added set_bypass() call

[bpickrel]

Bug fix: added a set_bypass() call that was missing from the reduce_reshape variant of the rewrite_reshapes pass in fusion reduction (the other variants already have it). This sets a flag to prevent the created module from being fused again (i.e. subsequent compiler passes that see the flag skip over the module), which could lead to an exception because it would try to create a fused_reduce instruction with an invalid argument list. Closes Issue #3033

[pfultz2]

This looks good.

[pfultz2]

For the other reviewers, adding the extra check in fused_reduce operator will get coverage for this issue with the current unit tests, so there is no need to write a new unit test.

Also its very likely such unit test would be removed in the future, which I dont have time to explain now.

[bpickrel]

Don't be too quick! The change broke an existing test, which I'm working on now. So we have code coverage whether we want it or not.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 91.82%. Comparing base (76d1c14) to head (d8567c0).
Report is 2 commits behind head on develop.

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #3116   +/-   ##
========================================
  Coverage    91.82%   91.82%           
========================================
  Files          486      486           
  Lines        18991    18994    +3     
========================================
+ Hits         17438    17441    +3     
  Misses        1553     1553           

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

[migraphx-bot]

Test	Batch	Rate new 4bdb66	Rate old bceef1	Diff	Compare
torchvision-resnet50	64	1,713.92	1,712.95	0.06%	✅
torchvision-resnet50_fp16	64	3,809.57	3,811.61	-0.05%	✅
torchvision-densenet121	32	1,451.91	1,458.96	-0.48%	✅
torchvision-densenet121_fp16	32	2,432.13	2,432.65	-0.02%	✅
torchvision-inceptionv3	32	882.93	883.89	-0.11%	✅
torchvision-inceptionv3_fp16	32	1,380.40	1,381.08	-0.05%	✅
cadene-inceptionv4	16	407.08	408.06	-0.24%	✅
cadene-resnext64x4	16	413.75	413.67	0.02%	✅
slim-mobilenet	64	3,822.24	3,824.46	-0.06%	✅
slim-nasnetalarge	64	97.02	97.02	0.00%	✅
slim-resnet50v2	64	1,651.48	1,651.41	0.00%	✅
bert-mrpc-onnx	8	590.45	589.10	0.23%	✅
bert-mrpc-tf	1	288.34	288.10	0.08%	✅
pytorch-examples-wlang-gru	1	335.51	300.11	11.80%	🔆
pytorch-examples-wlang-lstm	1	298.63	265.42	12.51%	🔆
torchvision-resnet50_1	1	431.00	437.05	-1.38%	✅
cadene-dpn92_1	1	243.70	243.98	-0.11%	✅
cadene-resnext101_1	1	187.43	189.16	-0.91%	✅
onnx-taau-downsample	1	204.07	204.02	0.02%	✅
dlrm-criteoterabyte	1	21.84	22.24	-1.78%	✅
dlrm-criteoterabyte_fp16	1	40.74	41.43	-1.68%	✅
agentmodel	1	6,069.77	6,319.63	-3.95%	🔴
unet_fp16	2	33.70	33.77	-0.20%	✅
resnet50v1_fp16	1	522.56	549.27	-4.86%	🔴
resnet50v1_int8	1	462.42	456.03	1.40%	✅
bert_base_cased_fp16	64	620.62	620.67	-0.01%	✅
bert_large_uncased_fp16	32	193.76	193.76	0.00%	✅
bert_large_fp16	1	104.05	103.76	0.28%	✅
distilgpt2_fp16	16	1,187.96	1,186.96	0.08%	✅
yolov5s	1	297.41	298.20	-0.27%	✅
tinyllama	1	23.34	23.32	0.08%	✅
vicuna-fastchat	1	133.12	133.50	-0.29%	✅
whisper-tiny-encoder	1	241.33	240.87	0.19%	✅
whisper-tiny-decoder	1	245.66	245.38	0.12%	✅

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

[codecov-commenter]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 91.82%. Comparing base (2dcca47) to head (4bdb666).
Report is 156 commits behind head on develop.

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #3116   +/-   ##
========================================
  Coverage    91.82%   91.82%           
========================================
  Files          486      486           
  Lines        18990    18993    +3     
========================================
+ Hits         17437    17440    +3     
  Misses        1553     1553           

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