diff options
| author | Sayed Adel <seiko@imavr.com> | 2020-07-08 09:27:13 +0200 |
|---|---|---|
| committer | Sayed Adel <seiko@imavr.com> | 2020-10-27 11:46:58 +0000 |
| commit | cb3efe8e03b53dbab457a99be1a48384312abe16 (patch) | |
| tree | 519f83bd1bda84f52fba88516561dd79e0f36826 /numpy/distutils/command/build.py | |
| parent | fcba5a6c901717110b9767b418df410d7c8c6e73 (diff) | |
| download | numpy-cb3efe8e03b53dbab457a99be1a48384312abe16.tar.gz | |
ENH: Expose the NumPy C SIMD vectorization interface "NPYV" to Python
'_simd' is a new module to bring the NumPy C SIMD vectorization interface "NPYV"
The module is designed to be extremely flexible so that it can accommodate any kind
intrinsics, also to generate a python interface almost similar to the C interface.
The main purpose of this module is to test NPYV intrinsics in python,
but still can be used as an effective solution in designing SIMD kernels.
Also add a new command-line argument `--simd-test` to control of targeted CPU features
for the `_simd` module.
Co-authored-by: Matti Picus <matti.picus@gmail.com>
Co-authored-by: Eric Wieser <wieser.eric@gmail.com>
Diffstat (limited to 'numpy/distutils/command/build.py')
| -rw-r--r-- | numpy/distutils/command/build.py | 12 |
1 files changed, 12 insertions, 0 deletions
diff --git a/numpy/distutils/command/build.py b/numpy/distutils/command/build.py index 60ba4c917..6025586cd 100644 --- a/numpy/distutils/command/build.py +++ b/numpy/distutils/command/build.py @@ -22,6 +22,8 @@ class build(old_build): "specify a list of dispatched CPU optimizations"), ('disable-optimization', None, "disable CPU optimized code(dispatch,simd,fast...)"), + ('simd-test=', None, + "specify a list of CPU optimizations to be tested against NumPy SIMD interface"), ] help_options = old_build.help_options + [ @@ -36,6 +38,16 @@ class build(old_build): self.cpu_baseline = "min" self.cpu_dispatch = "max -xop -fma4" # drop AMD legacy features by default self.disable_optimization = False + """ + the '_simd' module is a very large. Adding more dispatched features + will increase binary size and compile time. By default we minimize + the targeted features to those most commonly used by the NumPy SIMD interface(NPYV), + NOTE: any specified features will be ignored if they're: + - part of the baseline(--cpu-baseline) + - not part of dispatch-able features(--cpu-dispatch) + - not supported by compiler or platform + """ + self.simd_test = "BASELINE SSE2 SSE41 SSE42 XOP (FMA3 AVX2) AVX512F AVX512_SKX VSX VSX2 VSX3 NEON ASIMD" def finalize_options(self): build_scripts = self.build_scripts |