Add flag to dump mlir modules to mxrs
Codecov Report
Attention: Patch coverage is 0% with 13 lines in your changes missing coverage. Please review.
Project coverage is 92.16%. Comparing base (
275f854) to head (fff0dc9). Report is 142 commits behind head on develop.
| Files with missing lines | Patch % | Lines |
|---|---|---|
| src/shape.cpp | 0.00% | 9 Missing :warning: |
| src/program.cpp | 0.00% | 4 Missing :warning: |
Additional details and impacted files
@@ Coverage Diff @@
## develop #3182 +/- ##
===========================================
- Coverage 92.17% 92.16% -0.02%
===========================================
Files 512 512
Lines 21391 21394 +3
===========================================
Hits 19718 19718
- Misses 1673 1676 +3
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.
| Test | Batch | Rate new fff0dc |
Rate old ddc4c0 |
Diff | Compare |
|---|---|---|---|---|---|
| torchvision-resnet50 | 64 | 3,261.58 | 3,261.96 | -0.01% | :white_check_mark: |
| torchvision-resnet50_fp16 | 64 | 6,999.88 | 6,986.50 | 0.19% | :white_check_mark: |
| torchvision-densenet121 | 32 | 2,435.79 | 2,435.05 | 0.03% | :white_check_mark: |
| torchvision-densenet121_fp16 | 32 | 4,088.41 | 4,098.64 | -0.25% | :white_check_mark: |
| torchvision-inceptionv3 | 32 | 1,637.98 | 1,637.72 | 0.02% | :white_check_mark: |
| torchvision-inceptionv3_fp16 | 32 | 2,763.46 | 2,760.21 | 0.12% | :white_check_mark: |
| cadene-inceptionv4 | 16 | 776.37 | 776.83 | -0.06% | :white_check_mark: |
| cadene-resnext64x4 | 16 | 807.12 | 812.01 | -0.60% | :white_check_mark: |
| slim-mobilenet | 64 | 7,535.95 | 7,539.31 | -0.04% | :white_check_mark: |
| slim-nasnetalarge | 64 | 211.52 | 211.58 | -0.03% | :white_check_mark: |
| slim-resnet50v2 | 64 | 3,505.14 | 3,507.45 | -0.07% | :white_check_mark: |
| bert-mrpc-onnx | 8 | 1,146.38 | 1,148.38 | -0.17% | :white_check_mark: |
| bert-mrpc-tf | 1 | 469.29 | 462.39 | 1.49% | :white_check_mark: |
| pytorch-examples-wlang-gru | 1 | 426.36 | 416.01 | 2.49% | :white_check_mark: |
| pytorch-examples-wlang-lstm | 1 | 383.45 | 387.25 | -0.98% | :white_check_mark: |
| torchvision-resnet50_1 | 1 | 788.74 | 799.30 | -1.32% | :white_check_mark: |
| cadene-dpn92_1 | 1 | 424.20 | 413.07 | 2.69% | :white_check_mark: |
| cadene-resnext101_1 | 1 | 383.67 | 384.54 | -0.23% | :white_check_mark: |
| onnx-taau-downsample | 1 | 342.74 | 343.19 | -0.13% | :white_check_mark: |
| dlrm-criteoterabyte | 1 | 33.37 | 33.33 | 0.12% | :white_check_mark: |
| dlrm-criteoterabyte_fp16 | 1 | 52.70 | 52.75 | -0.10% | :white_check_mark: |
| agentmodel | 1 | 8,153.22 | 8,254.64 | -1.23% | :white_check_mark: |
| unet_fp16 | 2 | 58.97 | 58.74 | 0.39% | :white_check_mark: |
| resnet50v1_fp16 | 1 | 964.71 | 942.04 | 2.41% | :white_check_mark: |
| resnet50v1_int8 | 1 | 989.95 | 993.52 | -0.36% | :white_check_mark: |
| bert_base_cased_fp16 | 64 | 1,170.46 | 1,171.05 | -0.05% | :white_check_mark: |
| bert_large_uncased_fp16 | 32 | 363.49 | 363.48 | 0.00% | :white_check_mark: |
| bert_large_fp16 | 1 | 198.82 | 200.70 | -0.94% | :white_check_mark: |
| distilgpt2_fp16 | 16 | 2,203.34 | 2,201.26 | 0.09% | :white_check_mark: |
| yolov5s | 1 | 538.02 | 537.45 | 0.11% | :white_check_mark: |
| tinyllama | 1 | 43.56 | 43.68 | -0.28% | :white_check_mark: |
| vicuna-fastchat | 1 | 176.45 | 175.99 | 0.27% | :white_check_mark: |
| whisper-tiny-encoder | 1 | 418.43 | 418.69 | -0.06% | :white_check_mark: |
| whisper-tiny-decoder | 1 | 427.33 | 428.55 | -0.28% | :white_check_mark: |
This build is OK for merge :white_check_mark:
:red_circle:bert_large_uncased_fp16: FAILED: MIGraphX is not within tolerance - check verbose output