Adding skip-layer-normalization operator

[ahsan-ca]

Based off changes via- https://github.com/ROCm/AMDMIGraphX/pull/3865

Split these out from that branch

[codecov[bot]]

Codecov Report

Attention: Patch coverage is 91.30435% with 4 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
src/onnx/parse_skip_layer_normalization.cpp	91.30%	4 Missing :warning:

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #3917      +/-   ##
===========================================
- Coverage    92.03%   92.03%   -0.00%     
===========================================
  Files          524      525       +1     
  Lines        24077    24123      +46     
===========================================
+ Hits         22158    22200      +42     
- Misses        1919     1923       +4     

Files with missing lines	Coverage Δ
src/onnx/parse_skip_layer_normalization.cpp	91.30% <91.30%> (ø)

:rocket: New features to boost your workflow:

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

[ahsan-ca]

suggestion: please add tests for skip to be a 2d or a 3d tensor (for batch==1), if not already.

That's a good idea to have tests for these. I have added both the tests. Thanks for the suggestion. @lakhinderwalia

[ahsan-ca]

Moving the details from description to a comment since we use description for commits to explain the changes: Based off changes via- https://github.com/ROCm/AMDMIGraphX/pull/3865

Split these out from that branch

[migraphx-bot]

Test	Batch	Rate new 8d5d2e	Rate old fea22b	Diff	Compare
torchvision-resnet50	64	3,231.26	3,253.19	-0.67%	:white_check_mark:
torchvision-resnet50_fp16	64	6,874.09	6,901.24	-0.39%	:white_check_mark:
torchvision-densenet121	32	2,433.03	2,443.16	-0.41%	:white_check_mark:
torchvision-densenet121_fp16	32	4,206.52	4,208.93	-0.06%	:white_check_mark:
torchvision-inceptionv3	32	1,613.46	1,622.82	-0.58%	:white_check_mark:
torchvision-inceptionv3_fp16	32	2,697.51	2,710.58	-0.48%	:white_check_mark:
cadene-inceptionv4	16	749.15	754.69	-0.73%	:white_check_mark:
cadene-resnext64x4	16	809.58	815.30	-0.70%	:white_check_mark:
slim-mobilenet	64	6,652.63	6,692.20	-0.59%	:white_check_mark:
slim-nasnetalarge	64	196.55	197.48	-0.47%	:white_check_mark:
slim-resnet50v2	64	3,431.91	3,449.99	-0.52%	:white_check_mark:
bert-mrpc-onnx	8	1,142.82	1,150.34	-0.65%	:white_check_mark:
bert-mrpc-tf	1	463.22	464.45	-0.26%	:white_check_mark:
pytorch-examples-wlang-gru	1	472.07	478.39	-1.32%	:white_check_mark:
pytorch-examples-wlang-lstm	1	438.90	433.73	1.19%	:white_check_mark:
torchvision-resnet50_1	1	811.14	812.18	-0.13%	:white_check_mark:
cadene-dpn92_1	1	424.97	422.31	0.63%	:white_check_mark:
cadene-resnext101_1	1	392.95	394.45	-0.38%	:white_check_mark:
onnx-taau-downsample	1	395.03	397.81	-0.70%	:white_check_mark:
dlrm-criteoterabyte	1	31.80	31.95	-0.47%	:white_check_mark:
dlrm-criteoterabyte_fp16	1	50.95	51.01	-0.12%	:white_check_mark:
agentmodel	1	8,559.88	8,632.37	-0.84%	:white_check_mark:
unet_fp16	2	58.41	58.61	-0.33%	:white_check_mark:
resnet50v1_fp16	1	1,072.38	1,068.83	0.33%	:white_check_mark:
resnet50v1_int8	1	880.15	885.83	-0.64%	:white_check_mark:
bert_base_cased_fp16	64	1,162.34	1,169.88	-0.64%	:white_check_mark:
bert_large_uncased_fp16	32	354.18	355.96	-0.50%	:white_check_mark:
bert_large_fp16	1	193.40	195.30	-0.97%	:white_check_mark:
distilgpt2_fp16	16	2,215.81	2,230.97	-0.68%	:white_check_mark:
yolov5s	1	514.46	515.50	-0.20%	:white_check_mark:
tinyllama	1	43.61	43.85	-0.54%	:white_check_mark:
vicuna-fastchat	1	43.79	44.08	-0.65%	:white_check_mark:
whisper-tiny-encoder	1	411.65	413.06	-0.34%	:white_check_mark:
whisper-tiny-decoder	1	411.32	412.06	-0.18%	:white_check_mark:
llama2_7b	1	nan	nan	nan%	:x:
qwen1.5-7b	1	23.45	23.55	-0.43%	:white_check_mark:
phi3-3.8b	1	nan	nan	nan%	:x:
mask-rcnn	1	18.29	18.67	-2.05%	:white_check_mark:
llama3-8b	1	21.62	21.27	1.63%	:white_check_mark:
whisper-large-encoder	1	10.18	10.22	-0.43%	:white_check_mark:
whisper-large-decoder	1	97.71	99.12	-1.42%	:white_check_mark:
mistral-7b	1	23.65	23.75	-0.44%	:white_check_mark:
FLUX.1-schnell	1	903.71	892.58	1.25%	:white_check_mark:
nan	nan	nan	nan	nan%	:x:

This build is not recommended to merge :red_circle:

[migraphx-bot]

     :white_check_mark: bert-mrpc-onnx: PASSED: MIGraphX meets tolerance

     :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

     :white_check_mark: cadene-resnext101_1: PASSED: MIGraphX meets tolerance

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

     :white_check_mark: agentmodel: PASSED: MIGraphX meets tolerance

     :white_check_mark: unet: PASSED: MIGraphX meets tolerance

     :white_check_mark: resnet50v1: PASSED: MIGraphX meets tolerance

     :white_check_mark: bert_base_cased_fp16: PASSED: MIGraphX meets tolerance

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

     :white_check_mark: bert_large: PASSED: MIGraphX meets tolerance

     :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

:x:llama2_7b: 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/llama2_7b/decoder_model.onnx

:x:#qwen1.5-7b: ERROR - check error output

usage: accuracy_checker.py [-h] [--onnx ONNX] [--tf TF] [--provider PROVIDER]
[--batch BATCH] [--fill1] [--fill0] [--fp16]
[--argmax] [--verbose] [--tolerance TOLERANCE]
[--input-dim INPUT_DIM] [--target TARGET]
[--ort-run] [--ort-logging]
[--disable-offload-copy] [--disable-fast-math]
[--exhaustive_tune]
accuracy_checker.py: error: unrecognized arguments: input_ids attention_mask position_ids 1 256 @attention_mask 1 256 @position_ids 1 256

:x:phi3-3.8b: 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/phi3-3.8b/model.onnx

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

     :white_check_mark: llama3-8b: PASSED: MIGraphX meets tolerance

:x:#whisper-large-encoder: 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/include/migraphx/op/convolution.hpp:100: normalize_compute_shape: CONVOLUTION: mismatched channel numbers

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

     :white_check_mark: mistral-7b: PASSED: MIGraphX meets tolerance

     :white_check_mark: FLUX.1-schnell: PASSED: MIGraphX meets tolerance