[libcxx] r277357 - Improve shared_ptr dtor performance
Ben Craig via cfe-commits
cfe-commits at lists.llvm.org
Mon Aug 1 10:51:27 PDT 2016
Date: Mon Aug 1 12:51:26 2016
New Revision: 277357
Improve shared_ptr dtor performance
If the last destruction is uncontended, skip the atomic store on
__shared_weak_owners_. This shifts some costs from normal
shared_ptr usage to weak_ptr uses.
--- libcxx/trunk/src/memory.cpp (original)
+++ libcxx/trunk/src/memory.cpp Mon Aug 1 12:51:26 2016
@@ -96,7 +96,35 @@ __shared_weak_count::__release_shared()
- if (decrement(__shared_weak_owners_) == -1)
+ // NOTE: The acquire load here is an optimization of the very
+ // common case where a shared pointer is being destructed while
+ // having no other contended references.
+ // BENEFIT: We avoid expensive atomic stores like XADD and STREX
+ // in a common case. Those instructions are slow and do nasty
+ // things to caches.
+ // IS THIS SAFE? Yes. During weak destruction, if we see that we
+ // are the last reference, we know that no-one else is accessing
+ // us. If someone were accessing us, then they would be doing so
+ // while the last shared / weak_ptr was being destructed, and
+ // that's undefined anyway.
+ // If we see anything other than a 0, then we have possible
+ // contention, and need to use an atomicrmw primitive.
+ // The same arguments don't apply for increment, where it is legal
+ // (though inadvisable) to share shared_ptr references between
+ // threads, and have them all get copied at once. The argument
+ // also doesn't apply for __release_shared, because an outstanding
+ // weak_ptr::lock() could read / modify the shared count.
+ if (__libcpp_atomic_load(&__shared_weak_owners_, _AO_Aquire) == 0)
+ // no need to do this store, because we are about
+ // to destroy everything.
+ //__libcpp_atomic_store(&__shared_weak_owners_, -1, _AO_Release);
+ else if (decrement(__shared_weak_owners_) == -1)
More information about the cfe-commits