https://gcc.gnu.org/bugzilla/show_bug.cgi?id=80261
Bug ID: 80261
Summary: Worse code generated compared to clang with modulo
operation
Product: gcc
Version: 6.3.1
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: rtl-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: maksqwe1 at ukr dot net
Target Milestone: ---
....................
#include <cstdio>
#include <stdint.h>
typedef unsigned int uint;
uintptr_t g_array[131];
uintptr_t foo1(void *ptr)
{
constexpr size_t size = sizeof(g_array) / sizeof(uintptr_t);
return g_array[uint(uintptr_t(ptr)) % size];
}
uintptr_t foo2(void *ptr)
{
constexpr size_t size = sizeof(g_array) / sizeof(uintptr_t);
return g_array[uintptr_t(ptr) % size];
}
....................
This code produce more worse assembly code for foo2() compared to clang.
----------- x86-64 GCC 6.3(-O2 -std=c++11) -----------
foo1(void*):
mov eax, edi
mov edx, -98358029
mul edx
shr edx, 7
imul edx, edx, 131
sub edi, edx
mov rax, QWORD PTR g_array[0+rdi*8]
ret
foo2(void*):
mov rax, rdi
movabs rdx, 281629680514649643
mul rdx
shr rdx
mov rax, rdx
sal rax, 6
add rax, rdx
lea rax, [rdx+rax*2]
sub rdi, rax
mov rax, QWORD PTR g_array[0+rdi*8]
ret
g_array:
.zero 1048
------------------------------------------------------
----------- x86-64 CLang 3.9(-O2 -std=c++11) ---------
foo1(void*): # @foo1(void*)
mov ecx, edi
movabs rdx, 281629680514649643
mov rax, rcx
mul rdx
shr rdx
imul rax, rdx, 131
sub rcx, rax
mov rax, qword ptr [8*rcx + g_array]
ret
foo2(void*): # @foo2(void*)
movabs rcx, 281629680514649643
mov rax, rdi
mul rcx
shr rdx
imul rax, rdx, 131
sub rdi, rax
mov rax, qword ptr [8*rdi + g_array]
ret
g_array:
.zero 1048
------------------------------------------------------
https://godbolt.org/g/PEyju2
