Daniel Neilson 36d6cce30a [InstCombine] Fold compare of int constant against a splatted vector of ints ...

Summary:
Folding patterns like:
  %vec = shufflevector <4 x i8> %insvec, <4 x i8> undef, <4 x i32> zeroinitializer
  %cast = bitcast <4 x i8> %vec to i32
  %cond = icmp eq i32 %cast, 0
into:
  %ext = extractelement <4 x i8> %insvec, i32 0
  %cond = icmp eq i32 %ext, 0

Combined with existing rules, this allows us to fold patterns like:
  %insvec = insertelement <4 x i8> undef, i8 %val, i32 0
  %vec = shufflevector <4 x i8> %insvec, <4 x i8> undef, <4 x i32> zeroinitializer
  %cast = bitcast <4 x i8> %vec to i32
  %cond = icmp eq i32 %cast, 0
into:
  %cond = icmp eq i8 %val, 0

When we construct a splat vector via a shuffle, and bitcast the vector into an integer type for comparison against an integer constant. Then we can simplify the the comparison to compare the splatted value against the integer constant.

Reviewers: spatel, anna, mkazantsev

Reviewed By: spatel

Subscribers: efriedma, rengolin, llvm-commits

Differential Revision: https://reviews.llvm.org/D44997

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@329087 91177308-0d34-0410-b5e6-96231b3b80d8

2018-04-03 17:26:20 +00:00

..

ADCE

[ADCE][Dominators] Reapply: Teach ADCE to preserve dominators

2017-08-22 16:30:21 +00:00

AddDiscriminators

Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)

2018-01-19 17:13:12 +00:00

AggressiveInstCombine

[AggressiveInstCombine] Fixed TruncCombine class to handle TruncInst leaf node correctly.

2018-01-31 22:39:05 +00:00

AlignmentFromAssumptions

[AlignmentFromAssumptions] Set source and dest alignments of memory intrinsiscs separately

2018-02-22 18:55:59 +00:00

ArgumentPromotion

[ArgumentPromotion] don't break musttail invariant PR36543

2018-03-02 00:59:27 +00:00

AtomicExpand

Add address space mangling to lifetime intrinsics

2017-04-10 20:18:21 +00:00

BDCE

[BDCE] Salvage debug info from dying insts

2018-02-21 01:55:33 +00:00

BlockExtractor

BlockExtractor: Don’t delete functions directly

2018-03-12 22:28:18 +00:00

BranchFolding

Move branch folding test to a better location.

2015-12-03 19:41:25 +00:00

CalledValuePropagation

Add CalledValuePropagation pass

2017-10-25 13:40:08 +00:00

CallSiteSplitting

[CallSiteSplitting] Do not crash when BB's terminator changes.

2018-03-06 14:00:58 +00:00

CodeExtractor

[PartialInlining] Use isInlineViable to detect constructs preventing inlining.

2018-03-10 14:53:44 +00:00

CodeGenPrepare

[CGP] Fix the remove of matched phis in complex addressing mode

2018-03-12 03:50:07 +00:00

ConstantHoisting

Fix out-of-order stepping behavior in programs with hoisted constants.

2017-11-09 20:01:31 +00:00

ConstantMerge

Canonicalize the representation of empty an expression in DIGlobalVariableExpression

2017-08-30 18:06:51 +00:00

ConstProp

[TargetLibraryInfo] fix finite mathlib function availability

2018-01-08 17:38:09 +00:00

Coroutines

[Coroutines] Avoid assert splitting hidden coros

2018-04-02 23:39:40 +00:00

CorrelatedValuePropagation

Re-re-land: Teach CorrelatedValuePropagation to reduce the width of udiv/urem instructions.

2018-03-21 14:08:21 +00:00

CrossDSOCFI

[cfi] Build __cfi_check as Thumb when applicable.

2017-08-29 22:29:15 +00:00

DCE

[DCE] Salvage debug info from dead insts

2018-02-15 22:26:18 +00:00

DeadArgElim

[DeadArgumentElim] Clone function level metadatas

2018-04-02 17:27:38 +00:00

DeadStoreElimination

[DSE] Don't DSE stores that subsequent memmove calls read from

2018-02-20 23:19:34 +00:00

DivRemPairs

[DivRemPairs] split tests per target to account for bots that don't build for all targets

2017-09-09 14:10:59 +00:00

EarlyCSE

[EarlyCSE] Don't hide earler invariant.scopes

2018-03-15 18:12:27 +00:00

EliminateAvailableExternally

[PM] Port EliminateAvailableExternally pass to the new pass manager.

2016-05-05 02:37:32 +00:00

EntryExitInstrumenter

EntryExitInstrumenter: set DebugLocs on the inserted call instructions (PR35412)

2017-11-28 18:44:26 +00:00

ExpandMemCmp/X86

[x86, MemCmpExpansion] allow 2 pairs of loads per block (PR33325)

2018-01-06 16:16:04 +00:00

Float2Int

[PM] Port float2int to the new pass manager

2016-06-24 23:32:02 +00:00

ForcedFunctionAttrs

[attrs] Split off the forced attributes utility into its own pass that

2015-12-27 08:13:45 +00:00

FunctionAttrs

[PM][FunctionAttrs] add NoUnwind attribute inference to PostOrderFunctionAttrs pass

2018-03-23 21:46:16 +00:00

FunctionImport

[ThinLTO] Add an import cutoff for debugging/triaging

2018-04-01 15:54:40 +00:00

GCOVProfiling

Canonicalize the representation of empty an expression in DIGlobalVariableExpression

2017-08-30 18:06:51 +00:00

GlobalDCE

[PM] Teach the PGO instrumentation pasess to run GlobalDCE before

2017-05-25 07:15:09 +00:00

GlobalMerge

Canonicalize the representation of empty an expression in DIGlobalVariableExpression

2017-08-30 18:06:51 +00:00

GlobalOpt

[Evaluator] Evaluate load/store with bitcast

2018-03-13 10:19:50 +00:00

GlobalSplit

Fix one-after-the-end type metadata handling in globalsplit.

2017-03-07 22:18:48 +00:00

GuardWidening

[GuardWidening] Fix incorrect use of remove_if

2016-05-21 02:24:44 +00:00

GVN

Mark MergedLoadStoreMotion as not preserving MemDep results

2018-02-23 10:41:57 +00:00

GVNHoist

[MemorySSA] Fix exponential compile-time updating MemorySSA.

2018-03-26 19:52:54 +00:00

GVNSink

Add an @llvm.sideeffect intrinsic

2017-11-08 21:59:51 +00:00

IndirectBrExpand

Introduce the "retpoline" x86 mitigation technique for variant #2 of the speculative execution vulnerabilities disclosed today, specifically identified by CVE-2017-5715, "Branch Target Injection", and is one of the two halves to Spectre..

2018-01-22 22:05:25 +00:00

IndVarSimplify

[SCEV] Make exact taken count calculation more optimistic

2018-03-27 07:30:38 +00:00

InferAddressSpaces

[AMDGPU] Switch to the new addr space mapping by default

2018-02-02 16:07:16 +00:00

InferFunctionAttrs

Add argmononly attribute to strlen and wcslen, i.e. they only read memory (string) passed to them.

2017-06-18 03:10:26 +00:00

Inline

Treat inlining a notail call as a regular, non-tail call

2018-04-02 21:23:16 +00:00

InstCombine

[InstCombine] Fold compare of int constant against a splatted vector of ints

2018-04-03 17:26:20 +00:00

InstMerge

Remove the load hoisting code of MLSM, it is completely subsumed by GVNHoist

2017-01-24 19:55:36 +00:00

InstNamer

Add basic test case for -instnamer

2017-05-08 23:18:46 +00:00

InstSimplify

[PatternMatch] allow undef elements when matching vector FP +0.0

2018-03-25 21:16:33 +00:00

InterleavedAccess

[X86][LLVM]Expanding Supports lowerInterleaved{store|load}() in X86InterleavedAccess (VF64 stride 3-4)

2017-10-02 07:35:25 +00:00

Internalize

[Internalize] Test that __stack_chk_{guard, fail} are not internalized.

2016-06-05 19:08:54 +00:00

IPConstantProp

[IPSCCP] do not break musttail invariant (PR36485)

2018-03-01 01:19:18 +00:00

IRCE

[IRCE] Enable decreasing loops of non-const bound

2018-03-27 08:24:53 +00:00

JumpThreading

[JumpThreading] Don't select an edge that we know we can't thread

2018-03-29 16:01:26 +00:00

LCSSA

[Test] Fix the test to output to /dev/null instead of redirecting.

2018-02-23 19:03:04 +00:00

LICM

[LICM] Salvage DI from dying Instructions

2018-03-18 15:59:19 +00:00

LoadStoreVectorizer

[AMDGPU] Supported ds_read_b128 generation; Widened vector length for local address-space.

2018-03-09 17:41:39 +00:00

LoopDataPrefetch

[PM] Port LoopDataPrefetch AArch64 tests to new pass manager

2016-08-22 12:59:58 +00:00

LoopDeletion

[LoopDeletion] Handle users in unreachable block

2018-01-12 07:24:43 +00:00

LoopDistribute

Move test of lazy BFI with ORE to a generic directory

2017-01-13 00:16:23 +00:00

LoopIdiom

Adding a width of the GEP index to the Data Layout.

2018-02-14 06:58:08 +00:00

LoopInterchange

[LoopInterchange] Update tests so DA can handle access after D35430.

2018-04-03 16:37:58 +00:00

LoopLoadElim

[PM] Port LoopLoadElimination to the new pass manager and wire it into

2017-01-27 01:32:26 +00:00

LoopPredication

[LoopPredication] Add profitability check based on BPI

2018-03-22 16:03:59 +00:00

LoopReroll

Remove the obsolete offset parameter from @llvm.dbg.value

2017-07-28 20:21:02 +00:00

LoopRotate

[LoopRotate] Rotate loops with loop exiting latches

2018-04-01 12:48:24 +00:00

LoopSimplify

[SCEV] Make exact taken count calculation more optimistic

2018-03-27 07:30:38 +00:00

LoopSimplifyCFG

LPM: Drop require<loops> from these tests, it's redundant. NFC

2016-05-10 18:28:10 +00:00

LoopStrengthReduce

Revert "[PowerPC] LSR tunings for PowerPC"

2018-03-09 16:08:55 +00:00

LoopUnroll

peel loops with runtime small trip counts

2018-04-03 03:39:43 +00:00

LoopUnswitch

[SimplifyCFG] Re-apply Relax restriction for folding unconditional branches

2018-02-08 07:16:29 +00:00

LoopVectorize

[InstCombine] reassociate loop invariant GEP chains to enable LICM

2018-03-26 16:19:31 +00:00

LoopVersioning

[LAA] Correctly return a half-open range in expandBounds

2017-04-05 09:24:26 +00:00

LoopVersioningLICM

[LAA] Correctly return a half-open range in expandBounds

2017-04-05 09:24:26 +00:00

LowerAtomic

LowerAtomic: Don't skip optnone functions; atomic still need lowering (PR34020)

2017-08-23 15:43:28 +00:00

LowerExpectIntrinsic

Fix builin_expect lowering bug

2017-06-07 18:32:24 +00:00

LowerGuardIntrinsic

[PM] Port LowerGuardIntrinsic to the new PM.

2016-07-28 22:08:41 +00:00

LowerInvoke

[PM] Port LowerInvoke to the new pass manager

2016-08-12 17:28:27 +00:00

LowerSwitch

LowerSwitch: Fix producing invalid IR on unreachable code

2017-04-21 23:54:12 +00:00

LowerTypeTests

Use branch funnels for virtual calls when retpoline mitigation is enabled.

2018-03-09 19:11:44 +00:00

Mem2Reg

[Debugify] Add a pass to test debug info preservation

2017-12-08 21:57:28 +00:00

MemCpyOpt

[MemCpyOpt] Update to new API for memory intrinsic alignment

2018-03-21 14:14:55 +00:00

MergeFunc

Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)

2018-01-19 17:13:12 +00:00

MergeICmps

[MergeICmp] Fix a bug in entry block shuffled to middle of the chain

2018-03-20 11:57:54 +00:00

MetaRenamer

Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)

2018-01-19 17:13:12 +00:00

NameAnonGlobals

[ThinLTO] Ensure anonymous globals renamed even at -O0

2016-09-17 20:40:16 +00:00

NaryReassociate

Add early exit on reassociation of 0 expression.

2018-03-07 02:17:08 +00:00

NewGVN

[InstCombine, NewGVN] remove FP undef from tests

2018-03-08 14:57:08 +00:00

ObjCARC

[ObjCARC] Add funclet token to ARC marker

2018-03-20 20:45:41 +00:00

PartiallyInlineLibCalls

[PartiallyInlineLibCalls][x86] add TTI hook to allow sqrt inlining to depend on arg rather than result

2017-11-27 21:15:43 +00:00

PGOProfile

[PGO] Fix branch probability remarks assert

2018-03-27 18:55:56 +00:00

PhaseOrdering

Adding a width of the GEP index to the Data Layout.

2018-02-14 06:58:08 +00:00

PlaceSafepoints

Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)

2018-01-19 17:13:12 +00:00

PreISelIntrinsicLowering

[PM] Port PreISelIntrinsicLowering to the new PM

2016-06-24 20:13:42 +00:00

PruneEH

[PM][FunctionAttrs] add NoUnwind attribute inference to PostOrderFunctionAttrs pass

2018-03-23 21:46:16 +00:00

Reassociate

[Reassociate] fix test to be independent of FP undef

2018-03-08 22:05:27 +00:00

Reg2Mem

Move the personality function from LandingPadInst to Function

2015-06-17 20:52:32 +00:00

RewriteStatepointsForGC

[RewriteStatepoints] Fix stale parse points

2018-03-05 22:27:30 +00:00

SafeStack

[SafeStack] Use updated CreateMemCpy API to set more accurate source and destination alignments.

2018-02-12 22:39:47 +00:00

SampleProfile

Profiling tests: Endianess XFAIL for powerpc- (32-bit)

2018-01-09 20:09:23 +00:00

Scalarizer

Remove the obsolete offset parameter from @llvm.dbg.value

2017-07-28 20:21:02 +00:00

SCCP

Revert r328307: [IPSCCP] Use constant range information for comparisons of parameters.

2018-03-23 12:49:39 +00:00

SeparateConstOffsetFromGEP

[AMDGPU] Change constant addr space to 4

2018-02-13 18:00:25 +00:00

SimpleLoopUnswitch

[PM/Unswitch] Teach SimpleLoopUnswitch to do non-trivial unswitching,

2017-11-17 19:58:36 +00:00

SimplifyCFG

[SimplifyCFG] Create attribute for fuzzing-specific optimizations.

2018-03-22 17:07:51 +00:00

Sink

[Sink] Really really fix predicate in legality check

2018-01-11 21:28:57 +00:00

SLPVectorizer

[SLP] Fix PR36481: vectorize reassociated instructions.

2018-04-03 17:14:47 +00:00

SpeculateAroundPHIs

Add a new pass to speculate around PHI nodes with constant (integer) operands when profitable.

2017-11-28 11:32:31 +00:00

SpeculativeExecution

Revert r301950: SpeculativeExecution: Stop using whitelist for costs

2017-05-10 12:30:07 +00:00

SROA

[SROA] Take advantage of separate alignments for memcpy source and destination

2018-03-13 14:25:33 +00:00

StraightLineStrengthReduce

AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel

2017-03-21 21:39:51 +00:00

StripDeadPrototypes

[PM] Port StripDeadPrototypes to the new pass manager

2015-10-30 23:28:12 +00:00

StripSymbols

Canonicalize the representation of empty an expression in DIGlobalVariableExpression

2017-08-30 18:06:51 +00:00

StructurizeCFG

[StructurizeCFG] fix test to be independent of FP undef

2018-03-08 17:13:57 +00:00

SyntheticCountsPropagation

Add a pass to generate synthetic function entry counts.

2018-01-09 19:39:35 +00:00

TailCallElim

Remove this test

2017-11-28 22:39:38 +00:00

ThinLTOBitcodeWriter

[ThinLTO] fix test failure without x86 backend

2018-02-06 07:03:09 +00:00

Util

LowerDbgDeclare: ignore dbg.declares for allocas with volatile access

2018-03-09 00:45:04 +00:00

WholeProgramDevirt

Use branch funnels for virtual calls when retpoline mitigation is enabled.

2018-03-09 19:11:44 +00:00