Re: State of AVX512 support in NetBSD?

[Thomas Klausner <wiz%NetBSD.org@localhost>]

On Mon, Jul 29, 2024 at 11:59:12PM +0200, Thomas Klausner wrote:
> For my recent build trouble of lang/ghc98 that only I can see but pho@
> can't[1], upstream has suggested it might be a problem with AVX512
> support[2] in NetBSD. (My CPU supports AVX512, pho's doesn't.)
> 
> I'll give their suggestion (using -D__STDC_NO_ATOMICS__) a try, but
> does anyone know the actual state of AVX512 support on NetBSD?

This also affects py-numpy.

On a system with:

NumPy CPU features:  SSE SSE2 SSE3 SSSE3* SSE41* POPCNT* SSE42* AVX* F16C* FMA3* AVX2* AVX512F* AVX512CD* AVX512_KNL? AVX512_KNM? AVX512_SKX* AVX512_CLX* AVX512_CNL* AVX512_ICL* AVX512_SPR?

the self tests fail because of a Python coredump:


.......................Fatal Python error: Segmentation fault

Current thread 0x000070758c49e800 (most recent call first):
  File "/scratch/math/py-numpy/work/.destdir/usr/pkg/lib/python3.12/site-packages/numpy/_core/fromnumeric.py", line 1077 in sort
  File "/scratch/math/py-numpy/work/.destdir/usr/pkg/lib/python3.12/site-packages/numpy/_core/tests/test_multiarray.py", line 2307 in test_sort_degraded
  File "/usr/pkg/lib/python3.12/site-packages/_pytest/python.py", line 162 in pytest_pyfunc_call
  File "/usr/pkg/lib/python3.12/site-packages/pluggy/_callers.py", line 103 in _multicall
  File "/usr/pkg/lib/python3.12/site-packages/pluggy/_manager.py", line 120 in _hookexec
  File "/usr/pkg/lib/python3.12/site-packages/pluggy/_hooks.py", line 513 in __call__
  File "/usr/pkg/lib/python3.12/site-packages/_pytest/python.py", line 1632 in runtest
  File "/usr/pkg/lib/python3.12/site-packages/_pytest/runner.py", line 173 in pytest_runtest_call
  File "/usr/pkg/lib/python3.12/site-packages/pluggy/_callers.py", line 103 in _multicall
  File "/usr/pkg/lib/python3.12/site-packages/pluggy/_manager.py", line 120 in _hookexec
  File "/usr/pkg/lib/python3.12/site-packages/pluggy/_hooks.py", line 513 in __call__
  File "/usr/pkg/lib/python3.12/site-packages/_pytest/runner.py", line 241 in <lambda>
  File "/usr/pkg/lib/python3.12/site-packages/_pytest/runner.py", line 341 in from_call
  File "/usr/pkg/lib/python3.12/site-packages/_pytest/runner.py", line 240 in call_and_report
  File "/usr/pkg/lib/python3.12/site-packages/_pytest/runner.py", line 135 in runtestprotocol
  File "/usr/pkg/lib/python3.12/site-packages/_pytest/runner.py", line 116 in pytest_runtest_protocol
  File "/usr/pkg/lib/python3.12/site-packages/pluggy/_callers.py", line 103 in _multicall
  File "/usr/pkg/lib/python3.12/site-packages/pluggy/_manager.py", line 120 in _hookexec
  File "/usr/pkg/lib/python3.12/site-packages/pluggy/_hooks.py", line 513 in __call__
  File "/usr/pkg/lib/python3.12/site-packages/_pytest/main.py", line 364 in pytest_runtestloop
  File "/usr/pkg/lib/python3.12/site-packages/pluggy/_callers.py", line 103 in _multicall
  File "/usr/pkg/lib/python3.12/site-packages/pluggy/_manager.py", line 120 in _hookexec
  File "/usr/pkg/lib/python3.12/site-packages/pluggy/_hooks.py", line 513 in __call__
  File "/usr/pkg/lib/python3.12/site-packages/_pytest/main.py", line 339 in _main
  File "/usr/pkg/lib/python3.12/site-packages/_pytest/main.py", line 285 in wrap_session
  File "/usr/pkg/lib/python3.12/site-packages/_pytest/main.py", line 332 in pytest_cmdline_main
  File "/usr/pkg/lib/python3.12/site-packages/pluggy/_callers.py", line 103 in _multicall
  File "/usr/pkg/lib/python3.12/site-packages/pluggy/_manager.py", line 120 in _hookexec
  File "/usr/pkg/lib/python3.12/site-packages/pluggy/_hooks.py", line 513 in __call__
  File "/usr/pkg/lib/python3.12/site-packages/_pytest/config/__init__.py", line 178 in main
  File "/scratch/math/py-numpy/work/.destdir/usr/pkg/lib/python3.12/site-packages/numpy/_pytesttester.py", line 195 in __call__
  File "<string>", line 1 in <module>

Extension modules: numpy._core._multiarray_umath, numpy._core._multiarray_tests, numpy.linalg._umath_linalg, numpy._core._rational_tests, numpy._core._umath_tests, cython.cimports.libc.math, 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, numpy._core._simd, numpy._core._operand_flag_tests, numpy.linalg.lapack_lite, checks, limited_api2 (total: 20)
*** Signal 11

and the backtrace contains stats with:

#0  0x000070758c66d2fa in _lwp_kill () from /usr/lib/libc.so.12
#1  <signal handler called>
#2  0x000070758b8f9a95 in _mm512_mask_compressstoreu_epi64(void*, unsigned char, long long __vector(8)) (__A=...,
    __U=<error reading variable: Unable to access DWARF register number 118>, __P=0x707569bfcff0) at /usr/include/gcc-12/avx512fintrin.h:10911
#3  zmm_vector<long>::mask_compressstoreu(void*, unsigned char, long long __vector(8)) (x=...,
    mask=<error reading variable: Unable to access DWARF register number 118>, mem=0x707569bfcff0)
    at ../numpy/_core/src/npysort/x86-simd-sort/src/avx512-64bit-common.h:703
#4  avx512_double_compressstore<zmm_vector<long>, long, long long __vector(8)>(long*, long*, zmm_vector<long>::opmask_t, long long __vector(8)) (reg=...,
    k=<error reading variable: Unable to access DWARF register number 118>, right_addr=0x707569bfd008, left_addr=0x707569ba57c8)
    at ../numpy/_core/src/npysort/x86-simd-sort/src/xss-common-qsort.h:211
#5  zmm_vector<long>::double_compressstore(long*, long*, unsigned char, long long __vector(8)) (reg=...,
    k=<error reading variable: Unable to access DWARF register number 118>, right_addr=0x707569bfd008, left_addr=0x707569ba57c8)
    at ../numpy/_core/src/npysort/x86-simd-sort/src/avx512-64bit-common.h:778
#6  partition_vec<zmm_vector<long int>, Comparator<zmm_vector<long int>, false>, long int, __vector(8) long long int> (biggest_vec=<synthetic pointer>...,
    smallest_vec=<synthetic pointer>..., pivot_vec=..., curr_vec=..., r_store=0x707569bfd008, l_store=0x707569ba57c8)
    at ../numpy/_core/src/npysort/x86-simd-sort/src/xss-common-qsort.h:232
#7  partition_unrolled<zmm_vector<long>, Comparator<zmm_vector<long>, false>, 8, long> (arr=arr@entry=0x707569bfda40, left=955200, left@entry=0,
    right=999872, right@entry=1000000, pivot=pivot@entry=375000, smallest=smallest@entry=0x7f7fffbcd610, biggest=biggest@entry=0x7f7fffbcd618)
    at ../numpy/_core/src/npysort/x86-simd-sort/src/xss-common-qsort.h:462
#8  0x000070758b95c93c in qsort_<zmm_vector<long>, Comparator<zmm_vector<long>, false>, long> (arr=0x707569bfda40, left=<optimized out>, right=999999,
    max_iters=<optimized out>) at ../numpy/_core/src/npysort/x86-simd-sort/src/xss-common-qsort.h:553



Can someone please fix or disable AVX 512 support on NetBSD?
 Thomas