https://gcc.gnu.org/bugzilla/show_bug.cgi?id=80852
Bug ID: 80852
Summary: Optimisation missed for loop with condition that is
always true
Product: gcc
Version: 8.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c
Assignee: unassigned at gcc dot gnu.org
Reporter: drraph at gmail dot com
Target Milestone: ---
Consider this (slightly odd) code:
int foo(int num) {
int a = 0;
for (int x = 0; x < num; x+=2) {
if (!(x % 2)) {
a += x;
}
}
return a;
}
Note that the condition !(x % 2) is always true.
In clang and -O3 -march=core-avx2 you get:
foo(int): # @square(int)
test edi, edi
jle .LBB0_1
add edi, -1
mov eax, edi
shr eax
lea ecx, [rax - 1]
imul ecx, eax
and ecx, -2
and edi, -2
add edi, ecx
mov eax, edi
ret
.LBB0_1:
xor edi, edi
mov eax, edi
ret
This is clever as it avoids looping altogether.
gcc however doesn't know this trick and you get:
foo(int):
test edi, edi
jle .L7
lea eax, [rdi-1]
mov ecx, eax
shr ecx
add ecx, 1
cmp eax, 17
jbe .L8
mov edx, ecx
vmovdqa ymm1, YMMWORD PTR .LC0[rip]
xor eax, eax
vpxor xmm0, xmm0, xmm0
vmovdqa ymm2, YMMWORD PTR .LC1[rip]
shr edx, 3
.L5:
add eax, 1
vpaddd ymm0, ymm0, ymm1
vpaddd ymm1, ymm1, ymm2
cmp eax, edx
jb .L5
vpxor xmm1, xmm1, xmm1
mov esi, ecx
vperm2i128 ymm2, ymm0, ymm1, 33
and esi, -8
vpaddd ymm0, ymm0, ymm2
lea edx, [rsi+rsi]
vperm2i128 ymm2, ymm0, ymm1, 33
vpalignr ymm2, ymm2, ymm0, 8
vpaddd ymm0, ymm0, ymm2
vperm2i128 ymm1, ymm0, ymm1, 33
vpalignr ymm1, ymm1, ymm0, 4
vpaddd ymm0, ymm0, ymm1
vmovd eax, xmm0
cmp ecx, esi
je .L12
vzeroupper
.L3:
lea ecx, [rdx+2]
add eax, edx
cmp edi, ecx
jle .L10
add eax, ecx
lea ecx, [rdx+4]
cmp ecx, edi
jge .L10
add eax, ecx
lea ecx, [rdx+6]
cmp edi, ecx
jle .L10
add eax, ecx
lea ecx, [rdx+8]
cmp edi, ecx
jle .L10
add eax, ecx
lea ecx, [rdx+10]
cmp edi, ecx
jle .L10
add eax, ecx
lea ecx, [rdx+12]
cmp edi, ecx
jle .L10
add eax, ecx
lea ecx, [rdx+14]
cmp edi, ecx
jle .L10
add eax, ecx
add edx, 16
lea ecx, [rax+rdx]
cmp edi, edx
cmovg eax, ecx
ret
.L7:
xor eax, eax
.L10:
ret
.L12:
vzeroupper
ret
.L8:
xor edx, edx
xor eax, eax
jmp .L3
.LC0:
.long 0
.long 2
.long 4
.long 6
.long 8
.long 10
.long 12
.long 14
.LC1:
.long 16
.long 16
.long 16
.long 16
.long 16
.long 16
.long 16
.long 16
