Link xnn_executor_runner with optimized op library#8901
Conversation
|
Stack from ghstack (oldest at bottom): |
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/8901
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 2 PendingAs of commit 18c64ad with merge base 09ad20a ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
Thanks @swolchok! Ideally in OSS world we also have a executor_runner with optimized kernels, and use it as a test runner for all models. Maybe we can promote xnn_executor_runner to be this general runner. BTW this PR has diff from other commits? |
|
I'm having trouble exporting my stack; getting GitHub rate limits. Hopefully folks will review the bottom PR or two soon. |
fixed, please review |
7cbe7a1 to
7bc4529
Compare
7bc4529 to
764977b
Compare
|
|
||
| target_link_libraries( | ||
| xnn_executor_runner gflags portable_ops_lib ${xnn_executor_runner_libs} | ||
| xnn_executor_runner gflags optimized_native_cpu_ops_lib ${xnn_executor_runner_libs} |
There was a problem hiding this comment.
Thank you! So many perf cliffs because of this.
| target_compile_options(xnnpack_backend PUBLIC ${_common_compile_options}) | ||
| target_link_options_shared_lib(xnnpack_backend) | ||
|
|
||
| if(EXECUTORCH_BUILD_KERNELS_OPTIMIZED) |
There was a problem hiding this comment.
fixed build when XNNPACK is on but optimized lib is off. everything else (except corresponding change to line 149 below) is just cmake-format.
Doesn't seem to be any reason not to allow optimized ops for this one.
Doesn't seem to be any reason not to allow optimized ops for this one. ghstack-source-id: a8d06d4 ghstack-comment-id: 2695738759 Pull Request resolved: pytorch/executorch#8901
Doesn't seem to be any reason not to allow optimized ops for this one.