pytorch/benchmarks/static_runtime
Mike Iovine 7b0650d5cf Back out "[static-runtime] change the backend for permute_copy" (#89463)
Summary: This permute copy change seems to be causing huge regressions on machines without AVX512. Revert to mitigate. This shouldn't be problematic since the improvement from changing it was super small anyways.

Differential Revision: D41450088

Pull Request resolved: https://github.com/pytorch/pytorch/pull/89463
Approved by: https://github.com/hlu1
2022-11-22 06:26:10 +00:00
..
CMakeLists.txt [Static Runtime] Add auto-generated out variant dispatchers (#72603) 2022-02-28 08:39:10 +00:00
deep_wide_pt_bench.cc Replace all CHECK_ and DCHECK_ with TORCH_* macros (#82032) 2022-07-26 01:20:44 +00:00
deep_wide_pt.cc [NOOP][clangformat][codemod] Enable CLANGFORMAT for some folders in caffe2/* (#67746) 2021-11-03 12:23:14 -07:00
deep_wide_pt.h [SR] Fix broken unit test build (#76111) 2022-04-20 18:36:31 +00:00
test_cpu_fusion.cc [Static Runtime] Add test that runs NNC fused kernels in parallel (#73256) 2022-02-28 17:44:45 +00:00
test_generated_ops.cc Revive static_runtime_benchmark build and test (#87660) 2022-11-08 08:32:45 +00:00
test_static_module.cc Revive static_runtime_benchmark build and test (#87660) 2022-11-08 08:32:45 +00:00
test_static_runtime.cc Back out "[static-runtime] change the backend for permute_copy" (#89463) 2022-11-22 06:26:10 +00:00
test_utils.cc Revive static_runtime_benchmark build and test (#87660) 2022-11-08 08:32:45 +00:00
test_utils.h [SR] Fix StaticRuntime move ctor (#74927) 2022-04-07 02:16:37 +00:00