Commit dbb2e382 authored by zhuwenwen's avatar zhuwenwen
Browse files

update cmake args

parent 35393439
...@@ -16,7 +16,7 @@ set(PYTHON_SUPPORTED_VERSIONS "3.8" "3.9" "3.10" "3.11") ...@@ -16,7 +16,7 @@ set(PYTHON_SUPPORTED_VERSIONS "3.8" "3.9" "3.10" "3.11")
set(CUDA_SUPPORTED_ARCHS "7.0;7.5;8.0;8.6;8.9;9.0") set(CUDA_SUPPORTED_ARCHS "7.0;7.5;8.0;8.6;8.9;9.0")
# Supported AMD GPU architectures. # Supported AMD GPU architectures.
set(HIP_SUPPORTED_ARCHS "gfx908;gfx90a;gfx942;gfx926;gfx928;gfx1100") set(HIP_SUPPORTED_ARCHS "gfx908;gfx90a;gfx942;gfx1100;gfx906;gfx926;gfx928")
# #
# Supported/expected torch versions for CUDA/ROCm. # Supported/expected torch versions for CUDA/ROCm.
......
...@@ -114,7 +114,8 @@ function (get_torch_gpu_compiler_flags OUT_GPU_FLAGS GPU_LANG) ...@@ -114,7 +114,8 @@ function (get_torch_gpu_compiler_flags OUT_GPU_FLAGS GPU_LANG)
"-DUSE_ROCM" "-DUSE_ROCM"
"-U__HIP_NO_HALF_CONVERSIONS__" "-U__HIP_NO_HALF_CONVERSIONS__"
"-U__HIP_NO_HALF_OPERATORS__" "-U__HIP_NO_HALF_OPERATORS__"
"-fno-gpu-rdc") "-fno-gpu-rdc"
"--gpu-max-threads-per-block=1024")
endif() endif()
set(${OUT_GPU_FLAGS} ${GPU_FLAGS} PARENT_SCOPE) set(${OUT_GPU_FLAGS} ${GPU_FLAGS} PARENT_SCOPE)
......
...@@ -118,9 +118,6 @@ class cmake_build_ext(build_ext): ...@@ -118,9 +118,6 @@ class cmake_build_ext(build_ext):
'-DCMAKE_ARCHIVE_OUTPUT_DIRECTORY={}'.format(self.build_temp), '-DCMAKE_ARCHIVE_OUTPUT_DIRECTORY={}'.format(self.build_temp),
] ]
if _is_hip:
cmake_args += ['--gpu-max-threads-per-block=1024']
verbose = bool(int(os.getenv('VERBOSE', '0'))) verbose = bool(int(os.getenv('VERBOSE', '0')))
if verbose: if verbose:
cmake_args += ['-DCMAKE_VERBOSE_MAKEFILE=ON'] cmake_args += ['-DCMAKE_VERBOSE_MAKEFILE=ON']
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment