Fix rocBLAS failure for the case where standard shape has out-of-sequence strides

[ahsan-ca]

No description provided.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.29%. Comparing base (879f306) to head (a3b4d0c).
Report is 1 commits behind head on develop.

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #3786   +/-   ##
========================================
  Coverage    92.29%   92.29%           
========================================
  Files          519      519           
  Lines        22233    22233           
========================================
  Hits         20520    20520           
  Misses        1713     1713           

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

[kahmed10]

Is there a basic unit test we could write for this?

[migraphx-bot]

Test	Batch	Rate new a3b4d0	Rate old 879f30	Diff	Compare
torchvision-resnet50	64	3,234.90	3,236.69	-0.06%	✅
torchvision-resnet50_fp16	64	6,867.27	6,873.54	-0.09%	✅
torchvision-densenet121	32	2,429.54	2,438.75	-0.38%	✅
torchvision-densenet121_fp16	32	4,176.00	4,192.65	-0.40%	✅
torchvision-inceptionv3	32	1,612.22	1,615.33	-0.19%	✅
torchvision-inceptionv3_fp16	32	2,684.36	2,688.62	-0.16%	✅
cadene-inceptionv4	16	749.35	750.79	-0.19%	✅
cadene-resnext64x4	16	809.00	809.35	-0.04%	✅
slim-mobilenet	64	6,660.74	6,664.14	-0.05%	✅
slim-nasnetalarge	64	198.94	199.08	-0.07%	✅
slim-resnet50v2	64	3,422.20	3,429.15	-0.20%	✅
bert-mrpc-onnx	8	1,139.70	1,145.96	-0.55%	✅
bert-mrpc-tf	1	468.16	485.72	-3.61%	🔴
pytorch-examples-wlang-gru	1	424.67	474.72	-10.54%	🔴
pytorch-examples-wlang-lstm	1	408.24	441.95	-7.63%	🔴
torchvision-resnet50_1	1	800.13	810.09	-1.23%	✅
cadene-dpn92_1	1	415.56	432.90	-4.01%	🔴
cadene-resnext101_1	1	389.29	390.20	-0.23%	✅
onnx-taau-downsample	1	373.07	372.17	0.24%	✅
dlrm-criteoterabyte	1	30.54	31.81	-3.98%	🔴
dlrm-criteoterabyte_fp16	1	49.03	51.03	-3.94%	🔴
agentmodel	1	7,724.81	8,695.73	-11.17%	🔴
unet_fp16	2	57.72	57.99	-0.46%	✅
resnet50v1_fp16	1	1,036.15	1,028.78	0.72%	✅
resnet50v1_int8	1	786.92	781.22	0.73%	✅
bert_base_cased_fp16	64	1,172.18	1,172.51	-0.03%	✅
bert_large_uncased_fp16	32	362.19	362.46	-0.08%	✅
bert_large_fp16	1	199.33	199.81	-0.24%	✅
distilgpt2_fp16	16	2,213.48	2,217.59	-0.19%	✅
yolov5s	1	529.52	526.35	0.60%	✅
tinyllama	1	43.42	43.61	-0.45%	✅
vicuna-fastchat	1	43.79	43.85	-0.13%	✅
whisper-tiny-encoder	1	410.84	411.94	-0.27%	✅
whisper-tiny-decoder	1	407.62	406.88	0.18%	✅

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

[causten]

@ahsan-ca Need to fix the CI failure