flagos-ai / flagos-ai/FlagBLAS

TBSV accuray ci test fail in hygon

Open
#88 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
3
Forks
7
Avg merge
11h 54m
Merged PRs (30d)
38

Description

Run source .venv/bin/activate
WARNING: /opt/hyhal/lib/cmake/rocm_smi doesn't exist, please install the latest driver(version >= 6.3.15)
The rocm_smi_lib will be used in default
WARNING: /opt/hyhal/lib/cmake/rocm_smi doesn't exist, please install the latest driver(version >= 6.3.15)
The rocm_smi_lib will be used in default
Sourced Hygon DTK environment: /opt/dtk-26.04/env.sh
LD_LIBRARY_PATH=/opt/dtk-26.04/dcc/gcvm/lib:/opt/dtk-26.04/hip/lib:/opt/dtk-26.04/llvm/lib:/opt/dtk-26.04/lib:/opt/dtk-26.04/lib64:/opt/hyhal/lib:/opt/hyhal/lib64:/opt/dtk-26.04/dushmem/lib:/opt/dtk-26.04/opencl/lib:/opt/dtk-26.04/.hyhal/rocm_smi/lib:/opt/dtk-26.04/dcc/gcvm/lib:/opt/dtk-26.04/hip/lib:/opt/dtk-26.04/llvm/lib:/opt/dtk-26.04/lib:/opt/dtk-26.04/lib64:/opt/hyhal/lib:/opt/hyhal/lib64:/opt/dtk-26.04/dushmem/lib:/opt/dtk-26.04/opencl/lib:/opt/dtk-26.04/.hyhal/rocm_smi/lib:/opt/hyhal/lib/rocprofiler:/opt/hyhal/lib/criu/:/opt/hyhal/lib
Environment configured for vendor: hygon (BLAS_VENDOR=hygon)
PR_ID=87
Running unit tests for tests/test_tbsv.py
[correctness] reference backend: hipBLAS (--ref cuda)
============================= test session starts ==============================
platform linux -- Python 3.10.20, pytest-9.1.1, pluggy-1.6.0
rootdir: /home/secure/actions-runner/_work/FlagBLAS/FlagBLAS
configfile: pytest.ini
plugins: md-report-0.8.0
collected 1742 items

tests/test_tbsv.py ........Fatal Python error: Segmentation fault

Current thread 0x00007f2dc2764740 (most recent call first):
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 695 in visit_If
File "/home/secure/.local/share/uv/python/cpython-3.10-linux-x86_64-gnu/lib/python3.10/ast.py", line 418 in visit
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 1206 in visit
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 341 in visit_compound_statement
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 815 in visit_While
File "/home/secure/.local/share/uv/python/cpython-3.10-linux-x86_64-gnu/lib/python3.10/ast.py", line 418 in visit
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 1206 in visit
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 341 in visit_compound_statement
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 863 in visit_While
File "/home/secure/.local/share/uv/python/cpython-3.10-linux-x86_64-gnu/lib/python3.10/ast.py", line 418 in visit
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 1206 in visit
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 341 in visit_compound_statement
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 709 in visit_If
File "/home/secure/.local/share/uv/python/cpython-3.10-linux-x86_64-gnu/lib/python3.10/ast.py", line 418 in visit
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 1206 in visit
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 341 in visit_compound_statement
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 709 in visit_If
File "/home/secure/.local/share/uv/python/cpython-3.10-linux-x86_64-gnu/lib/python3.10/ast.py", line 418 in visit
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 1206 in visit
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 341 in visit_compound_statement
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 709 in visit_If
File "/home/secure/.local/share/uv/python/cpython-3.10-linux-x86_64-gnu/lib/python3.10/ast.py", line 418 in visit
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 1206 in visit
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 341 in visit_compound_statement
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 438 in visit_FunctionDef
File "/home/secure/.local/share/uv/python/cpython-3.10-linux-x86_64-gnu/lib/python3.10/ast.py", line 418 in visit
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 1206 in visit
File "/home/secure/.local/share/uv/python/cpython-3.10-linux-x86_64-gnu/lib/python3.10/ast.py", line 426 in generic_visit
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 349 in visit_Module
File "/home/secure/.local/share/uv/python/cpython-3.10-linux-x86_64-gnu/lib/python3.10/ast.py", line 418 in visit
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 1206 in visit
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/code_generator.py", line 1299 in ast_to_ttir
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/compiler.py", line 122 in make_ir
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/compiler/compiler.py", line 295 in compile
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/runtime/jit.py", line 680 in run
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/src/flag_blas/utils/libentry.py", line 743 in run
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/triton/runtime/jit.py", line 339 in
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/src/flag_blas/ops/level2/tbsv.py", line 1226 in _complex_tbsv
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/src/flag_blas/ops/level2/tbsv.py", line 1252 in ctbsv
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/src/flag_blas/runtime/backend/_hygon/ops/tbsv.py", line 114 in ctbsv
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/tests/test_tbsv.py", line 312 in test_tbsv_perf_shape_coverage
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/python.py", line 167 in pytest_pyfunc_call
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_callers.py", line 121 in _multicall
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_manager.py", line 120 in _hookexec
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_hooks.py", line 512 in __call__
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/python.py", line 1707 in runtest
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/runner.py", line 184 in pytest_runtest_call
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_callers.py", line 121 in _multicall
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_manager.py", line 120 in _hookexec
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_hooks.py", line 512 in __call__
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/runner.py", line 250 in
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/runner.py", line 361 in from_call
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/runner.py", line 249 in call_and_report
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/runner.py", line 139 in runtestprotocol
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/runner.py", line 118 in pytest_runtest_protocol
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_callers.py", line 121 in _multicall
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_manager.py", line 120 in _hookexec
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_hooks.py", line 512 in __call__
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/main.py", line 408 in pytest_runtestloop
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_callers.py", line 121 in _multicall
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_manager.py", line 120 in _hookexec
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_hooks.py", line 512 in __call__
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/main.py", line 384 in _main
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/main.py", line 330 in wrap_session
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/main.py", line 377 in pytest_cmdline_main
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_callers.py", line 121 in _multicall
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_manager.py", line 120 in _hookexec
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_hooks.py", line 512 in __call__
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/config/__init__.py", line 229 in _main
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/config/__init__.py", line 253 in _console_main
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pytest/__main__.py", line 9 in
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/coverage/execfile.py", line 222 in run
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/coverage/cmdline.py", line 1053 in do_run
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/coverage/cmdline.py", line 863 in command_line
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/coverage/cmdline.py", line 1174 in main
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/bin/coverage", line 10 in

Extension modules: numpy.core._multiarray_umath, numpy.core._multiarray_tests, numpy.linalg._umath_linalg, numpy.fft._pocketfft_internal, numpy.random._common, numpy.random.bit_generator, numpy.random._bounded_integers, numpy.random._mt19937, numpy.random.mtrand, numpy.random._philox, numpy.random._pcg64, numpy.random._sfc64, numpy.random._generator, torch._C, torch._C._dynamo.autograd_compiler, torch._C._dynamo.eval_frame, torch._C._dynamo.guards, torch._C._dynamo.utils, torch._C._fft, torch._C._linalg, torch._C._nested, torch._C._nn, torch._C._sparse, torch._C._special, yaml._yaml, sqlalchemy.cyextension.collections, sqlalchemy.cyextension.immutabledict, sqlalchemy.cyextension.processors, sqlalchemy.cyextension.resultproxy, sqlalchemy.cyextension.util, greenlet._greenlet, scipy._lib._ccallback_c, scipy.linalg._fblas, scipy.linalg._flapack, scipy.linalg.cython_lapack, scipy.linalg._cythonized_array_utils, scipy.linalg._solve_toeplitz, scipy.linalg._decomp_lu_cython, scipy.linalg._matfuncs_sqrtm_triu, scipy.linalg._matfuncs_expm, scipy.linalg._linalg_pythran, scipy.linalg.cython_blas, scipy.linalg._decomp_update, scipy.sparse._sparsetools, _csparsetools, scipy.sparse._csparsetools, scipy.sparse.linalg._dsolve._superlu, scipy.sparse.linalg._eigen.arpack._arpack, scipy.sparse.linalg._propack._spropack, scipy.sparse.linalg._propack._dpropack, scipy.sparse.linalg._propack._cpropack, scipy.sparse.linalg._propack._zpropack, scipy.sparse.csgraph._tools, scipy.sparse.csgraph._shortest_path, scipy.sparse.csgraph._traversal, scipy.sparse.csgraph._min_spanning_tree, scipy.sparse.csgraph._flow, scipy.sparse.csgraph._matching, scipy.sparse.csgraph._reordering, hip_utils, __triton_launcher (total: 61)
tools/run_op.sh: line 100: 2536715 Segmentation fault (core dumped) coverage run -m pytest -s ${EXTRA_OPTS} ${item}
Error: File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/runner.py", line 118 in pytest_runtest_protocol
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_callers.py", line 121 in _multicall
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_manager.py", line 120 in _hookexec
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_hooks.py", line 512 in __call__
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/main.py", line 408 in pytest_runtestloop
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_callers.py", line 121 in _multicall
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_manager.py", line 120 in _hookexec
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_hooks.py", line 512 in __call__
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/main.py", line 384 in _main
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/main.py", line 330 in wrap_session
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/main.py", line 377 in pytest_cmdline_main
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_callers.py", line 121 in _multicall
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_manager.py", line 120 in _hookexec
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pluggy/_hooks.py", line 512 in __call__
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/config/__init__.py", line 229 in _main
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/_pytest/config/__init__.py", line 253 in _console_main
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/pytest/__main__.py", line 9 in
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/coverage/execfile.py", line 222 in run
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/coverage/cmdline.py", line 1053 in do_run
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/coverage/cmdline.py", line 863 in command_line
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/lib/python3.10/site-packages/coverage/cmdline.py", line 1174 in main
File "/home/secure/actions-runner/_work/FlagBLAS/FlagBLAS/.venv/bin/coverage", line 10 in

Extension modules: numpy.core._multiarray_umath, numpy.core._multiarray_tests, numpy.linalg._umath_linalg, numpy.fft._pocketfft_internal, numpy.random._common, numpy.random.bit_generator, numpy.random._bounded_integers, numpy.random._mt19937, numpy.random.mtrand, numpy.random._philox, numpy.random._pcg64, numpy.random._sfc64, numpy.random._generator, torch._C, torch._C._dynamo.autograd_compiler, torch._C._dynamo.eval_frame, torch._C._dynamo.guards, torch._C._dynamo.utils, torch._C._fft, torch._C._linalg, torch._C._nested, torch._C._nn, torch._C._sparse, torch._C._special, yaml._yaml, sqlalchemy.cyextension.collections, sqlalchemy.cyextension.immutabledict, sqlalchemy.cyextension.processors, sqlalchemy.cyextension.resultproxy, sqlalchemy.cyextension.util, greenlet._greenlet, scipy._lib._ccallback_c, scipy.linalg._fblas, scipy.linalg._flapack, scipy.linalg.cython_lapack, scipy.linalg._cythonized_array_utils, scipy.linalg._solve_toeplitz, scipy.linalg._decomp_lu_cython, scipy.linalg._matfuncs_sqrtm_triu, scipy.linalg._matfuncs_expm, scipy.linalg._linalg_pythran
flag_blas import OK

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reproducing the failure in tests/test_tbsv.py, especially test_tbsv_perf_shape_coverage at line 312, in the Hygon environment described. Then read src/flag_blas/runtime/backend/_hygon/ops/tbsv.py and src/flag_blas/ops/level2/tbsv.py around the traced ctbsv calls. Done means the test suite completes without the segmentation fault and the TBSV accuracy checks pass on Hygon.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
backend, testing
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.