benchmarks: add MFU% column to benchmark output#2377
Merged
tridao merged 1 commit intoDao-AILab:mainfrom Mar 22, 2026
Merged
Conversation
- Add MFU% column to benchmark output - Add dtype parameter to get_peak_flops to correctly scale peak FLOPS for FP8 (2x), FP32 (0.5x), and FP16/BF16 (1x, identical throughput) - Fix H200 (989 TFLOPS) and H20 (148 TFLOPS) values - Add H100 NVL (835 TFLOPS), L40S (362 TFLOPS), B300 (3.5 PFLOPS), GB200/GB300 (2.5 PFLOPS) entries - Add source URLs and sparsity notes from NVIDIA datasheets
Johnsonms
force-pushed
the
add-mfu-benchmark
branch
from
a7f1b9d to
6b41e16
Compare
tridao
approved these changes
Mar 22, 2026
zhuochenKIDD
pushed a commit
to zhuochenKIDD/flash-attention
that referenced
this pull request
Mar 25, 2026
- Add MFU% column to benchmark output - Add dtype parameter to get_peak_flops to correctly scale peak FLOPS for FP8 (2x), FP32 (0.5x), and FP16/BF16 (1x, identical throughput) - Fix H200 (989 TFLOPS) and H20 (148 TFLOPS) values - Add H100 NVL (835 TFLOPS), L40S (362 TFLOPS), B300 (3.5 PFLOPS), GB200/GB300 (2.5 PFLOPS) entries - Add source URLs and sparsity notes from NVIDIA datasheets
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds get_peak_flops() for known NVIDIA GPUs (B300, B200, H200, H100, A100, etc.) and shows ms/TFLOPS/MFU% per cell in the benchmark table.
H100 Before
H100 After:
B200 Before:
B200 After:
B300 Before:
B300 Afer:
