MIGraphX build support for MacOS (ref)

[kahmed10]

Motivation

experimental changes to actually build on MacOS and run ref target for the time being.

Technical Details

Required some changes like explicit type casting in order to compile.

Changelog Category

Add a CHANGELOG.md entry for any option other than Not Applicable

• • Added: New functionality.
• • Changed: Changes to existing functionality.
• • Removed: Functionality or support that has been removed. (Compared to a previous release)
• • Optimized: Component performance that has been optimized or improved.
• • Resolved Issues: Known issues from a previous version that have been resolved.
• • Not Applicable: This PR is not to be included in the changelog.

Follow the LLVM AI Tool Use Policy for contributions using AI.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #5073   +/-   ##
========================================
  Coverage    92.90%   92.90%           
========================================
  Files          603      603           
  Lines        32526    32528    +2     
========================================
+ Hits         30217    30219    +2     
  Misses        2309     2309           

Files with missing lines	Coverage Δ
src/fileutils.cpp	100.00% <ø> (ø)
src/include/migraphx/generic_float.hpp	97.39% <ø> (ø)
src/include/migraphx/verify.hpp	75.00% <100.00%> (ø)
src/simplify_dyn_ops.cpp	99.37% <100.00%> (+<0.01%)	⬆️

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[gh-app-migraphx-bot-pr-write]

Test	Batch	New Rate (802dd6)	Old Rate (939a41)*	Diff	Status
torchvision-resnet50	64	1,282.51	3,137.65	-59.13%	🔴
torchvision-resnet50_fp16	64	1,908.22	6,664.17	-71.37%	🔴
torchvision-densenet121	32	606.73	2,696.53	-77.50%	🔴
torchvision-densenet121_fp16	32	1,365.88	4,546.91	-69.96%	🔴
torchvision-inceptionv3	32	1,883.90	1,789.44	5.28%	🔆
torchvision-inceptionv3_fp16	32	4,421.12	2,837.26	55.82%	🔆
cadene-inceptionv4	16	822.63	820.89	0.21%	✅
cadene-resnext64x4	16	538.91	584.90	-7.86%	🔴
slim-mobilenet	64	7,573.23	7,391.43	2.46%	✅
slim-nasnetalarge	64	126.32	208.95	-39.55%	🔴
slim-resnet50v2	64	1,903.24	2,401.77	-20.76%	🔴
bert-mrpc-onnx	8	1,170.04	888.28	31.72%	🔆
bert-mrpc-tf	1	502.13	369.82	35.78%	🔆
pytorch-examples-wlang-gru	1	278.92	482.91	-42.24%	🔴
pytorch-examples-wlang-lstm	1	381.41	436.18	-12.56%	🔴
torchvision-resnet50_1	1	344.39	699.41	-50.76%	🔴
cadene-dpn92_1	1	440.98	442.31	-0.30%	✅
cadene-resnext101_1	1	293.46	364.07	-19.40%	🔴
onnx-taau-downsample	1	848.76	401.79	111.24%	🔆
dlrm-criteoterabyte	1	1.09	31.86	-96.58%	🔴
dlrm-criteoterabyte_fp16	1	43.20	51.73	-16.49%	🔴
agentmodel	1	9,062.32	12,642.67	-28.32%	🔴
unet_fp16	2	10.95	57.08	-80.81%	🔴
resnet50v1_fp16	1	256.57	943.42	-72.80%	🔴
resnet50v1_int8	1	1,670.18	935.85	78.47%	🔆
bert_base_cased_fp16	64	1,045.69	1,072.35	-2.49%	✅
bert_large_uncased_fp16	32	317.81	342.15	-7.11%	🔴
bert_large_fp16	1	81.05	80.24	1.01%	✅
distilgpt2_fp16	16	2,062.67	859.88	139.88%	🔆
yolov5s	1	560.59	526.66	6.44%	🔆
tinyllama	1	35.96	45.81	-21.51%	🔴
vicuna-fastchat	1	43.96	44.09	-0.30%	✅
whisper-tiny-encoder	1	413.71	412.40	0.32%	✅
whisper-tiny-decoder	1	411.62	410.21	0.34%	✅
llama2_7b	1	20.98	20.70	1.37%	✅
qwen1.5-7b	1	23.66	23.58	0.35%	✅
phi3-3.8b	1	26.82	26.47	1.33%	✅
llama3-8b	1	11.29	21.78	-48.15%	🔴
whisper-large-encoder	1	10.21	10.16	0.56%	✅
whisper-large-decoder	1	105.17	105.84	-0.63%	✅
mistral-7b	1	23.84	23.72	0.50%	✅
FLUX.1-schnell	1	742.79	771.10	-3.67%	✅

Regressions detected 🔴

* No develop baseline was found for this PR's branch point; compared against the latest available develop run instead.

[gh-app-migraphx-bot-pr-write]

Test	Status	Result
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
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
llama2_7b	✅	PASSED: MIGraphX meets tolerance
qwen1.5-7b	✅	PASSED: MIGraphX meets tolerance
phi3-3.8b	✅	PASSED: MIGraphX meets tolerance
llama3-8b	✅	PASSED: MIGraphX meets tolerance
whisper-large-encoder	✅	PASSED: MIGraphX meets tolerance
whisper-large-decoder	✅	PASSED: MIGraphX meets tolerance
mistral-7b	✅	PASSED: MIGraphX meets tolerance
FLUX.1-schnell	✅	PASSED: MIGraphX meets tolerance