Move unary operators around shape transformation

[pfultz2]

This also removes the old unary rewriting in simplify_reshapes. They are not really useful.

[codecov]

Codecov Report

Attention: Patch coverage is 98.07692% with 1 lines in your changes are missing coverage. Please review.

Project coverage is 91.87%. Comparing base (8e4b561) to head (584f637).

❗ Current head 584f637 differs from pull request most recent head 5d181c9. Consider uploading reports for the commit 5d181c9 to get more accurate results

Files	Patch %	Lines
src/simplify_reshapes.cpp	98.07%	1 Missing ⚠️

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #2958   +/-   ##
========================================
  Coverage    91.86%   91.87%           
========================================
  Files          484      484           
  Lines        18609    18642   +33     
========================================
+ Hits         17095    17127   +32     
- Misses        1514     1515    +1     

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

[migraphx-bot]

Test	Batch	Rate new 5d181c	Rate old 6e496c	Diff	Compare
torchvision-resnet50	64	2,822.03	2,822.08	-0.00%	✅
torchvision-resnet50_fp16	64	6,575.54	6,576.28	-0.01%	✅
torchvision-densenet121	32	2,093.49	2,082.78	0.51%	✅
torchvision-densenet121_fp16	32	3,688.22	3,682.90	0.14%	✅
torchvision-inceptionv3	32	1,606.23	1,605.12	0.07%	✅
torchvision-inceptionv3_fp16	32	2,554.05	2,556.36	-0.09%	✅
cadene-inceptionv4	16	717.21	717.74	-0.07%	✅
cadene-resnext64x4	16	680.35	680.43	-0.01%	✅
slim-mobilenet	64	5,896.66	5,896.72	-0.00%	✅
slim-nasnetalarge	64	154.07	153.86	0.14%	✅
slim-resnet50v2	64	2,589.20	2,590.74	-0.06%	✅
bert-mrpc-onnx	8	919.78	920.30	-0.06%	✅
bert-mrpc-tf	1	399.99	399.87	0.03%	✅
pytorch-examples-wlang-gru	1	421.01	473.55	-11.10%	🔴
pytorch-examples-wlang-lstm	1	388.65	384.16	1.17%	✅
torchvision-resnet50_1	1	609.67	608.37	0.21%	✅
cadene-dpn92_1	1	393.27	394.09	-0.21%	✅
cadene-resnext101_1	1	332.05	331.53	0.16%	✅
onnx-taau-downsample	1	305.53	306.82	-0.42%	✅
dlrm-criteoterabyte	1	28.78	28.78	0.01%	✅
dlrm-criteoterabyte_fp16	1	48.17	48.33	-0.34%	✅
agentmodel	1	7,604.04	7,705.76	-1.32%	✅
unet_fp16	2	57.73	57.66	0.12%	✅
resnet50v1_fp16	1	882.27	894.16	-1.33%	✅
resnet50v1_int8	1	807.51	821.48	-1.70%	✅
bert_base_cased_fp16	64	1,052.71	1,053.05	-0.03%	✅
bert_large_uncased_fp16	32	301.47	301.57	-0.03%	✅
bert_large_fp16	1	158.71	158.77	-0.04%	✅
distilgpt2_fp16	16	1,861.58	1,861.43	0.01%	✅
yolov5s	1	476.05	475.18	0.18%	✅
tinyllama	1	32.97	32.97	-0.01%	✅
vicuna-fastchat	1	157.97	158.91	-0.60%	✅
whisper-tiny-encoder	1	348.70	347.66	0.30%	✅
whisper-tiny-decoder	1	396.63	396.34	0.07%	✅

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