coredump in segmm_

[sandrew11]

#0 0x000055eca5413a75 in sgemm_incopy ()
#1 0x000055eca53f670f in sgemm_tn ()
#2 0x000055eca53f4d79 in sgemm_ ()
#3 0x000055eca52d9bda in faiss::(anonymous namespace)::exhaustive_inner_product_blas<faiss::HeapResultHandler<faiss::CMin<float, long> > > (res=..., ny=64, nx=64, d=128, y=0x7fca661be000,
x=) at third_party/faiss/faiss/faiss/impl/ResultHandler.h:88
#4 faiss::knn_inner_product (x=, y=, d=128, nx=64, ny=, k=1, val=0x7fca62d35200, ids=0x7fca661dfc00, sel=)
at third_party/faiss/faiss/faiss/utils/distances.cpp:636
#5 0x000055eca52d9d8e in faiss::knn_inner_product (x=, y=, d=, nx=, ny=, res=res@entry=0x7fca58dbe1c0, sel=0x0)
at third_party/faiss/faiss/faiss/utils/distances.cpp:667

There is coredump in some linux environment. Asking for everyone's help, please tell me the reason for this coredump

[martin-frbg]

Which version of OpenBLAS, which cpu, which compiler, what does the code and data look like that leads to the coredump ?

[sandrew11]

Which version of OpenBLAS, which cpu, which compiler, what does the code and data look like that leads to the coredump ?
openblas version: 0.3.21
lscpu:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 42 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 16
On-line CPU(s) list: 0-15
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) CPU E5-2690 v4 @ 2.60GHz
CPU family: 6
Model: 79
Thread(s) per core: 1
Core(s) per socket: 1
Socket(s): 16
Stepping: 1
BogoMIPS: 5187.98
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology cpuid tsc_known_freq pni pclmulqdq
ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2
erms invpcid rtm rdseed adx smap xsaveopt arat flush_l1d
Virtualization features:
Hypervisor vendor: KVM
Virtualization type: full
Caches (sum of all):
L1d: 512 KiB (16 instances)
L1i: 512 KiB (16 instances)
L2: 64 MiB (16 instances)
L3: 256 MiB (16 instances)
NUMA:
NUMA node(s): 1
NUMA node0 CPU(s): 0-15
Vulnerabilities:
Gather data sampling: Not affected
Itlb multihit: KVM: Mitigation: VMX unsupported
L1tf: Mitigation; PTE Inversion
Mds: Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Meltdown: Vulnerable
Mmio stale data: Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
Reg file data sampling: Not affected
Retbleed: Not affected
Spec rstack overflow: Not affected
Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Spectre v2: Vulnerable, IBPB: disabled, STIBP: disabled, PBRSB-eIBRS: Not affected
Srbds: Not affected
Tsx async abort: Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown

compiler:gcc

in faiss::exhaustive_inner_product_blas
https://github.com/facebookresearch/faiss/blob/main/faiss/utils/distances.cpp
sgemm_("Transpose",
"Not transpose",
&nyi,
&nxi,
&di,
&one,
y + j0 * d,
&di,
x + i0 * d,
&di,
&zero,
ip_block.get(),
&nyi);

[martin-frbg]

I do not know FAISS, what do I need to do to trigger the error there - is it with a supplied example ? But 0.3.21 is two years old, there is a good chance that this was resolved in the meantime.

[martin-frbg]

I cannot reproduce this with simple cases based on the examples in the FAISS tutorial, please provide
a code sample that demonstrates the problem.