ROCmSoftwarePlatform
Add ONNX parsing for SkipSimplifiedLayerNormalization
Codecov Report
Attention: Patch coverage is 93.93939% with 2 lines in your changes missing coverage. Please review.
Project coverage is 92.25%. Comparing base (
03c43e5) to head (a3dae61). Report is 154 commits behind head on develop.
| Files with missing lines | Patch % | Lines |
|---|---|---|
| ...onnx/parse_skip_simplified_layer_normalization.cpp | 93.93% | 2 Missing :warning: |
Additional details and impacted files
@@ Coverage Diff @@
## develop #3140 +/- ##
========================================
Coverage 92.25% 92.25%
========================================
Files 500 501 +1
Lines 20054 20087 +33
========================================
+ Hits 18500 18531 +31
- Misses 1554 1556 +2
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.
🚨 Try these New Features:
- Flaky Tests Detection - Detect and resolve failed and flaky tests
![codecov[bot] avatar](https://avatars.githubusercontent.com/in/254?v=4 "Published by a pub.dev verified publisher"){kind=small}
| Test | Batch | Rate new a3dae6 |
Rate old 273d81 |
Diff | Compare |
|---|---|---|---|---|---|
| torchvision-resnet50 | 64 | 3,246.16 | 3,251.64 | -0.17% | :white_check_mark: |
| torchvision-resnet50_fp16 | 64 | 6,984.28 | 6,991.78 | -0.11% | :white_check_mark: |
| torchvision-densenet121 | 32 | 2,434.09 | 2,434.61 | -0.02% | :white_check_mark: |
| torchvision-densenet121_fp16 | 32 | 4,074.48 | 4,073.09 | 0.03% | :white_check_mark: |
| torchvision-inceptionv3 | 32 | 1,632.80 | 1,636.36 | -0.22% | :white_check_mark: |
| torchvision-inceptionv3_fp16 | 32 | 2,736.68 | 2,738.76 | -0.08% | :white_check_mark: |
| cadene-inceptionv4 | 16 | 774.68 | 776.27 | -0.20% | :white_check_mark: |
| cadene-resnext64x4 | 16 | 808.47 | 809.36 | -0.11% | :white_check_mark: |
| slim-mobilenet | 64 | 7,437.76 | 7,455.99 | -0.24% | :white_check_mark: |
| slim-nasnetalarge | 64 | 207.99 | 208.09 | -0.05% | :white_check_mark: |
| slim-resnet50v2 | 64 | 3,333.96 | 3,343.59 | -0.29% | :white_check_mark: |
| bert-mrpc-onnx | 8 | 1,152.90 | 1,147.91 | 0.44% | :white_check_mark: |
| bert-mrpc-tf | 1 | 310.08 | 305.42 | 1.53% | :white_check_mark: |
| pytorch-examples-wlang-gru | 1 | 410.50 | 430.33 | -4.61% | :red_circle: |
| pytorch-examples-wlang-lstm | 1 | 441.06 | 440.22 | 0.19% | :white_check_mark: |
| torchvision-resnet50_1 | 1 | 804.23 | 765.01 | 5.13% | :high_brightness: |
| cadene-dpn92_1 | 1 | 426.81 | 434.49 | -1.77% | :white_check_mark: |
| cadene-resnext101_1 | 1 | 378.78 | 372.41 | 1.71% | :white_check_mark: |
| onnx-taau-downsample | 1 | 342.68 | 343.93 | -0.36% | :white_check_mark: |
| dlrm-criteoterabyte | 1 | 35.01 | 35.07 | -0.15% | :white_check_mark: |
| dlrm-criteoterabyte_fp16 | 1 | 58.11 | 58.07 | 0.08% | :white_check_mark: |
| agentmodel | 1 | 7,799.89 | 8,142.66 | -4.21% | :red_circle: |
| unet_fp16 | 2 | 57.78 | 57.95 | -0.29% | :white_check_mark: |
| resnet50v1_fp16 | 1 | 1,003.70 | 913.83 | 9.83% | :high_brightness: |
| resnet50v1_int8 | 1 | 976.57 | 961.09 | 1.61% | :white_check_mark: |
| bert_base_cased_fp16 | 64 | 1,147.32 | 1,148.86 | -0.13% | :white_check_mark: |
| bert_large_uncased_fp16 | 32 | 354.43 | 355.19 | -0.21% | :white_check_mark: |
| bert_large_fp16 | 1 | 209.92 | 211.63 | -0.81% | :white_check_mark: |
| distilgpt2_fp16 | 16 | 2,155.79 | 2,153.35 | 0.11% | :white_check_mark: |
| yolov5s | 1 | 534.49 | 502.62 | 6.34% | :high_brightness: |
| tinyllama | 1 | 43.39 | 43.39 | 0.00% | :white_check_mark: |
| vicuna-fastchat | 1 | 170.91 | 174.27 | -1.93% | :white_check_mark: |
| whisper-tiny-encoder | 1 | 408.45 | 408.53 | -0.02% | :white_check_mark: |
| whisper-tiny-decoder | 1 | 430.59 | 431.61 | -0.24% | :white_check_mark: |
This build is not recommended to merge :red_circle:
:red_circle:bert_large_uncased_fp16: FAILED: MIGraphX is not within tolerance - check verbose output