Matt Arsenault 24ce89b717 Fix asserts in AMDGCN fmed3 folding by handling more cases of NaN ... Better NaN handling for AMDGCN fmed3. All operands are checked for NaN now. The checks were moved before the canonicalization to provide a better mapping from fclamp. Changed the behaviour of fmed3(x,y,NaN) to return max(x,y) instead of min(x,y) in light of this. Updated tests as a result and added some new cases to cover the fix. Patch by Alan Baker llvm-svn: 336375		2018-07-05 17:05:36 +00:00
..
AggressiveInstCombine	Move Analysis/Utils/Local.h back to Transforms	2018-06-04 21:23:21 +00:00
Coroutines	Move Analysis/Utils/Local.h back to Transforms	2018-06-04 21:23:21 +00:00
Hello	…
IPO	[UnrollAndJam] New Unroll and Jam pass	2018-07-01 12:47:30 +00:00
InstCombine	Fix asserts in AMDGCN fmed3 folding by handling more cases of NaN	2018-07-05 17:05:36 +00:00
Instrumentation	[HWASan] Do not retag allocas before return from the function.	2018-06-29 20:20:17 +00:00
ObjCARC	ProvenanceAnalysis: Store WeakTrackingVH instead of Value* in UnderlyingValue Cache.	2018-06-21 05:14:00 +00:00
Scalar	[PM/LoopUnswitch] Fix PR37651 by correctly invalidating SCEV when	2018-07-03 09:13:27 +00:00
Utils	[DebugInfo] Corrections for salvageDebugInfo	2018-07-03 11:29:00 +00:00
Vectorize	[SLPVectorizer] Begin abstracting InstructionsState alternate matching away from opcodes. NFCI.	2018-07-05 12:30:44 +00:00
CMakeLists.txt	Another try to commit 323321 (aggressive instruction combine).	2018-01-25 12:06:32 +00:00
LLVMBuild.txt	Another try to commit 323321 (aggressive instruction combine).	2018-01-25 12:06:32 +00:00