Add a trim size flag

[pfultz2]

This allows us to easily extract subgraphs using the driver directly.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.33%. Comparing base (1169776) to head (91c14a3).
Report is 1 commits behind head on develop.

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #3746   +/-   ##
========================================
  Coverage    92.33%   92.33%           
========================================
  Files          519      519           
  Lines        22261    22261           
========================================
  Hits         20555    20555           
  Misses        1706     1706           

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

[migraphx-bot]

Test	Batch	Rate new 91c14a	Rate old 3aee3a	Diff	Compare
torchvision-resnet50	64	3,235.31	3,235.04	0.01%	✅
torchvision-resnet50_fp16	64	6,859.70	6,877.66	-0.26%	✅
torchvision-densenet121	32	2,432.20	2,436.52	-0.18%	✅
torchvision-densenet121_fp16	32	4,180.66	4,189.80	-0.22%	✅
torchvision-inceptionv3	32	1,613.33	1,613.28	0.00%	✅
torchvision-inceptionv3_fp16	32	2,670.74	2,677.62	-0.26%	✅
cadene-inceptionv4	16	750.28	750.18	0.01%	✅
cadene-resnext64x4	16	809.15	808.82	0.04%	✅
slim-mobilenet	64	6,661.78	6,663.29	-0.02%	✅
slim-nasnetalarge	64	199.07	198.98	0.05%	✅
slim-resnet50v2	64	3,424.77	3,424.55	0.01%	✅
bert-mrpc-onnx	8	1,138.44	1,141.83	-0.30%	✅
bert-mrpc-tf	1	477.46	473.12	0.92%	✅
pytorch-examples-wlang-gru	1	432.03	473.81	-8.82%	🔴
pytorch-examples-wlang-lstm	1	402.89	426.27	-5.49%	🔴
torchvision-resnet50_1	1	783.87	796.61	-1.60%	✅
cadene-dpn92_1	1	413.48	428.61	-3.53%	🔴
cadene-resnext101_1	1	389.85	389.68	0.04%	✅
onnx-taau-downsample	1	371.55	372.29	-0.20%	✅
dlrm-criteoterabyte	1	30.53	30.54	-0.04%	✅
dlrm-criteoterabyte_fp16	1	48.97	49.05	-0.18%	✅
agentmodel	1	7,772.97	8,978.43	-13.43%	🔴
unet_fp16	2	57.75	57.93	-0.32%	✅
resnet50v1_fp16	1	981.32	1,010.88	-2.93%	✅
resnet50v1_int8	1	787.40	802.03	-1.82%	✅
bert_base_cased_fp16	64	1,172.30	1,172.65	-0.03%	✅
bert_large_uncased_fp16	32	362.43	362.27	0.04%	✅
bert_large_fp16	1	197.78	198.55	-0.39%	✅
distilgpt2_fp16	16	2,216.47	2,215.63	0.04%	✅
yolov5s	1	519.33	530.86	-2.17%	✅
tinyllama	1	43.50	43.55	-0.11%	✅
vicuna-fastchat	1	43.83	43.92	-0.20%	✅
whisper-tiny-encoder	1	411.10	410.51	0.14%	✅
whisper-tiny-decoder	1	405.71	407.47	-0.43%	✅

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