Fix bug in computing dominator

[pfultz2]

We were not propagating the dominators for single input instructions, which caused us to miss some dominators.

[codecov[bot]]

Codecov Report

All modified and coverable lines are covered by tests :white_check_mark:

Project coverage is 91.79%. Comparing base (9cdd85d) to head (98c05af). Report is 3 commits behind head on develop.

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #3069   +/-   ##
========================================
  Coverage    91.78%   91.79%           
========================================
  Files          486      486           
  Lines        18864    18866    +2     
========================================
+ Hits         17315    17318    +3     
+ Misses        1549     1548    -1     

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.

[migraphx-bot]

Test	Batch	Rate new 98c05a	Rate old bc6c79	Diff	Compare
torchvision-resnet50	64	2,958.69	2,950.97	0.26%	:white_check_mark:
torchvision-resnet50_fp16	64	6,554.93	6,566.23	-0.17%	:white_check_mark:
torchvision-densenet121	32	2,426.26	2,421.23	0.21%	:white_check_mark:
torchvision-densenet121_fp16	32	3,963.77	3,992.03	-0.71%	:white_check_mark:
torchvision-inceptionv3	32	1,662.52	1,659.26	0.20%	:white_check_mark:
torchvision-inceptionv3_fp16	32	2,597.13	2,598.65	-0.06%	:white_check_mark:
cadene-inceptionv4	16	778.09	776.84	0.16%	:white_check_mark:
cadene-resnext64x4	16	740.52	740.86	-0.05%	:white_check_mark:
slim-mobilenet	64	6,919.14	6,918.90	0.00%	:white_check_mark:
slim-nasnetalarge	64	177.14	177.18	-0.02%	:white_check_mark:
slim-resnet50v2	64	2,876.74	2,876.68	0.00%	:white_check_mark:
bert-mrpc-onnx	8	1,064.98	1,064.43	0.05%	:white_check_mark:
bert-mrpc-tf	1	485.35	511.61	-5.13%	:red_circle:
pytorch-examples-wlang-gru	1	429.71	371.38	15.71%	:high_brightness:
pytorch-examples-wlang-lstm	1	401.41	409.57	-1.99%	:white_check_mark:
torchvision-resnet50_1	1	793.25	790.15	0.39%	:white_check_mark:
cadene-dpn92_1	1	439.67	394.00	11.59%	:high_brightness:
cadene-resnext101_1	1	367.12	362.65	1.23%	:white_check_mark:
onnx-taau-downsample	1	349.54	349.17	0.11%	:white_check_mark:
dlrm-criteoterabyte	1	33.51	33.45	0.17%	:white_check_mark:
dlrm-criteoterabyte_fp16	1	56.30	56.69	-0.69%	:white_check_mark:
agentmodel	1	7,444.35	7,460.35	-0.21%	:white_check_mark:
unet_fp16	2	57.18	57.31	-0.23%	:white_check_mark:
resnet50v1_fp16	1	963.33	869.63	10.77%	:high_brightness:
resnet50v1_int8	1	772.70	823.61	-6.18%	:red_circle:
bert_base_cased_fp16	64	1,012.89	1,012.93	-0.00%	:white_check_mark:
bert_large_uncased_fp16	32	316.70	316.62	0.02%	:white_check_mark:
bert_large_fp16	1	nan	nan	nan%	:x:
distilgpt2_fp16	16	1,993.34	1,994.48	-0.06%	:white_check_mark:
yolov5s	1	519.59	501.26	3.66%	:high_brightness:
tinyllama	1	45.01	44.99	0.03%	:white_check_mark:
vicuna-fastchat	1	174.26	178.18	-2.20%	:white_check_mark:
whisper-tiny-encoder	1	404.19	404.60	-0.10%	:white_check_mark:
whisper-tiny-decoder	1	424.29	424.85	-0.13%	:white_check_mark:

This build is not recommended to merge :red_circle:

[migraphx-bot]

:x: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

     :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

     :white_check_mark: cadene-dpn92_1: PASSED: MIGraphX meets tolerance

:x:cadene-resnext101_1: ERROR - check error output

2024-05-10 16:44:41.152258142 [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.
2024-05-10 16:44:41.158345836 [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 ''

     :white_check_mark: dlrm-criteoterabyte: PASSED: MIGraphX meets tolerance

     :white_check_mark: agentmodel: PASSED: MIGraphX meets tolerance

:x: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

     :white_check_mark: resnet50v1: PASSED: MIGraphX meets tolerance

:red_circle:bert_base_cased_fp16: FAILED: MIGraphX is not within tolerance - check verbose output

:red_circle:bert_large_uncased_fp16: FAILED: MIGraphX is not within tolerance - check verbose output

:x: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

     :white_check_mark: yolov5s: PASSED: MIGraphX meets tolerance

     :white_check_mark: tinyllama: PASSED: MIGraphX meets tolerance

     :white_check_mark: vicuna-fastchat: PASSED: MIGraphX meets tolerance

     :white_check_mark: whisper-tiny-encoder: PASSED: MIGraphX meets tolerance

     :white_check_mark: whisper-tiny-decoder: PASSED: MIGraphX meets tolerance

     :white_check_mark: distilgpt2_fp16: PASSED: MIGraphX meets tolerance