diff --git a/src/include/storage/s_lock.h b/src/include/storage/s_lock.h
index 180c013..2a9c1c4 100644
--- a/src/include/storage/s_lock.h
+++ b/src/include/storage/s_lock.h
@@ -199,6 +199,15 @@ spin_delay(void)
 typedef unsigned char slock_t;
 
 #define TAS(lock) tas(lock)
+/*
+ * On Intel EM64T, it's a win to use a non-locking test before the xchg proper.
+ *
+ * See also Implementing Scalable Atomic Locks for Multi-Core Intel(tm) EM64T
+ * and IA32 by Michael Chynoweth and Mary R. Lee. As of this writing, it is
+ * available at:
+ * http://software.intel.com/en-us/articles/implementing-scalable-atomic-locks-for-multi-core-intel-em64t-and-ia32-architectures
+ */
+#define TAS_SPIN(lock)    (*(lock) ? 1 : TAS(lock))
 
 static __inline__ int
 tas(volatile slock_t *lock)