Revert "Add support for MaxPool unit8 type"

[causten]

Reverts #2973
Need to resolve Clang ASAN failure in CI

[migraphx-bot]

Test	Batch	Rate new a3dd2b	Rate old 70c338	Diff	Compare
torchvision-resnet50	64	2,789.70	2,790.00	-0.01%	✅
torchvision-resnet50_fp16	64	6,198.91	6,199.57	-0.01%	✅
torchvision-densenet121	32	2,066.68	2,084.35	-0.85%	✅
torchvision-densenet121_fp16	32	3,610.98	3,605.22	0.16%	✅
torchvision-inceptionv3	32	1,599.14	1,601.61	-0.15%	✅
torchvision-inceptionv3_fp16	32	2,557.10	2,556.65	0.02%	✅
cadene-inceptionv4	16	716.07	716.23	-0.02%	✅
cadene-resnext64x4	16	678.25	677.92	0.05%	✅
slim-mobilenet	64	5,812.63	5,811.31	0.02%	✅
slim-nasnetalarge	64	154.19	154.23	-0.02%	✅
slim-resnet50v2	64	2,579.04	2,578.74	0.01%	✅
bert-mrpc-onnx	8	969.20	969.17	0.00%	✅
bert-mrpc-tf	1	409.95	410.10	-0.04%	✅
pytorch-examples-wlang-gru	1	400.28	392.78	1.91%	✅
pytorch-examples-wlang-lstm	1	377.97	370.94	1.90%	✅
torchvision-resnet50_1	1	601.89	606.52	-0.76%	✅
cadene-dpn92_1	1	388.27	383.07	1.36%	✅
cadene-resnext101_1	1	323.28	324.89	-0.50%	✅
onnx-taau-downsample	1	307.08	306.95	0.04%	✅
dlrm-criteoterabyte	1	28.53	28.54	-0.03%	✅
dlrm-criteoterabyte_fp16	1	47.23	47.10	0.27%	✅
agentmodel	1	7,334.01	7,467.31	-1.79%	✅
unet_fp16	2	57.47	57.50	-0.05%	✅
resnet50v1_fp16	1	900.33	878.12	2.53%	✅
resnet50v1_int8	1	774.43	791.31	-2.13%	✅
bert_base_cased_fp16	64	1,021.87	1,021.83	0.00%	✅
bert_large_uncased_fp16	32	299.02	298.84	0.06%	✅
bert_large_fp16	1	156.34	158.53	-1.39%	✅
distilgpt2_fp16	16	1,834.90	1,834.50	0.02%	✅
yolov5s	1	472.19	470.88	0.28%	✅
tinyllama	1	33.00	33.01	-0.03%	✅
vicuna-fastchat	1	158.54	157.97	0.36%	✅
whisper-tiny-encoder	1	352.33	352.77	-0.13%	✅
whisper-tiny-decoder	1	397.26	399.88	-0.66%	✅

This build is OK for 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

[umangyadav]

You can just comment out uint8_type test here instead of reverting entire PR

[nives-vukovic]

@umangyadav As far as I can see on our local setup, by adding -fno-sanitize=float-cast-overflow to

AMDMIGraphX/Jenkinsfile

Lines 166 to 170 in ee68f72

	stage('Clang ASAN') {
	def sanitizers = "undefined,address"
	def debug_flags = "-g -O2 -fno-omit-frame-pointer -fsanitize=${sanitizers} -fno-sanitize-recover=${sanitizers}"
	def gpu_targets = getgputargets()
	cmake_build(flags: "-DCMAKE_BUILD_TYPE=debug -DMIGRAPHX_ENABLE_PYTHON=Off -DMIGRAPHX_ENABLE_GPU=Off -DMIGRAPHX_ENABLE_CPU=On -DCMAKE_CXX_FLAGS_DEBUG='${debug_flags}' -DCMAKE_C_FLAGS_DEBUG='${debug_flags}' -DGPU_TARGETS='${gpu_targets}'")

, these kind of errors should be resolved.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 91.78%. Comparing base (c7d5f09) to head (9aa24ba).
Report is 3 commits behind head on develop.

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #3057   +/-   ##
========================================
  Coverage    91.78%   91.78%           
========================================
  Files          485      485           
  Lines        18856    18863    +7     
========================================
+ Hits         17307    17314    +7     
  Misses        1549     1549           

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