improve noop elimination for slice and slice_scatter#151175
improve noop elimination for slice and slice_scatter#151175BoyuanFeng wants to merge 6 commits intomainfrom
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/151175
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 55762e0 with merge base 184ac8c ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
| statically_known_true(sym_eq(start, 0)) | ||
| and statically_known_true(end >= 2**63 - 1) | ||
| and ( | ||
| statically_known_true(end >= 2**63 - 1) |
There was a problem hiding this comment.
statically_known_true(end >= slice_dim_size) is unelated to statically_known_true(end >= 2**63 - 1) for dynamic shape cases. So we still keep statically_known_true(end >= 2**63 - 1). See test/inductor/test_gpu_cpp_wrapper.py::DynamicShapesGpuWrapperGpuTests.test_cat_slice_cat_cuda_dynamic_shapes_gpu_wrapper
|
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
Improves noop elimination for `slice` and `slice_scatter`. Pull Request resolved: pytorch#151175 Approved by: https://github.com/zou3519
Improves noop elimination for `slice` and `slice_scatter`. Pull Request resolved: pytorch#151175 Approved by: https://github.com/zou3519
Improves noop elimination for
sliceandslice_scatter.cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @ipiszy @chenyang78 @kadeng @muchulee8 @amjames @chauhang @aakhundov