|
|
|
|
project('cudamodule', 'cuda', version : '1.0.0')
|
|
|
|
|
|
|
|
|
|
nvcc = meson.get_compiler('cuda')
|
|
|
|
|
cuda = import('unstable-cuda')
|
|
|
|
|
|
|
|
|
|
arch_flags = cuda.nvcc_arch_flags(nvcc.version(), 'Auto', detected: ['6.0'])
|
|
|
|
|
arch_readable = cuda.nvcc_arch_readable(nvcc.version(), 'Auto', detected: ['6.0'])
|
|
|
|
|
driver_version = cuda.min_driver_version(nvcc.version())
|
|
|
|
|
|
|
|
|
|
message('NVCC version: ' + nvcc.version())
|
|
|
|
|
message('NVCC flags: ' + ' '.join(arch_flags))
|
|
|
|
|
message('NVCC readable: ' + ' '.join(arch_readable))
|
|
|
|
|
message('Driver version: >=' + driver_version)
|
|
|
|
|
|
|
|
|
|
exe = executable('prog', 'prog.cu', cuda_args: arch_flags)
|
|
|
|
|
test('cudatest', exe)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
#
|
|
|
|
|
# Assert Series
|
|
|
|
|
#
|
|
|
|
|
|
|
|
|
|
# Sanity test.
|
|
|
|
|
assert(' '.join(cuda.nvcc_arch_flags('11.1', '8.6')) ==
|
|
|
|
|
'-gencode arch=compute_86,code=sm_86')
|
|
|
|
|
|
|
|
|
|
# CUDA Toolkit too old, flag filtered out.
|
|
|
|
|
assert(' '.join(cuda.nvcc_arch_flags('11.0', '8.6')) ==
|
|
|
|
|
'')
|
|
|
|
|
|
|
|
|
|
# Named architectures.
|
|
|
|
|
assert(' '.join(cuda.nvcc_arch_flags('11.0', 'Ampere')) ==
|
|
|
|
|
'-gencode arch=compute_80,code=sm_80')
|
|
|
|
|
|
|
|
|
|
# Splitting & deduplication.
|
|
|
|
|
assert(' '.join(cuda.nvcc_arch_flags('11.0', 'Ampere;8.0,8.0')) ==
|
|
|
|
|
'-gencode arch=compute_80,code=sm_80')
|
|
|
|
|
|
|
|
|
|
# Same, but list supplied as list.
|
|
|
|
|
assert(' '.join(cuda.nvcc_arch_flags('11.0', ['Ampere', '8.0', '8.0'])) ==
|
|
|
|
|
'-gencode arch=compute_80,code=sm_80')
|
|
|
|
|
|
|
|
|
|
# Same, but mode set to Auto with detected set to a string with a variety of separators.
|
|
|
|
|
assert(' '.join(cuda.nvcc_arch_flags('11.0', 'Auto', detected: 'Ampere;8.0,8.0')) ==
|
|
|
|
|
'-gencode arch=compute_80,code=sm_80')
|
|
|
|
|
|
|
|
|
|
# Same, but detected set to a list.
|
|
|
|
|
assert(' '.join(cuda.nvcc_arch_flags('11.0', 'Auto', detected: ['Ampere', '8.0', '8.0'])) ==
|
|
|
|
|
'-gencode arch=compute_80,code=sm_80')
|
|
|
|
|
|
|
|
|
|
# Ask for 8.6 binary with 8.0-level PTX.
|
|
|
|
|
assert(' '.join(cuda.nvcc_arch_flags('11.1', '8.6(8.0)')) ==
|
|
|
|
|
'-gencode arch=compute_80,code=sm_86')
|
|
|
|
|
|
|
|
|
|
# Same, but keep the 8.0 PTX.
|
|
|
|
|
assert(' '.join(cuda.nvcc_arch_flags('11.1', '8.6(8.0)+PTX')) ==
|
|
|
|
|
'-gencode arch=compute_80,code=sm_86 -gencode arch=compute_80,code=compute_80')
|
|
|
|
|
|
|
|
|
|
# Detected Ampere RTX 3090 on CUDA 10.2, saturate to 7.5+PTX
|
|
|
|
|
assert(' '.join(cuda.nvcc_arch_flags('10.2', 'Auto', detected: ['8.0'])) ==
|
|
|
|
|
'-gencode arch=compute_75,code=sm_75 -gencode arch=compute_75,code=compute_75')
|
|
|
|
|
|
|
|
|
|
# Failed to auto-detect with CUDA 10.2, default to common GPUs (3.0;3.5;5.0;5.2;6.0;6.1;7.0;7.5+PTX)
|
|
|
|
|
assert(' '.join(cuda.nvcc_arch_flags('10.2', 'Auto', detected: [])) ==
|
|
|
|
|
'-gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=sm_35 '+
|
|
|
|
|
'-gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 '+
|
|
|
|
|
'-gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 '+
|
|
|
|
|
'-gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=sm_75 '+
|
|
|
|
|
'-gencode arch=compute_75,code=compute_75')
|
|
|
|
|
|
