https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114647
Bug ID: 114647
Summary: missing DCE when looping over a VLA
Product: gcc
Version: 14.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: middle-end
Assignee: unassigned at gcc dot gnu.org
Reporter: franckbehaghel_gcc at protonmail dot com
Target Milestone: ---
$cat foo.cpp
#include "stdint.h"
#include "stdio.h"
void foo(int n)
{
uint64_t a[n];
for (uint32_t i=0;i<n;i++) a[i] = i;
printf(" ");
}
At O3, gcc vectorize the loop but do not remove it:
foo(int):
push rbp
movsx rax, edi
lea rax, [15+rax*8]
and rax, -16
mov rbp, rsp
sub rsp, rax
test edi, edi
je .L2
lea edx, [rdi-1]
cmp edx, 2
jbe .L2
shr edi, 2
mov ecx, 4
pxor xmm2, xmm2
mov rax, rsp
mov edx, edi
movdqa xmm1, XMMWORD PTR .LC0[rip]
movd xmm4, ecx
sal rdx, 5
pshufd xmm4, xmm4, 0
add rdx, rsp
.L4:
movdqa xmm0, xmm1
add rax, 32
paddd xmm1, xmm4
movdqa xmm3, xmm0
punpckhdq xmm0, xmm2
punpckldq xmm3, xmm2
movups XMMWORD PTR [rax-16], xmm0
movups XMMWORD PTR [rax-32], xmm3
cmp rdx, rax
jne .L4
.L2:
mov edi, 32
call putchar
leave
ret
clang ( c or c++ ) does remove the loop :
foo: # @foo
mov edi, 32
jmp putchar@PLT # TAILCALL
