https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109441
Bug ID: 109441
Summary: missed optimization when all elements of vector are
known
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
Reference: https://godbolt.org/z/af4x6zhz9
When all elements of vector are 0, then the compiler should be able to remove
the loop and just return 0.
Testcase:
#include<vector>
using namespace std;
using T = int;
T v() {
T s;
std::vector<T> v;
v.resize(1000, 0);
for (auto i = 0; i < v.size(); ++i) {
s += v[i];
}
return s;
}
$ g++ -O3 -std=c++17
.LC0:
.string "vector::_M_fill_insert"
v():
push rbx
pxor xmm0, xmm0
mov edx, 1000
xor esi, esi
sub rsp, 48
lea rcx, [rsp+12]
lea rdi, [rsp+16]
mov QWORD PTR [rsp+32], 0
mov DWORD PTR [rsp+12], 0
movaps XMMWORD PTR [rsp+16], xmm0
call std::vector<int, std::allocator<int>
>::_M_fill_insert(__gnu_cxx::__normal_iterator<int*, std::vector<int,
std::allocator<int> > >, unsigned long, int const&)
mov rdx, QWORD PTR [rsp+24]
mov rdi, QWORD PTR [rsp+16]
mov rax, rdx
sub rax, rdi
mov rsi, rax
sar rsi, 2
cmp rdx, rdi
je .L99
test rax, rax
mov ecx, 1
cmovne rcx, rsi
cmp rax, 12
jbe .L107
mov rdx, rcx
pxor xmm0, xmm0
mov rax, rdi
shr rdx, 2
sal rdx, 4
add rdx, rdi
.L101:
movdqu xmm2, XMMWORD PTR [rax]
add rax, 16
paddd xmm0, xmm2
cmp rdx, rax
jne .L101
movdqa xmm1, xmm0
psrldq xmm1, 8
paddd xmm0, xmm1
movdqa xmm1, xmm0
psrldq xmm1, 4
paddd xmm0, xmm1
movd ebx, xmm0
test cl, 3
je .L99
and rcx, -4
mov eax, ecx
.L100:
lea edx, [rax+1]
add ebx, DWORD PTR [rdi+rcx*4]
movsx rdx, edx
cmp rdx, rsi
jnb .L99
add eax, 2
lea rcx, [0+rdx*4]
add ebx, DWORD PTR [rdi+rdx*4]
cdqe
cmp rax, rsi
jnb .L99
add ebx, DWORD PTR [rdi+4+rcx]
.L99:
test rdi, rdi
je .L98
mov rsi, QWORD PTR [rsp+32]
sub rsi, rdi
call operator delete(void*, unsigned long)
.L98:
add rsp, 48
mov eax, ebx
pop rbx
ret
.L107:
xor eax, eax
xor ecx, ecx
jmp .L100
mov rbx, rax
jmp .L105
v() [clone .cold]:
