https://gcc.gnu.org/bugzilla/show_bug.cgi?id=86072
Bug ID: 86072
Summary: Poor codegen with atomics
Product: gcc
Version: 9.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c++
Assignee: unassigned at gcc dot gnu.org
Reporter: redbeard0531 at gmail dot com
Target Milestone: ---
https://godbolt.org/g/aEFhq8
#include <atomic>
std::atomic<int> progress{-1};
void combine_writes1() {
// These should be reduced to a single store(0,release),
// At least as long as release-sequnce includes same-thread
// relaxed stores. If that is removed, this should just be
// a single relaxed store.
progress.store(0, std::memory_order_relaxed);
progress.store(0, std::memory_order_relaxed);
progress.store(0, std::memory_order_release);
progress.store(0, std::memory_order_release);
progress.store(0, std::memory_order_relaxed);
progress.store(0, std::memory_order_relaxed);
}
void combine_writes2() {
// Ditto above, but should store 5.
progress.store(0, std::memory_order_relaxed);
progress.store(1, std::memory_order_relaxed);
progress.store(2, std::memory_order_release);
progress.store(3, std::memory_order_release);
progress.store(4, std::memory_order_relaxed);
progress.store(5, std::memory_order_relaxed);
}
void combine_loads() {
// These should be reduced to either a single acquire-load
// or an acquire fence.
progress.load(std::memory_order_relaxed);
progress.load(std::memory_order_relaxed);
progress.load(std::memory_order_acquire);
progress.load(std::memory_order_acquire);
progress.load(std::memory_order_relaxed);
progress.load(std::memory_order_relaxed);
}
combine_writes1():
xor eax, eax
mov DWORD PTR progress[rip], eax
mov DWORD PTR progress[rip], eax
mov DWORD PTR progress[rip], eax
mov DWORD PTR progress[rip], eax
mov DWORD PTR progress[rip], eax
mov DWORD PTR progress[rip], eax
ret
combine_writes2():
mov DWORD PTR progress[rip], 0
mov DWORD PTR progress[rip], 1
mov DWORD PTR progress[rip], 2
mov DWORD PTR progress[rip], 3
mov DWORD PTR progress[rip], 4
mov DWORD PTR progress[rip], 5
ret
combine_loads():
mov eax, DWORD PTR progress[rip]
mov eax, DWORD PTR progress[rip]
mov eax, DWORD PTR progress[rip]
mov eax, DWORD PTR progress[rip]
mov eax, DWORD PTR progress[rip]
mov eax, DWORD PTR progress[rip]
ret
progress:
.long -1
This example seems to ICE segfaulting gcc trunk: https://godbolt.org/g/M4ZQGS
Possibly related: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=86056
