Fuse all pointwise inputs with mlir not just the first one found

[pfultz2]

No description provided.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.18%. Comparing base (ed3037e) to head (f71650a).
Report is 2 commits behind head on develop.

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #3629   +/-   ##
========================================
  Coverage    92.18%   92.18%           
========================================
  Files          513      513           
  Lines        21576    21576           
========================================
  Hits         19889    19889           
  Misses        1687     1687           

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

---

🚨 Try these New Features:

• Flaky Tests Detection - Detect and resolve failed and flaky tests

[migraphx-bot]

Test	Batch	Rate new a12f76	Rate old b39a93	Diff	Compare
torchvision-resnet50	64	3,260.83	3,257.00	0.12%	✅
torchvision-resnet50_fp16	64	6,979.07	6,984.63	-0.08%	✅
torchvision-densenet121	32	2,437.26	2,433.00	0.18%	✅
torchvision-densenet121_fp16	32	4,073.32	4,080.77	-0.18%	✅
torchvision-inceptionv3	32	1,629.87	1,627.81	0.13%	✅
torchvision-inceptionv3_fp16	32	2,744.07	2,746.31	-0.08%	✅
cadene-inceptionv4	16	765.29	764.38	0.12%	✅
cadene-resnext64x4	16	809.85	811.17	-0.16%	✅
slim-mobilenet	64	7,468.26	7,464.41	0.05%	✅
slim-nasnetalarge	64	208.50	208.42	0.04%	✅
slim-resnet50v2	64	3,440.18	3,439.84	0.01%	✅
bert-mrpc-onnx	8	1,147.08	1,153.73	-0.58%	✅
bert-mrpc-tf	1	468.05	497.12	-5.85%	🔴
pytorch-examples-wlang-gru	1	422.14	432.34	-2.36%	✅
pytorch-examples-wlang-lstm	1	395.17	390.79	1.12%	✅
torchvision-resnet50_1	1	781.03	810.22	-3.60%	🔴
cadene-dpn92_1	1	396.98	397.26	-0.07%	✅
cadene-resnext101_1	1	382.30	383.26	-0.25%	✅
onnx-taau-downsample	1	345.77	345.68	0.03%	✅
dlrm-criteoterabyte	1	33.33	33.33	0.01%	✅
dlrm-criteoterabyte_fp16	1	52.76	52.75	0.02%	✅
agentmodel	1	7,827.24	9,841.45	-20.47%	🔴
unet_fp16	2	58.92	58.82	0.17%	✅
resnet50v1_fp16	1	945.59	956.50	-1.14%	✅
resnet50v1_int8	1	1,004.04	1,048.16	-4.21%	🔴
bert_base_cased_fp16	64	1,170.89	1,170.84	0.00%	✅
bert_large_uncased_fp16	32	363.83	363.68	0.04%	✅
bert_large_fp16	1	199.02	200.40	-0.69%	✅
distilgpt2_fp16	16	2,202.35	2,199.24	0.14%	✅
yolov5s	1	542.51	534.53	1.49%	✅
tinyllama	1	43.46	43.46	-0.00%	✅
vicuna-fastchat	1	173.76	175.10	-0.76%	✅
whisper-tiny-encoder	1	418.36	418.56	-0.05%	✅
whisper-tiny-decoder	1	426.44	434.23	-1.79%	✅

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

[turneram]

Between this and #3632, I'm seeing all fusions and mxr size down to 10.5GB