Bf16 Verify Onnx Tests

[richagadgil]

Tests with different ONNX representations than half:

• mean_bf16_test
• instance_norm_bf16 tests

Tests for half that do not seem to have BF16 counterpart:

• mod_test_half

Tests Failing:

• gelu_default_bf16_test

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.19%. Comparing base (0ad8073) to head (141bd27).
Report is 2 commits behind head on develop.

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #3627      +/-   ##
===========================================
+ Coverage    92.17%   92.19%   +0.01%     
===========================================
  Files          513      513              
  Lines        21584    21598      +14     
===========================================
+ Hits         19895    19912      +17     
+ Misses        1689     1686       -3     

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

---

🚨 Try these New Features:

• Flaky Tests Detection - Detect and resolve failed and flaky tests

[migraphx-bot]

Test	Batch	Rate new 141bd2	Rate old 0ad807	Diff	Compare
torchvision-resnet50	64	3,258.95	3,239.44	0.60%	✅
torchvision-resnet50_fp16	64	6,989.04	6,989.98	-0.01%	✅
torchvision-densenet121	32	2,434.87	2,435.40	-0.02%	✅
torchvision-densenet121_fp16	32	4,091.51	4,083.28	0.20%	✅
torchvision-inceptionv3	32	1,628.91	1,630.36	-0.09%	✅
torchvision-inceptionv3_fp16	32	2,744.99	2,743.98	0.04%	✅
cadene-inceptionv4	16	765.34	765.72	-0.05%	✅
cadene-resnext64x4	16	810.19	811.01	-0.10%	✅
slim-mobilenet	64	7,475.22	7,471.20	0.05%	✅
slim-nasnetalarge	64	208.54	208.50	0.02%	✅
slim-resnet50v2	64	3,440.25	3,438.88	0.04%	✅
bert-mrpc-onnx	8	1,150.21	1,147.12	0.27%	✅
bert-mrpc-tf	1	466.60	469.98	-0.72%	✅
pytorch-examples-wlang-gru	1	427.95	416.34	2.79%	✅
pytorch-examples-wlang-lstm	1	391.90	463.26	-15.40%	🔴
torchvision-resnet50_1	1	779.45	770.23	1.20%	✅
cadene-dpn92_1	1	405.63	399.89	1.44%	✅
cadene-resnext101_1	1	381.92	382.62	-0.18%	✅
onnx-taau-downsample	1	346.14	345.09	0.30%	✅
dlrm-criteoterabyte	1	33.34	33.34	-0.01%	✅
dlrm-criteoterabyte_fp16	1	52.78	52.72	0.12%	✅
agentmodel	1	10,531.37	10,261.49	2.63%	✅
unet_fp16	2	58.94	58.87	0.12%	✅
resnet50v1_fp16	1	939.79	982.51	-4.35%	🔴
resnet50v1_int8	1	1,025.48	1,007.17	1.82%	✅
bert_base_cased_fp16	64	1,170.14	1,169.34	0.07%	✅
bert_large_uncased_fp16	32	363.21	363.46	-0.07%	✅
bert_large_fp16	1	198.06	198.15	-0.04%	✅
distilgpt2_fp16	16	2,203.57	2,201.47	0.10%	✅
yolov5s	1	529.90	536.48	-1.23%	✅
tinyllama	1	43.43	43.38	0.13%	✅
vicuna-fastchat	1	172.58	172.97	-0.23%	✅
whisper-tiny-encoder	1	417.78	418.04	-0.06%	✅
whisper-tiny-decoder	1	427.56	423.83	0.88%	✅

This build is not recommended to merge 🔴

[migraphx-bot]

     ✅ 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