https://bugs.llvm.org/show_bug.cgi?id=45700
Bug ID: 45700
Summary: Failure to optimize condition into sbb
Product: libraries
Version: trunk
Hardware: PC
OS: Linux
Status: NEW
Severity: enhancement
Priority: P
Component: Backend: X86
Assignee: [email protected]
Reporter: [email protected]
CC: [email protected], [email protected],
[email protected], [email protected]
int f(int a, unsigned b, unsigned c)
{
if (b <= c)
a++;
return a;
}
This optimizes into an sbb on gcc :
f(int, unsigned int, unsigned int):
mov eax, edi
cmp edx, esi
sbb eax, -1
ret
With LLVM, this is output instead :
f(int, unsigned int, unsigned int):
xor eax, eax
cmp esi, edx
setbe al
add eax, edi
ret
And I doubt that is faster than the sbb.
--
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