create simplify_dyn_ops pass and add variable slice optimization

[CharlieL7]

• New compiler pass that simplifies dynamic shapes related operators to their static versions if possible
• Will normally be used after a split_single_dyn_dim pass

[migraphx-bot]

Test	Batch	Rate new 37f878	Rate old c2e01b	Diff	Compare
torchvision-resnet50	64	2,284.07	2,284.87	-0.04%	✅
torchvision-resnet50_fp16	64	5,369.26	5,357.62	0.22%	✅
torchvision-densenet121	32	1,828.67	1,829.81	-0.06%	✅
torchvision-densenet121_fp16	32	3,392.74	3,378.73	0.41%	✅
torchvision-inceptionv3	32	1,338.84	1,335.78	0.23%	✅
torchvision-inceptionv3_fp16	32	2,584.27	2,585.25	-0.04%	✅
cadene-inceptionv4	16	682.32	679.39	0.43%	✅
cadene-resnext64x4	16	590.32	590.19	0.02%	✅
slim-mobilenet	64	7,211.76	7,216.76	-0.07%	✅
slim-nasnetalarge	64	237.11	236.57	0.23%	✅
slim-resnet50v2	64	2,530.75	2,530.71	0.00%	✅
bert-mrpc-onnx	8	721.51	721.25	0.04%	✅
bert-mrpc-tf	1	388.44	391.28	-0.73%	✅
pytorch-examples-wlang-gru	1	304.83	303.90	0.31%	✅
pytorch-examples-wlang-lstm	1	315.39	311.77	1.16%	✅
torchvision-resnet50_1	1	561.17	555.70	0.98%	✅
torchvision-inceptionv3_1	1	305.77	306.97	-0.39%	✅
cadene-dpn92_1	1	346.26	351.70	-1.55%	✅
cadene-resnext101_1	1	221.04	220.52	0.24%	✅
slim-vgg16_1	1	224.28	224.37	-0.04%	✅
slim-mobilenet_1	1	1,488.38	1,468.80	1.33%	✅
slim-inceptionv4_1	1	220.24	221.26	-0.46%	✅
onnx-taau-downsample	1	322.84	322.42	0.13%	✅
dlrm-criteoterabyte	1	21.70	21.67	0.13%	✅
dlrm-criteoterabyte_fp16	1	40.53	40.54	-0.03%	✅
agentmodel	1	5,767.54	5,779.11	-0.20%	✅
unet_fp16	2	55.15	55.07	0.15%	✅

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

🔴cadene-dpn92_1: FAILED: MIGraphX is not within tolerance - check verbose output

    :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

[codecov]

Codecov Report

Merging #2161 (5a31122) into develop (800d19c) will increase coverage by 0.02%.
Report is 1 commits behind head on develop.
The diff coverage is 100.00%.

❗ Current head 5a31122 differs from pull request most recent head f79f412. Consider uploading reports for the commit f79f412 to get more accurate results

@@             Coverage Diff             @@
##           develop    #2161      +/-   ##
===========================================
+ Coverage    91.51%   91.53%   +0.02%     
===========================================
  Files          427      429       +2     
  Lines        15972    16011      +39     
===========================================
+ Hits         14616    14655      +39     
  Misses        1356     1356              

Files Changed	Coverage Δ
src/split_single_dyn_dim.cpp	92.59% <ø> (-1.44%)	⬇️
src/include/migraphx/simplify_dyn_ops.hpp	100.00% <100.00%> (ø)
src/simplify_dyn_ops.cpp	100.00% <100.00%> (ø)

[TedThemistokleous]

ORT failure seems to be unrelated to your changes right now. Overall just answer some Q's I have