The following function gets optimized at -O3 to:
long long tmod2(long long x)
{
return x % 2;
}
mov %rdi,%rdx
shr $0x3f,%rdx
lea (%rdi,%rdx,1),%rax
and $0x1,%eax
sub %rdx,%rax
retq
This is very good code. Unfortunately, the 128 bit version doesn't get
optimized nearly so well.
__int128_t tmod2(__int128_t x)
{
return x % 2;
}
mov %rsi,%rdx
mov %rdi,%r8
xor %ecx,%ecx
shr $0x3f,%rdx
push %rbx
add %rdx,%r8
xor %edi,%edi
mov %r8,%rsi
mov %rdi,%r9
and $0x1,%esi
mov %rsi,%r8
sub %rdx,%r8
sbb %rcx,%r9
mov %r8,%rax
mov %r9,%rdx
pop %rbx
retq
It looks like this simple variation of the 64bit algorithm will work for the
128 bit version:
mov %rsi,%rdx <--- Just changed rdi into rsi
shr $0x3f,%rdx <--- nicely already calculates high bytes in rdx
lea (%rdi,%rdx,1),%rax
and $0x1,%eax
sub %rdx,%rax
retq
--
Summary: missed optimization of constant __int128_t modulus
Product: gcc
Version: 4.5.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: middle-end
AssignedTo: unassigned at gcc dot gnu dot org
ReportedBy: svfuerst at gmail dot com
GCC build triplet: x86_64-linux
GCC host triplet: x86_64-linux
GCC target triplet: x86_64-linux
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=43883
