[AIMIGRAPHX-885] Add concat reshape matcher

[TedThemistokleous]

Motivation

Adds a matcher for the concat_reshape matching. Partial piece when breaking up #4723

Technical Details

Partial changes to allow for MLP batched towers and uses this concat_rehsape matcher

Changelog Category

Add a CHANGELOG.md entry for any option other than Not Applicable

• • [x ] Added: New functionality.
• • Changed: Changes to existing functionality.
• • Removed: Functionality or support that has been removed. (Compared to a previous release)
• • Optimized: Component performance that has been optimized or improved.
• • Resolved Issues: Known issues from a previous version that have been resolved.
• • Not Applicable: This PR is not to be included in the changelog.

[gh-app-migraphx-bot-pr-write]

Test	Batch	New Rate (ec6867)	Old Rate (241f7a)	Diff	Status
torchvision-resnet50	64	2,872.80	3,158.05	-9.03%	🔴
torchvision-resnet50_fp16	64	6,511.94	6,678.10	-2.49%	✅
torchvision-densenet121	32	2,674.91	2,705.33	-1.12%	✅
torchvision-densenet121_fp16	32	4,515.81	4,480.31	0.79%	✅
torchvision-inceptionv3	32	1,732.55	1,772.37	-2.25%	✅
torchvision-inceptionv3_fp16	32	2,787.70	2,613.31	6.67%	🔆
cadene-inceptionv4	16	824.60	444.89	85.35%	🔆
cadene-resnext64x4	16	780.31	412.50	89.17%	🔆
slim-mobilenet	64	8,387.71	8,419.17	-0.37%	✅
slim-nasnetalarge	64	226.13	nan	nan	❌
slim-resnet50v2	64	3,313.76	1,641.82	101.83%	🔆
bert-mrpc-onnx	8	1,173.10	1,165.20	0.68%	✅
bert-mrpc-tf	1	490.68	492.10	-0.29%	✅
pytorch-examples-wlang-gru	1	342.83	334.96	2.35%	✅
pytorch-examples-wlang-lstm	1	512.55	469.54	9.16%	🔆
torchvision-resnet50_1	1	779.45	760.64	2.47%	✅
cadene-dpn92_1	1	463.44	457.65	1.27%	✅
cadene-resnext101_1	1	364.17	363.68	0.13%	✅
onnx-taau-downsample	1	399.85	401.93	-0.52%	✅
dlrm-criteoterabyte	1	32.40	12.36	162.07%	🔆
dlrm-criteoterabyte_fp16	1	51.79	29.66	74.62%	🔆
agentmodel	1	9,432.27	10,523.13	-10.37%	🔴
unet_fp16	2	56.87	57.23	-0.61%	✅
resnet50v1_fp16	1	939.45	959.87	-2.13%	✅
resnet50v1_int8	1	929.89	942.92	-1.38%	✅
bert_base_cased_fp16	64	1,098.07	1,092.47	0.51%	✅
bert_large_uncased_fp16	32	346.36	345.19	0.34%	✅
bert_large_fp16	1	203.41	203.23	0.08%	✅
distilgpt2_fp16	16	2,093.83	2,096.77	-0.14%	✅
yolov5s	1	568.33	564.74	0.64%	✅
tinyllama	1	18.30	46.00	-60.22%	🔴
vicuna-fastchat	1	44.21	44.04	0.39%	✅
whisper-tiny-encoder	1	417.44	419.55	-0.50%	✅
whisper-tiny-decoder	1	52.38	414.85	-87.37%	🔴
llama2_7b	1	20.34	20.42	-0.40%	✅
qwen1.5-7b	1	12.76	21.75	-41.33%	🔴
phi3-3.8b	1	11.34	26.81	-57.71%	🔴
llama3-8b	1	21.75	21.83	-0.38%	✅
whisper-large-encoder	1	3.05	6.50	-53.07%	🔴
whisper-large-decoder	1	2.61	106.80	-97.55%	🔴
mistral-7b	1	15.73	23.85	-34.05%	🔴
FLUX.1-schnell	1	763.51	763.88	-0.05%	✅

Regressions detected 🔴

[gh-app-migraphx-bot-pr-write]

Test	Status	Result
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
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	🔴	FAILED: MIGraphX is not within tolerance - check verbose output
llama2_7b	✅	PASSED: MIGraphX meets tolerance
qwen1.5-7b	✅	PASSED: MIGraphX meets tolerance
phi3-3.8b	✅	PASSED: MIGraphX meets tolerance
llama3-8b	✅	PASSED: MIGraphX meets tolerance
whisper-large-decoder	✅	PASSED: MIGraphX meets tolerance
mistral-7b	✅	PASSED: MIGraphX meets tolerance
FLUX.1-schnell	✅	PASSED: MIGraphX meets tolerance

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #4984   +/-   ##
========================================
  Coverage    92.73%   92.74%           
========================================
  Files          592      594    +2     
  Lines        31289    31351   +62     
========================================
+ Hits         29015    29074   +59     
- Misses        2274     2277    +3     

Files with missing lines	Coverage Δ
src/simplify_reshapes.cpp	97.99% <100.00%> (+0.02%)	⬆️

... and 5 files with indirect coverage changes

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.