Remove list initialization for prefix_scan_sum

[TedThemistokleous]

This seems to cause an error as seen in : https://ontrack-internal.amd.com/browse/SWDEV-443633

Issue with using list initialization for inputs in the compute shape function of prefix_scan_sum.

related to #2827

[pfultz2]

I think it would be better to make the shape(const std::vector<shape>& subs) explicit, that might fix the issue which seems due to implicit conversions.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 91.64%. Comparing base (5d6196a) to head (2e3f19d).
Report is 7 commits behind head on develop.

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #2828      +/-   ##
===========================================
- Coverage    91.64%   91.64%   -0.01%     
===========================================
  Files          472      472              
  Lines        17848    17881      +33     
===========================================
+ Hits         16357    16387      +30     
- Misses        1491     1494       +3     

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

[migraphx-bot]

Test	Batch	Rate new 718175	Rate old e57fcd	Diff	Compare
torchvision-resnet50	64	3,035.35	3,030.45	0.16%	✅
torchvision-resnet50_fp16	64	7,052.98	7,048.49	0.06%	✅
torchvision-densenet121	32	2,443.21	2,443.36	-0.01%	✅
torchvision-densenet121_fp16	32	4,131.93	4,119.95	0.29%	✅
torchvision-inceptionv3	32	1,652.37	1,652.86	-0.03%	✅
torchvision-inceptionv3_fp16	32	2,615.36	2,618.44	-0.12%	✅
cadene-inceptionv4	16	775.71	777.23	-0.19%	✅
cadene-resnext64x4	16	744.80	744.93	-0.02%	✅
slim-mobilenet	64	6,714.96	6,718.05	-0.05%	✅
slim-nasnetalarge	64	173.95	174.17	-0.13%	✅
slim-resnet50v2	64	2,955.71	2,958.91	-0.11%	✅
bert-mrpc-onnx	8	1,002.83	1,002.64	0.02%	✅
bert-mrpc-tf	1	416.17	425.71	-2.24%	✅
pytorch-examples-wlang-gru	1	314.67	313.97	0.23%	✅
pytorch-examples-wlang-lstm	1	265.42	271.66	-2.30%	✅
torchvision-resnet50_1	1	785.98	724.69	8.46%	🔆
cadene-dpn92_1	1	431.10	428.02	0.72%	✅
cadene-resnext101_1	1	364.69	364.01	0.19%	✅
onnx-taau-downsample	1	349.28	349.39	-0.03%	✅
dlrm-criteoterabyte	1	28.43	28.42	0.06%	✅
dlrm-criteoterabyte_fp16	1	49.12	49.17	-0.10%	✅
agentmodel	1	4,915.60	4,078.59	20.52%	🔆
unet_fp16	2	55.27	55.18	0.17%	✅
resnet50v1_fp16	1	950.07	894.72	6.19%	🔆
resnet50v1_int8	1	817.78	816.48	0.16%	✅
bert_base_cased_fp16	64	952.34	952.68	-0.04%	✅
bert_large_uncased_fp16	32	308.38	308.50	-0.04%	✅
bert_large_fp16	1	nan	nan	nan%	❌
distilgpt2_fp16	16	1,775.40	1,776.50	-0.06%	✅
yolov5s	1	524.47	521.95	0.48%	✅
tinyllama	1	43.92	43.91	0.03%	✅
vicuna-fastchat	1	177.82	174.87	1.69%	✅
whisper-tiny-encoder	1	383.17	383.99	-0.21%	✅
whisper-tiny-decoder	1	411.49	410.01	0.36%	✅

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

2024-03-06 19:59:15.933647857 [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.
2024-03-06 19:59:15.944626750 [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