Pass tests/gpu/jit.cpp with BF16

[richagadgil]

No description provided.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.15%. Comparing base (a678b48) to head (e0754d1).
Report is 1 commits behind head on develop.

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #3639   +/-   ##
========================================
  Coverage    92.15%   92.15%           
========================================
  Files          514      514           
  Lines        21956    21956           
========================================
  Hits         20234    20234           
  Misses        1722     1722           

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

[migraphx-bot]

Test	Batch	Rate new b81e18	Rate old a30b25	Diff	Compare
torchvision-resnet50	64	3,255.79	3,254.31	0.05%	✅
torchvision-resnet50_fp16	64	6,982.51	6,986.93	-0.06%	✅
torchvision-densenet121	32	2,433.92	2,432.26	0.07%	✅
torchvision-densenet121_fp16	32	4,098.73	4,102.15	-0.08%	✅
torchvision-inceptionv3	32	1,627.74	1,627.22	0.03%	✅
torchvision-inceptionv3_fp16	32	2,744.45	2,744.59	-0.01%	✅
cadene-inceptionv4	16	765.40	764.44	0.13%	✅
cadene-resnext64x4	16	814.42	812.75	0.21%	✅
slim-mobilenet	64	7,467.61	7,463.39	0.06%	✅
slim-nasnetalarge	64	209.01	208.94	0.03%	✅
slim-resnet50v2	64	3,440.88	3,440.19	0.02%	✅
bert-mrpc-onnx	8	1,146.74	1,143.08	0.32%	✅
bert-mrpc-tf	1	476.26	469.87	1.36%	✅
pytorch-examples-wlang-gru	1	423.36	513.89	-17.62%	🔴
pytorch-examples-wlang-lstm	1	395.51	386.92	2.22%	✅
torchvision-resnet50_1	1	805.09	776.87	3.63%	🔆
cadene-dpn92_1	1	433.57	395.29	9.68%	🔆
cadene-resnext101_1	1	382.51	373.27	2.48%	✅
onnx-taau-downsample	1	345.42	345.34	0.02%	✅
dlrm-criteoterabyte	1	33.35	33.31	0.14%	✅
dlrm-criteoterabyte_fp16	1	52.73	52.72	0.02%	✅
agentmodel	1	8,387.01	8,185.78	2.46%	✅
unet_fp16	2	58.78	58.75	0.06%	✅
resnet50v1_fp16	1	956.35	945.03	1.20%	✅
resnet50v1_int8	1	1,021.64	987.38	3.47%	🔆
bert_base_cased_fp16	64	1,170.44	1,169.56	0.08%	✅
bert_large_uncased_fp16	32	363.28	363.05	0.06%	✅
bert_large_fp16	1	198.41	198.54	-0.07%	✅
distilgpt2_fp16	16	2,200.65	2,199.18	0.07%	✅
yolov5s	1	529.43	534.87	-1.02%	✅
tinyllama	1	43.40	43.39	0.00%	✅
vicuna-fastchat	1	174.59	175.67	-0.61%	✅
whisper-tiny-encoder	1	417.36	417.72	-0.09%	✅
whisper-tiny-decoder	1	425.40	428.36	-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

[causten]

Hold before merging until CI moves to 6.3