https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113801
Bug ID: 113801
Summary: Missed optimization of loop invariant elimination
Product: gcc
Version: 14.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: 652023330028 at smail dot nju.edu.cn
Target Milestone: ---
Hello, we noticed that maybe there is a missed optimization for loop invariant
elimination.
Loop invariant: b+d.
https://godbolt.org/z/8fn48TGKv
int a, c;
void func(int b, int d) {
for (int i=0; i < 400; i += 1) {
a += a;
b += c;
d += -c;
a += b + d;
}
}
But GCC -O3
func(int, int):
mov ecx, DWORD PTR a[rip]
mov r8d, DWORD PTR c[rip]
mov edx, 400
.L2:
mov eax, edi
mov r9d, esi
add edi, r8d
sub esi, r8d
add eax, r9d
lea ecx, [rax+rcx*2]
sub edx, 1
jne .L2
mov DWORD PTR a[rip], ecx
ret
Expected code:
Like optimizing the equivalent func2:
void func2(int b, int d) {
for (int i=0; i < 400; i += 1) {
a += a;
//b += c;
//d += -c;
a += b + d;
}
}
Result:
func2(int, int):
mov edx, DWORD PTR a[rip]
lea ecx, [rdi+rsi]
mov eax, 400
.L6:
lea edx, [rcx+rdx*2]
sub eax, 1
jne .L6
mov DWORD PTR a[rip], edx
ret
Or like Clang:
func(int, int): # @func(int, int)
mov edx, dword ptr [rip + a]
add edi, esi
lea eax, [rdi + rdi]
mov ecx, 400
.LBB0_1: # =>This Inner Loop Header: Depth=1
lea edx, [rax + 4*rdx]
add edx, edi
lea edx, [rax + 4*rdx]
add edx, edi
lea edx, [rax + 4*rdx]
add edx, edi
lea edx, [rax + 4*rdx]
add edx, edi
add ecx, -8
jne .LBB0_1
mov dword ptr [rip + a], edx
ret
Thank you very much for your time and effort! We look forward to hearing from
you.
