Commit cf9e4fbd authored by Hans Wennborg's avatar Hans Wennborg
Browse files

Merging r322473: 

------------------------------------------------------------------------
r322473 | a.elovikov | 2018-01-15 02:56:07 -0800 (Mon, 15 Jan 2018) | 23 lines

[LV] Don't call recordVectorLoopValueForInductionCast for newly-created IV from a trunc.

Summary:
This method is supposed to be called for IVs that have casts in their use-def
chains that are completely ignored after vectorization under PSE. However, for
truncates of such IVs the same InductionDescriptor is used during
creation/widening of both original IV based on PHINode and new IV based on
TruncInst.

This leads to unintended second call to recordVectorLoopValueForInductionCast
with a VectorLoopVal set to the newly created IV for a trunc and causes an
assert due to attempt to store new information for already existing entry in the
map. This is wrong and should not be done.

Fixes PR35773.

Reviewers: dorit, Ayal, mssimpso

Reviewed By: dorit

Subscribers: RKSimon, dim, dcaballe, hsaito, llvm-commits, hiraditya

Differential Revision: https://reviews.llvm.org/D41913
------------------------------------------------------------------------

llvm-svn: 322673
parent d461c802

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

+7 −2
Original line number Diff line number Diff line
@@ -2630,9 +2630,12 @@ void InnerLoopVectorizer::createVectorIntOrFpInductionPHI( 
  Instruction *LastInduction = VecInd;

  for (unsigned Part = 0; Part < UF; ++Part) {

    VectorLoopValueMap.setVectorValue(EntryVal, Part, LastInduction);

    recordVectorLoopValueForInductionCast(II, LastInduction, Part);



    if (isa<TruncInst>(EntryVal))

      addMetadata(LastInduction, EntryVal);

    else

      recordVectorLoopValueForInductionCast(II, LastInduction, Part);



    LastInduction = cast<Instruction>(addFastMathFlag(

        Builder.CreateBinOp(AddOp, LastInduction, SplatVF, "step.add")));

  }
@@ -2754,15 +2757,17 @@ void InnerLoopVectorizer::widenIntOrFpInduction(PHINode *IV, TruncInst *Trunc) { 


  // If we haven't yet vectorized the induction variable, splat the scalar

  // induction variable, and build the necessary step vectors.

  // TODO: Don't do it unless the vectorized IV is really required.

  if (!VectorizedIV) {

    Value *Broadcasted = getBroadcastInstrs(ScalarIV);

    for (unsigned Part = 0; Part < UF; ++Part) {

      Value *EntryPart =

          getStepVector(Broadcasted, VF * Part, Step, ID.getInductionOpcode());

      VectorLoopValueMap.setVectorValue(EntryVal, Part, EntryPart);

      recordVectorLoopValueForInductionCast(ID, EntryPart, Part);

      if (Trunc)

        addMetadata(EntryPart, Trunc);

      else

        recordVectorLoopValueForInductionCast(ID, EntryPart, Part);

    }

  }

llvm/test/Transforms/LoopVectorize/pr35773.ll

0 → 100644
+53 −0
Original line number Diff line number Diff line 
; RUN: opt -S -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 < %s 2>&1 | FileCheck %s

target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"

@a = common local_unnamed_addr global i32 0, align 4

@b = common local_unnamed_addr global i8 0, align 1



; Function Attrs: norecurse nounwind uwtable

define void @doit1() local_unnamed_addr{

entry:

  br label %for.body



for.body:

  %main.iv = phi i32 [ 0, %entry ], [ %inc, %for.body ]



  %i8.iv = phi i8 [ 0, %entry ], [ %i8.add, %for.body ]

  %i32.iv = phi i32 [ 0, %entry ], [ %i32.add, %for.body ]



  %trunc.to.be.converted.to.new.iv = trunc i32 %i32.iv to i8

  %i8.add = add i8 %i8.iv, %trunc.to.be.converted.to.new.iv



  %noop.conv.under.pse = and i32 %i32.iv, 255

  %i32.add = add nuw nsw i32 %noop.conv.under.pse, 9



  %inc = add i32 %main.iv, 1

  %tobool = icmp eq i32 %inc, 16

  br i1 %tobool, label %for.cond.for.end_crit_edge, label %for.body



; CHECK-LABEL: @doit1(

; CHECK:       vector.body:

; CHECK-NEXT:    [[MAIN_IV:%.*]] = phi i32 [ 0, [[VECTOR_PH:%.*]] ], [ [[MAIN_IV_NEXT:%.*]], [[VECTOR_BODY:%.*]] ]

; CHECK-NEXT:    [[I8_IV:%.*]] = phi <4 x i8> [ zeroinitializer, [[VECTOR_PH]] ], [ [[I8_IV_NEXT:%.*]], [[VECTOR_BODY]] ]

; CHECK-NEXT:    [[I32_IV:%.*]] = phi <4 x i32> [ <i32 0, i32 9, i32 18, i32 27>, [[VECTOR_PH]] ], [ [[I32_IV_NEXT:%.*]], [[VECTOR_BODY]] ]

; CHECK-NEXT:    [[IV_FROM_TRUNC:%.*]] = phi <4 x i8> [ <i8 0, i8 9, i8 18, i8 27>, [[VECTOR_PH]] ], [ [[IV_FROM_TRUNC_NEXT:%.*]], [[VECTOR_BODY]] ]



; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[MAIN_IV]], i32 0

; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer

; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i32> [[BROADCAST_SPLAT]], <i32 0, i32 1, i32 2, i32 3>

; CHECK-NEXT:    [[TMP7:%.*]] = add i32 [[MAIN_IV]], 0



; CHECK-NEXT:    [[I8_IV_NEXT]] = add <4 x i8> [[I8_IV]], [[IV_FROM_TRUNC]]



; CHECK-NEXT:    [[MAIN_IV_NEXT]] = add i32 [[MAIN_IV]], 4

; CHECK-NEXT:    [[I32_IV_NEXT]] = add <4 x i32> [[I32_IV]], <i32 36, i32 36, i32 36, i32 36>

; CHECK-NEXT:    [[IV_FROM_TRUNC_NEXT]] = add <4 x i8> [[IV_FROM_TRUNC]], <i8 36, i8 36, i8 36, i8 36>

; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i32 [[MAIN_IV_NEXT]], 16

; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0



for.cond.for.end_crit_edge:

  store i8 %i8.add, i8* @b, align 1

  br label %for.end



for.end:

  ret void

}