Horton

Commits

DateSubjectAuthorReleases
2013-06-04 Add ARM64 (aarch64) support to s_lock.h. Tom Lane 9.2.5
2013-06-04 Add ARM64 (aarch64) support to s_lock.h. Tom Lane 9.3.0
2012-01-07 Use __sync_lock_test_and_set() for spinlocks on ARM, if available. Tom Lane 8.3.18
2012-01-07 Use __sync_lock_test_and_set() for spinlocks on ARM, if available. Tom Lane 8.4.11
2012-01-07 Use __sync_lock_test_and_set() for spinlocks on ARM, if available. Tom Lane 9.0.7
2012-01-07 Use __sync_lock_test_and_set() for spinlocks on ARM, if available. Tom Lane 9.1.3
2012-01-07 Use __sync_lock_test_and_set() for spinlocks on ARM, if available. Tom Lane 9.2.0
2012-01-03 Use a non-locking initial test in TAS_SPIN on PPC. Tom Lane 9.2.0
2012-01-02 Use LWSYNC in place of SYNC/ISYNC in PPC spinlocks, where possible. Tom Lane 9.2.0
2012-01-02 Use 4-byte slock_t on both PPC and PPC64. Tom Lane 9.2.0
2012-01-02 Use mutex hint bit in PPC LWARX instructions, where possible. Tom Lane 9.2.0
2011-08-29 Use a non-locking test in TAS_SPIN() on all IA64 platforms. Tom Lane 9.2.0
2009-12-31 Redefine Datum as uintptr_t, instead of unsigned long. Tom Lane 9.0.0
2009-07-27 Add s_lock support for SuperH architecture. Tom Lane 9.0.0
2007-08-05 Apparently icc doesn't always define __ICC, and it's more correct to Tom Lane 8.3.0
2007-07-16 Hmm, so evidently _check_lock and _clear_lock take an argument of type Tom Lane 8.3.0
2007-07-16 So our reward for including <sys/atomic_op.h> seems to be a bunch of Tom Lane 8.3.0
2007-07-16 On AIX, include <sys/atomic_op.h> so that the functions we use for Tom Lane 8.3.0
2007-05-04 tas() support for Renesas' M32R processor. Kazuhiro Inaoka Tom Lane 8.3.0
2006-11-28 Back-patch HEAD's fixes to recognize __ppc64__ as equivalent to __powerpc64__. Tom Lane 8.1.6
2006-06-01 Back-port Postgres 7.4 spinlock code into 7.3 branch. This adds Tom Lane 7.3.16
2006-04-19 Recognize __ppc64__, which seems to be Apple's spelling of the predefined Tom Lane 8.2.0
2005-10-11 Add infrastructure for making spins_per_delay variable depending on Tom Lane 8.1.0
2005-10-11 Don't use a non-locked pre-test of the spinlock on x86_64 machines. Tom Lane 8.1.0
2005-08-29 Sigh, looks like you need '.set mips2' before you can access MIPS Tom Lane 8.0.4