https://gcc.gnu.org/bugzilla/show_bug.cgi?id=54412
John Platts <john_platts at hotmail dot com> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |john_platts at hotmail dot com
--- Comment #28 from John Platts <john_platts at hotmail dot com> ---
The correct way to align the stack to a 32-byte or 64-byte boundary on 64-bit
Windows is to use a frame pointer in a function that requires stack realignment
and then realign the stack to the required alignment once the frame pointer is
set and all of the non-volatile registers used in the function are saved.
class Avx2VectorGenerator {
public:
virtual __m256i NextVector() = 0;
};
__m256i Example_AVX2_Func(Avx2VectorGenerator* generator, size_t iterations);
Example_AVX2_Func:
pushq %rbp
.seh_pushreg %rbp
pushq %rbx
.seh_pushreg %rbx
pushq %rdi
.seh_pushreg %rdi
movq %rsp, %rbp
.seh_setframe %rbp, 0
.seh_endprologue
/* Set rbx to generator and rdi to iterations */
movq %rcx, %rbx
movq %rdx, %rdi
/* It is okay to allocate additional stack memory */
/* and re-align the stack pointer outside of the */
/* SEH prologue as there is a frame pointer in this */
/* function */
subq $64, %rsp
andq $-32, %rsp
/* Zero out the result vector */
vpxor %ymm0, %ymm0, %ymm0
test %rdi, %rdi
jz .loop_complete
.loop_iteration_start:
/* Save the result vector to 32(%rsp) */
vmovdqa 32(%rsp), ymm0
/* Move generator into rcx */
movq %rbx, %rcx
/* Move the pointer to the NextVector() virtual member func */
/* into rax */
movq (%rbx), %rax
/* Call generator->NextVector() */
call *(%rax)
/* Add the result of generator->NextVector() to the result vector */
vpaddb 32(%rsp), %ymm0, %ymm0
/* Decrement iterations by 1 */
sub $1, %rdi
/* Jump back to the beginning of the loop if iterations is non-zero */
jnz .loop_iteration_start
.loop_complete:
lea (%rbp), %rsp
pop %rdi
pop %rbx
pop %rbp
ret
.seh_endproc
