https://bugs.llvm.org/show_bug.cgi?id=41255
Bug ID: 41255
Summary: Modulo to cmov conversion
Product: libraries
Version: trunk
Hardware: PC
OS: Linux
Status: NEW
Severity: enhancement
Priority: P
Component: Scalar Optimizations
Assignee: [email protected]
Reporter: [email protected]
CC: [email protected]
Hi,
int g = 0;
void cnt1(int n) {
g++;
g %= n;
}
void cnt2(int n) {
g++;
if (g==n) g=0;
}
int main(int argc, char**argv) {
int e = atoi(argv[1]);
for (int i = 0; i < e; ++i) {
cnt1(7);
}
printf("%d", g);
}
CNT1 version on Haswell with -O3:
time ./a.out 65384546
3
real 0m0.294s
user 0m0.294s
sys 0m0.000s
CNT1 with GCC-9 -O3 is much faster. -O3 -fno-unroll-loops for Clang doesn't fix
it:
time ./a.out 65384546
3
real 0m0.247s
user 0m0.247s
sys 0m0.000s
GCC:
.L9:
lea eax, [rsi+1]
add ecx, 1
movsx rsi, eax
cdq
imul rsi, rsi, -1840700269
shr rsi, 32
add esi, eax
sar esi, 2
sub esi, edx
lea edx, [0+rsi*8]
sub edx, esi
sub eax, edx
mov esi, eax
cmp ecx, edi
jne .L9
mov DWORD PTR g[rip], eax
Clang:
.LBB2_1:
lea ecx, [rsi + 1]
movsxd rcx, ecx
imul rcx, rcx, -1840700269
shr rcx, 32
lea ecx, [rcx + rsi]
add ecx, 1
mov edx, ecx
shr edx, 31
sar ecx, 2
add ecx, edx
lea edx, [8*rcx]
sub ecx, edx
lea esi, [rsi + rcx]
add esi, 1
add eax, -1
jne .LBB2_1
mov dword ptr [rip + g], esi
Small differences in codegen, I don't see a reason why this code is
slower/faster.
CNT2 version is the best (unrolling and generated cmov in Clang helps a lot,
GCC is slower since it does not use cmov):
time ./a.out 65384546
3
real 0m0.031s
user 0m0.031s
sys 0m0.000s
Maybe is it worth to do this transformation?
--
You are receiving this mail because:
You are on the CC list for the bug._______________________________________________
llvm-bugs mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-bugs
