Add benchmark tracing

[pfultz2]

No description provided.

[codecov]

Codecov Report

Merging #2354 (7a76682) into develop (6ae4227) will not change coverage.
The diff coverage is n/a.

❗ Current head 7a76682 differs from pull request most recent head e462171. Consider uploading reports for the commit e462171 to get more accurate results

@@           Coverage Diff            @@
##           develop    #2354   +/-   ##
========================================
  Coverage    91.36%   91.36%           
========================================
  Files          440      440           
  Lines        16530    16530           
========================================
  Hits         15101    15101           
  Misses        1429     1429           

[umangyadav]

Perhaps keep this check earlier and only print solutions that has binary ?
Because I suspect with CK there would be a lot of solutions with no binary. it would just unnecessarily clobber terminal.

[migraphx-bot]

Test	Batch	Rate new e46217	Rate old f47e0b	Diff	Compare
torchvision-resnet50	64	2,855.33	2,853.14	0.08%	✅
torchvision-resnet50_fp16	64	6,488.25	6,482.66	0.09%	✅
torchvision-densenet121	32	2,097.55	2,106.95	-0.45%	✅
torchvision-densenet121_fp16	32	3,686.78	3,666.25	0.56%	✅
torchvision-inceptionv3	32	1,596.46	1,594.27	0.14%	✅
torchvision-inceptionv3_fp16	32	2,594.37	2,595.06	-0.03%	✅
cadene-inceptionv4	16	708.17	708.14	0.00%	✅
cadene-resnext64x4	16	698.07	698.14	-0.01%	✅
slim-mobilenet	64	8,351.35	8,357.67	-0.08%	✅
slim-nasnetalarge	64	227.12	226.77	0.15%	✅
slim-resnet50v2	64	2,678.83	2,681.09	-0.08%	✅
bert-mrpc-onnx	8	824.82	824.72	0.01%	✅
bert-mrpc-tf	1	389.33	387.78	0.40%	✅
pytorch-examples-wlang-gru	1	296.53	298.45	-0.64%	✅
pytorch-examples-wlang-lstm	1	308.61	307.98	0.20%	✅
torchvision-resnet50_1	1	605.76	602.40	0.56%	✅
torchvision-inceptionv3_1	1	340.62	340.55	0.02%	✅
cadene-dpn92_1	1	397.39	393.77	0.92%	✅
cadene-resnext101_1	1	329.93	329.42	0.16%	✅
slim-vgg16_1	1	463.41	464.76	-0.29%	✅
slim-mobilenet_1	1	2,024.79	2,045.48	-1.01%	✅
slim-inceptionv4_1	1	214.20	217.44	-1.49%	✅
onnx-taau-downsample	1	306.71	306.01	0.23%	✅
dlrm-criteoterabyte	1	21.69	21.73	-0.18%	✅
dlrm-criteoterabyte_fp16	1	40.75	40.71	0.10%	✅
agentmodel	1	5,818.49	5,735.52	1.45%	✅
unet_fp16	2	55.99	56.01	-0.03%	✅
resnet50v1_fp16	1	924.92	935.41	-1.12%	✅
bert_base_cased_fp16	64	971.11	971.36	-0.03%	✅
bert_large_uncased_fp16	32	305.21	305.22	-0.00%	✅
bert_large_fp16	1	167.34	167.02	0.19%	✅
distilgpt2_fp16	16	1,278.54	1,279.22	-0.05%	✅

This build is OK for merge ✅

[migraphx-bot]

    :white_check_mark:bert-mrpc-onnx: PASSED: MIGraphX meets tolerance

    :white_check_mark:bert-mrpc-tf: PASSED: MIGraphX meets tolerance

    :white_check_mark:pytorch-examples-wlang-gru: PASSED: MIGraphX meets tolerance

    :white_check_mark:pytorch-examples-wlang-lstm: PASSED: MIGraphX meets tolerance

    :white_check_mark:torchvision-resnet50_1: PASSED: MIGraphX meets tolerance

🔴torchvision-inceptionv3_1: FAILED: MIGraphX is not within tolerance - check verbose output

    :white_check_mark:cadene-dpn92_1: PASSED: MIGraphX meets tolerance

    :white_check_mark:cadene-resnext101_1: PASSED: MIGraphX meets tolerance

    :white_check_mark:slim-vgg16_1: PASSED: MIGraphX meets tolerance

    :white_check_mark:slim-mobilenet_1: PASSED: MIGraphX meets tolerance

🔴slim-inceptionv4_1: FAILED: MIGraphX is not within tolerance - check verbose output

    :white_check_mark:dlrm-criteoterabyte: PASSED: MIGraphX meets tolerance

    :white_check_mark:agentmodel: PASSED: MIGraphX meets tolerance

    :white_check_mark:unet: PASSED: MIGraphX meets tolerance

    :white_check_mark:resnet50v1: PASSED: MIGraphX meets tolerance

🔴bert_base_cased_fp16: FAILED: MIGraphX is not within tolerance - check verbose output

🔴bert_large_uncased_fp16: FAILED: MIGraphX is not within tolerance - check verbose output

    :white_check_mark:bert_large: PASSED: MIGraphX meets tolerance

🔴distilgpt2_fp16: FAILED: MIGraphX is not within tolerance - check verbose output

[pfultz2]

This adds tracing to the benchmarking.