Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

MI300 specific FP8 ASM fix #3547

Merged
merged 8 commits into from
Oct 23, 2024
Merged

MI300 specific FP8 ASM fix #3547

merged 8 commits into from
Oct 23, 2024

Conversation

CharlieL7
Copy link
Collaborator

@CharlieL7 CharlieL7 commented Oct 22, 2024

Disables the fp8 ASM on MI300 for non-FNUZ types. MI300 only has hardware support for FNUZ FP8 types. Fixes test_verify bugs seen on MI300.

@CharlieL7 CharlieL7 self-assigned this Oct 22, 2024
@CharlieL7 CharlieL7 added bugfix Fixes a bug found in the code. simple small or simple changes labels Oct 22, 2024
@migraphx-bot
Copy link
Collaborator

Test Batch Rate new
25840d
Rate old
b73def
Diff Compare
torchvision-resnet50 64 3,260.10 3,257.93 0.07%
torchvision-resnet50_fp16 64 6,991.63 6,992.99 -0.02%
torchvision-densenet121 32 2,437.02 2,432.26 0.20%
torchvision-densenet121_fp16 32 4,105.40 4,038.39 1.66%
torchvision-inceptionv3 32 1,639.82 1,638.89 0.06%
torchvision-inceptionv3_fp16 32 2,764.70 2,761.69 0.11%
cadene-inceptionv4 16 776.41 776.39 0.00%
cadene-resnext64x4 16 811.61 811.37 0.03%
slim-mobilenet 64 7,536.52 7,532.73 0.05%
slim-nasnetalarge 64 211.56 211.42 0.06%
slim-resnet50v2 64 3,503.55 3,507.25 -0.11%
bert-mrpc-onnx 8 1,144.94 1,147.76 -0.25%
bert-mrpc-tf 1 464.28 469.91 -1.20%
pytorch-examples-wlang-gru 1 422.70 514.96 -17.92% 🔴
pytorch-examples-wlang-lstm 1 382.88 386.61 -0.97%
torchvision-resnet50_1 1 779.78 772.05 1.00%
cadene-dpn92_1 1 398.26 398.73 -0.12%
cadene-resnext101_1 1 383.39 383.67 -0.07%
onnx-taau-downsample 1 343.43 342.33 0.32%
dlrm-criteoterabyte 1 33.33 33.33 0.01%
dlrm-criteoterabyte_fp16 1 52.73 52.70 0.04%
agentmodel 1 8,371.77 8,056.20 3.92% 🔆
unet_fp16 2 58.95 58.92 0.05%
resnet50v1_fp16 1 1,022.62 950.32 7.61% 🔆
resnet50v1_int8 1 1,008.30 1,000.02 0.83%
bert_base_cased_fp16 64 1,169.99 1,169.24 0.06%
bert_large_uncased_fp16 32 363.81 363.69 0.03%
bert_large_fp16 1 199.75 198.89 0.43%
distilgpt2_fp16 16 2,203.59 2,203.09 0.02%
yolov5s 1 534.76 540.85 -1.13%
tinyllama 1 43.53 43.43 0.22%
vicuna-fastchat 1 169.82 170.64 -0.48%
whisper-tiny-encoder 1 418.02 418.21 -0.05%
whisper-tiny-decoder 1 430.16 426.10 0.95%

This build is not recommended to merge 🔴

@migraphx-bot
Copy link
Collaborator


     ✅ bert-mrpc-onnx: PASSED: MIGraphX meets tolerance

     ✅ bert-mrpc-tf: PASSED: MIGraphX meets tolerance

     ✅ pytorch-examples-wlang-gru: PASSED: MIGraphX meets tolerance

     ✅ pytorch-examples-wlang-lstm: PASSED: MIGraphX meets tolerance

     ✅ torchvision-resnet50_1: PASSED: MIGraphX meets tolerance

     ✅ cadene-dpn92_1: PASSED: MIGraphX meets tolerance

     ✅ cadene-resnext101_1: PASSED: MIGraphX meets tolerance

     ✅ dlrm-criteoterabyte: PASSED: MIGraphX meets tolerance

     ✅ agentmodel: PASSED: MIGraphX meets tolerance

     ✅ unet: PASSED: MIGraphX meets tolerance

     ✅ resnet50v1: PASSED: MIGraphX meets tolerance

     ✅ bert_base_cased_fp16: PASSED: MIGraphX meets tolerance

🔴bert_large_uncased_fp16: FAILED: MIGraphX is not within tolerance - check verbose output


     ✅ bert_large: PASSED: MIGraphX meets tolerance

     ✅ yolov5s: PASSED: MIGraphX meets tolerance

     ✅ tinyllama: PASSED: MIGraphX meets tolerance

     ✅ vicuna-fastchat: PASSED: MIGraphX meets tolerance

     ✅ whisper-tiny-encoder: PASSED: MIGraphX meets tolerance

     ✅ whisper-tiny-decoder: PASSED: MIGraphX meets tolerance

     ✅ distilgpt2_fp16: PASSED: MIGraphX meets tolerance

Copy link

codecov bot commented Oct 23, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.16%. Comparing base (3c3d007) to head (25840d4).
Report is 1 commits behind head on develop.

Additional details and impacted files
@@           Coverage Diff            @@
##           develop    #3547   +/-   ##
========================================
  Coverage    92.16%   92.16%           
========================================
  Files          512      512           
  Lines        21401    21401           
========================================
  Hits         19724    19724           
  Misses        1677     1677           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@causten causten merged commit 6e2f0dd into develop Oct 23, 2024
43 of 44 checks passed
@causten causten deleted the mi300_fp8_intrinsics_fix branch October 23, 2024 02:01
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bugfix Fixes a bug found in the code. simple small or simple changes
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants