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

Insert contiguous on mlir inputs that are not packed or broadcasted #3039

Merged
merged 4 commits into from
May 7, 2024

Conversation

pfultz2
Copy link
Collaborator

@pfultz2 pfultz2 commented May 4, 2024

No description provided.

@pfultz2 pfultz2 requested a review from causten as a code owner May 4, 2024 00:23
@pfultz2 pfultz2 linked an issue May 4, 2024 that may be closed by this pull request
Copy link

codecov bot commented May 4, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 91.76%. Comparing base (2bdd02d) to head (58000cf).
Report is 1 commits behind head on develop.

Additional details and impacted files
@@             Coverage Diff             @@
##           develop    #3039      +/-   ##
===========================================
- Coverage    91.76%   91.76%   -0.01%     
===========================================
  Files          485      485              
  Lines        18774    18775       +1     
===========================================
  Hits         17228    17228              
- Misses        1546     1547       +1     

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

@migraphx-bot
Copy link
Collaborator

Test Batch Rate new
58000c
Rate old
e32966
Diff Compare
torchvision-resnet50 64 2,788.14 2,815.58 -0.97%
torchvision-resnet50_fp16 64 6,196.57 6,398.98 -3.16% 🔴
torchvision-densenet121 32 2,085.63 2,103.88 -0.87%
torchvision-densenet121_fp16 32 3,612.96 3,692.26 -2.15%
torchvision-inceptionv3 32 1,597.76 1,603.69 -0.37%
torchvision-inceptionv3_fp16 32 2,558.12 2,548.50 0.38%
cadene-inceptionv4 16 715.73 716.87 -0.16%
cadene-resnext64x4 16 677.87 680.42 -0.37%
slim-mobilenet 64 5,811.74 5,946.96 -2.27%
slim-nasnetalarge 64 154.33 154.01 0.21%
slim-resnet50v2 64 2,576.81 2,587.09 -0.40%
bert-mrpc-onnx 8 968.78 920.88 5.20% 🔆
bert-mrpc-tf 1 399.61 397.60 0.51%
pytorch-examples-wlang-gru 1 397.01 395.98 0.26%
pytorch-examples-wlang-lstm 1 367.14 370.77 -0.98%
torchvision-resnet50_1 1 601.45 609.31 -1.29%
cadene-dpn92_1 1 384.33 392.49 -2.08%
cadene-resnext101_1 1 323.22 331.97 -2.64%
onnx-taau-downsample 1 307.05 306.30 0.25%
dlrm-criteoterabyte 1 28.48 28.86 -1.32%
dlrm-criteoterabyte_fp16 1 47.19 48.00 -1.69%
agentmodel 1 7,315.98 7,356.89 -0.56%
unet_fp16 2 57.48 57.55 -0.12%
resnet50v1_fp16 1 898.32 896.07 0.25%
resnet50v1_int8 1 786.86 793.93 -0.89%
bert_base_cased_fp16 64 1,022.10 1,033.68 -1.12%
bert_large_uncased_fp16 32 298.90 300.33 -0.48%
bert_large_fp16 1 156.28 160.05 -2.36%
distilgpt2_fp16 16 1,832.79 1,856.85 -1.30%
yolov5s 1 468.05 472.11 -0.86%
tinyllama 1 32.99 32.95 0.14%
vicuna-fastchat 1 159.68 158.60 0.68%
whisper-tiny-encoder 1 352.82 353.26 -0.12%
whisper-tiny-decoder 1 401.44 396.71 1.19%

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

@causten causten merged commit 156122b into develop May 7, 2024
48 of 50 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

gpu::mlir_op: Shapes are not packed nor broadcasted
5 participants