Set attribute to help bypass the warning about amdgpu_waves_per_eu

[lakhinderwalia]

The upgraded tool chain is giving a new compile warning that needs to be bypassed for the topk test to successfully compile, and run.

[ RUN ] test_topk<migraphx::shape::half_type, 1000, 120000>
/tmp/comgr-d7a292/input/main.cpp:11:22: error: failed to meet occupancy target given by 'amdgpu-waves-per-eu' in 'topk_kernel': desired occupancy was 2, final occupancy is 1 [-Werror,-Wpass-failed]

[pfultz2]

We should be disabling the warning or setting the warning to -Wno-error instead of setting this attribute.

[pfultz2]

This could have a performance impact setting this especially for all kernels. Its best to use the defaults set by the compiler.

[lakhinderwalia]

This is a range specification, where 1 at its lower end (of the range) is being for some reason excluded in a certain version -- that should be separately investigated elsewhere. This is a hint to the compiler, of the range, and so the compiler should be free to pick whatever it should from an expanded range. You should only see a performance impact, logically speaking, if we were to constrict the range specification above. Whereas I have made it as wide as possible.

In the change above, there should be no performance impact. Thanks.

[pfultz2]

The compiler doesn't use the widest range by default. It sets the range based on the block size and properties of the hardware. By widening the range we can lose some optimizations that comes from the more restrictive range.

[lakhinderwalia]

While we try to resolve this, please take a look at PR 4226, so we can resolve QA issues, the main goal here.

[migraphx-bot]

Test	Batch	Rate new 918283	Rate old 018cae	Diff	Compare
torchvision-resnet50	64	3,247.40	3,248.22	-0.03%	✅
torchvision-resnet50_fp16	64	6,961.71	6,961.14	0.01%	✅
torchvision-densenet121	32	2,450.76	2,449.97	0.03%	✅
torchvision-densenet121_fp16	32	4,170.57	4,164.44	0.15%	✅
torchvision-inceptionv3	32	1,636.60	1,636.10	0.03%	✅
torchvision-inceptionv3_fp16	32	2,760.19	2,752.74	0.27%	✅
cadene-inceptionv4	16	771.57	771.22	0.04%	✅
cadene-resnext64x4	16	818.91	818.68	0.03%	✅
slim-mobilenet	64	7,460.56	7,459.63	0.01%	✅
slim-nasnetalarge	64	211.06	211.08	-0.01%	✅
slim-resnet50v2	64	3,344.50	3,342.04	0.07%	✅
bert-mrpc-onnx	8	1,145.14	1,145.42	-0.02%	✅
bert-mrpc-tf	1	445.65	442.53	0.70%	✅
pytorch-examples-wlang-gru	1	294.77	298.60	-1.28%	✅
pytorch-examples-wlang-lstm	1	404.81	411.85	-1.71%	✅
torchvision-resnet50_1	1	767.18	767.54	-0.05%	✅
cadene-dpn92_1	1	386.19	392.42	-1.59%	✅
cadene-resnext101_1	1	392.00	393.79	-0.45%	✅
onnx-taau-downsample	1	395.74	395.77	-0.01%	✅
dlrm-criteoterabyte	1	33.76	33.77	-0.03%	✅
dlrm-criteoterabyte_fp16	1	51.24	51.25	-0.02%	✅
agentmodel	1	8,334.03	8,931.04	-6.68%	🔴
unet_fp16	2	59.14	59.14	0.01%	✅
resnet50v1_fp16	1	980.63	978.22	0.25%	✅
resnet50v1_int8	1	1,030.81	1,025.85	0.48%	✅
bert_base_cased_fp16	64	1,107.47	1,107.56	-0.01%	✅
bert_large_uncased_fp16	32	345.29	345.42	-0.04%	✅
bert_large_fp16	1	197.48	196.96	0.26%	✅
distilgpt2_fp16	16	2,117.26	2,118.48	-0.06%	✅
yolov5s	1	566.10	570.35	-0.75%	✅
tinyllama	1	43.95	43.98	-0.07%	✅
vicuna-fastchat	1	45.27	45.38	-0.22%	✅
whisper-tiny-encoder	1	417.62	417.79	-0.04%	✅
whisper-tiny-decoder	1	400.51	409.99	-2.31%	✅
llama2_7b	1	19.16	19.16	0.00%	✅
qwen1.5-7b	1	23.53	23.54	-0.02%	✅
phi3-3.8b	1	26.70	26.67	0.10%	✅
mask-rcnn	1	12.51	12.44	0.57%	✅
llama3-8b	1	21.72	21.73	-0.05%	✅
whisper-large-encoder	1	10.22	10.22	-0.01%	✅
whisper-large-decoder	1	96.60	96.35	0.26%	✅
mistral-7b	1	23.73	23.74	-0.05%	✅
FLUX.1-schnell	1	738.85	742.55	-0.50%	✅
nan	nan	nan	nan	nan%	❌

This build is not recommended to merge 🔴

[migraphx-bot]

     ✅ bert-mrpc-onnx: PASSED: MIGraphX meets tolerance

❌bert-mrpc-tf: ERROR - check error output

error: unknown warning option '-Wnrvo' [-Werror,-Wunknown-warning-option]

error: unknown warning option '-Wnrvo' [-Werror,-Wunknown-warning-option]

2025-08-08 16:42:13.363812: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: SSE3 SSE4.1 SSE4.2 AVX AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1754689338.796337 173517 gpu_device.cc:2022] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 62951 MB memory: -> device: 0, name: AMD Instinct MI250X/MI250, pci bus id: 0000:b3:00.0
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1754689339.695586 173517 mlir_graph_optimization_pass.cc:401] MLIR V1 optimization pass is not enabled
2025-08-08 16:42:28.331802: E external/local_xla/xla/service/gpu/llvm_gpu_backend/gpu_backend_lib.cc:250] bitcode module is required by this HLO module but was not found at ./opencl.bc
2025-08-08 16:42:28.331993: E external/local_xla/xla/service/gpu/llvm_gpu_backend/gpu_backend_lib.cc:250] bitcode module is required by this HLO module but was not found at ./opencl.bc
2025-08-08 16:42:28.332063: E external/local_xla/xla/service/gpu/llvm_gpu_backend/gpu_backend_lib.cc:250] bitcode module is required by this HLO module but was not found at ./opencl.bc
2025-08-08 16:42:28.332117: E external/local_xla/xla/service/gpu/llvm_gpu_backend/gpu_backend_lib.cc:250] bitcode module is required by this HLO module but was not found at ./opencl.bc
2025-08-08 16:42:28.332162: E external/local_xla/xla/service/gpu/llvm_gpu_backend/gpu_backend_lib.cc:250] bitcode module is required by this HLO module but was not found at ./opencl.bc
2025-08-08 16:42:28.332192: E external/local_xla/xla/service/gpu/llvm_gpu_backend/gpu_backend_lib.cc:250] bitcode module is required by this HLO module but was not found at ./opencl.bc
2025-08-08 16:42:28.332243: E external/local_xla/xla/service/gpu/llvm_gpu_backend/gpu_backend_lib.cc:250] bitcode module is required by this HLO module but was not found at ./opencl.bc
2025-08-08 16:42:28.332293: E external/local_xla/xla/service/gpu/llvm_gpu_backend/gpu_backend_lib.cc:250] bitcode module is required by this HLO module but was not found at ./opencl.bc
error: Failure when generating HSACO
error: Failure when generating HSACO
error: Failure when generating HSACO
error: Failure when generating HSACO
error: Failure when generating HSACO
error: Failure when generating HSACO
error: Failure when generating HSACO
error: Failure when generating HSACO
2025-08-08 16:42:28.333307: E tensorflow/compiler/mlir/tools/kernel_gen/tf_framework_c_interface.cc:228] INTERNAL: Generating device code failed.
2025-08-08 16:42:28.334401: W tensorflow/core/framework/op_kernel.cc:1829] UNKNOWN: JIT compilation failed.
2025-08-08 16:42:28.334420: I tensorflow/core/framework/local_rendezvous.cc:405] Local rendezvous is aborting with status: UNKNOWN: JIT compilation failed.
[[{{node import/bert/embeddings/LayerNorm/moments/SquaredDifference}}]]
2025-08-08 16:42:28.334431: I tensorflow/core/framework/local_rendezvous.cc:405] Local rendezvous is aborting with status: UNKNOWN: JIT compilation failed.
[[{{node import/bert/embeddings/LayerNorm/moments/SquaredDifference}}]]
[[import/loss/output/_21]]
2025-08-08 16:42:28.334448: I tensorflow/core/framework/local_rendezvous.cc:424] Local rendezvous recv item cancelled. Key hash: 11217777527359497193
Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/client/session.py", line 1407, in _do_call
return fn(*args)
File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/client/session.py", line 1390, in _run_fn
return self._call_tf_sessionrun(options, feed_dict, fetch_list,
File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/client/session.py", line 1483, in _call_tf_sessionrun
return tf_session.TF_SessionRun_wrapper(self._session, options, feed_dict,
tensorflow.python.framework.errors_impl.UnknownError: 2 root error(s) found.
(0) UNKNOWN: JIT compilation failed.
[[{{node import/bert/embeddings/LayerNorm/moments/SquaredDifference}}]]
[[import/loss/output/_21]]
(1) UNKNOWN: JIT compilation failed.
[[{{node import/bert/embeddings/LayerNorm/moments/SquaredDifference}}]]
0 successful operations.
0 derived errors ignored.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 359, in
main()
File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 335, in main
y_out = sess.run(y, feed_dict=tf_dict)
File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/client/session.py", line 977, in run
result = self._run(None, fetches, feed_dict, options_ptr,
File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/client/session.py", line 1220, in _run
results = self._do_run(handle, final_targets, final_fetches,
File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/client/session.py", line 1400, in _do_run
return self._do_call(_run_fn, feeds, fetches, targets, options,
File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/client/session.py", line 1426, in _do_call
raise type(e)(node_def, op, message) # pylint: disable=no-value-for-parameter
tensorflow.python.framework.errors_impl.UnknownError: Graph execution error:

Detected at node 'import/bert/embeddings/LayerNorm/moments/SquaredDifference' defined at (most recent call last):
Node: 'import/bert/embeddings/LayerNorm/moments/SquaredDifference'
Detected at node 'import/bert/embeddings/LayerNorm/moments/SquaredDifference' defined at (most recent call last):
Node: 'import/bert/embeddings/LayerNorm/moments/SquaredDifference'
2 root error(s) found.
(0) UNKNOWN: JIT compilation failed.
[[{{node import/bert/embeddings/LayerNorm/moments/SquaredDifference}}]]
[[import/loss/output/_21]]
(1) UNKNOWN: JIT compilation failed.
[[{{node import/bert/embeddings/LayerNorm/moments/SquaredDifference}}]]
0 successful operations.
0 derived errors ignored.

Original stack trace for 'import/bert/embeddings/LayerNorm/moments/SquaredDifference':

     ✅ 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: FAILED: MIGraphX is not within tolerance - check verbose output

     ✅ 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

     ✅ llama2_7b: PASSED: MIGraphX meets tolerance

     ✅ qwen1.5-7b: PASSED: MIGraphX meets tolerance

     ✅ phi3-3.8b: PASSED: MIGraphX meets tolerance

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

     ✅ llama3-8b: PASSED: MIGraphX meets tolerance

     ✅ whisper-large-decoder: PASSED: MIGraphX meets tolerance

     ✅ mistral-7b: PASSED: MIGraphX meets tolerance

     ✅ FLUX.1-schnell: PASSED: MIGraphX meets tolerance