QOL improvements to float8 gemm benchmark #596
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Summary: 1. add more options for shape generation, such as - square: M == K == N sweeping through powers of 2 - sweep: M, K, N each sweeping through powers of 2 - custom: user specifies a single value of M, K, N 2. fix a bug when calling `torch._scaled_mm`, we should create the scales outside the benchmark for a less biased result 3. add sweep over `fast_accum` setting 4. add ability to save result to file, for easy analysis later Test Plan: ``` time python benchmarks/float8/bench_matmul.py --out_filename ~/local/tmp/20240803_f8_gemm_sweep_2.csv --shape_gen_name sweep // result: https://gist.github.com/vkuzo/1d82e84ddd8aac8166695d819ebc8883 ``` Reviewers: Subscribers: Tasks: Tags:
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/596
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 5586749 with merge base ed83ae2 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
y-sq
approved these changes
Aug 5, 2024
drisspg
approved these changes
Aug 5, 2024
jainapurva
pushed a commit
that referenced
this pull request
Aug 7, 2024
Summary: 1. add more options for shape generation, such as - square: M == K == N sweeping through powers of 2 - sweep: M, K, N each sweeping through powers of 2 - custom: user specifies a single value of M, K, N 2. fix a bug when calling `torch._scaled_mm`, we should create the scales outside the benchmark for a less biased result 3. add sweep over `fast_accum` setting 4. add ability to save result to file, for easy analysis later Test Plan: ``` time python benchmarks/float8/bench_matmul.py --out_filename ~/local/tmp/20240803_f8_gemm_sweep_2.csv --shape_gen_name sweep // result: https://gist.github.com/vkuzo/1d82e84ddd8aac8166695d819ebc8883 ``` Reviewers: Subscribers: Tasks: Tags:
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary:
torch._scaled_mm, we should create the scales outside the benchmark for a less biased resultfast_accumsettingTest Plan:
Reviewers:
Subscribers:
Tasks:
Tags: