bf16 verify tests

[richagadgil]

No description provided.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.32%. Comparing base (5dc0199) to head (309f788).
Report is 3 commits behind head on develop.

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #3707      +/-   ##
===========================================
+ Coverage    92.29%   92.32%   +0.03%     
===========================================
  Files          519      519              
  Lines        22233    22233              
===========================================
+ Hits         20520    20527       +7     
+ Misses        1713     1706       -7     

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

[migraphx-bot]

Test	Batch	Rate new 309f78	Rate old 5dc019	Diff	Compare
torchvision-resnet50	64	3,232.57	3,229.26	0.10%	✅
torchvision-resnet50_fp16	64	6,866.53	6,862.73	0.06%	✅
torchvision-densenet121	32	2,429.38	2,429.91	-0.02%	✅
torchvision-densenet121_fp16	32	4,178.99	4,173.61	0.13%	✅
torchvision-inceptionv3	32	1,612.46	1,611.02	0.09%	✅
torchvision-inceptionv3_fp16	32	2,681.03	2,683.26	-0.08%	✅
cadene-inceptionv4	16	748.59	749.06	-0.06%	✅
cadene-resnext64x4	16	809.02	808.64	0.05%	✅
slim-mobilenet	64	6,661.87	6,657.58	0.06%	✅
slim-nasnetalarge	64	198.96	198.90	0.03%	✅
slim-resnet50v2	64	3,423.69	3,424.77	-0.03%	✅
bert-mrpc-onnx	8	1,138.71	1,138.15	0.05%	✅
bert-mrpc-tf	1	470.56	470.57	-0.00%	✅
pytorch-examples-wlang-gru	1	434.10	425.82	1.94%	✅
pytorch-examples-wlang-lstm	1	378.54	397.58	-4.79%	🔴
torchvision-resnet50_1	1	802.82	789.46	1.69%	✅
cadene-dpn92_1	1	417.64	415.00	0.64%	✅
cadene-resnext101_1	1	388.75	389.35	-0.15%	✅
onnx-taau-downsample	1	372.59	372.43	0.04%	✅
dlrm-criteoterabyte	1	30.56	30.53	0.08%	✅
dlrm-criteoterabyte_fp16	1	49.14	49.09	0.09%	✅
agentmodel	1	7,712.84	7,273.63	6.04%	🔆
unet_fp16	2	57.71	57.82	-0.19%	✅
resnet50v1_fp16	1	993.15	978.89	1.46%	✅
resnet50v1_int8	1	791.06	781.27	1.25%	✅
bert_base_cased_fp16	64	1,173.13	1,171.32	0.15%	✅
bert_large_uncased_fp16	32	362.31	362.15	0.04%	✅
bert_large_fp16	1	199.74	198.55	0.60%	✅
distilgpt2_fp16	16	2,211.02	2,214.29	-0.15%	✅
yolov5s	1	514.21	515.26	-0.20%	✅
tinyllama	1	43.46	43.42	0.08%	✅
vicuna-fastchat	1	43.74	43.81	-0.16%	✅
whisper-tiny-encoder	1	410.90	410.65	0.06%	✅
whisper-tiny-decoder	1	403.89	406.71	-0.69%	✅

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