Remove int8x4 format completely

[umangyadav]

rocblas_int8x4 format is deprecated since rocm-5.6.0 and is going to get removed in 6.0.

MIOpen uses miopenint8x4 format to call into GEMM based kernels and has removed support for miopenint8x4 format recently.

This PR removes int8x4 format and related logic from codebase completely.

[codecov]

Codecov Report

Merging #2373 (9ec3586) into develop (d1305d0) will not change coverage.
Report is 1 commits behind head on develop.
The diff coverage is n/a.

❗ Current head 9ec3586 differs from pull request most recent head f5c4ca6. Consider uploading reports for the commit f5c4ca6 to get more accurate results

@@           Coverage Diff            @@
##           develop    #2373   +/-   ##
========================================
  Coverage    91.36%   91.36%           
========================================
  Files          440      440           
  Lines        16547    16547           
========================================
  Hits         15118    15118           
  Misses        1429     1429           

[migraphx-bot]

Test	Batch	Rate new 16cc67	Rate old 0a4254	Diff	Compare
torchvision-resnet50	64	2,848.50	nan	nan%	❌
torchvision-resnet50_fp16	64	6,478.07	6,474.16	0.06%	✅
torchvision-densenet121	32	2,081.59	2,101.68	-0.96%	✅
torchvision-densenet121_fp16	32	3,677.59	3,678.61	-0.03%	✅
torchvision-inceptionv3	32	1,594.17	1,593.70	0.03%	✅
torchvision-inceptionv3_fp16	32	2,589.92	2,589.65	0.01%	✅
cadene-inceptionv4	16	706.90	706.74	0.02%	✅
cadene-resnext64x4	16	697.08	696.92	0.02%	✅
slim-mobilenet	64	8,348.23	8,348.98	-0.01%	✅
slim-nasnetalarge	64	226.67	226.53	0.06%	✅
slim-resnet50v2	64	2,670.28	2,675.70	-0.20%	✅
bert-mrpc-onnx	8	824.26	825.03	-0.09%	✅
bert-mrpc-tf	1	390.38	389.87	0.13%	✅
pytorch-examples-wlang-gru	1	297.65	300.63	-0.99%	✅
pytorch-examples-wlang-lstm	1	311.61	313.31	-0.54%	✅
torchvision-resnet50_1	1	601.11	601.88	-0.13%	✅
torchvision-inceptionv3_1	1	339.10	335.92	0.95%	✅
cadene-dpn92_1	1	393.74	396.97	-0.81%	✅
cadene-resnext101_1	1	329.67	327.19	0.76%	✅
slim-vgg16_1	1	463.52	463.58	-0.01%	✅
slim-mobilenet_1	1	2,054.37	2,045.25	0.45%	✅
slim-inceptionv4_1	1	213.50	217.42	-1.80%	✅
onnx-taau-downsample	1	307.42	305.88	0.50%	✅
dlrm-criteoterabyte	1	21.66	21.68	-0.09%	✅
dlrm-criteoterabyte_fp16	1	40.73	40.74	-0.01%	✅
agentmodel	1	5,783.76	5,898.77	-1.95%	✅
unet_fp16	2	55.92	55.95	-0.05%	✅
resnet50v1_fp16	1	941.14	958.96	-1.86%	✅
bert_base_cased_fp16	64	969.98	969.75	0.02%	✅
bert_large_uncased_fp16	32	304.75	304.78	-0.01%	✅
bert_large_fp16	1	166.99	166.70	0.18%	✅
distilgpt2_fp16	16	1,276.21	1,277.20	-0.08%	✅

This build is not recommended to merge 🔴

[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

🔴torchvision-inceptionv3_1: FAILED: MIGraphX is not within tolerance - check verbose output

    :white_check_mark:cadene-dpn92_1: PASSED: MIGraphX meets tolerance

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

    :white_check_mark:slim-vgg16_1: PASSED: MIGraphX meets tolerance

    :white_check_mark:slim-mobilenet_1: PASSED: MIGraphX meets tolerance

🔴slim-inceptionv4_1: FAILED: MIGraphX is not within tolerance - check verbose output

    :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

🔴bert_base_cased_fp16: FAILED: MIGraphX is not within tolerance - check verbose output

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

    :white_check_mark:bert_large: PASSED: MIGraphX meets tolerance

🔴distilgpt2_fp16: FAILED: MIGraphX is not within tolerance - check verbose output