mirror of
https://github.com/gentoo-mirror/gentoo.git
synced 2026-01-04 13:47:35 -08:00
d3e730b5c6
Signed-off-by: Sv. Lockal <lockalsash@gmail.com> Part-of: https://github.com/gentoo/gentoo/pull/42717 Signed-off-by: Sam James <sam@gentoo.org>
53 lines
4.0 KiB
Diff
53 lines
4.0 KiB
Diff
Option --parallel-jobs is only supported by amdclang++
|
|
|
|
Upstream bug: https://github.com/GPUOpen-LibrariesAndSDKs/HIPRT/issues/21
|
|
--- a/contrib/Orochi/scripts/kernelCompile.py
|
|
+++ b/contrib/Orochi/scripts/kernelCompile.py
|
|
@@ -17,7 +17,7 @@ def compile( index ):
|
|
if index == 0 :
|
|
command = [
|
|
"hipcc",
|
|
- "-x", "hip", "..\ParallelPrimitives\RadixSortKernels.h", "-O3", "-std=c++17", "-ffast-math", "--cuda-device-only", "--genco", "-I../", "-include", "hip/hip_runtime.h", "-parallel-jobs=15"]
|
|
+ "-x", "hip", "..\ParallelPrimitives\RadixSortKernels.h", "-O3", "-std=c++17", "-ffast-math", "--cuda-device-only", "--genco", "-I../", "-include", "hip/hip_runtime.h"]
|
|
#command.append( "--offload-arch=gfx1100" )
|
|
for i in enumArch( "gfx900" ):
|
|
command.append( "--offload-arch=" + i )
|
|
--- a/scripts/bitcodes/compile.py
|
|
+++ b/scripts/bitcodes/compile.py
|
|
@@ -117,15 +117,15 @@ def compileAmd():
|
|
parallel_jobs = 15
|
|
|
|
dst = 'hiprt' + hiprt_ver + '_' + hip_version + '_amd_lib' + postfix
|
|
- cmd = hipccpath + ' -x hip ../../hiprt/impl/hiprt_kernels_bitcode.h -O3 -std=c++17 ' + targets + ' -fgpu-rdc -c --gpu-bundle-output -c -emit-llvm -I../../contrib/Orochi/ -I../../ -DHIPRT_BITCODE_LINKING -ffast-math -parallel-jobs=' + str(parallel_jobs) + ' -o ' + dst
|
|
+ cmd = hipccpath + ' -x hip ../../hiprt/impl/hiprt_kernels_bitcode.h -O3 -std=c++17 ' + targets + ' -fgpu-rdc -c --gpu-bundle-output -c -emit-llvm -I../../contrib/Orochi/ -I../../ -DHIPRT_BITCODE_LINKING -ffast-math -o ' + dst
|
|
compileScript(cmd, dst)
|
|
|
|
dst = 'hiprt' + hiprt_ver + '_' + hip_version + '_amd.hipfb'
|
|
- cmd = hipccpath + ' -x hip ../../hiprt/impl/hiprt_kernels.h -O3 -std=c++17 ' + targets + ' -mllvm -amdgpu-early-inline-all=false -mllvm -amdgpu-function-calls=true --genco -I../../ -DHIPRT_BITCODE_LINKING -ffast-math -parallel-jobs=' + str(parallel_jobs) + ' -o ' + dst
|
|
+ cmd = hipccpath + ' -x hip ../../hiprt/impl/hiprt_kernels.h -O3 -std=c++17 ' + targets + ' -mllvm -amdgpu-early-inline-all=false -mllvm -amdgpu-function-calls=true --genco -I../../ -DHIPRT_BITCODE_LINKING -ffast-math -o ' + dst
|
|
compileScript(cmd, dst)
|
|
|
|
dst = 'oro_compiled_kernels.hipfb'
|
|
- cmd = hipccpath + ' -x hip ../../contrib/Orochi/ParallelPrimitives/RadixSortKernels.h -O3 -std=c++17 ' + targets + ' --genco -I../../contrib/Orochi/ -include hip/hip_runtime.h -DHIPRT_BITCODE_LINKING -ffast-math -parallel-jobs=' + str(parallel_jobs) + ' -o ' + dst
|
|
+ cmd = hipccpath + ' -x hip ../../contrib/Orochi/ParallelPrimitives/RadixSortKernels.h -O3 -std=c++17 ' + targets + ' --genco -I../../contrib/Orochi/ -include hip/hip_runtime.h -DHIPRT_BITCODE_LINKING -ffast-math -o ' + dst
|
|
compileScript(cmd, dst)
|
|
|
|
|
|
--- a/scripts/bitcodes/precompile_bitcode.py
|
|
+++ b/scripts/bitcodes/precompile_bitcode.py
|
|
@@ -127,12 +127,12 @@ def compileAmd():
|
|
|
|
# compile custom function table
|
|
hiprt_custom_func = 'hiprt' + hiprt_ver + '_' + hip_version + '_custom_func_table.bc'
|
|
- cmd = hipccpath + ' -O3 -std=c++17 ' + targets + ' -fgpu-rdc -c --gpu-bundle-output -c -emit-llvm -I../../ -ffast-math ../../test/bitcodes/custom_func_table.cpp -parallel-jobs=15 -o ' + hiprt_custom_func
|
|
+ cmd = hipccpath + ' -O3 -std=c++17 ' + targets + ' -fgpu-rdc -c --gpu-bundle-output -c -emit-llvm -I../../ -ffast-math ../../test/bitcodes/custom_func_table.cpp -o ' + hiprt_custom_func
|
|
compileScript('compiling ', cmd, hiprt_custom_func)
|
|
|
|
# compiling unit test
|
|
hiprt_unit_test = 'hiprt' + hiprt_ver + '_' + hip_version + '_unit_test'+ postfix
|
|
- cmd = hipccpath + ' -O3 -std=c++17 ' + targets + ' -fgpu-rdc -c --gpu-bundle-output -c -emit-llvm -I../../ -ffast-math -D BLOCK_SIZE=64 -D SHARED_STACK_SIZE=16 ../../test/bitcodes/unit_test.cpp -parallel-jobs=15 -o ' + hiprt_unit_test
|
|
+ cmd = hipccpath + ' -O3 -std=c++17 ' + targets + ' -fgpu-rdc -c --gpu-bundle-output -c -emit-llvm -I../../ -ffast-math -D BLOCK_SIZE=64 -D SHARED_STACK_SIZE=16 ../../test/bitcodes/unit_test.cpp -o ' + hiprt_unit_test
|
|
compileScript('compiling ', cmd, hiprt_unit_test)
|
|
|
|
# linking
|