llvm-project/llvm/test/Transforms
Marek Olsak 33eb4d947d AMDGPU: Add a fast path for icmp.i1(src, false, NE)
Summary:
This allows moving the condition from the intrinsic to the standard ICmp
opcode, so that LLVM can do simplifications on it. The icmp.i1 intrinsic
is an identity for retrieving the SGPR mask.

And we can also get the mask from and i1, or i1, xor i1.

Reviewers: arsenm, nhaehnle

Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits

Differential Revision: https://reviews.llvm.org/D52060

llvm-svn: 351150
2019-01-15 02:13:18 +00:00
..
ADCE
AddDiscriminators
AggressiveInstCombine [AggressiveInstCombine] convert rotate with guard branch into funnel shift (PR34924) 2018-12-17 21:14:51 +00:00
AlignmentFromAssumptions
ArgumentPromotion [IPO][AVR] Create new Functions in the default address space specified in the data layout 2018-12-18 09:52:52 +00:00
AtomicExpand AMDGPU: Expand atomicrmw nand in IR 2018-10-02 03:50:56 +00:00
BDCE [BDCE] Remove dead uses of arguments 2019-01-04 21:21:43 +00:00
BlockExtractor [hot-cold-split] Name split functions with ".cold" suffix 2018-10-24 18:53:47 +00:00
BranchFolding
CallSiteSplitting [CallSiteSplitting] Report edge deletion to DomTreeUpdater 2018-11-29 15:27:04 +00:00
CalledValuePropagation
CanonicalizeAliases [ThinLTO] Handle chains of aliases 2019-01-04 19:04:54 +00:00
CodeExtractor [CodeExtractor] Do not extract unsafe lifetime markers 2019-01-04 17:43:22 +00:00
CodeGenPrepare [CodeGenPrepare] Fix bad IR created by large offset GEP splitting. 2018-12-19 22:52:04 +00:00
ConstProp [ConstantFolding] Fold undef for integer intrinsics 2019-01-11 21:18:00 +00:00
ConstantHoisting X86/TargetTransformInfo: Report div/rem constant immediate costs as TCC_Free 2018-10-11 23:14:35 +00:00
ConstantMerge
Coroutines [coroutines] Improve suspend point simplification 2018-12-11 21:23:09 +00:00
CorrelatedValuePropagation [test] Add a set of test for constant folding deopt operands with CVP 2018-12-13 00:54:05 +00:00
CrossDSOCFI
DCE
DeadArgElim [IPO][AVR] Create new Functions in the default address space specified in the data layout 2018-12-18 09:52:52 +00:00
DeadStoreElimination [BasicAA] Don't assume tail calls with byval don't alias allocas 2018-08-14 01:24:35 +00:00
DivRemPairs
EarlyCSE [EarlyCSE] If DI can't be salvaged, mark it as unavailable. 2018-12-17 01:42:39 +00:00
EliminateAvailableExternally
EntryExitInstrumenter
ExpandMemCmp/X86 Re-land r349731 "[CodeGen][ExpandMemcmp] Add an option for allowing overlapping loads. 2018-12-20 13:01:04 +00:00
Float2Int
ForcedFunctionAttrs
FunctionAttrs [FuncAttrs] Remove "access range attributes" for read-none functions 2018-09-11 11:51:29 +00:00
FunctionImport [ThinLTO] Allow importing of functions with var args 2018-12-01 05:11:46 +00:00
GCOVProfiling [DebugInfo] IR/Bitcode changes for DISubprogram flags. 2018-11-28 21:14:32 +00:00
GVN [GVN] Don't perform scalar PRE on GEPs 2018-12-06 16:11:58 +00:00
GVNHoist [MemorySSAUpdater] Avoid creating self-referencing MemoryDefs 2018-09-11 14:29:59 +00:00
GVNSink [Local] Make DoesKMove required for combineMetadata. 2018-08-24 11:40:04 +00:00
GlobalDCE GlobalDCE: Teach isEmptyFunction() to ignore debug intrinsics. 2018-11-16 17:47:21 +00:00
GlobalMerge [GlobalMerge] Allow merging globals with explicit section markings. 2018-08-02 23:54:16 +00:00
GlobalOpt [DebugInfo][GlobalOpt] Fix -debugify for globalopt shrinking globals to booleans. 2018-10-23 16:35:51 +00:00
GlobalSplit
GuardWidening [GuardWidening] Ignore guards with trivial conditions 2018-08-22 02:40:49 +00:00
HotColdSplit [CodeExtractor] Do not extract unsafe lifetime markers 2019-01-04 17:43:22 +00:00
IPConstantProp Recommit r333268: [IPSCCP] Use PredicateInfo to propagate facts from cmp instructions. 2018-08-23 11:04:00 +00:00
IRCE Revert "[SCEV][NFC] Check NoWrap flags before lexicographical comparison of SCEVs" 2018-08-27 21:41:37 +00:00
IndVarSimplify Return "[IndVars] Smart hard uses detection" 2018-11-08 11:54:35 +00:00
IndirectBrExpand
InferAddressSpaces AMDGPU: Fix tests using old number for constant address space 2018-09-10 02:54:25 +00:00
InferFunctionAttrs Allow norecurse attribute on functions that have debug infos. 2018-12-05 16:48:00 +00:00
Inline [Inliner] Assert that the computed inline threshold is non-negative. 2019-01-09 19:26:17 +00:00
InstCombine AMDGPU: Add a fast path for icmp.i1(src, false, NE) 2019-01-15 02:13:18 +00:00
InstMerge [DebugInfo][InstMerge] Fix -debugify for phi node created by -mldst-motion 2018-11-02 18:25:41 +00:00
InstNamer
InstSimplify [ConstantFolding] Consolidate and extend bitcount intrinsic tests; NFC 2018-12-20 19:46:52 +00:00
InterleavedAccess
Internalize
JumpThreading [Jump Threading] Unfold a select insn that feeds a switch via a phi node 2019-01-11 15:52:57 +00:00
LCSSA [DebugInfo][LCSSA] Rewrite pre-existing debug values outside loop 2018-10-16 08:06:48 +00:00
LICM Use MemorySSA in LICM to do sinking and hoisting. 2019-01-10 19:29:04 +00:00
LoadStoreVectorizer [PM] Port LoadStoreVectorizer to the new pass manager. 2018-12-07 08:23:37 +00:00
LoopDataPrefetch
LoopDeletion Fix RUN line in test/Transforms/LoopDeletion/crashbc.ll 2019-01-10 09:58:23 +00:00
LoopDistribute [Unroll/UnrollAndJam/Vectorizer/Distribute] Add followup loop attributes. 2018-12-12 17:32:52 +00:00
LoopIdiom [LoopIdiomRecognize] Add CTTZ support 2018-12-26 21:59:48 +00:00
LoopInstSimplify Update MemorySSA in LoopInstSimplify. 2018-08-22 20:05:21 +00:00
LoopInterchange [LoopInterchange] Support reductions across inner and outer loop. 2018-11-08 20:44:19 +00:00
LoopLoadElim
LoopPredication
LoopReroll
LoopRotate Update MemorySSA in LoopRotate. 2018-10-24 22:46:45 +00:00
LoopSimplify Revert r346810 "Preserve loop metadata when splitting exit blocks" 2018-11-14 01:47:32 +00:00
LoopSimplifyCFG [NFC] Add failing test on LCSSA form preservation of LoopSimplifyCFG 2018-12-28 10:43:37 +00:00
LoopStrengthReduce [LoopStrengthReduce] ComplexityLimit as an option 2018-11-29 08:34:22 +00:00
LoopTransformWarning [TransformWarning] Do not warn missed transformations in optnone functions. 2018-12-14 19:45:43 +00:00
LoopUnroll [UnrollRuntime] Fix domTree failures in multiexit unrolling 2019-01-08 17:16:25 +00:00
LoopUnrollAndJam [Unroll/UnrollAndJam/Vectorizer/Distribute] Add followup loop attributes. 2018-12-12 17:32:52 +00:00
LoopUnswitch Update MemorySSA in LoopUnswitch. 2018-09-11 19:19:21 +00:00
LoopVectorize [LoopVectorizer] give more advice in remark about failure to vectorize call 2019-01-12 15:27:15 +00:00
LoopVersioning Re-apply "[SCEV] Strengthen StrengthenNoWrapFlags (reapply r334428)." 2018-07-13 23:58:46 +00:00
LoopVersioningLICM
LowerAtomic
LowerExpectIntrinsic
LowerGuardIntrinsic
LowerInvoke
LowerSwitch
LowerTypeTests [LowerTypeTests] Limit when icall jumptable entries are emitted 2018-07-13 19:57:39 +00:00
MakeGuardsExplicit Introduce llvm.experimental.widenable_condition intrinsic 2018-12-07 14:39:46 +00:00
Mem2Reg [Mem2Reg] Fix nondeterministic corner case 2018-11-30 19:20:02 +00:00
MemCpyOpt [BasicAA] Fix AA bug on dynamic allocas and stackrestore 2018-12-21 19:59:03 +00:00
MergeFunc [MergeFunc] Erase unused duplicate functions if they are discardable 2019-01-11 17:56:35 +00:00
MergeICmps [MergeICmps] Do not perform the transformation if GEP is used outside of block 2018-11-05 18:16:32 +00:00
MetaRenamer
NameAnonGlobals
NaryReassociate
NewGVN [NewGVN] Update use counts for SSA copies when replacing them by their operands. 2018-12-15 00:32:38 +00:00
ObjCARC Teach ObjCARC optimizer about equivalent PHIs when eliminating autoreleaseRV/retainRV pairs 2019-01-03 01:38:08 +00:00
PGOProfile [PGO] Exit early if all count values are zero 2018-11-07 23:51:20 +00:00
PartiallyInlineLibCalls
PhaseOrdering [InstCombine] canonicalize raw IR rotate patterns to funnel shift 2019-01-01 21:51:39 +00:00
PlaceSafepoints
PreISelIntrinsicLowering Preserve the linkage for objc* intrinsics as clang will set them to weak_external in some cases 2018-12-18 22:42:08 +00:00
PruneEH [Transforms] Preserve metadata when converting invoke to call. 2018-12-14 18:15:11 +00:00
Reassociate [PatternMatch] Handle undef vectors consistently 2018-11-20 16:08:19 +00:00
Reg2Mem
RewriteStatepointsForGC NFC - Various typo fixes in tests 2018-07-04 13:28:39 +00:00
SCCP [ConstantFold] Use getMinSignedBits for APInt in isIndexInRangeOfArrayType. 2018-12-12 18:55:14 +00:00
SLPVectorizer Update GettingStarted guide to recommend that people use the new 2019-01-14 22:27:32 +00:00
SROA Introduce llvm.loop.parallel_accesses and llvm.access.group metadata. 2018-12-20 04:58:07 +00:00
SafeStack SafeStack: Prevent OOB reads with mem intrinsics 2018-08-30 20:44:51 +00:00
SampleProfile [SampleFDO] handle ProfileSampleAccurate when initializing function entry count 2018-12-13 21:51:42 +00:00
ScalarizeMaskedMemIntrin/X86 [ScalarizeMaskedMemIntrin] Use MinAlign to calculate alignment for the scalar load/stores to handle element types that are byte-sized but not powers of 2. 2018-09-28 03:35:37 +00:00
Scalarizer Introduce llvm.loop.parallel_accesses and llvm.access.group metadata. 2018-12-20 04:58:07 +00:00
SeparateConstOffsetFromGEP
SimpleLoopUnswitch Update MemorySSA in SimpleLoopUnswitch. 2018-12-04 14:23:37 +00:00
SimplifyCFG Introduce llvm.loop.parallel_accesses and llvm.access.group metadata. 2018-12-20 04:58:07 +00:00
Sink
SpeculateAroundPHIs
SpeculativeExecution
StraightLineStrengthReduce [SLSR] use 'match' to simplify code; NFC 2018-10-23 14:07:39 +00:00
StripDeadPrototypes
StripSymbols
StructurizeCFG StructurizeCFG: Simplify inserted PHI nodes 2018-10-17 15:37:41 +00:00
SyntheticCountsPropagation
TailCallElim [TailCallElim] Enable marking of calls with byval as tails 2018-10-08 18:03:40 +00:00
ThinLTOBitcodeWriter [LTO] Record whether LTOUnit splitting is enabled in index 2019-01-11 18:31:57 +00:00
Util [Util] Refer to [s|z]exts of args when converting dbg.declares (fix PR35400) 2018-12-15 00:03:33 +00:00
WholeProgramDevirt [ThinLTO] Efficiency fix for writing type id records in per-module indexes 2018-09-25 20:14:40 +00:00