Skip to content

Debug symbols docs update#4985

Merged
causten merged 3 commits into
developfrom
debug_symbols_docs_update
Jun 18, 2026
Merged

Debug symbols docs update#4985
causten merged 3 commits into
developfrom
debug_symbols_docs_update

Conversation

@CharlieL7

@CharlieL7 CharlieL7 commented Jun 17, 2026

Copy link
Copy Markdown
Collaborator

Motivation

  • Improve the documentation for debug symbols with Netron usage and horizontal fusion example.

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.

@CharlieL7 CharlieL7 self-assigned this Jun 17, 2026
Copilot AI review requested due to automatic review settings June 17, 2026 19:52
@CharlieL7 CharlieL7 requested review from a team and causten as code owners June 17, 2026 19:52
@CharlieL7 CharlieL7 added simple small or simple changes skip bot checks Skips the Performance and Accuracy CI tests labels Jun 17, 2026
Copilot AI reviewed Jun 17, 2026
View reviewed changes

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR updates the developer documentation for MIGraphX debug symbols, expanding guidance on how to enable and inspect symbols across different workflows (driver, Python, and Netron) and adding an additional example illustrating symbol propagation through horizontal fusion.

Changes:

  • Fix the C++ example to use the onnx_options::set_use_debug_symbols(...) API.
  • Document Python parse_onnx(..., use_debug_symbols=True) usage for enabling debug symbols.
  • Add examples for symbol propagation during horizontal fusion and add a Netron-based visualization workflow (including an image).

Comment thread docs/dev/debug_symbols.rst
Comment on lines 33 to 36
{
migraphx::onnx_options options;
options.set_use_debug_symbols = true;
options.set_use_debug_symbols(true);
auto prog = migraphx::parse_onnx("conv_transpose_test.onnx", options);
@CharlieL7 CharlieL7 requested a review from eddieliao June 17, 2026 20:45
@gh-app-migraphx-bot-pr-write

gh-app-migraphx-bot-pr-write Bot commented Jun 18, 2026

Copy link
Copy Markdown
Test Batch New Rate (22586f) Old Rate (241f7a)* Diff Status
torchvision-resnet50 64 2,973.70 3,158.05 -5.84% 🔴
torchvision-resnet50_fp16 64 6,059.92 6,678.10 -9.26% 🔴
torchvision-densenet121 32 2,210.23 2,705.33 -18.30% 🔴
torchvision-densenet121_fp16 32 2,298.27 4,480.31 -48.70% 🔴
torchvision-inceptionv3 32 338.02 1,772.37 -80.93% 🔴
torchvision-inceptionv3_fp16 32 1,715.29 2,613.31 -34.36% 🔴
cadene-inceptionv4 16 709.82 444.89 59.55% 🔆
cadene-resnext64x4 16 781.78 412.50 89.52% 🔆
slim-mobilenet 64 8,260.76 8,419.17 -1.88% ✅
slim-nasnetalarge 64 196.09 nan nan ❌
slim-resnet50v2 64 3,111.90 1,641.82 89.54% 🔆
bert-mrpc-onnx 8 1,171.77 1,165.20 0.56% ✅
bert-mrpc-tf 1 442.79 492.10 -10.02% 🔴
pytorch-examples-wlang-gru 1 332.36 334.96 -0.77% ✅
pytorch-examples-wlang-lstm 1 228.22 469.54 -51.40% 🔴
torchvision-resnet50_1 1 677.30 760.64 -10.96% 🔴
cadene-dpn92_1 1 276.52 457.65 -39.58% 🔴
cadene-resnext101_1 1 338.26 363.68 -6.99% 🔴
onnx-taau-downsample 1 400.43 401.93 -0.37% ✅
dlrm-criteoterabyte 1 1.11 12.36 -91.01% 🔴
dlrm-criteoterabyte_fp16 1 51.82 29.66 74.73% 🔆
agentmodel 1 10,971.85 10,523.13 4.26% ✅
unet_fp16 2 17.75 57.23 -68.99% 🔴
resnet50v1_fp16 1 931.17 959.87 -2.99% ✅
resnet50v1_int8 1 931.80 942.92 -1.18% ✅
bert_base_cased_fp16 64 1,093.66 1,092.47 0.11% ✅
bert_large_uncased_fp16 32 316.56 345.19 -8.29% 🔴
bert_large_fp16 1 205.83 203.23 1.28% ✅
distilgpt2_fp16 16 2,090.27 2,096.77 -0.31% ✅
yolov5s 1 564.97 564.74 0.04% ✅
tinyllama 1 45.87 46.00 -0.28% ✅
vicuna-fastchat 1 44.03 44.04 -0.01% ✅
whisper-tiny-encoder 1 415.91 419.55 -0.87% ✅
whisper-tiny-decoder 1 416.47 414.85 0.39% ✅
llama2_7b 1 20.34 20.42 -0.38% ✅
qwen1.5-7b 1 23.59 21.75 8.44% 🔆
phi3-3.8b 1 26.65 26.81 -0.60% ✅
llama3-8b 1 21.72 21.83 -0.53% ✅
whisper-large-encoder 1 10.25 6.50 57.85% 🔆
whisper-large-decoder 1 88.94 106.80 -16.73% 🔴
mistral-7b 1 23.74 23.85 -0.47% ✅
FLUX.1-schnell 1 752.72 763.88 -1.46% ✅

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

gh-app-migraphx-bot-pr-write Bot commented Jun 18, 2026

Copy link
Copy Markdown
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
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
llama3-8b ✅ PASSED: MIGraphX meets tolerance
whisper-large-encoder ❌ ERROR - check error output
traceback
2026-06-17 19:07:03.548225 [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

@causten causten merged commit f54ca35 into develop Jun 18, 2026
43 of 47 checks passed
@causten causten deleted the debug_symbols_docs_update branch June 18, 2026 01:43
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

Copilot code review Copilot Copilot left review comments

@kahmed10 kahmed10 kahmed10 approved these changes

@eddieliao eddieliao eddieliao approved these changes

@TedThemistokleous TedThemistokleous Awaiting requested review from TedThemistokleous

@causten causten Awaiting requested review from causten causten is a code owner

Assignees

@CharlieL7 CharlieL7

Labels

simple small or simple changes skip bot checks Skips the Performance and Accuracy CI tests

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

5 participants

@CharlieL7 @kahmed10 @eddieliao @causten