Rewrite 1x1 convolutions to gemm

[pfultz2]

This allows us to use rocblas for some gemms.

[shivadbhavsar]

Might be worthwhile to have a 1x1x1 test case too since its allowed here to make sure it generalizes to the 3D case

[migraphx-bot]

Test	Batch	Rate new 84a941	Rate old 71fd27	Diff	Compare
torchvision-resnet50	64	3,124.05	3,258.47	-4.13%	🔴
torchvision-resnet50_fp16	64	6,649.81	6,989.35	-4.86%	🔴
torchvision-densenet121	32	2,428.73	2,437.00	-0.34%	✅
torchvision-densenet121_fp16	32	4,077.64	4,070.38	0.18%	✅
torchvision-inceptionv3	32	1,630.56	1,639.85	-0.57%	✅
torchvision-inceptionv3_fp16	32	2,730.00	2,763.41	-1.21%	✅
cadene-inceptionv4	16	759.80	776.50	-2.15%	✅
cadene-resnext64x4	16	678.47	808.24	-16.06%	🔴
slim-mobilenet	64	7,488.79	7,538.65	-0.66%	✅
slim-nasnetalarge	64	nan	211.54	nan%	❌
slim-resnet50v2	64	3,284.27	3,507.21	-6.36%	🔴
bert-mrpc-onnx	8	1,148.87	1,150.51	-0.14%	✅
bert-mrpc-tf	1	464.17	475.19	-2.32%	✅
pytorch-examples-wlang-gru	1	515.53	426.61	20.84%	🔆
pytorch-examples-wlang-lstm	1	386.85	376.26	2.81%	✅
torchvision-resnet50_1	1	704.37	785.19	-10.29%	🔴
cadene-dpn92_1	1	408.01	399.09	2.24%	✅
cadene-resnext101_1	1	325.51	383.01	-15.01%	🔴
onnx-taau-downsample	1	343.43	343.03	0.12%	✅
dlrm-criteoterabyte	1	33.33	33.33	0.01%	✅
dlrm-criteoterabyte_fp16	1	52.76	52.73	0.06%	✅
agentmodel	1	8,392.57	8,178.96	2.61%	✅
unet_fp16	2	58.68	58.92	-0.41%	✅
resnet50v1_fp16	1	886.30	925.30	-4.22%	🔴
resnet50v1_int8	1	1,022.34	1,011.55	1.07%	✅
bert_base_cased_fp16	64	1,170.96	1,169.93	0.09%	✅
bert_large_uncased_fp16	32	355.40	363.31	-2.18%	✅
bert_large_fp16	1	192.32	200.50	-4.08%	🔴
distilgpt2_fp16	16	2,200.66	2,194.69	0.27%	✅
yolov5s	1	545.09	533.06	2.26%	✅
tinyllama	1	43.47	43.45	0.04%	✅
vicuna-fastchat	1	175.62	172.29	1.94%	✅
whisper-tiny-encoder	1	417.46	417.95	-0.12%	✅
whisper-tiny-decoder	1	428.13	425.65	0.58%	✅

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