(3)));
+typedef short short4 __attribute__((ext_vector_type(4)));
+typedef short short8 __attribute__((ext_vector_type(8)));
+typedef short short16 __attribute__((ext_vector_type(16)));
+typedef ushort ushort2 __attribute__((ext_vector_type(2)));
+typedef ushort ushort3 __attribute__((ext_vector_type(3)));
+typedef ushort ushort4 __attribute__((ext_vector_type(4)));
+typedef ushort ushort8 __attribute__((ext_vector_type(8)));
+typedef ushort ushort16 __attribute__((ext_vector_type(16)));
+typedef int int2 __attribute__((ext_vector_type(2)));
+typedef int int3 __attribute__((ext_vector_type(3)));
+typedef int int4 __attribute__((ext_vector_type(4)));
+typedef int int8 __attribute__((ext_vector_type(8)));
+typedef int int16 __attribute__((ext_vector_type(16)));
+typedef uint uint2 __attribute__((ext_vector_type(2)));
+typedef uint uint3 __attribute__((ext_vector_type(3)));
+typedef uint uint4 __attribute__((ext_vector_type(4)));
+typedef uint uint8 __attribute__((ext_vector_type(8)));
+typedef uint uint16 __attribute__((ext_vector_type(16)));
+typedef long long2 __attribute__((ext_vector_type(2)));
+typedef long long3 __attribute__((ext_vector_type(3)));
+typedef long long4 __attribute__((ext_vector_type(4)));
+typedef long long8 __attribute__((ext_vector_type(8)));
+typedef long long16 __attribute__((ext_vector_type(16)));
+typedef ulong ulong2 __attribute__((ext_vector_type(2)));
+typedef ulong ulong3 __attribute__((ext_vector_type(3)));
+typedef ulong ulong4 __attribute__((ext_vector_type(4)));
+typedef ulong ulong8 __attribute__((ext_vector_type(8)));
+typedef ulong ulong16 __attribute__((ext_vector_type(16)));
+typedef float float2 __attribute__((ext_vector_type(2)));
+typedef float float3 __attribute__((ext_vector_type(3)));
+typedef float float4 __attribute__((ext_vector_type(4)));
+typedef float float8 __attribute__((ext_vector_type(8)));
+typedef float float16 __attribute__((ext_vector_type(16)));
+#ifdef cl_khr_fp16
+#pragma OPENCL EXTENSION cl_khr_fp16 : enable
+typedef half half2 __attribute__((ext_vector_type(2)));
+typedef half half3 __attribute__((ext_vector_type(3)));
+typedef half half4 __attribute__((ext_vector_type(4)));
+typedef half half8 __attribute__((ext_vector_type(8)));
+typedef half half16 __attribute__((ext_vector_type(16)));
+#endif
+#ifdef cl_khr_fp64
+#if __OPENCL_C_VERSION__ < CL_VERSION_1_2
+#pragma OPENCL EXTENSION cl_khr_fp64 : enable
+#endif
+typedef double double2 __attribute__((ext_vector_type(2)));
+typedef double double3 __attribute__((ext_vector_type(3)));
+typedef double double4 __attribute__((ext_vector_type(4)));
+typedef double double8 __attribute__((ext_vector_type(8)));
+typedef double double16 __attribute__((ext_vector_type(16)));
+#endif
+
+#if defined(__OPENCL_CPP_VERSION__) || (__OPENCL_C_VERSION__ >= CL_VERSION_2_0)
+#define NULL ((void*)0)
+#endif
+
+/**
+ * Value of maximum non-infinite single-precision floating-point
+ * number.
+ */
+#define MAXFLOAT 0x1.fffffep127f
+
+/**
+ * A positive float constant expression. HUGE_VALF evaluates
+ * to +infinity. Used as an error value returned by the built-in
+ * math functions.
+ */
+#define HUGE_VALF (__builtin_huge_valf())
+
+/**
+ * A positive double constant expression. HUGE_VAL evaluates
+ * to +infinity. Used as an error value returned by the built-in
+ * math functions.
+ */
+#define HUGE_VAL (__builtin_huge_val())
+
+/**
+ * A constant expression of type float representing positive or
+ * unsigned infinity.
+ */
+#define INFINITY (__builtin_inff())
+
+/**
+ * A constant expression of type float representing a quiet NaN.
+ */
+#define NAN as_float(INT_MAX)
+
+#define FP_ILOGB0    INT_MIN
+#define FP_ILOGBNAN  INT_MAX
+
+#define FLT_DIG 6
+#define FLT_MANT_DIG 24
+#define FLT_MAX_10_EXP +38
+#define FLT_MAX_EXP +128
+#define FLT_MIN_10_EXP -37
+#define FLT_MIN_EXP -125
+#define FLT_RADIX 2
+#define FLT_MAX 0x1.fffffep127f
+#define FLT_MIN 0x1.0p-126f
+#define FLT_EPSILON 0x1.0p-23f
+
+#define M_E_F         2.71828182845904523536028747135266250f
+#define M_LOG2E_F     1.44269504088896340735992468100189214f
+#define M_LOG10E_F    0.434294481903251827651128918916605082f
+#define M_LN2_F       0.693147180559945309417232121458176568f
+#define M_LN10_F      2.30258509299404568401799145468436421f
+#define M_PI_F        3.14159265358979323846264338327950288f
+#define M_PI_2_F      1.57079632679489661923132169163975144f
+#define M_PI_4_F      0.785398163397448309615660845819875721f
+#define M_1_PI_F      0.318309886183790671537767526745028724f
+#define M_2_PI_F      0.636619772367581343075535053490057448f
+#define M_2_SQRTPI_F  1.12837916709551257389615890312154517f
+#define M_SQRT2_F     1.41421356237309504880168872420969808f
+#define M_SQRT1_2_F   0.707106781186547524400844362104849039f
+
+#define DBL_DIG 15
+#define DBL_MANT_DIG 53
+#define DBL_MAX_10_EXP +308
+#define DBL_MAX_EXP +1024
+#define DBL_MIN_10_EXP -307
+#define DBL_MIN_EXP -1021
+#define DBL_RADIX 2
+#define DBL_MAX 0x1.fffffffffffffp1023
+#define DBL_MIN 0x1.0p-1022
+#define DBL_EPSILON 0x1.0p-52
+
+#define M_E           0x1.5bf0a8b145769p+1
+#define M_LOG2E       0x1.71547652b82fep+0
+#define M_LOG10E      0x1.bcb7b1526e50ep-2
+#define M_LN2         0x1.62e42fefa39efp-1
+#define M_LN10        0x1.26bb1bbb55516p+1
+#define M_PI          0x1.921fb54442d18p+1
+#define M_PI_2        0x1.921fb54442d18p+0
+#define M_PI_4        0x1.921fb54442d18p-1
+#define M_1_PI        0x1.45f306dc9c883p-2
+#define M_2_PI        0x1.45f306dc9c883p-1
+#define M_2_SQRTPI    0x1.20dd750429b6dp+0
+#define M_SQRT2       0x1.6a09e667f3bcdp+0
+#define M_SQRT1_2     0x1.6a09e667f3bcdp-1
+
+#ifdef cl_khr_fp16
+
+#define HALF_DIG 3
+#define HALF_MANT_DIG 11
+#define HALF_MAX_10_EXP +4
+#define HALF_MAX_EXP +16
+#define HALF_MIN_10_EXP -4
+#define HALF_MIN_EXP -13
+#define HALF_RADIX 2
+#define HALF_MAX ((0x1.ffcp15h))
+#define HALF_MIN ((0x1.0p-14h))
+#define HALF_EPSILON ((0x1.0p-10h))
+
+#define M_E_H         2.71828182845904523536028747135266250h
+#define M_LOG2E_H     1.44269504088896340735992468100189214h
+#define M_LOG10E_H    0.434294481903251827651128918916605082h
+#define M_LN2_H       0.693147180559945309417232121458176568h
+#define M_LN10_H      2.30258509299404568401799145468436421h
+#define M_PI_H        3.14159265358979323846264338327950288h
+#define M_PI_2_H      1.57079632679489661923132169163975144h
+#define M_PI_4_H      0.785398163397448309615660845819875721h
+#define M_1_PI_H      0.318309886183790671537767526745028724h
+#define M_2_PI_H      0.636619772367581343075535053490057448h
+#define M_2_SQRTPI_H  1.12837916709551257389615890312154517h
+#define M_SQRT2_H     1.41421356237309504880168872420969808h
+#define M_SQRT1_2_H   0.707106781186547524400844362104849039h
+
+#endif //cl_khr_fp16
+
+#define CHAR_BIT  8
+#define SCHAR_MAX 127
+#define SCHAR_MIN (-128)
+#define UCHAR_MAX 255
+#define CHAR_MAX  SCHAR_MAX
+#define CHAR_MIN  SCHAR_MIN
+#define USHRT_MAX 65535
+#define SHRT_MAX  32767
+#define SHRT_MIN  (-32768)
+#define UINT_MAX  0xffffffff
+#define INT_MAX   2147483647
+#define INT_MIN   (-2147483647-1)
+#define ULONG_MAX 0xffffffffffffffffUL
+#define LONG_MAX  0x7fffffffffffffffL
+#define LONG_MIN  (-0x7fffffffffffffffL-1)
+
+// OpenCL v1.1 s6.11.8, v1.2 s6.12.8, v2.0 s6.13.8 - Synchronization Functions
+
+// Flag type and values for barrier, mem_fence, read_mem_fence, write_mem_fence
+typedef uint cl_mem_fence_flags;
+
+/**
+ * Queue a memory fence to ensure correct
+ * ordering of memory operations to local memory
+ */
+#define CLK_LOCAL_MEM_FENCE    0x01
+
+/**
+ * Queue a memory fence to ensure correct
+ * ordering of memory operations to global memory
+ */
+#define CLK_GLOBAL_MEM_FENCE   0x02
+
+#if defined(__OPENCL_CPP_VERSION__) || (__OPENCL_C_VERSION__ >= CL_VERSION_2_0)
+
+typedef enum memory_scope {
+  memory_scope_work_item = __OPENCL_MEMORY_SCOPE_WORK_ITEM,
+  memory_scope_work_group = __OPENCL_MEMORY_SCOPE_WORK_GROUP,
+  memory_scope_device = __OPENCL_MEMORY_SCOPE_DEVICE,
+  memory_scope_all_svm_devices = __OPENCL_MEMORY_SCOPE_ALL_SVM_DEVICES,
+#if defined(cl_intel_subgroups) || defined(cl_khr_subgroups)
+  memory_scope_sub_group = __OPENCL_MEMORY_SCOPE_SUB_GROUP
+#endif
+} memory_scope;
+
+/**
+ * Queue a memory fence to ensure correct ordering of memory
+ * operations between work-items of a work-group to
+ * image memory.
+ */
+#define CLK_IMAGE_MEM_FENCE  0x04
+
+#ifndef ATOMIC_VAR_INIT
+#define ATOMIC_VAR_INIT(x) (x)
+#endif //ATOMIC_VAR_INIT
+#define ATOMIC_FLAG_INIT 0
+
+// enum values aligned with what clang uses in EmitAtomicExpr()
+typedef enum memory_order
+{
+  memory_order_relaxed = __ATOMIC_RELAXED,
+  memory_order_acquire = __ATOMIC_ACQUIRE,
+  memory_order_release = __ATOMIC_RELEASE,
+  memory_order_acq_rel = __ATOMIC_ACQ_REL,
+  memory_order_seq_cst = __ATOMIC_SEQ_CST
+} memory_order;
+
+#endif // defined(__OPENCL_CPP_VERSION__) || (__OPENCL_C_VERSION__ >= CL_VERSION_2_0)
+
+// OpenCL v1.1 s6.11.3, v1.2 s6.12.14, v2.0 s6.13.14 - Image Read and Write Functions
+
+// These values need to match the runtime equivalent
+//
+// Addressing Mode.
+//
+#define CLK_ADDRESS_NONE                0
+#define CLK_ADDRESS_CLAMP_TO_EDGE       2
+#define CLK_ADDRESS_CLAMP               4
+#define CLK_ADDRESS_REPEAT              6
+#define CLK_ADDRESS_MIRRORED_REPEAT     8
+
+//
+// Coordination Normalization
+//
+#define CLK_NORMALIZED_COORDS_FALSE     0
+#define CLK_NORMALIZED_COORDS_TRUE      1
+
+//
+// Filtering Mode.
+//
+#define CLK_FILTER_NEAREST              0x10
+#define CLK_FILTER_LINEAR               0x20
+
+#ifdef cl_khr_gl_msaa_sharing
+#pragma OPENCL EXTENSION cl_khr_gl_msaa_sharing : enable
+#endif //cl_khr_gl_msaa_sharing
+
+//
+// Channel Datatype.
+//
+#define CLK_SNORM_INT8        0x10D0
+#define CLK_SNORM_INT16       0x10D1
+#define CLK_UNORM_INT8        0x10D2
+#define CLK_UNORM_INT16       0x10D3
+#define CLK_UNORM_SHORT_565   0x10D4
+#define CLK_UNORM_SHORT_555   0x10D5
+#define CLK_UNORM_INT_101010  0x10D6
+#define CLK_SIGNED_INT8       0x10D7
+#define CLK_SIGNED_INT16      0x10D8
+#define CLK_SIGNED_INT32      0x10D9
+#define CLK_UNSIGNED_INT8     0x10DA
+#define CLK_UNSIGNED_INT16    0x10DB
+#define CLK_UNSIGNED_INT32    0x10DC
+#define CLK_HALF_FLOAT        0x10DD
+#define CLK_FLOAT             0x10DE
+#define CLK_UNORM_INT24       0x10DF
+
+// Channel order, numbering must be aligned with cl_channel_order in cl.h
+//
+#define CLK_R         0x10B0
+#define CLK_A         0x10B1
+#define CLK_RG        0x10B2
+#define CLK_RA        0x10B3
+#define CLK_RGB       0x10B4
+#define CLK_RGBA      0x10B5
+#define CLK_BGRA      0x10B6
+#define CLK_ARGB      0x10B7
+#define CLK_INTENSITY 0x10B8
+#define CLK_LUMINANCE 0x10B9
+#define CLK_Rx                0x10BA
+#define CLK_RGx               0x10BB
+#define CLK_RGBx              0x10BC
+#define CLK_DEPTH             0x10BD
+#define CLK_DEPTH_STENCIL     0x10BE
+#if __OPENCL_C_VERSION__ >= CL_VERSION_2_0
+#define CLK_sRGB              0x10BF
+#define CLK_sRGBx             0x10C0
+#define CLK_sRGBA             0x10C1
+#define CLK_sBGRA             0x10C2
+#define CLK_ABGR              0x10C3
+#endif //__OPENCL_C_VERSION__ >= CL_VERSION_2_0
+
+// OpenCL v2.0 s6.13.16 - Pipe Functions
+#if defined(__OPENCL_CPP_VERSION__) || (__OPENCL_C_VERSION__ >= CL_VERSION_2_0)
+#define CLK_NULL_RESERVE_ID (__builtin_astype(((void*)(__SIZE_MAX__)), reserve_id_t))
+
+// OpenCL v2.0 s6.13.17 - Enqueue Kernels
+#define CL_COMPLETE                                 0x0
+#define CL_RUNNING                                  0x1
+#define CL_SUBMITTED                                0x2
+#define CL_QUEUED                                   0x3
+
+#define CLK_SUCCESS                                 0
+#define CLK_ENQUEUE_FAILURE                         -101
+#define CLK_INVALID_QUEUE                           -102
+#define CLK_INVALID_NDRANGE                         -160
+#define CLK_INVALID_EVENT_WAIT_LIST                 -57
+#define CLK_DEVICE_QUEUE_FULL                       -161
+#define CLK_INVALID_ARG_SIZE                        -51
+#define CLK_EVENT_ALLOCATION_FAILURE                -100
+#define CLK_OUT_OF_RESOURCES                        -5
+
+#define CLK_NULL_QUEUE                              0
+#define CLK_NULL_EVENT (__builtin_astype(((void*)(__SIZE_MAX__)), clk_event_t))
+
+// execution model related definitions
+#define CLK_ENQUEUE_FLAGS_NO_WAIT                   0x0
+#define CLK_ENQUEUE_FLAGS_WAIT_KERNEL               0x1
+#define CLK_ENQUEUE_FLAGS_WAIT_WORK_GROUP           0x2
+
+typedef int kernel_enqueue_flags_t;
+typedef int clk_profiling_info;
+
+// Profiling info name (see capture_event_profiling_info)
+#define CLK_PROFILING_COMMAND_EXEC_TIME 0x1
+
+#define MAX_WORK_DIM 3
+
+typedef struct {
+  unsigned int workDimension;
+  size_t globalWorkOffset[MAX_WORK_DIM];
+  size_t globalWorkSize[MAX_WORK_DIM];
+  size_t localWorkSize[MAX_WORK_DIM];
+} ndrange_t;
+
+#endif // defined(__OPENCL_CPP_VERSION__) || (__OPENCL_C_VERSION__ >= CL_VERSION_2_0)
+
+#ifdef cl_intel_device_side_avc_motion_estimation
+#pragma OPENCL EXTENSION cl_intel_device_side_avc_motion_estimation : begin
+
+#define CLK_AVC_ME_MAJOR_16x16_INTEL 0x0
+#define CLK_AVC_ME_MAJOR_16x8_INTEL 0x1
+#define CLK_AVC_ME_MAJOR_8x16_INTEL 0x2
+#define CLK_AVC_ME_MAJOR_8x8_INTEL 0x3
+
+#define CLK_AVC_ME_MINOR_8x8_INTEL 0x0
+#define CLK_AVC_ME_MINOR_8x4_INTEL 0x1
+#define CLK_AVC_ME_MINOR_4x8_INTEL 0x2
+#define CLK_AVC_ME_MINOR_4x4_INTEL 0x3
+
+#define CLK_AVC_ME_MAJOR_FORWARD_INTEL 0x0
+#define CLK_AVC_ME_MAJOR_BACKWARD_INTEL 0x1
+#define CLK_AVC_ME_MAJOR_BIDIRECTIONAL_INTEL 0x2
+
+#define CLK_AVC_ME_PARTITION_MASK_ALL_INTEL 0x0
+#define CLK_AVC_ME_PARTITION_MASK_16x16_INTEL 0x7E
+#define CLK_AVC_ME_PARTITION_MASK_16x8_INTEL 0x7D
+#define CLK_AVC_ME_PARTITION_MASK_8x16_INTEL 0x7B
+#define CLK_AVC_ME_PARTITION_MASK_8x8_INTEL 0x77
+#define CLK_AVC_ME_PARTITION_MASK_8x4_INTEL 0x6F
+#define CLK_AVC_ME_PARTITION_MASK_4x8_INTEL 0x5F
+#define CLK_AVC_ME_PARTITION_MASK_4x4_INTEL 0x3F
+
+#define CLK_AVC_ME_SLICE_TYPE_PRED_INTEL 0x0
+#define CLK_AVC_ME_SLICE_TYPE_BPRED_INTEL 0x1
+#define CLK_AVC_ME_SLICE_TYPE_INTRA_INTEL 0x2
+
+#define CLK_AVC_ME_SEARCH_WINDOW_EXHAUSTIVE_INTEL 0x0
+#define CLK_AVC_ME_SEARCH_WINDOW_SMALL_INTEL 0x1
+#define CLK_AVC_ME_SEARCH_WINDOW_TINY_INTEL 0x2
+#define CLK_AVC_ME_SEARCH_WINDOW_EXTRA_TINY_INTEL 0x3
+#define CLK_AVC_ME_SEARCH_WINDOW_DIAMOND_INTEL 0x4
+#define CLK_AVC_ME_SEARCH_WINDOW_LARGE_DIAMOND_INTEL 0x5
+#define CLK_AVC_ME_SEARCH_WINDOW_RESERVED0_INTEL 0x6
+#define CLK_AVC_ME_SEARCH_WINDOW_RESERVED1_INTEL 0x7
+#define CLK_AVC_ME_SEARCH_WINDOW_CUSTOM_INTEL 0x8
+
+#define CLK_AVC_ME_SAD_ADJUST_MODE_NONE_INTEL 0x0
+#define CLK_AVC_ME_SAD_ADJUST_MODE_HAAR_INTEL 0x2
+
+#define CLK_AVC_ME_SUBPIXEL_MODE_INTEGER_INTEL 0x0
+#define CLK_AVC_ME_SUBPIXEL_MODE_HPEL_INTEL 0x1
+#define CLK_AVC_ME_SUBPIXEL_MODE_QPEL_INTEL 0x3
+
+#define CLK_AVC_ME_COST_PRECISION_QPEL_INTEL 0x0
+#define CLK_AVC_ME_COST_PRECISION_HPEL_INTEL 0x1
+#define CLK_AVC_ME_COST_PRECISION_PEL_INTEL 0x2
+#define CLK_AVC_ME_COST_PRECISION_DPEL_INTEL 0x3
+
+#define CLK_AVC_ME_BIDIR_WEIGHT_QUARTER_INTEL 0x10
+#define CLK_AVC_ME_BIDIR_WEIGHT_THIRD_INTEL 0x15
+#define CLK_AVC_ME_BIDIR_WEIGHT_HALF_INTEL 0x20
+#define CLK_AVC_ME_BIDIR_WEIGHT_TWO_THIRD_INTEL 0x2B
+#define CLK_AVC_ME_BIDIR_WEIGHT_THREE_QUARTER_INTEL 0x30
+
+#define CLK_AVC_ME_BORDER_REACHED_LEFT_INTEL 0x0
+#define CLK_AVC_ME_BORDER_REACHED_RIGHT_INTEL 0x2
+#define CLK_AVC_ME_BORDER_REACHED_TOP_INTEL 0x4
+#define CLK_AVC_ME_BORDER_REACHED_BOTTOM_INTEL 0x8
+
+#define CLK_AVC_ME_INTRA_16x16_INTEL 0x0
+#define CLK_AVC_ME_INTRA_8x8_INTEL 0x1
+#define CLK_AVC_ME_INTRA_4x4_INTEL 0x2
+
+#define CLK_AVC_ME_SKIP_BLOCK_PARTITION_16x16_INTEL 0x0
+#define CLK_AVC_ME_SKIP_BLOCK_PARTITION_8x8_INTEL 0x4000
+
+#define CLK_AVC_ME_SKIP_BLOCK_16x16_FORWARD_ENABLE_INTEL (0x1 << 24)
+#define CLK_AVC_ME_SKIP_BLOCK_16x16_BACKWARD_ENABLE_INTEL (0x2 << 24)
+#define CLK_AVC_ME_SKIP_BLOCK_16x16_DUAL_ENABLE_INTEL (0x3 << 24)
+#define CLK_AVC_ME_SKIP_BLOCK_8x8_FORWARD_ENABLE_INTEL (0x55 << 24)
+#define CLK_AVC_ME_SKIP_BLOCK_8x8_BACKWARD_ENABLE_INTEL (0xAA << 24)
+#define CLK_AVC_ME_SKIP_BLOCK_8x8_DUAL_ENABLE_INTEL (0xFF << 24)
+#define CLK_AVC_ME_SKIP_BLOCK_8x8_0_FORWARD_ENABLE_INTEL (0x1 << 24)
+#define CLK_AVC_ME_SKIP_BLOCK_8x8_0_BACKWARD_ENABLE_INTEL (0x2 << 24)
+#define CLK_AVC_ME_SKIP_BLOCK_8x8_1_FORWARD_ENABLE_INTEL (0x1 << 26)
+#define CLK_AVC_ME_SKIP_BLOCK_8x8_1_BACKWARD_ENABLE_INTEL (0x2 << 26)
+#define CLK_AVC_ME_SKIP_BLOCK_8x8_2_FORWARD_ENABLE_INTEL (0x1 << 28)
+#define CLK_AVC_ME_SKIP_BLOCK_8x8_2_BACKWARD_ENABLE_INTEL (0x2 << 28)
+#define CLK_AVC_ME_SKIP_BLOCK_8x8_3_FORWARD_ENABLE_INTEL (0x1 << 30)
+#define CLK_AVC_ME_SKIP_BLOCK_8x8_3_BACKWARD_ENABLE_INTEL (0x2 << 30)
+
+#define CLK_AVC_ME_BLOCK_BASED_SKIP_4x4_INTEL 0x00
+#define CLK_AVC_ME_BLOCK_BASED_SKIP_8x8_INTEL 0x80
+
+#define CLK_AVC_ME_INTRA_LUMA_PARTITION_MASK_ALL_INTEL 0x0
+#define CLK_AVC_ME_INTRA_LUMA_PARTITION_MASK_16x16_INTEL 0x6
+#define CLK_AVC_ME_INTRA_LUMA_PARTITION_MASK_8x8_INTEL 0x5
+#define CLK_AVC_ME_INTRA_LUMA_PARTITION_MASK_4x4_INTEL 0x3
+
+#define CLK_AVC_ME_INTRA_NEIGHBOR_LEFT_MASK_ENABLE_INTEL 0x60
+#define CLK_AVC_ME_INTRA_NEIGHBOR_UPPER_MASK_ENABLE_INTEL 0x10
+#define CLK_AVC_ME_INTRA_NEIGHBOR_UPPER_RIGHT_MASK_ENABLE_INTEL 0x8
+#define CLK_AVC_ME_INTRA_NEIGHBOR_UPPER_LEFT_MASK_ENABLE_INTEL 0x4
+
+#define CLK_AVC_ME_LUMA_PREDICTOR_MODE_VERTICAL_INTEL 0x0
+#define CLK_AVC_ME_LUMA_PREDICTOR_MODE_HORIZONTAL_INTEL 0x1
+#define CLK_AVC_ME_LUMA_PREDICTOR_MODE_DC_INTEL 0x2
+#define CLK_AVC_ME_LUMA_PREDICTOR_MODE_DIAGONAL_DOWN_LEFT_INTEL 0x3
+#define CLK_AVC_ME_LUMA_PREDICTOR_MODE_DIAGONAL_DOWN_RIGHT_INTEL 0x4
+#define CLK_AVC_ME_LUMA_PREDICTOR_MODE_PLANE_INTEL 0x4
+#define CLK_AVC_ME_LUMA_PREDICTOR_MODE_VERTICAL_RIGHT_INTEL 0x5
+#define CLK_AVC_ME_LUMA_PREDICTOR_MODE_HORIZONTAL_DOWN_INTEL 0x6
+#define CLK_AVC_ME_LUMA_PREDICTOR_MODE_VERTICAL_LEFT_INTEL 0x7
+#define CLK_AVC_ME_LUMA_PREDICTOR_MODE_HORIZONTAL_UP_INTEL 0x8
+#define CLK_AVC_ME_CHROMA_PREDICTOR_MODE_DC_INTEL 0x0
+#define CLK_AVC_ME_CHROMA_PREDICTOR_MODE_HORIZONTAL_INTEL 0x1
+#define CLK_AVC_ME_CHROMA_PREDICTOR_MODE_VERTICAL_INTEL 0x2
+#define CLK_AVC_ME_CHROMA_PREDICTOR_MODE_PLANE_INTEL 0x3
+
+#define CLK_AVC_ME_FRAME_FORWARD_INTEL 0x1
+#define CLK_AVC_ME_FRAME_BACKWARD_INTEL 0x2
+#define CLK_AVC_ME_FRAME_DUAL_INTEL 0x3
+
+#define CLK_AVC_ME_INTERLACED_SCAN_TOP_FIELD_INTEL 0x0
+#define CLK_AVC_ME_INTERLACED_SCAN_BOTTOM_FIELD_INTEL 0x1
+
+#define CLK_AVC_ME_INITIALIZE_INTEL 0x0
+
+#define CLK_AVC_IME_PAYLOAD_INITIALIZE_INTEL 0x0
+#define CLK_AVC_REF_PAYLOAD_INITIALIZE_INTEL 0x0
+#define CLK_AVC_SIC_PAYLOAD_INITIALIZE_INTEL 0x0
+
+#define CLK_AVC_IME_RESULT_INITIALIZE_INTEL 0x0
+#define CLK_AVC_REF_RESULT_INITIALIZE_INTEL 0x0
+#define CLK_AVC_SIC_RESULT_INITIALIZE_INTEL 0x0
+
+#define CLK_AVC_IME_RESULT_SINGLE_REFERENCE_STREAMOUT_INITIALIZE_INTEL 0x0
+#define CLK_AVC_IME_RESULT_SINGLE_REFERENCE_STREAMIN_INITIALIZE_INTEL 0x0
+#define CLK_AVC_IME_RESULT_DUAL_REFERENCE_STREAMOUT_INITIALIZE_INTEL 0x0
+#define CLK_AVC_IME_RESULT_DUAL_REFERENCE_STREAMIN_INITIALIZE_INTEL 0x0
+
+#pragma OPENCL EXTENSION cl_intel_device_side_avc_motion_estimation : end
+#endif // cl_intel_device_side_avc_motion_estimation
+
+#endif //_OPENCL_BASE_H_
@@ -0,0 +1,35 @@
+/*===---- __clang_openmp_math.h - OpenMP target math support ---------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#if defined(__NVPTX__) && defined(_OPENMP)
+/// TODO:
+/// We are currently reusing the functionality of the Clang-CUDA code path
+/// as an alternative to the host declarations provided by math.h and cmath.
+/// This is suboptimal.
+///
+/// We should instead declare the device functions in a similar way, e.g.,
+/// through OpenMP 5.0 variants, and afterwards populate the module with the
+/// host declarations by unconditionally including the host math.h or cmath,
+/// respectively. This is actually what the Clang-CUDA code path does, using
+/// __device__ instead of variants to avoid redeclarations and get the desired
+/// overload resolution.
+
+#define __CUDA__
+
+#if defined(__cplusplus)
+  #include <__clang_cuda_cmath.h>
+#endif
+
+#undef __CUDA__
+
+/// Magic macro for stopping the math.h/cmath host header from being included.
+#define __CLANG_NO_HOST_MATH__
+
+#endif
+
@@ -0,0 +1,33 @@
+/*===---- __clang_openmp_math_declares.h - OpenMP math declares ------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#ifndef __CLANG_OPENMP_MATH_DECLARES_H__
+#define __CLANG_OPENMP_MATH_DECLARES_H__
+
+#ifndef _OPENMP
+#error "This file is for OpenMP compilation only."
+#endif
+
+#if defined(__NVPTX__) && defined(_OPENMP)
+
+#define __CUDA__
+
+#if defined(__cplusplus)
+  #include <__clang_cuda_math_forward_declares.h>
+#endif
+
+/// Include declarations for libdevice functions.
+#include <__clang_cuda_libdevice_declares.h>
+/// Provide definitions for these functions.
+#include <__clang_cuda_device_functions.h>
+
+#undef __CUDA__
+
+#endif
+#endif
@@ -0,0 +1,16 @@
+/*===-------------- cmath - Alternative cmath header -----------------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#include <__clang_openmp_math.h>
+
+#ifndef __CLANG_NO_HOST_MATH__
+#include_next <cmath>
+#else
+#undef __CLANG_NO_HOST_MATH__
+#endif
@@ -0,0 +1,17 @@
+/*===------------- math.h - Alternative math.h header ----------------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#include <__clang_openmp_math.h>
+
+#ifndef __CLANG_NO_HOST_MATH__
+#include_next <math.h>
+#else
+#undef __CLANG_NO_HOST_MATH__
+#endif
+
@@ -1,22 +1,8 @@
 /*===---- pconfigintrin.h - X86 platform configuration ---------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -30,6 +16,8 @@

 #define __PCONFIG_KEY_PROGRAM 0x00000001

+#if __has_extension(gnu_asm)
+
 /* Define the default attributes for the functions in this file. */
 #define __DEFAULT_FN_ATTRS \
  __attribute__((__always_inline__, __nodebug__,  __target__("pconfig")))
@@ -47,4 +35,6 @@ _pconfig_u32(unsigned int __leaf, __SIZE_TYPE__ __d[])

 #undef __DEFAULT_FN_ATTRS

+#endif /* __has_extension(gnu_asm) */
+
 #endif
@@ -1,23 +1,9 @@
 /*===---- pkuintrin.h - PKU intrinsics -------------------------------------===
 *
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- pmmintrin.h - SSE3 intrinsics ------------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -1,22 +1,8 @@
 /*===---- popcntintrin.h - POPCNT intrinsics -------------------------------===
 *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
@@ -43,22 +29,6 @@ _mm_popcnt_u32(unsigned int __A)
  return __builtin_popcount(__A);
 }

-/// Counts the number of bits in the source operand having a value of 1.
-///
-/// \headerfile <x86intrin.h>
-///
-/// This intrinsic corresponds to the <c> POPCNT </c> instruction.
-///
-/// \param __A
-///    A signed 32-bit integer operand.
-/// \returns A 32-bit integer containing the number of bits with value 1 in the
-///    source operand.
-static __inline__ int __DEFAULT_FN_ATTRS
-_popcnt32(int __A)
-{
-  return __builtin_popcount(__A);
-}
-
 #ifdef __x86_64__
 /// Counts the number of bits in the source operand having a value of 1.
 ///
@@ -75,22 +45,6 @@ _mm_popcnt_u64(unsigned long long __A)
 {
  return __builtin_popcountll(__A);
 }
-
-/// Counts the number of bits in the source operand having a value of 1.
-///
-/// \headerfile <x86intrin.h>
-///
-/// This intrinsic corresponds to the <c> POPCNT </c> instruction.
-///
-/// \param __A
-///    A signed 64-bit integer operand.
-/// \returns A 64-bit integer containing the number of bits with value 1 in the
-///    source operand.
-static __inline__ long long __DEFAULT_FN_ATTRS
-_popcnt64(long long __A)
-{
-  return __builtin_popcountll(__A);
-}
 #endif /* __x86_64__ */

 #undef __DEFAULT_FN_ATTRS
@@ -0,0 +1,44 @@
+/*===---- mm_malloc.h - Implementation of _mm_malloc and _mm_free ----------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#ifndef _MM_MALLOC_H_INCLUDED
+#define _MM_MALLOC_H_INCLUDED
+
+#include <stdlib.h>
+
+/* We can't depend on <stdlib.h> since the prototype of posix_memalign
+   may not be visible.  */
+#ifndef __cplusplus
+extern int posix_memalign (void **, size_t, size_t);
+#else
+extern "C" int posix_memalign (void **, size_t, size_t) throw ();
+#endif
+
+static __inline void *
+_mm_malloc (size_t size, size_t alignment)
+{
+  /* PowerPC64 ELF V2 ABI requires quadword alignment.  */
+  size_t vec_align = sizeof (__vector float);
+  void *ptr;
+
+  if (alignment < vec_align)
+    alignment = vec_align;
+  if (posix_memalign (&ptr, alignment, size) == 0)
+    return ptr;
+  else
+    return NULL;
+}
+
+static __inline void
+_mm_free (void * ptr)
+{
+  free (ptr);
+}
+
+#endif /* _MM_MALLOC_H_INCLUDED */
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Malte LangkabelandGitHub	f6e8a2125d	logic: respect class qualifyer in method call for python post processing (#951 ) If the class of a called method is explicitly specified ("Base.__init__()"), only record an ambiguous edge to that method.	2020-03-30 21:24:23 +02:00
Eberhard GrätherandGitHub	31cbf6c11a	logic: Fixed multiple main declarations not shown as separate symbols when declaring file has same name (#950 ) regards #233	2020-03-30 13:49:14 +02:00
mlangkabel	f37716dc82	build: improve error handling if windows deployment cannot find the proper tools	2020-03-30 12:02:55 +02:00
Eberhard GrätherandGitHub	d13c21f6f3	ui/test: Manual testing fixes (#949 ) * Fixed tooltip list items not activated on click * Fixed crash when clearing focused graph edges after displaying graph with no edges * Updated and fixed manual graph view tests * Fixed previous location refocused when activating local symbol * Fixed crash in graph view after showing empty graph	2020-03-29 23:32:49 +02:00
Eberhard Graether	a4d1403722	docs: Updated documentation to release 2020.1 * removed steps from Source Group setup * added installation guide for Linux AppImage * added new focus navigation shortcuts	2020-03-29 17:26:09 +02:00
Eberhard GrätherandGitHub	bf6a017720	build: Provide AppImage package for Linux (issue #279 ) (#945 ) * Create AppImage package using linuxdeployqt in Travis CI * Renamed appPath() to sharedDataPath() * Fixed include error in tutorial	2020-03-29 17:10:30 +02:00
Eberhard GrätherandGitHub	76562bb8ee	ui: Fixes related to focus navigation (#948 ) Scroll graph area with Ctrl + Arrows Moved graph zoom to Ctrl + Shift + Up/Down Scroll code area with Ctrl + Arrows Fixed graph showing focus when activating the active symbol Made links in project description focus-able Fixed parent graph node not showing focus after hovering edge to child node	2020-03-29 16:01:22 +02:00
Andreas StallingerandGitHub	57fd9f277a	build: rename TestSettings in MigratorTestSuite to enable UNITY_BUILD (#947 ) Run cmake (minimum version 3.16) with -DCMAKE_UNITY_BUILD=ON to reduce build time.	2020-03-27 14:38:55 +01:00
Eberhard GrätherandGitHub	eaa263be44	ui: Fix copy shortcut for selected code broken #943 fixes #940	2020-03-23 18:10:21 +01:00
Eberhard GrätherandGitHub	38925292b7	ui: Iterate code references within the same line when holding Shift (#936 )	2020-03-05 15:41:17 +01:00
Eberhard Graether	e8f258ba1d	res: Changelog for Sourcetrail 2020.1.103-beta	2020-03-02 23:00:05 +01:00
Eberhard Graether	b98634f226	build: Fixed macOS app notarization issues * fixed code signing issues for app notarization * extended bundle_install.sh script with optional app notarization * also made DMG package creation optional	2020-03-02 22:44:19 +01:00
Eberhard Graether	140e0059e8	ui: Make content of help dialogs selectable (issue #805 )	2020-03-02 16:19:31 +01:00
mlangkabel	da7cd9411b	build: change linux CI to deploy release builds for tags	2020-03-02 16:15:31 +01:00
Eberhard GrätherandGitHub	b0616778f3	ui: Keyboard controls (#935 ) * switch focus between views with Tab * move focus within views with WASD/HJKL/Arrows * move focus between graph edges by holding Shift * move focus between code references by holding Shift * removed graph panning with WASD and moved zooming to Alt + W/S * removed graph navigation by pressing starting character in graph view lists * changed local reference and custom trail shortcuts * updated Keyboard Shortcuts window * use common back and forward shortcuts and YZ & Shift + YZ * fix macOS issue where widgets don't get proper focus after creating a new tab * don't use shared_ptr in QtMainView fixes #486, #327, #214, #210	2020-03-02 14:48:03 +01:00
Timothee "TTimo" Besset GitHub Eberhard Gräther	f4b37f9763	logic: Fixing a crash in SharedMemory::ScopedAccess use (#912 ) Co-authored-by: Eberhard Gräther <egraether@coati.io>	2020-03-02 12:23:57 +01:00
Eberhard Graether	5e475b75c8	res: Updated SPONSORS.md - March 2020	2020-03-02 10:19:20 +01:00
Malte LangkabelandGitHub	3e6d8fcce5	buid: fix remaining msvc warnings for 64 bit build (#934 )	2020-03-02 09:51:15 +01:00
Malte LangkabelandGitHub	ad464fc1b1	logic: discard non-existing paths in path detectors (#930 ) This prevents the automatic path detection from adding paths to the project settings or application settings that cause the "you have missing paths" dialog to pop up when saving the settings.	2020-02-24 19:59:21 +01:00
Malte LangkabelandGitHub	4dd0cb7590	data: update python indexer to v1.db25.p3 (#929 )	2020-02-24 16:14:57 +01:00
Eberhard GrätherandGitHub	3a29d23a56	src: Fixed QtThreadedFunctor gets sometimes stuck (#926 ) * It happens when executed both from Qt and TaskScheduler thread in parallel. * I found that the signal within QtThreadedFunctorHelper::operator() was sometimes not emitted and therefore QtThreadedFunctorHelper::execute() was never called.	2020-02-19 09:06:25 +01:00
Malte LangkabelandGitHub	437f06d21b	src: extract NoteType::Type to NodeKind (#925 )	2020-02-14 20:35:02 +01:00
Malte LangkabelandGitHub	a30f47e27f	build: Treat warnings as errors (#923 ) * squash and rebase andronov-alexey:treat_warnings_as_errors from pull request #850 * fix remaining warnings in java lib	2020-02-14 16:34:04 +01:00
Eberhard GrätherandGitHub	e5c1a118d7	data: Updated LLVM/Clang config headers to release 9.0.0 (#922 )	2020-02-13 15:41:08 +01:00
Malte LangkabelandGitHub	db95591645	util: Fix FilePath::isValid() and add tests (#908 ) * fixed bug that caused FilePath to be invalid for files with extension * added tests for FilePath::isValid() fixes #907	2020-02-13 00:29:15 +01:00
Eberhard GrätherandGitHub	3be685dbc9	test: Fixed test code causing exceptions in FilePath::exists() (#921 )	2020-02-12 23:29:51 +01:00
Eberhard GrätherandGitHub	b0143adeed	logic: Fix crash in update check on premature Qt object deletion (#920 )	2020-02-12 22:14:20 +01:00
Waqar AhmedandGitHub	222e3d578a	perf: Fix more clazy qstring-allocation warnings and pass parameters by reference (#910 ) * Fix some more clazy-qstring-allocation warnings * Fix missing refs on large types in lib_gui * Fix trivially copyable types being passed by ref in lib_gui	2020-02-12 22:13:36 +01:00
Timothee "TTimo" BessetandGitHub	71ef2f31a1	util: Making FilePath::exists noexcept so the noexcept version of boost::filesystem::exists is used (#919 )	2020-02-12 16:53:39 +01:00
Timothee "TTimo" BessetandGitHub	4da9c53931	logic: Fix an indexer crash (#911 )	2020-02-12 08:20:20 +01:00
Eberhard GrätherandGitHub	08f43173c0	ui: Refresh UI state only after every style refresh in each view finished (#917 ) Separated UI refresh into 'style' and 'state' refresh to avoid race condition between task scheduler thread and UI thread that affected code view state. fixes #916	2020-02-11 01:19:44 +01:00
Eberhard GrätherandGitHub	9fc0a05c3b	ui: Fixes in Source Group UI (issue #723 ) (#915 ) * fixed Source Group setup from Visual Studio Extension * fixed crashes in project setup due to use of std::shared_ptr * fixed source file count not updated on 'show files' click * fixed passing wheel events to parents when list boxes can't handle them	2020-02-10 23:45:31 +01:00
Eberhard GrätherandGitHub	9c40d26002	ui: Mark required contents with * in Source Group setup (issue #723 ) (#914 ) * And show '*required' label at bottom of each page	2020-02-10 21:27:18 +01:00
Eberhard GrätherandGitHub	260f1227bc	Removed multiple dialog steps in Source Group setup (issue #723 ) (#913 ) * removed QtSourceGroupWizard, QtSourceGroupWizardPage and context types * removed isInForm flag of QtProjectWizardContent * added check of empty source paths * set project window as parent for message boxes, so they don't get hidden behind main window * fixed issues when removing and duplicating source groups * updated project setup tests to no steps	2020-02-10 20:00:36 +01:00