diff options
| author | Olexa Bilaniuk <obilaniu@gmail.com> | 2020-10-24 10:07:54 -0400 |
|---|---|---|
| committer | Olexa Bilaniuk <obilaniu@gmail.com> | 2020-11-05 14:50:22 -0500 |
| commit | 3f6977c866efa93e777123031bbfadb232b65b41 (patch) | |
| tree | 3baa238eee1976e9a48b51596867f2353037bcab /test cases | |
| parent | cfd31e38a8606a16f2965bfb61442e77793fae56 (diff) | |
| download | meson-3f6977c866efa93e777123031bbfadb232b65b41.zip meson-3f6977c866efa93e777123031bbfadb232b65b41.tar.gz meson-3f6977c866efa93e777123031bbfadb232b65b41.tar.bz2 | |
Update CUDA module's nvcc_arch_flags() and nvcc_arch_readable() for new
CUDA Toolkits.
Also harden internal logic and add several asserts in the testcase.
Diffstat (limited to 'test cases')
| -rw-r--r-- | test cases/cuda/3 cudamodule/meson.build | 54 |
1 files changed, 54 insertions, 0 deletions
diff --git a/test cases/cuda/3 cudamodule/meson.build b/test cases/cuda/3 cudamodule/meson.build index 8410535..fd5e83f 100644 --- a/test cases/cuda/3 cudamodule/meson.build +++ b/test cases/cuda/3 cudamodule/meson.build @@ -14,3 +14,57 @@ 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') + |