Ggtcf

When I run the code on my machine, the program goes segmentation fault.

#include <immintrin.h>
#include <stdint.h>

static inline __m256i load_vector(__m256i const * addr)
 __m256i res = _mm256_load_si256(addr);
 return res;

void test2()
 int32_t *src;
 src = _mm_malloc(sizeof(__m256i), 32);
 __m256i vec = load_vector((__m256i const * )src);
 _mm_free(src);


int main(int argc,char *argv[])
 test2();
 return 0;

I tried to debug this with gdb and it goes segmentation fault when _mm256_load_si256 is called.

I run the code on cygwin gcc on AMD 2990wx CPU.
How can be happen such things?

I did further debug. _mm_malloc wasn't the problem, it was alignment of local variables.

At the second vmovdqa to store the vector into the caller's pointer, RAX was not 32-byte aligned. vec in test2 seems not to be aligned. (Cygwin/mingw return the __m256i vector by reference with the caller passing a hidden pointer, unlike the standard Windows x64 calling convention that return it by value).

This is the known Cygwin bug (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=54412) that Mysticial linked in comments: Cygwin GCC can't safely use AVX because it doesn't properly align the stack for __m256i locals that get stored to memory. (Cygwin/MinGW gcc will properly align alignas(32) int arr[8] = 0;, but they do it by aligning a separate pointer, not RSP or RBP. Apparently there's some SEH limitation on stack frame manipulation)

Clang, MSVC, and ICC all support __m256i properly.

With optimization enabled gcc often won't make faulting code, but sometimes even optimized code will store/reload a 32-byte vector to the stack.

_ZL11load_vectorPKDv4_x:
.LFB3671:
 .file 2 "min_case.c"
 .loc 2 4 0
 .cfi_startproc
 pushq %rbp
 .seh_pushreg %rbp
 .cfi_def_cfa_offset 16
 .cfi_offset 6, -16
 movq %rsp, %rbp
 .seh_setframe %rbp, 0
 .cfi_def_cfa_register 6
 subq $16, %rsp
 .seh_stackalloc 16
 .seh_endprologue
 movq %rcx, 16(%rbp)
 movq %rdx, 24(%rbp)
 movq 24(%rbp), %rax
 movq %rax, -8(%rbp)
.LBB4:
.LBB5:
 .file 3 "/usr/lib/gcc/x86_64-pc-cygwin/7.4.0/include/avxintrin.h"
 .loc 3 909 0
 movq -8(%rbp), %rax
 vmovdqa (%rax), %ymm0
.LBE5:
.LBE4:
 .loc 2 5 0
 movq 16(%rbp), %rax
 vmovdqa %ymm0, (%rax)
 .loc 2 6 0
 movq 16(%rbp), %rax
 addq $16, %rsp
 popq %rbp
 .cfi_restore 6
 .cfi_def_cfa 7, 8
 ret

__m256i was not aligned in this test-case:

#include <immintrin.h>
#include <stdint.h>
#include <assert.h>
#include <stdio.h>
#include <stdlib.h>

const char* check_alignment(const void *ptr, uintptr_t alignment)
 return (((uintptr_t)ptr) & (alignment - 1)) == 0 ? "aligned" : "NOT aligned";


static inline __m256i load_vector(__m256i const * addr)
 printf("addr:%sn", check_alignment(addr, 32));
 __m256i res;
 printf("&res:%sn", check_alignment(&res, 32));
 res = _mm256_load_si256(addr);
 return res;

void test2()
 int32_t *src;
 src = (int32_t *)_mm_malloc(sizeof(__m256i), 32);
 src[0] = 0; src[0] = 1; src[2] = 2; src[3] = 3;
 src[4] = 4; src[5] = 5; src[6] = 6; src[7] = 7;
 __m256i vec = load_vector((__m256i const * )src);
 _mm_free(src);


int main(int argc,char *argv[])
 test2();
 return 0;


// results
// addr:aligned
// &res:NOT aligned
// Segmentation fault