`torch.cuda.synchronize()` is a heavy hammer and distorts benchmarking results a lot. Timer provides results that are closer to kernel times observed in profiler.
If you want, instead of `blocked_autorange` you can use `timeit` that repeats the stmt fixed number of times.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/75393
Approved by: https://github.com/davidberard98
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/75108
- Add option to only run some graphs
- Add NNC Static vs Dynamic
- Update make_tensor bc it wasnt using strides
Test Plan: Imported from OSS
Reviewed By: ejguan
Differential Revision: D35374000
Pulled By: eellison
fbshipit-source-id: df16b8647f2309a8837207cacba55d30f46845ce
(cherry picked from commit 19feb54db049186972b47548cf3d83e76512adfd)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/74076
Extends the repro script to cpu and NNC. As in file:
Usage:
```
1. Run your script and pipe into a log file
PYTORCH_JIT_LOG_LEVEL=">>tensorexpr_fuser" python3 my_test.py &> log.txt
2. Run log_extract:
log_extract.py log.txt --baseline --nnc
```
Test Plan: Imported from OSS
Reviewed By: gchanan
Differential Revision: D34946883
Pulled By: eellison
fbshipit-source-id: 644012dbbca0b490820ef83e761c06b0dd009e52
(cherry picked from commit 5256c8f3ff8545033d1335cc96d34194abda1370)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/73881
NVFuser fusion groups can contain nvfuser-only ops, e.g. `prim::reshape_copy`. Previously, we couldn't get a baseline performance measurement because the nvfuser-only ops would error out on nnc- and no-fusion- runs. Instead, dump the fallback graphs, after the fallbacks are corrected into runnable fallbacks.
Test Plan: Imported from OSS
Reviewed By: eellison
Differential Revision: D34698307
Pulled By: davidberard98
fbshipit-source-id: c357b2736b789bfd347afe9c83a1b610b64881e0
(cherry picked from commit 5918d826502ff75fbc22d242844ae6435dd7d22a)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/72889
The script along with the GRAPH_EXPORT macro will allow for an easy way to extract IR from logs. One use case in this diff is to extract the fusion groups from nvfuser, so that the fusions can be tested individually.
Usage (e.g. for nvfuser test)
1. Write some test.py file that uses nvfuser
2. `PYTORCH_JIT_LOG_LEVEL=">>graph_fuser" python3 test.py 2>&1 | tee output.txt`
3. `python3 pytorch/scripts/jit/log_extract.py output.txt --nvfuser`
This will run with and without nvfuser to compare the output.
Alternatively, use `--output` to dump the IR so that it can be used in other applications.
Currently, only `--output` works (since generating input tensors is not supported)
Test Plan: Imported from OSS
Reviewed By: ngimel
Differential Revision: D34440189
Pulled By: davidberard98
fbshipit-source-id: fca0f619200ee37aba34bb39b69e6c640c263e26
(cherry picked from commit eb319166075db160f1628f0de545641fbecde8be)
