https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114559
Bug ID: 114559
Summary: After function inlining some optimizations missing
Product: gcc
Version: 14.0
Status: UNCONFIRMED
Keywords: missed-optimization
Severity: normal
Priority: P3
Component: middle-end
Assignee: unassigned at gcc dot gnu.org
Reporter: antoshkka at gmail dot com
Target Milestone: ---
Consider the example:
template <class Func>
int AtomicUpdate(int& atomic, Func updater) {
int old_value = atomic;
while (true) {
const int new_value = updater(int{old_value});
if (old_value == new_value) return old_value;
if (__atomic_compare_exchange_n(&atomic, &old_value, new_value, 1, 5, 5))
return new_value;
}
}
int AtomicMin(int& atomic, int value) {
return AtomicUpdate(atomic, [value](int old_value) {
return value < old_value ? value : old_value;
});
}
With -O2 GCC produces the assembly:
AtomicMin(int&, int):
mov eax, DWORD PTR [rdi]
.L3:
cmp esi, eax
mov edx, eax
cmovle edx, esi
jge .L4
lock cmpxchg DWORD PTR [rdi], edx
jne .L3
.L1:
mov eax, edx
ret
.L4:
mov edx, eax
jmp .L1
However, a more optimal assembly is possible:
AtomicMin(int&, int): # @AtomicMin(int&, int)
mov eax, dword ptr [rdi]
.LBB0_1: # =>This Inner Loop Header: Depth=1
cmp eax, esi
jle .LBB0_4
lock cmpxchg dword ptr [rdi], esi
jne .LBB0_1
mov eax, esi
.LBB0_4:
ret
Note that manual inlining of the lambda improves the codegen:
int AtomicMin(int& atomic, int value) {
int old_value = atomic;
while (true) {
const int new_value = (value < old_value ? value : old_value);
if (old_value == new_value) return old_value;
if (__atomic_compare_exchange_n(&atomic, &old_value, new_value, 1, 5, 5))
return new_value;
}
}
Results in
AtomicMin(int&, int):
mov eax, DWORD PTR [rdi]
.L3:
cmp esi, eax
mov edx, eax
cmovle edx, esi
jge .L1
lock cmpxchg DWORD PTR [rdi], edx
jne .L3
.L1:
mov eax, edx
ret
Godbolt playground: https://godbolt.org/z/G6YEGb15q
