1 files changed, 96 insertions, 0 deletions
diff --git a/sci-libs/rocBLAS/files/Tensile-4.3.0-hsaco-compile-specified-arch.patch b/sci-libs/rocBLAS/files/Tensile-4.3.0-hsaco-compile-specified-arch.patch
new file mode 100644
index 000000000000..8e6753781a2a
--- /dev/null
+++ b/sci-libs/rocBLAS/files/Tensile-4.3.0-hsaco-compile-specified-arch.patch
@@ -0,0 +1,96 @@
+https://github.com/ROCmSoftwarePlatform/Tensile/issues/1395
+https://github.com/ROCmSoftwarePlatform/Tensile/pull/1398
+
+--- a/Tensile/TensileCreateLibrary.py
++++ b/Tensile/TensileCreateLibrary.py
+@@ -136,6 +136,35 @@ def which(p):
+                 return candidate
+     return None
+ 
++def splitArchs():
++  # Helper for architecture
++  def isSupported(arch):
++    return globalParameters["AsmCaps"][arch]["SupportedISA"] and \
++           globalParameters["AsmCaps"][arch]["SupportedSource"]
++
++  if ";" in globalParameters["Architecture"]:
++    wantedArchs = globalParameters["Architecture"].split(";")
++  else:
++    wantedArchs = globalParameters["Architecture"].split("_")
++  archs = []
++  cmdlineArchs = []
++  if "all" in wantedArchs:
++    for arch in globalParameters['SupportedISA']:
++      if isSupported(arch):
++        if (arch == (9,0,6) or arch == (9,0,8) or arch == (9,0,10)):
++          if (arch == (9,0,10)):
++            archs += [gfxName(arch) + '-xnack+']
++            cmdlineArchs += [gfxName(arch) + ':xnack+']
++          archs += [gfxName(arch) + '-xnack-']
++          cmdlineArchs += [gfxName(arch) + ':xnack-']
++        else:
++          archs += [gfxName(arch)]
++          cmdlineArchs += [gfxName(arch)]
++  else:
++    for arch in wantedArchs:
++      archs += [re.sub(":", "-", arch)]
++      cmdlineArchs += [arch]
++  return archs, cmdlineArchs
+ 
+ def buildSourceCodeObjectFile(CxxCompiler, outputPath, kernelFile):
+     buildPath = ensurePath(os.path.join(globalParameters['WorkingPath'], 'code_object_tmp'))
+@@ -149,24 +178,8 @@ def buildSourceCodeObjectFile(CxxCompiler, outputPath, kernelFile):
+     objectFilename = base + '.o'
+     soFilename = base + '.so'
+ 
+-    def isSupported(arch):
+-        return globalParameters["AsmCaps"][arch]["SupportedISA"] and \
+-               globalParameters["AsmCaps"][arch]["SupportedSource"]
+-
+     if (CxxCompiler == "hipcc"):
+-      archs = []
+-      cmdlineArchs = []
+-      for arch in globalParameters['SupportedISA']:
+-        if isSupported(arch):
+-          if (arch == (9,0,6) or arch == (9,0,8) or arch == (9,0,10)):
+-            if (arch == (9,0,10)):
+-              archs += [gfxName(arch) + '-xnack+']
+-              cmdlineArchs += [gfxName(arch) + ':xnack+']
+-            archs += [gfxName(arch) + '-xnack-']
+-            cmdlineArchs += [gfxName(arch) + ':xnack-']
+-          else:
+-            archs += [gfxName(arch)]
+-            cmdlineArchs += [gfxName(arch)]
++      archs, cmdlineArchs = splitArchs()
+ 
+       archFlags = ['--offload-arch=' + arch for arch in cmdlineArchs]
+ 
+@@ -1063,11 +1076,6 @@ def buildObjectFileNames(solutionWriter, kernelWriterSource, kernelWriterAssembl
+   sourceKernels = list([k for k in kernels if k['KernelLanguage'] == 'Source'])
+   asmKernels = list([k for k in kernels if k['KernelLanguage'] == 'Assembly'])
+ 
+-  # Helper for architecture
+-  def isSupported(arch):
+-        return globalParameters["AsmCaps"][arch]["SupportedISA"] and \
+-               globalParameters["AsmCaps"][arch]["SupportedSource"]
+-
+   # Build a list of kernel object names.
+   for kernel in sourceKernels:
+     sourceKernelNames += [kernelWriterSource.getKernelFileBase(kernel)]
+@@ -1081,15 +1089,7 @@ def buildObjectFileNames(solutionWriter, kernelWriterSource, kernelWriterAssembl
+ 
+   # Source based kernels are built for all supported architectures
+   if (cxxCompiler == 'hipcc'):
+-    sourceArchs = []
+-    for arch in globalParameters['SupportedISA']:
+-      if isSupported(arch):
+-        if (arch == (9,0,6) or arch == (9,0,8) or arch == (9,0,10)):
+-          if (arch == (9,0,10)):
+-            sourceArchs += [gfxName(arch) + '-xnack+']
+-          sourceArchs += [gfxName(arch) + '-xnack-']
+-        else:
+-          sourceArchs += [gfxName(arch)]
++    sourceArchs, _ = splitArchs()
+   else:
+     raise RuntimeError("Unknown compiler %s" % cxxCompiler)
+