Bump mlir with fix

[causten]

No description provided.

[migraphx-bot]

Test	Batch	Rate new 940149	Rate old 9186c3	Diff	Compare
torchvision-resnet50	64	2,977.44	3,015.62	-1.27%	✅
torchvision-resnet50_fp16	64	6,758.10	6,801.72	-0.64%	✅
torchvision-densenet121	32	2,419.62	2,421.88	-0.09%	✅
torchvision-densenet121_fp16	32	4,083.72	4,058.33	0.63%	✅
torchvision-inceptionv3	32	1,663.51	1,662.88	0.04%	✅
torchvision-inceptionv3_fp16	32	2,596.45	2,604.51	-0.31%	✅
cadene-inceptionv4	16	776.70	775.77	0.12%	✅
cadene-resnext64x4	16	743.58	744.74	-0.16%	✅
slim-mobilenet	64	7,035.30	7,034.80	0.01%	✅
slim-nasnetalarge	64	176.62	177.81	-0.67%	✅
slim-resnet50v2	64	2,866.51	2,878.86	-0.43%	✅
bert-mrpc-onnx	8	1,057.87	1,055.81	0.19%	✅
bert-mrpc-tf	1	472.54	462.04	2.27%	✅
pytorch-examples-wlang-gru	1	359.02	420.52	-14.62%	🔴
pytorch-examples-wlang-lstm	1	333.53	344.76	-3.26%	🔴
torchvision-resnet50_1	1	735.52	796.17	-7.62%	🔴
cadene-dpn92_1	1	432.91	428.51	1.03%	✅
cadene-resnext101_1	1	362.11	363.74	-0.45%	✅
onnx-taau-downsample	1	349.61	350.19	-0.17%	✅
dlrm-criteoterabyte	1	33.55	33.76	-0.62%	✅
dlrm-criteoterabyte_fp16	1	59.22	58.36	1.47%	✅
agentmodel	1	6,101.69	7,361.93	-17.12%	🔴
unet_fp16	2	57.25	57.29	-0.06%	✅
resnet50v1_fp16	1	884.66	893.54	-0.99%	✅
resnet50v1_int8	1	852.46	828.37	2.91%	✅
bert_base_cased_fp16	64	1,027.66	1,007.02	2.05%	✅
bert_large_uncased_fp16	32	318.67	304.60	4.62%	🔆
bert_large_fp16	1	nan	nan	nan%	❌
distilgpt2_fp16	16	2,013.73	1,999.48	0.71%	✅
yolov5s	1	508.91	503.97	0.98%	✅
tinyllama	1	44.76	44.75	0.03%	✅
vicuna-fastchat	1	182.48	178.06	2.48%	✅
whisper-tiny-encoder	1	402.99	402.52	0.12%	✅
whisper-tiny-decoder	1	418.81	421.40	-0.61%	✅

This build is not recommended to merge 🔴

[migraphx-bot]

❌bert-mrpc-onnx: ERROR - check error output

Traceback (most recent call last):
File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 340, in
main()
File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 205, in main
model = migraphx.parse_onnx(model_name, default_dim_value=batch)
RuntimeError: /src/AMDMIGraphX/src/onnx/onnx_parser.cpp:264: parse_from: PARSE_FROM: Failed reading onnx file: /new-saved-models/huggingface-transformers/bert_mrpc1.onnx

     ✅ 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: ERROR - check error output

2024-04-23 08:07:03.047650441 [W:onnxruntime:, model.cc:183 Model] ONNX Runtime only guarantees support for models stamped with opset version 7 or above for opset domain 'ai.onnx'. Please upgrade your model to opset 7 or higher. For now, this opset 6 model may run depending upon legacy support of some older opset version operators.
2024-04-23 08:07:03.058518241 [W:onnxruntime:, transpose_optimizer.cc:28 ApplyImpl] Transpose optimizer failed: Unsupported ONNX opset: 6
Traceback (most recent call last):
File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 340, in
main()
File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 267, in main
sess = ort.InferenceSession(model_name,
File "/usr/local/lib/python3.8/dist-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 419, in init
self._create_inference_session(providers, provider_options, disabled_optimizers)
File "/usr/local/lib/python3.8/dist-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 463, in _create_inference_session
sess.initialize_session(providers, provider_options, disabled_optimizers)
onnxruntime.capi.onnxruntime_pybind11_state.NotImplemented: [ONNXRuntimeError] : 9 : NOT_IMPLEMENTED : Could not find an implementation for BatchNormalization(6) node with name ''

     ✅ dlrm-criteoterabyte: PASSED: MIGraphX meets tolerance

     ✅ agentmodel: PASSED: MIGraphX meets tolerance

❌unet: ERROR - check error output

Traceback (most recent call last):
File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 340, in
main()
File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 207, in main
model = migraphx.parse_onnx(model_name,
RuntimeError: /src/AMDMIGraphX/src/onnx/onnx_parser.cpp:264: parse_from: PARSE_FROM: Failed reading onnx file: /new-saved-models/unet/model.onnx

     ✅ 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: ERROR - check error output

Traceback (most recent call last):
File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 340, in
main()
File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 205, in main
model = migraphx.parse_onnx(model_name, default_dim_value=batch)
RuntimeError: /src/AMDMIGraphX/src/onnx/onnx_parser.cpp:264: parse_from: PARSE_FROM: Failed reading onnx file: /new-saved-models/bert/model.onnx

     ✅ 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

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 91.77%. Comparing base (9186c37) to head (9401494).

Additional details and impacted files

@@             Coverage Diff              @@
##           develop    #2988       +/-   ##
============================================
+ Coverage         0   91.77%   +91.77%     
============================================
  Files            0      484      +484     
  Lines            0    18711    +18711     
============================================
+ Hits             0    17172    +17172     
- Misses           0     1539     +1539     

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