Revert "Revert "Fixed instruction::replace() logic. ""

[causten]

This PR is PR#3553 Something is failing in Jenkins CI that will need to be addressed

[migraphx-bot]

Test	Batch	Rate new c7e2d8	Rate old 71fd27	Diff	Compare
torchvision-resnet50	64	3,259.44	3,258.47	0.03%	:white_check_mark:
torchvision-resnet50_fp16	64	nan	6,989.35	nan%	:x:
torchvision-densenet121	32	2,436.33	2,437.00	-0.03%	:white_check_mark:
torchvision-densenet121_fp16	32	nan	4,070.38	nan%	:x:
torchvision-inceptionv3	32	1,637.78	1,639.85	-0.13%	:white_check_mark:
torchvision-inceptionv3_fp16	32	nan	2,763.41	nan%	:x:
cadene-inceptionv4	16	777.44	776.50	0.12%	:white_check_mark:
cadene-resnext64x4	16	811.03	808.24	0.35%	:white_check_mark:
slim-mobilenet	64	7,537.85	7,538.65	-0.01%	:white_check_mark:
slim-nasnetalarge	64	211.51	211.54	-0.01%	:white_check_mark:
slim-resnet50v2	64	nan	3,507.21	nan%	:x:
bert-mrpc-onnx	8	1,148.87	1,150.51	-0.14%	:white_check_mark:
bert-mrpc-tf	1	466.56	475.19	-1.82%	:white_check_mark:
pytorch-examples-wlang-gru	1	428.79	426.61	0.51%	:white_check_mark:
pytorch-examples-wlang-lstm	1	384.62	376.26	2.22%	:white_check_mark:
torchvision-resnet50_1	1	801.87	785.19	2.12%	:white_check_mark:
cadene-dpn92_1	1	435.11	399.09	9.03%	:high_brightness:
cadene-resnext101_1	1	384.96	383.01	0.51%	:white_check_mark:
onnx-taau-downsample	1	nan	343.03	nan%	:x:
dlrm-criteoterabyte	1	33.34	33.33	0.05%	:white_check_mark:
dlrm-criteoterabyte_fp16	1	52.73	52.73	0.01%	:white_check_mark:
agentmodel	1	8,427.79	8,178.96	3.04%	:high_brightness:
unet_fp16	2	nan	58.92	nan%	:x:
resnet50v1_fp16	1	nan	925.30	nan%	:x:
resnet50v1_int8	1	nan	1,011.55	nan%	:x:
bert_base_cased_fp16	64	nan	1,169.93	nan%	:x:
bert_large_uncased_fp16	32	nan	363.31	nan%	:x:
bert_large_fp16	1	nan	200.50	nan%	:x:
distilgpt2_fp16	16	nan	2,194.69	nan%	:x:
yolov5s	1	544.51	533.06	2.15%	:white_check_mark:
tinyllama	1	nan	43.45	nan%	:x:
vicuna-fastchat	1	174.38	172.29	1.22%	:white_check_mark:
whisper-tiny-encoder	1	418.71	417.95	0.18%	:white_check_mark:
whisper-tiny-decoder	1	nan	425.65	nan%	:x:

This build is not recommended to merge :red_circle:

[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

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

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

     :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

:x:bert_base_cased_fp16: ERROR - check error output

:x:bert_large_uncased_fp16: ERROR - check error output

     :white_check_mark: bert_large: PASSED: MIGraphX meets tolerance

     :white_check_mark: yolov5s: PASSED: MIGraphX meets tolerance

:x:tinyllama: ERROR - check error output

     :white_check_mark: vicuna-fastchat: PASSED: MIGraphX meets tolerance

     :white_check_mark: whisper-tiny-encoder: PASSED: MIGraphX meets tolerance

:x:whisper-tiny-decoder: ERROR - check error output

:x:distilgpt2_fp16: ERROR - check error output

[tcgu-amd]

@causten I created another PR https://github.com/ROCm/AMDMIGraphX/pull/3574 that has the fixed the version. It passed the Azure CI tests; just trying to get it past tidy and a few other checks. Thanks!

[causten]

Already reverted