reorder_slice_add_mul matcher

[aarushjain29]

No description provided.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.17%. Comparing base (45b59bc) to head (3950cd3).
Report is 46 commits behind head on develop.

Additional details and impacted files

@@            Coverage Diff            @@
##           develop    #3478    +/-   ##
=========================================
  Coverage    92.16%   92.17%            
=========================================
  Files          512      513     +1     
  Lines        21403    21684   +281     
=========================================
+ Hits         19726    19987   +261     
- Misses        1677     1697    +20     

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

[pfultz2]

Unit tests needs to be added.

[pfultz2]

Remove this.

[pfultz2]

Move the literal generation to the loop below.

[pfultz2]

Remove this as well, just generate the literal directly.

[pfultz2]

Literals should be generated in the loop:

        for(int i = 0; i < 3; ++i)
        {
            auto lit1 = m1.add_literal(migraphx::generate_literal(s1, i));
            auto lit2 = m1.add_literal(migraphx::generate_literal(s2, i));
            auto dot_i = m1.add_instruction(migraphx::make_op("dot"), a, lit1);
            auto add_i = m1.add_instruction(migraphx::make_op("add"), dot_i, lit2);
            add_results.push_back(add_i);
        }

[pfultz2]

Generate literals in the loop:

        for(int i = 0; i < 3; ++i)
        {
            auto lit1 = m1.add_literal(migraphx::generate_literal(s2, i));
            auto lit2 = m1.add_literal(migraphx::generate_literal(s1, i));
            auto lit3 = m1.add_literal(migraphx::generate_literal(s2, i + 3));
            auto add_i = m1.add_instruction(migraphx::make_op("add"), a, lit1);
            auto dot_i = m1.add_instruction(migraphx::make_op("dot"), add_i, lit2);
            auto add_final =
                m1.add_instruction(migraphx::make_op("add"), dot_i, lit3);
            final_add_results.push_back(add_final);
        }

[migraphx-bot]

Test	Batch	Rate new 0d99d2	Rate old 871fd5	Diff	Compare
torchvision-resnet50	64	3,255.89	3,258.37	-0.08%	✅
torchvision-resnet50_fp16	64	6,986.11	6,985.89	0.00%	✅
torchvision-densenet121	32	2,435.59	2,434.83	0.03%	✅
torchvision-densenet121_fp16	32	4,075.57	4,096.10	-0.50%	✅
torchvision-inceptionv3	32	1,636.73	1,628.27	0.52%	✅
torchvision-inceptionv3_fp16	32	2,757.43	2,743.48	0.51%	✅
cadene-inceptionv4	16	776.22	765.47	1.40%	✅
cadene-resnext64x4	16	810.14	808.90	0.15%	✅
slim-mobilenet	64	7,533.63	7,462.01	0.96%	✅
slim-nasnetalarge	64	211.53	208.42	1.49%	✅
slim-resnet50v2	64	3,504.76	3,439.75	1.89%	✅
bert-mrpc-onnx	8	1,144.61	1,150.01	-0.47%	✅
bert-mrpc-tf	1	467.21	480.28	-2.72%	✅
pytorch-examples-wlang-gru	1	534.67	417.96	27.92%	🔆
pytorch-examples-wlang-lstm	1	393.46	381.48	3.14%	🔆
torchvision-resnet50_1	1	788.10	785.76	0.30%	✅
cadene-dpn92_1	1	398.61	436.17	-8.61%	🔴
cadene-resnext101_1	1	382.93	382.70	0.06%	✅
onnx-taau-downsample	1	342.47	345.53	-0.88%	✅
dlrm-criteoterabyte	1	33.34	33.33	0.02%	✅
dlrm-criteoterabyte_fp16	1	52.72	52.73	-0.02%	✅
agentmodel	1	9,410.44	8,218.68	14.50%	🔆
unet_fp16	2	58.83	58.88	-0.08%	✅
resnet50v1_fp16	1	939.59	921.67	1.94%	✅
resnet50v1_int8	1	1,035.51	1,011.55	2.37%	✅
bert_base_cased_fp16	64	1,171.13	1,168.76	0.20%	✅
bert_large_uncased_fp16	32	363.77	363.10	0.18%	✅
bert_large_fp16	1	200.44	200.24	0.10%	✅
distilgpt2_fp16	16	2,199.13	2,194.57	0.21%	✅
yolov5s	1	544.28	530.30	2.64%	✅
tinyllama	1	43.38	43.40	-0.05%	✅
vicuna-fastchat	1	175.14	168.83	3.74%	🔆
whisper-tiny-encoder	1	416.41	417.90	-0.36%	✅
whisper-tiny-decoder	1	436.98	427.53	2.21%	✅

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