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

Enable fuse_pointwise and fuse_reduce in the driver #2588

Merged
merged 4 commits into from
Jan 3, 2024

Conversation

pfultz2
Copy link
Collaborator

@pfultz2 pfultz2 commented Jan 3, 2024

No description provided.

@codecov-commenter
Copy link

codecov-commenter commented Jan 3, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Comparison is base (afbf889) 91.38% compared to head (54b4810) 91.38%.

❗ Current head 54b4810 differs from pull request most recent head e400e68. Consider uploading reports for the commit e400e68 to get more accurate results

❗ Your organization needs to install the Codecov GitHub app to enable full functionality.

Additional details and impacted files
@@           Coverage Diff            @@
##           develop    #2588   +/-   ##
========================================
  Coverage    91.38%   91.38%           
========================================
  Files          456      456           
  Lines        17241    17241           
========================================
  Hits         15756    15756           
  Misses        1485     1485           

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

@migraphx-bot
Copy link
Collaborator

Test Batch Rate new
5097fd
Rate old
4ee186
Diff Compare
torchvision-resnet50 64 2,834.66 2,835.51 -0.03%
torchvision-resnet50_fp16 64 6,506.60 6,501.90 0.07%
torchvision-densenet121 32 2,090.27 2,086.72 0.17%
torchvision-densenet121_fp16 32 3,665.50 3,664.21 0.04%
torchvision-inceptionv3 32 1,597.88 1,594.28 0.23%
torchvision-inceptionv3_fp16 32 2,561.95 2,561.82 0.00%
cadene-inceptionv4 16 722.33 722.33 0.00%
cadene-resnext64x4 16 692.20 692.43 -0.03%
slim-mobilenet 64 8,330.59 8,330.42 0.00%
slim-nasnetalarge 64 230.68 230.69 -0.00%
slim-resnet50v2 64 2,664.45 2,664.21 0.01%
bert-mrpc-onnx 8 813.35 813.12 0.03%
bert-mrpc-tf 1 390.08 387.86 0.57%
pytorch-examples-wlang-gru 1 298.09 298.02 0.02%
pytorch-examples-wlang-lstm 1 317.22 318.30 -0.34%
torchvision-resnet50_1 1 606.91 608.12 -0.20%
torchvision-inceptionv3_1 1 341.33 345.85 -1.31%
cadene-dpn92_1 1 403.83 403.97 -0.03%
cadene-resnext101_1 1 327.50 328.82 -0.40%
slim-vgg16_1 1 459.45 461.65 -0.48%
slim-mobilenet_1 1 2,113.13 2,117.15 -0.19%
slim-inceptionv4_1 1 214.05 213.84 0.10%
onnx-taau-downsample 1 305.04 305.90 -0.28%
dlrm-criteoterabyte 1 21.58 21.62 -0.20%
dlrm-criteoterabyte_fp16 1 40.65 40.61 0.10%
agentmodel 1 6,032.82 5,914.08 2.01%
unet_fp16 2 54.78 54.78 -0.01%
resnet50v1_fp16 1 946.27 936.29 1.07%
bert_base_cased_fp16 64 924.68 924.67 0.00%
bert_large_uncased_fp16 32 290.66 290.71 -0.02%
bert_large_fp16 1 172.24 172.02 0.13%
distilgpt2_fp16 16 1,282.00 1,282.64 -0.05%

This build is OK for 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

     ✅ torchvision-inceptionv3_1: PASSED: MIGraphX meets tolerance

     ✅ cadene-dpn92_1: PASSED: MIGraphX meets tolerance

     ✅ cadene-resnext101_1: PASSED: MIGraphX meets tolerance

     ✅ slim-vgg16_1: PASSED: MIGraphX meets tolerance

     ✅ slim-mobilenet_1: PASSED: MIGraphX meets tolerance

     ✅ slim-inceptionv4_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: PASSED: MIGraphX meets tolerance

     ✅ bert_large: PASSED: MIGraphX meets tolerance

🔴distilgpt2_fp16: FAILED: MIGraphX is not within tolerance - check verbose output

@causten causten merged commit d6b4b8d into develop Jan 3, 2024
14 of 16 checks passed
@causten causten deleted the driver-fuse-passes branch January 3, 2024 19:37
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.

5 participants