Improve picking max block size

[pfultz2]

Motivation

Technical Details

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.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #4958      +/-   ##
===========================================
+ Coverage    92.71%   92.72%   +0.01%     
===========================================
  Files          589      590       +1     
  Lines        31160    31233      +73     
===========================================
+ Hits         28888    28960      +72     
- Misses        2272     2273       +1     

see 1 file with indirect coverage changes

🚀 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 (2eccfd)	Old Rate (32632f)	Diff	Status
torchvision-resnet50	64	981.28	1,318.83	-25.59%	🔴
torchvision-resnet50_fp16	64	3,449.65	2,631.70	31.08%	🔆
torchvision-densenet121	32	2,537.09	2,519.25	0.71%	✅
torchvision-densenet121_fp16	32	4,119.51	627.96	556.01%	🔆
torchvision-inceptionv3	32	649.13	1,717.02	-62.19%	🔴
torchvision-inceptionv3_fp16	32	469.50	286.00	64.16%	🔆
cadene-inceptionv4	16	160.11	124.09	29.03%	🔆
cadene-resnext64x4	16	328.48	744.84	-55.90%	🔴
slim-mobilenet	64	5,969.09	8,388.21	-28.84%	🔴
slim-nasnetalarge	64	164.48	124.79	31.81%	🔆
slim-resnet50v2	64	1,418.97	1,253.10	13.24%	🔆
bert-mrpc-onnx	8	542.81	652.82	-16.85%	🔴
bert-mrpc-tf	1	66.86	485.34	-86.22%	🔴
pytorch-examples-wlang-gru	1	30.96	375.24	-91.75%	🔴
pytorch-examples-wlang-lstm	1	192.99	462.74	-58.29%	🔴
torchvision-resnet50_1	1	564.54	771.86	-26.86%	🔴
cadene-dpn92_1	1	446.79	472.97	-5.54%	🔴
cadene-resnext101_1	1	364.24	363.38	0.24%	✅
onnx-taau-downsample	1	358.97	365.31	-1.74%	✅
dlrm-criteoterabyte	1	0.75	27.57	-97.27%	🔴
dlrm-criteoterabyte_fp16	1	39.41	43.92	-10.28%	🔴
agentmodel	1	9,083.81	9,792.59	-7.24%	🔴
unet_fp16	2	5.31	44.26	-88.01%	🔴
resnet50v1_fp16	1	18.99	969.36	-98.04%	🔴
resnet50v1_int8	1	77.81	98.82	-21.26%	🔴
bert_base_cased_fp16	64	333.60	536.11	-37.77%	🔴
bert_large_uncased_fp16	32	317.48	237.93	33.44%	🔆
bert_large_fp16	1	121.50	62.82	93.42%	🔆
distilgpt2_fp16	16	2,095.93	1,000.04	109.58%	🔆
yolov5s	1	564.05	493.39	14.32%	🔆
tinyllama	1	40.33	25.42	58.70%	🔆
vicuna-fastchat	1	43.97	9.47	364.11%	🔆
whisper-tiny-encoder	1	249.37	114.66	117.49%	🔆
whisper-tiny-decoder	1	83.76	100.84	-16.94%	🔴
llama2_7b	1	18.14	19.49	-6.93%	🔴
qwen1.5-7b	1	12.09	23.65	-48.88%	🔴
phi3-3.8b	1	26.86	2.19	1124.30%	🔆
llama3-8b	1	10.29	3.34	208.06%	🔆
whisper-large-encoder	1	7.92	10.29	-23.05%	🔴
whisper-large-decoder	1	96.46	106.86	-9.74%	🔴
mistral-7b	1	7.10	23.60	-69.92%	🔴
FLUX.1-schnell	1	137.01	759.86	-81.97%	🔴

Regressions detected 🔴

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

Test	Status	Result
bert-mrpc-onnx	✅	PASSED: MIGraphX meets tolerance
bert-mrpc-tf	❌	ERROR - check error output traceback Traceback (most recent call last): File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 377, in main() File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 313, in main import tensorflow as tf File "/usr/local/lib/python3.10/dist-packages/tensorflow/init.py", line 38, in from tensorflow.python.tools import module_util as _module_util File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/init.py", line 36, in from tensorflow.python import pywrap_tensorflow as _pywrap_tensorflow File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/pywrap_tensorflow.py", line 26, in self_check.preload_check() File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/platform/self_check.py", line 63, in preload_check from tensorflow.python.platform import _pywrap_cpu_feature_guard ImportError: libamdhip64.so.6: cannot open shared object file: No such file or directory
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
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	❌	ERROR - check error output traceback 2026-06-12 18:05:06.967511 [WARN] [/data/src/onnx/onnx_parser.cpp:282] Model has unbound symbolic dimension(s): batch_size, encoder_sequence_length, feature_size. These default to 1 and may cause unexpected behavior. Try setting --dim-param @<name> <value> or --input-dim @<input> <dims> if program compilation fails. Traceback (most recent call last): File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 377, in main() File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 224, in main model = migraphx.parse_onnx(model_name, default_dim_value=batch) RuntimeError: /data/src/include/migraphx/op/convolution.hpp:113: normalize_compute_shape: CONVOLUTION: mismatched channel numbers: input channels (1) != weights channels (80) * group (1)
whisper-large-decoder	✅	PASSED: MIGraphX meets tolerance
mistral-7b	✅	PASSED: MIGraphX meets tolerance
FLUX.1-schnell	✅	PASSED: MIGraphX meets tolerance