gentoo resync : 25.03.2022

7 files changed, 305 insertions, 75 deletions

diff --git a/dev-util/Tensile/Manifest b/dev-util/Tensile/Manifest
index b873575497a2..6972e0b87371 100644
--- a/dev-util/Tensile/Manifest
+++ b/dev-util/Tensile/Manifest
@@ -1,5 +1,9 @@
+AUX Tensile-4.3.0-fix-arch-parse.patch 424 BLAKE2B ac89228abe3173a4cabcb90a679be3706a39cf6bebc448fb17dc9a94be5c5c75289e53fb867c17a3bc36330079905302a83736663d2f743c9805c97253b9fec0 SHA512 131e9fa7c39f12fbbbc37ace0d29162ff2805e8435985d3edab7e678d89587a2ee9cc1549eee21842c42e99e4a4fba3125fa34fec3dbc9f61cff96d8eeaf5b25
+AUX Tensile-4.3.0-gentoopath.patch 2770 BLAKE2B 72f5d6ae4f447603f2e02bba8ac25bbc85382327ac4e15c2978c2bdd5ab7ff937e71e1dab006d548fd104eb4401b878ba5a67acfc535b456eee532836c90eb1c SHA512 030c616fc12fc25d4749f6bd9914afd6be6844ba44796e928183031e6f5dd98df238379a7b26225306233798b5d32ab1b4cf28f39775b2b7a17040c4f704106f
+AUX Tensile-4.3.0-gfx1031.patch 7037 BLAKE2B ea2e5dec9d5f6749a78cae4d1659a08b712e548cdca29dabde29f52a60f443eac0c10bac27667545816e5b6b89835ee5e79d766028bad79ba17e5b14a4bf5ea9 SHA512 2b1936a6e5b52bf2f6aaa70255be9f78e82329f7855a3db56d769fed13934ca2c2671f089bc5aea43c4a0e67d3ec8ad185e32f7ade03c515b3c74a683568b192
 AUX Tensile-4.3.0-hsaco-compile-specified-arch.patch 3859 BLAKE2B 4590978cff0fdb0501ba2405615775cb3f8900ce164c3d57cc59dfe82e1adc25376b6463855a045f5e0652cc985b0015566b95ff28327c59f2db875a84cb49b3 SHA512 57520f1d46f46c7cfd5b8c3ae307da07695c19479b687ce994ad9fba2e755ed7c776c3d8bee8e0642c7613a5d53d8469f329b1eb07563c13d2f7bda8b3d36687
 AUX Tensile-4.3.0-output-commands.patch 1629 BLAKE2B c43395d8e8aeb956d5eb84c8a34ad4b995ed32499ceababeb22d5ca3ac5ee6e8ef353a1467a77943a441f0840b9a6ad1f53202ec8673ef3753aa2bec1395fec4 SHA512 45bdae1d87f6e31d337b22f146b9dee25f4f87357c6ac52bd843556dd742431db10efb55fb8ef815cc9941b5b9f05970d43a6fec0f2d9195c30c633e33d138bf
+AUX Tensile-4.3.0-use-ninja.patch 957 BLAKE2B cb919b224aaeb3b9d65a755ff0688aa823b70361d2ee940d62f33828c118a60c88cd0f108b6e34b22097d9c4c5122a4db2808332a97cd6e7685a4447570b7552 SHA512 3d206a093e870fc95f0ed42e08691144589112d4581f73ba1c4c74ed9bdad0812ec4f67a6076a8a3ac9ab89c61c70f1baaedb774e0908177473be2d206858bf4
 DIST rocm-Tensile-4.3.0.tar.gz 14250149 BLAKE2B 030138eaca2a0aadd96801e6dbd72e510716dd90553ef3795c5e04e00a34a05ecae82b24f755e4033a4acfcdb1cf26291da1e7902bb090f89a010d403e832beb SHA512 126db0b413c716fba8d5be9bff7a44fd1badacbf32f3db8d0db649819177db37ebd56fd22dd3c809655f5d29675be115e698cd10bc3d0b4b23878ae3726fce47
-EBUILD Tensile-4.3.0.ebuild 1995 BLAKE2B 66474ff936214aeede2613b80522a2bd376216115b7c0cdbb046443b81146226d8ca0c2ea7c4f28661dfd1ed0e94e9e225211acc1a21ba8f74107819cb00ca8b SHA512 ca29d0652e6ee50f287def381ea44cb4e6657a73e03e4c030c24b9ddf8ea95256e11891896e14b6498c4b9eebc5d20388045927c701fc62be7dcdcd67c385b11
+EBUILD Tensile-4.3.0-r1.ebuild 2730 BLAKE2B ecbed69974d2d179cf0309c8265d394dfbfcd4ea9ef77448f4d4553aa51569bb5dced2c3404b387621e42037e62ed28b4de9ca0db472e4265f0f6b28e1dd630a SHA512 136eb9243bde86b66509d6e91b78a74a1e50727387eef515726efa9258f9e94a503a272bad4e5eeab30867b58522441d50a3dbcfec496197c3d2feee8469b2dd
 MISC metadata.xml 349 BLAKE2B 363f31b1d597e4c4959c588c9765154049c7c9692bbd64a0736226261b6232c75af7cbf255de59813cd10b9d45b30cf08d4ad0eb1422bf956264377a58002340 SHA512 d83250993581f9b23b43b8553cf46fe75411232ca7ec18c32c070d6acb0f9c7a01769755a3f11b4c5aafe40a63ee0c3817fc45dd01325ce02bbf557d5ab0cdea
diff --git a/dev-util/Tensile/Tensile-4.3.0-r1.ebuild b/dev-util/Tensile/Tensile-4.3.0-r1.ebuild
new file mode 100644
index 000000000000..143867819d04
--- /dev/null
+++ b/dev-util/Tensile/Tensile-4.3.0-r1.ebuild
@@ -0,0 +1,86 @@
+# Copyright 1999-2022 Gentoo Authors
+# Distributed under the terms of the GNU General Public License v2
+
+EAPI=8
+
+PYTHON_COMPAT=( python3_{8..10} )
+DISTUTILS_USE_PEP517=setuptools
+inherit distutils-r1
+
+DESCRIPTION="Stretching GPU performance for GEMMs and tensor contractions"
+HOMEPAGE="https://github.com/ROCmSoftwarePlatform/Tensile"
+SRC_URI="https://github.com/ROCmSoftwarePlatform/Tensile/archive/rocm-${PV}.tar.gz -> rocm-Tensile-${PV}.tar.gz"
+S="${WORKDIR}/${PN}-rocm-${PV}"
+
+LICENSE="MIT"
+KEYWORDS="~amd64"
+SLOT="0/$(ver_cut 1-2)"
+
+# Not compatible with recent versions of pytest
+RESTRICT="test"
+
+RDEPEND="${PYTHON_DEPS}
+	dev-python/pyyaml[${PYTHON_USEDEP}]
+	dev-python/msgpack[${PYTHON_USEDEP}]
+	>=dev-util/rocm-smi-4.3.0
+"
+DEPEND="${RDEPEND}
+	dev-util/hip:${SLOT}
+"
+
+PATCHES=( "${FILESDIR}"/${PN}-4.3.0-output-commands.patch
+		  "${FILESDIR}"/${PN}-4.3.0-hsaco-compile-specified-arch.patch
+		  "${FILESDIR}"/${PN}-4.3.0-gfx1031.patch
+		  "${FILESDIR}"/${PN}-4.3.0-fix-arch-parse.patch
+		  "${FILESDIR}"/${PN}-4.3.0-use-ninja.patch
+		  "${FILESDIR}"/${PN}-4.3.0-gentoopath.patch
+	  )
+
+src_prepare() {
+	distutils-r1_src_prepare
+
+	pushd ${PN} || die
+
+	sed -e "/ROCM_SMI_ROOT/s,lib,$(get_libdir)," \
+		-i Source/cmake/FindROCmSMI.cmake || die
+	sed -r -e "/TENSILE_USE_LLVM/s/ON/OFF/" \
+		-i Source/CMakeLists.txt || die
+	sed -e "/chmod 755/d" -i Source/TensileCreateLibrary.cmake || die # remove chmod 755 on
+	sed -e "s,\${Tensile_ROOT}/bin/,,g" -i Source/TensileCreateLibrary.cmake cmake/TensileConfig.cmake || die # ${Tensile_ROOT}/bin does not exists; call command directly
+
+	local Tensile_share_dir="\"${EPREFIX}/usr/share/${PN}\""
+	sed -e "/HipClangVersion/s/0,0,0/$(hipconfig -v)/" \
+		-e "/SourcePath/s,globalParameters\[\"ScriptPath\"\],${Tensile_share_dir}," \
+		-i Common.py || die
+
+	sed  -e "/CMAKE_CXX_COMPILER/s,globalParameters\[\"ROCmBinPath\"\],\"${EPREFIX}/usr/lib/hip/bin\"," -i ClientExecutable.py || die
+
+	sed -e "/scriptDir/s,os.path.dirname(os.path.realpath(__file__)),${Tensile_share_dir}," -i ReplacementKernels.py || die
+
+	sed -e "s,os.path.dirname(os.path.realpath(__file__)),${Tensile_share_dir},g" -i ${PN}.py || die
+
+	sed -e "s|os\.path\.dirname.*$|\"${EPREFIX}/usr/share/Tensile/Source\", end='')|" -i __init__.py || die
+
+	popd || die
+
+	sed -e "/package_data/d" -e "/data_files/d" -i setup.py || die
+}
+
+python_install() {
+	distutils-r1_python_install
+
+	python_moduleinto Tensile
+	pushd Tensile
+	python_domodule Components
+	python_newexe Utilities/merge.py ${PN}-merge
+}
+
+src_install() {
+	distutils-r1_src_install
+
+	pushd ${PN} || die
+	insinto /usr/share/${PN}
+	doins -r Configs Perf ReplacementKernels ReplacementKernels-cov3 Source
+	insinto /usr/$(get_libdir)/cmake/${PN}
+	doins cmake/*.cmake
+}
diff --git a/dev-util/Tensile/Tensile-4.3.0.ebuild b/dev-util/Tensile/Tensile-4.3.0.ebuild
deleted file mode 100644
index cf33fb19cf10..000000000000
--- a/dev-util/Tensile/Tensile-4.3.0.ebuild
+++ /dev/null
@@ -1,74 +0,0 @@
-# Copyright 1999-2022 Gentoo Authors
-# Distributed under the terms of the GNU General Public License v2
-
-EAPI=8
-
-PYTHON_COMPAT=( python3_{8..10} )
-DISTUTILS_USE_PEP517=setuptools
-inherit distutils-r1
-
-DESCRIPTION="Stretching GPU performance for GEMMs and tensor contractions"
-HOMEPAGE="https://github.com/ROCmSoftwarePlatform/Tensile"
-SRC_URI="https://github.com/ROCmSoftwarePlatform/Tensile/archive/rocm-${PV}.tar.gz -> rocm-Tensile-${PV}.tar.gz"
-S="${WORKDIR}/${PN}-rocm-${PV}"
-
-LICENSE="MIT"
-KEYWORDS="~amd64"
-SLOT="0/$(ver_cut 1-2)"
-
-# Not compatible with recent versions of pytest
-RESTRICT="test"
-
-RDEPEND="${PYTHON_DEPS}
-	dev-python/pyyaml[${PYTHON_USEDEP}]
-	dev-python/msgpack[${PYTHON_USEDEP}]
-"
-DEPEND="${RDEPEND}
-	dev-util/hip:${SLOT}
-"
-BDEPEND="test? (
-	dev-util/rocminfo:${SLOT}
-)"
-
-PATCHES=(
-	"${FILESDIR}/Tensile-${PV}-hsaco-compile-specified-arch.patch" # backported from upstream, should remove after 4.3.0
-	"${FILESDIR}/Tensile-4.3.0-output-commands.patch"
-)
-
-CMAKE_USE_DIR="${WORKDIR}/Source"
-
-distutils_enable_tests pytest
-
-src_prepare() {
-	distutils-r1_src_prepare
-
-	mv ${PN}/Source "${WORKDIR}"/ || die
-	sed -e "/ROCM_SMI_ROOT/s,lib,$(get_libdir)," \
-		-i "${WORKDIR}"/Source/cmake/FindROCmSMI.cmake || die
-	sed -r -e "/TENSILE_USE_LLVM/s/ON/OFF/" \
-		-i "${WORKDIR}"/Source/CMakeLists.txt || die
-
-	sed -e "/HipClangVersion/s/0,0,0/$(ver_rs 1-3 ,)/" \
-		-e "/SourcePath/s,os\.path\.join.*$,\"${EPREFIX}/usr/share/${PN}\"," \
-		-i ${PN}/Common.py || die
-
-	sed -e "s|os\.path\.dirname.*$|\"${EPREFIX}/usr/share/Tensile\", end='')|" \
-		-i ${PN}/__init__.py || die
-}
-
-src_test() {
-	ROCM_PATH="${EPREFIX}/usr/" distutils-r1_src_test
-}
-
-src_install() {
-	distutils-r1_src_install
-
-	# Move the cmake files to the correct directory
-	mkdir -p "${ED}/usr/$(get_libdir)/cmake/${PN}" || die
-	mv "${ED}/usr/cmake/"* "${ED}/usr/$(get_libdir)/cmake/${PN}" || die
-	rm -r "${ED}/usr/cmake" || die
-
-	insinto /usr/share/${PN}
-	doins -r "${WORKDIR}"/Source/*
-	dosym . /usr/share/${PN}/Source
-}
diff --git a/dev-util/Tensile/files/Tensile-4.3.0-fix-arch-parse.patch b/dev-util/Tensile/files/Tensile-4.3.0-fix-arch-parse.patch
new file mode 100644
index 000000000000..01b94b32cb6e
--- /dev/null
+++ b/dev-util/Tensile/files/Tensile-4.3.0-fix-arch-parse.patch
@@ -0,0 +1,12 @@
+Index: Tensile-rocm-4.3.0/Tensile/Tensile.py
+===================================================================
+--- Tensile-rocm-4.3.0.orig/Tensile/Tensile.py
++++ Tensile-rocm-4.3.0/Tensile/Tensile.py
+@@ -97,7 +97,6 @@ def addCommonArguments(argParser):
+     """
+ 
+     (key, value) = par.split("=")
+-    value = eval(value)
+     return (key, value)
+ 
+   argParser.add_argument("-d", "--device", dest="device", type=int, \
diff --git a/dev-util/Tensile/files/Tensile-4.3.0-gentoopath.patch b/dev-util/Tensile/files/Tensile-4.3.0-gentoopath.patch
new file mode 100644
index 000000000000..6fda0ddc6a8d
--- /dev/null
+++ b/dev-util/Tensile/files/Tensile-4.3.0-gentoopath.patch
@@ -0,0 +1,62 @@
+Index: Tensile-rocm-4.3.0/Tensile/Source/client/CMakeLists.txt
+===================================================================
+--- Tensile-rocm-4.3.0.orig/Tensile/Source/client/CMakeLists.txt
++++ Tensile-rocm-4.3.0/Tensile/Source/client/CMakeLists.txt
+@@ -50,3 +50,5 @@ endif()
+ foreach(arch IN LISTS TENSILE_GPU_ARCHS)
+     target_link_libraries(tensile_client PRIVATE "--amdgpu-target=${arch}")
+ endforeach(arch)
++
++target_link_libraries(tensile_client PRIVATE LLVMSupport)
+Index: Tensile-rocm-4.3.0/Tensile/Source/lib/CMakeLists.txt
+===================================================================
+--- Tensile-rocm-4.3.0.orig/Tensile/Source/lib/CMakeLists.txt
++++ Tensile-rocm-4.3.0/Tensile/Source/lib/CMakeLists.txt
+@@ -48,7 +48,7 @@ set(tensile_sources  ${tensile_sources}
+     )
+ 
+ if(TENSILE_USE_LLVM)
+-    find_package(LLVM 13.0 QUIET CONFIG)
++    find_package(LLVM PATHS /opt/gentoo/usr/lib/llvm/roc QUIET CONFIG)
+     if(NOT LLVM_FOUND)
+         find_package(LLVM 12.0 QUIET CONFIG)
+         if(NOT LLVM_FOUND)
+Index: Tensile-rocm-4.3.0/Tensile/Common.py
+===================================================================
+--- Tensile-rocm-4.3.0.orig/Tensile/Common.py
++++ Tensile-rocm-4.3.0/Tensile/Common.py
+@@ -1667,7 +1667,7 @@ def assignGlobalParameters( config ):
+     else:
+       print2(" %24s: %8s (unspecified)" % (key, defaultValue))
+ 
+-  globalParameters["ROCmPath"] = "/opt/rocm"
++  globalParameters["ROCmPath"] = "/opt/gentoo/usr"
+   if "ROCM_PATH" in os.environ:
+     globalParameters["ROCmPath"] = os.environ.get("ROCM_PATH")
+   if "TENSILE_ROCM_PATH" in os.environ:
+Index: Tensile-rocm-4.3.0/Tensile/ClientWriter.py
+===================================================================
+--- Tensile-rocm-4.3.0.orig/Tensile/ClientWriter.py
++++ Tensile-rocm-4.3.0/Tensile/ClientWriter.py
+@@ -284,7 +284,7 @@ def getBuildNewClientLibraryScript(build
+   import io
+   runScriptFile = io.StringIO()
+ 
+-  callCreateLibraryCmd = globalParameters["ScriptPath"] + "/bin/TensileCreateLibrary"
++  callCreateLibraryCmd = "TensileCreateLibrary"
+ 
+ 
+   if globalParameters["MergeFiles"]:
+Index: Tensile-rocm-4.3.0/Tensile/GenerateSummations.py
+===================================================================
+--- Tensile-rocm-4.3.0.orig/Tensile/GenerateSummations.py
++++ Tensile-rocm-4.3.0/Tensile/GenerateSummations.py
+@@ -57,7 +57,7 @@ def createLibraryForBenchmark(logicPath,
+     Selection.
+     """
+ 
+-    pythonExePath = os.path.join(os.path.dirname(os.path.realpath(__file__)), "bin", "TensileCreateLibrary")
++    pythonExePath = "TensileCreateLibrary"
+     args = [pythonExePath, \
+         "--merge-files", "--no-legacy-components", \
+         "--new-client-only", "--no-short-file-names", "--no-library-print-debug", "--architecture=all", \
diff --git a/dev-util/Tensile/files/Tensile-4.3.0-gfx1031.patch b/dev-util/Tensile/files/Tensile-4.3.0-gfx1031.patch
new file mode 100644
index 000000000000..99abceb7c44d
--- /dev/null
+++ b/dev-util/Tensile/files/Tensile-4.3.0-gfx1031.patch
@@ -0,0 +1,119 @@
+--- Tensile-rocm-4.3.0/pytest.ini	2021-04-22 22:35:33.000000000 +0800
++++ Tensile-rocm-4.3.0/pytest.ini	2021-09-30 17:32:21.382806851 +0800
+@@ -88,6 +88,7 @@
+  xfail-gfx1011: architecture
+  xfail-gfx1012: architecture
+  xfail-gfx1030: architecture
++ xfail-gfx1031: architecture
+  skip-gfx000:  architecture
+  skip-gfx900:  architecture
+  skip-gfx906:  architecture
+@@ -97,3 +98,4 @@
+  skip-gfx1011: architecture
+  skip-gfx1012: architecture
+  skip-gfx1030: architecture
++ skip-gfx1031: architecture
+--- Tensile-rocm-4.3.0/Tensile/Common.py	2021-10-05 14:41:22.490754124 +0800
++++ Tensile-rocm-4.3.0/Tensile/Common.py	2021-09-30 17:33:19.041724015 +0800
+@@ -200,7 +200,7 @@
+ globalParameters["MergeFiles"] = True             # F=store every solution and kernel in separate file; T=store all solutions in single file
+ 
+ globalParameters["MaxFileName"] = 64              # If a file name would be longer than this, shorten it with a hash.
++globalParameters["SupportedISA"] = [(8,0,3), (9,0,0), (9,0,6), (9,0,8), (9,0,10), (10,1,0), (10,1,1), (10,1,2), (10,3,0),(10,3,1)] # assembly kernels writer supports these architectures
+-globalParameters["SupportedISA"] = [(8,0,3), (9,0,0), (9,0,6), (9,0,8), (9,0,10), (10,1,0), (10,1,1), (10,1,2), (10,3,0)] # assembly kernels writer supports these architectures
+ 
+ globalParameters["GenerateManifestAndExit"] = False               # Output manifest file with list of expected library objects and exit
+ globalParameters["ClientBuildPath"] = "0_Build"                   # subdirectory for host code build directory
+@@ -265,7 +265,7 @@
+   'gfx906':'vega20', 'gfx906:xnack+':'vega20', 'gfx906:xnack-':'vega20',
+   'gfx908':'arcturus','gfx908:xnack+':'arcturus', 'gfx908:xnack-':'arcturus',
+   'gfx90a':'aldebaran', 'gfx90a:xnack+':'aldebaran', 'gfx90a:xnack-':'aldebaran',
++  'gfx1010':'navi10', 'gfx1011':'navi11', 'gfx1012':'navi12', 'gfx1030':'navi21', 'gfx1031':'navi22',
+-  'gfx1010':'navi10', 'gfx1011':'navi11', 'gfx1012':'navi12', 'gfx1030':'navi21'
+ }
+ 
+ def getArchitectureName(gfxName):
+--- Tensile-rocm-4.3.0/Tensile/KernelWriterAssembly.py	2021-04-22 22:35:33.000000000 +0800
++++ Tensile-rocm-4.3.0/Tensile/KernelWriterAssembly.py	2021-09-30 17:27:06.696711144 +0800
+@@ -2257,7 +2257,7 @@
+ 
+     # integer i8x4
+     elif kernel["ProblemType"]["DataType"].isInt8x4():
++      if self.version == (9,0,6) or self.version == (9,0,8) or self.version == (9,0,10) or self.version == (10,3,0) or self.version == (10,3,1):
+-      if self.version == (9,0,6) or self.version == (9,0,8) or self.version == (9,0,10) or self.version == (10,3,0):
+         for b in range(0, kernel["ThreadTile1"]):
+           for a in range(0, kernel["ThreadTile0"]):
+             for iui in range(0, innerUnroll):
+--- Tensile-rocm-4.3.0/Tensile/Source/CMakeLists.txt	2021-04-22 22:35:33.000000000 +0800
++++ Tensile-rocm-4.3.0/Tensile/Source/CMakeLists.txt	2021-09-30 17:29:12.846345541 +0800
+@@ -51,7 +51,7 @@
+     endif()
+ 
+     if(CMAKE_CXX_COMPILER STREQUAL "hipcc")
++      set(TENSILE_GPU_ARCHS gfx803 gfx900 gfx906:xnack- gfx908:xnack- gfx90a:xnack- gfx1010 gfx1011 gfx1012 gfx1030 gfx1031 CACHE STRING "GPU architectures")
+-      set(TENSILE_GPU_ARCHS gfx803 gfx900 gfx906:xnack- gfx908:xnack- gfx90a:xnack- gfx1010 gfx1011 gfx1012 gfx1030 CACHE STRING "GPU architectures")
+     else()
+       set(TENSILE_GPU_ARCHS gfx803 gfx900 gfx906 gfx908 gfx90a CACHE STRING "GPU architectures")
+     endif()
+@@ -104,7 +104,7 @@
+     set_property( CACHE Tensile_CODE_OBJECT_VERSION PROPERTY STRINGS V2 V3)
+     set_property( CACHE Tensile_COMPILER PROPERTY STRINGS hipcc)
+     set(Tensile_ARCHITECTURE all CACHE STRING "Which GPU architecture to use")
++    set_property( CACHE Tensile_ARCHITECTURE PROPERTY STRINGS all gfx000 gfx900 gfx906:xnack- gfx908:xnack- gfx90a:xnack- gfx1010 gfx1011 gfx1012 gfx1030 gfx1031)
+-    set_property( CACHE Tensile_ARCHITECTURE PROPERTY STRINGS all gfx000 gfx900 gfx906:xnack- gfx908:xnack- gfx90a:xnack- gfx1010 gfx1011 gfx1012 gfx1030)
+     set_property( CACHE Tensile_LIBRARY_FORMAT PROPERTY STRINGS yaml msgpack)
+ 
+     message( STATUS "Tensile_CODE_OBJECT_VERSION from Tensile/Source/CMakeLists.txt: ${Tensile_CODE_OBJECT_VERSION}")
+@@ -206,7 +206,7 @@
+         ${Tensile_RUNTIME_LANGUAGE}     # HIP or OCL
+         ${Tensile_COMPILER}             # hipcc
+         ${Tensile_CODE_OBJECT_VERSION}  # V2 or V3
++        ${Tensile_ARCHITECTURE}         # all, gfx000, gfx803, gfx900, gfx906:xnack-, gfx908:xnack-, gfx90a:xnack-, gfx1010, gfx1011, gfx1012, gfx1030, gfx1031
+-        ${Tensile_ARCHITECTURE}         # all, gfx000, gfx803, gfx900, gfx906:xnack-, gfx908:xnack-, gfx90a:xnack-, gfx1010, gfx1011, gfx1012, gfx1030
+         ${Tensile_LIBRARY_FORMAT}       # yaml or msgpack
+         ${Tensile_MERGE_FILES}          # ON or OFF
+         ${Tensile_SHORT_FILE_NAMES}     # ON or OFF
+--- Tensile-rocm-4.3.0/Tensile/Source/lib/include/Tensile/AMDGPU.hpp	2021-04-22 22:35:33.000000000 +0800
++++ Tensile-rocm-4.3.0/Tensile/Source/lib/include/Tensile/AMDGPU.hpp	2021-09-30 17:48:11.277066515 +0800
+@@ -62,7 +62,8 @@
+             gfx1010 = 1010,
+             gfx1011 = 1011,
+             gfx1012 = 1012,
++            gfx1030 = 1030,
++            gfx1031 = 1031
+-            gfx1030 = 1030
+         };
+ 
+         AMDGPU();
+--- Tensile-rocm-4.3.0/Tensile/Source/lib/include/Tensile/Serialization/Predicates.hpp	2021-04-22 22:35:33.000000000 +0800
++++ Tensile-rocm-4.3.0/Tensile/Source/lib/include/Tensile/Serialization/Predicates.hpp	2021-09-30 17:31:26.075845249 +0800
+@@ -215,6 +215,7 @@
+                 iot::enumCase(io, value, "gfx1011", AMDGPU::Processor::gfx1011);
+                 iot::enumCase(io, value, "gfx1012", AMDGPU::Processor::gfx1012);
+                 iot::enumCase(io, value, "gfx1030", AMDGPU::Processor::gfx1030);
++                iot::enumCase(io, value, "gfx1031", AMDGPU::Processor::gfx1031);
+             }
+         };
+     } // namespace Serialization
+--- Tensile-rocm-4.3.0/Tensile/Source/lib/source/AMDGPU.cpp	2021-04-22 22:35:33.000000000 +0800
++++ Tensile-rocm-4.3.0/Tensile/Source/lib/source/AMDGPU.cpp	2021-09-30 17:31:45.195486318 +0800
+@@ -82,6 +82,8 @@
+             return stream << "gfx1012";
+         case AMDGPU::Processor::gfx1030:
+             return stream << "gfx1030";
++        case AMDGPU::Processor::gfx1031:
++            return stream << "gfx1031";
+         }
+         return stream;
+     }
+--- Tensile-rocm-4.3.0/Tensile/Source/TensileCreateLibrary.cmake	2021-04-22 22:35:33.000000000 +0800
++++ Tensile-rocm-4.3.0/Tensile/Source/TensileCreateLibrary.cmake	2021-09-30 17:29:24.766121912 +0800
+@@ -138,7 +138,7 @@
+     add_library(Tensile ${options} ${Tensile_SOURCE_FILES})
+     # specify gpu targets
+     if( Tensile_ARCHITECTURE MATCHES "all" )
++      set( Tensile_HIP_ISA "gfx803" "gfx900" "gfx906" "gfx908" "gfx1010" "gfx1011" "gfx1012" "gfx1030", "gfx1031")
+-      set( Tensile_HIP_ISA "gfx803" "gfx900" "gfx906" "gfx908" "gfx1010" "gfx1011" "gfx1012" "gfx1030")
+     else()
+       set( Tensile_HIP_ISA ${Tensile_ARCHITECTURE})
+     endif()
diff --git a/dev-util/Tensile/files/Tensile-4.3.0-use-ninja.patch b/dev-util/Tensile/files/Tensile-4.3.0-use-ninja.patch
new file mode 100644
index 000000000000..6645efd72fb1
--- /dev/null
+++ b/dev-util/Tensile/files/Tensile-4.3.0-use-ninja.patch
@@ -0,0 +1,21 @@
+Index: Tensile-rocm-4.3.0/Tensile/ClientExecutable.py
+===================================================================
+--- Tensile-rocm-4.3.0.orig/Tensile/ClientExecutable.py
++++ Tensile-rocm-4.3.0/Tensile/ClientExecutable.py
+@@ -36,6 +36,7 @@ class CMakeEnvironment:
+ 
+         args = ['cmake']
+         args += itertools.chain.from_iterable([ ['-D', '{}={}'.format(key, value)] for key,value in self.options.items()])
++        args += itertools.chain.from_iterable([ ['-G', 'Ninja'], [ '-D', 'CMAKE_EXPORT_COMPILE_COMMANDS=ON' ] ])
+         args += [self.sourceDir]
+ 
+         Common.print2(' '.join(args))
+@@ -43,7 +44,7 @@ class CMakeEnvironment:
+             subprocess.check_call(args, cwd=Common.ensurePath(self.buildDir))
+ 
+     def build(self):
+-        args = ['make', '-j']
++        args = ['ninja']
+         Common.print2(' '.join(args))
+         with Common.ClientExecutionLock():
+             subprocess.check_call(args, cwd=self.buildDir)