https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94084
Bug ID: 94084
Summary: Optimizer produces suboptimal code related to
loop-invariant
Product: gcc
Version: 9.2.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c
Assignee: unassigned at gcc dot gnu.org
Reporter: zhongyunde at huawei dot com
Target Milestone: ---
For the following case1 and case2, we can known the global value base is a loop
invariant value, so the load insn can be lifted out of the loop kernel.
But we can find that the case1 and case2 have different result, and the code of
case1 need more optimization.
test base on the x86-64 with https://gcc.godbolt.org/
== [case1] ======================================
extern int base;
void foo (int dest[], int src[], int n)
{
int i;
// #pragma no_swp
for (i=0; i < n; i++)
dest[base+i] = src[base+i];
}
foo:
test edx, edx
jle .L1
xor ecx, ecx
.L3:
mov eax, DWORD PTR base[rip] /* expected exist out of loop */
add eax, ecx
add ecx, 1
cdqe
mov r8d, DWORD PTR [rsi+rax*4]
mov DWORD PTR [rdi+rax*4], r8d
cmp edx, ecx
jne .L3
.L1:
ret
== [case2] ======================================
extern int base;
extern int dest[], src[];
void foo (int n)
{
int i;
// #pragma no_swp
for (i=0; i < n; i++)
dest[base+i] = src[base+i];
}
foo:
test edi, edi
jle .L1
movsx rdx, DWORD PTR base[rip] /* already exist out of loop */
lea ecx, [rdi-1]
lea rcx, [rdx+1+rcx]
lea rax, [0+rdx*4]
sal rcx, 2
.L3:
mov edx, DWORD PTR src[rax]
add rax, 4
mov DWORD PTR dest[rax-4], edx
cmp rax, rcx
jne .L3
.L1:
ret
