https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109441
--- Comment #1 from AK <hiraditya at msn dot com> ---
I guess a better test case is this:
#include<vector>
using namespace std;
using T = int;
T v(std::vector<T> v) {
T s;
std::fill(v.begin(), v.end(), T());
for (auto i = 0; i < v.size(); ++i) {
s += v[i];
}
return s;
}
which has similar effect.
$ g++ -O3 -std=c++17
v(std::vector<int, std::allocator<int> >):
push rbp
push rbx
sub rsp, 8
mov rbp, QWORD PTR [rdi+8]
mov rcx, QWORD PTR [rdi]
cmp rcx, rbp
je .L7
sub rbp, rcx
mov rdi, rcx
xor esi, esi
mov rbx, rcx
mov rdx, rbp
call memset
mov rdi, rbp
mov edx, 1
mov rcx, rbx
sar rdi, 2
test rbp, rbp
cmovne rdx, rdi
cmp rbp, 12
jbe .L8
mov rax, rdx
pxor xmm0, xmm0
shr rax, 2
sal rax, 4
add rax, rbx
.L4:
movdqu xmm2, XMMWORD PTR [rbx]
add rbx, 16
paddd xmm0, xmm2
cmp rbx, rax
jne .L4
movdqa xmm1, xmm0
psrldq xmm1, 8
paddd xmm0, xmm1
movdqa xmm1, xmm0
psrldq xmm1, 4
paddd xmm0, xmm1
movd eax, xmm0
test dl, 3
je .L1
and rdx, -4
mov esi, edx
.L3:
add eax, DWORD PTR [rcx+rdx*4]
lea edx, [rsi+1]
movsx rdx, edx
cmp rdx, rdi
jnb .L1
add esi, 2
lea r8, [0+rdx*4]
add eax, DWORD PTR [rcx+rdx*4]
movsx rsi, esi
cmp rsi, rdi
jnb .L1
add eax, DWORD PTR [rcx+4+r8]
.L1:
add rsp, 8
pop rbx
pop rbp
ret
.L7:
add rsp, 8
xor eax, eax
pop rbx
pop rbp
ret
.L8:
xor eax, eax
xor esi, esi
xor edx, edx
jmp .L3