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 test_mod<migraphx::shape::half_type> verify test #3125

Merged
merged 1 commit into from
May 28, 2024

Conversation

gyulaz-htec
Copy link
Collaborator

@gyulaz-htec gyulaz-htec commented May 28, 2024

This is a follow up on #3086 . That change fixed the test_mod<migraphx::shape::half_type> verify test as well. We can enable it now.
Fixes #2488

@gyulaz-htec gyulaz-htec requested a review from causten as a code owner May 28, 2024 08:44
@gyulaz-htec gyulaz-htec requested review from umangyadav and removed request for causten May 28, 2024 08:44
Copy link

codecov bot commented May 28, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 91.82%. Comparing base (2dcca47) to head (6795fe0).
Report is 156 commits behind head on develop.

Additional details and impacted files
@@           Coverage Diff            @@
##           develop    #3125   +/-   ##
========================================
  Coverage    91.82%   91.82%           
========================================
  Files          486      486           
  Lines        18990    18990           
========================================
  Hits         17437    17437           
  Misses        1553     1553           

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

@migraphx-bot
Copy link
Collaborator

Test Batch Rate new
6795fe
Rate old
2dcca4
Diff Compare
torchvision-resnet50 64 1,705.57 1,714.10 -0.50%
torchvision-resnet50_fp16 64 2,355.23 3,811.43 -38.21% 🔴
torchvision-densenet121 32 1,454.86 1,450.26 0.32%
torchvision-densenet121_fp16 32 2,281.82 2,432.41 -6.19% 🔴
torchvision-inceptionv3 32 625.38 883.39 -29.21% 🔴
torchvision-inceptionv3_fp16 32 464.40 1,379.96 -66.35% 🔴
cadene-inceptionv4 16 388.13 407.66 -4.79% 🔴
cadene-resnext64x4 16 413.69 413.82 -0.03%
slim-mobilenet 64 3,822.81 3,817.29 0.14%
slim-nasnetalarge 64 93.98 97.04 -3.15% 🔴
slim-resnet50v2 64 1,651.37 1,652.04 -0.04%
bert-mrpc-onnx 8 589.81 589.54 0.05%
bert-mrpc-tf 1 288.69 283.17 1.95%
pytorch-examples-wlang-gru 1 342.72 333.67 2.71%
pytorch-examples-wlang-lstm 1 266.27 267.97 -0.64%
torchvision-resnet50_1 1 453.68 437.86 3.61% 🔆
cadene-dpn92_1 1 244.01 231.38 5.46% 🔆
cadene-resnext101_1 1 66.22 189.21 -65.00% 🔴
onnx-taau-downsample 1 203.98 203.93 0.02%
dlrm-criteoterabyte 1 13.45 21.87 -38.50% 🔴
dlrm-criteoterabyte_fp16 1 40.66 40.70 -0.11%
agentmodel 1 6,018.08 6,106.42 -1.45%
unet_fp16 2 32.42 33.74 -3.90% 🔴
resnet50v1_fp16 1 550.55 558.27 -1.38%
resnet50v1_int8 1 462.91 462.93 -0.00%
bert_base_cased_fp16 64 603.44 620.74 -2.79%
bert_large_uncased_fp16 32 193.81 193.83 -0.01%
bert_large_fp16 1 103.87 103.94 -0.06%
distilgpt2_fp16 16 1,186.93 1,187.97 -0.09%
yolov5s 1 296.97 297.03 -0.02%
tinyllama 1 23.31 23.33 -0.07%
vicuna-fastchat 1 133.30 133.31 -0.01%
whisper-tiny-encoder 1 241.34 240.86 0.20%
whisper-tiny-decoder 1 245.99 245.88 0.04%

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 eb731ae into develop May 28, 2024
46 checks passed
@causten causten deleted the fmod_mod_test branch May 28, 2024 14:12
lajagapp pushed a commit to lajagapp/AMDMIGraphX that referenced this pull request Jul 8, 2024
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.

mod verify test for the half_type is failing to compile.
4 participants