emscripten-fastcomp/test/CodeGen/X86/atomic8.ll, branch 1.13.2LLVM with the emscripten fastcomp javascript backendhttps://git.amat.us/emscripten-fastcomp/atom/test/CodeGen/X86/atomic8.ll?h=1.13.22013-03-06T00:17:04ZFix PR153552013-03-06T00:17:04ZMichael Liaomichael.liao@intel.com2013-03-06T00:17:04Zurn:sha1:c537f79dcd9d91577b8e0a41c11f68b628d73af4
- Clear 'mayStore' flag when loading from the atomic variable before the
spin loop
- Clear kill flag from one use to multiple use in registers forming the
address to that atomic variable
- don't use a physical register as live-in register in BB (neither entry
nor landing pad.) by copying it into virtual register
(patch by Cameron Zwarich)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176538 91177308-0d34-0410-b5e6-96231b3b80d8
Add missing i8 max/min/umax/umin support2012-09-21T03:18:52ZMichael Liaomichael.liao@intel.com2012-09-21T03:18:52Zurn:sha1:fe87c302aa600fdac6d80349cde21e06337f8bfe
- Fix PR5145 and turn on test 8-bit atomic ops
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164358 91177308-0d34-0410-b5e6-96231b3b80d8
Re-work X86 code generation of atomic ops with spin-loop2012-09-20T03:06:15ZMichael Liaomichael.liao@intel.com2012-09-20T03:06:15Zurn:sha1:b118a073d7434727a4ea5a5762f54e54e72bef4f
- Rewrite/merge pseudo-atomic instruction emitters to address the
following issue:
* Reduce one unnecessary load in spin-loop
previously the spin-loop looks like
thisMBB:
newMBB:
ld t1 = [bitinstr.addr]
op t2 = t1, [bitinstr.val]
not t3 = t2 (if Invert)
mov EAX = t1
lcs dest = [bitinstr.addr], t3 [EAX is implicit]
bz newMBB
fallthrough -->nextMBB
the 'ld' at the beginning of newMBB should be lift out of the loop
as lcs (or CMPXCHG on x86) will load the current memory value into
EAX. This loop is refined as:
thisMBB:
EAX = LOAD [MI.addr]
mainMBB:
t1 = OP [MI.val], EAX
LCMPXCHG [MI.addr], t1, [EAX is implicitly used & defined]
JNE mainMBB
sinkMBB:
* Remove immopc as, so far, all pseudo-atomic instructions has
all-register form only, there is no immedidate operand.
* Remove unnecessary attributes/modifiers in pseudo-atomic instruction
td
* Fix issues in PR13458
- Add comprehensive tests on atomic ops on various data types.
NOTE: Some of them are turned off due to missing functionality.
- Revise tests due to the new spin-loop generated.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164281 91177308-0d34-0410-b5e6-96231b3b80d8