[llvm] r303763 - [LV] Update type in cost model for scalarization
Matthew Simpson via llvm-commits
llvm-commits at lists.llvm.org
Mon May 29 19:54:54 PDT 2017
Sorry for the breakage. I just returned from vacation and will take a look.
Thanks for the test case.
-- Matt
On Fri, May 26, 2017 at 11:22 PM, Yung, Douglas via llvm-commits <
llvm-commits at lists.llvm.org> wrote:
> Hi Matthew,
>
> Your commit seems to have caused a crash in one of our internal code
> bases. I have filed the details in PR33193. Can you take a look?
>
> Douglas Yung
>
> > -----Original Message-----
> > From: llvm-commits [mailto:llvm-commits-bounces at lists.llvm.org] On
> Behalf Of
> > Matthew Simpson via llvm-commits
> > Sent: Wednesday, May 24, 2017 8:26
> > To: llvm-commits at lists.llvm.org
> > Subject: [llvm] r303763 - [LV] Update type in cost model for
> scalarization
> >
> > Author: mssimpso
> > Date: Wed May 24 10:26:15 2017
> > New Revision: 303763
> >
> > URL: http://llvm.org/viewvc/llvm-project?rev=303763&view=rev
> > Log:
> > [LV] Update type in cost model for scalarization
> >
> > For non-uniform instructions marked for scalarization, we should update
> > `VectorTy` when computing instruction costs to reflect the scalar type.
> In
> > addition to determining instruction costs, this type is also used to
> signal
> > that all instructions in the loop will be scalarized. This currently
> affects
> > memory instructions and non-pointer induction variables and their
> updates. (We
> > also mark GEPs scalar after vectorization, but their cost is computed
> together
> > with memory instructions.) For scalarized induction updates, this patch
> also
> > scales the scalar cost by the vectorization factor, corresponding to each
> > induction step.
> >
> > Added:
> > llvm/trunk/test/Transforms/LoopVectorize/AArch64/no_
> vector_instructions.ll
> > Modified:
> > llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
> >
> > Modified: llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
> > URL: http://llvm.org/viewvc/llvm-
> > project/llvm/trunk/lib/Transforms/Vectorize/
> LoopVectorize.cpp?rev=303763&r1=30
> > 3762&r2=303763&view=diff
> > ============================================================
> ==================
> > --- llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp (original)
> > +++ llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp Wed May 24
> > +++ 10:26:15 2017
> > @@ -7173,7 +7173,7 @@ LoopVectorizationCostModel::getInstructi
> > // Note: Even if all instructions are scalarized, return true if any
> memory
> > // accesses appear in the loop to get benefits from address folding
> etc.
> > bool TypeNotScalarized =
> > - VF > 1 && !VectorTy->isVoidTy() && TTI.getNumberOfParts(VectorTy)
> < VF;
> > + VF > 1 && VectorTy->isVectorTy() &&
> > + TTI.getNumberOfParts(VectorTy) < VF;
> > return VectorizationCostTy(C, TypeNotScalarized); }
> >
> > @@ -7312,7 +7312,7 @@ unsigned LoopVectorizationCostModel::get
> > Type *RetTy = I->getType();
> > if (canTruncateToMinimalBitwidth(I, VF))
> > RetTy = IntegerType::get(RetTy->getContext(), MinBWs[I]);
> > - VectorTy = ToVectorTy(RetTy, VF);
> > + VectorTy = isScalarAfterVectorization(I, VF) ? RetTy :
> > + ToVectorTy(RetTy, VF);
> > auto SE = PSE.getSE();
> >
> > // TODO: We need to estimate the cost of intrinsic calls.
> > @@ -7445,9 +7445,10 @@ unsigned LoopVectorizationCostModel::get
> > } else if (Legal->isUniform(Op2)) {
> > Op2VK = TargetTransformInfo::OK_UniformValue;
> > }
> > - SmallVector<const Value *, 4> Operands(I->operand_values());
> > - return TTI.getArithmeticInstrCost(I->getOpcode(), VectorTy, Op1VK,
> > - Op2VK, Op1VP, Op2VP, Operands);
> > + SmallVector<const Value *, 4> Operands(I->operand_values());
> > + unsigned N = isScalarAfterVectorization(I, VF) ? VF : 1;
> > + return N * TTI.getArithmeticInstrCost(I->getOpcode(), VectorTy,
> Op1VK,
> > + Op2VK, Op1VP, Op2VP,
> > + Operands);
> > }
> > case Instruction::Select: {
> > SelectInst *SI = cast<SelectInst>(I); @@ -7470,7 +7471,15 @@
> unsigned
> > LoopVectorizationCostModel::get
> > }
> > case Instruction::Store:
> > case Instruction::Load: {
> > - VectorTy = ToVectorTy(getMemInstValueType(I), VF);
> > + unsigned Width = VF;
> > + if (Width > 1) {
> > + InstWidening Decision = getWideningDecision(I, Width);
> > + assert(Decision != CM_Unknown &&
> > + "CM decision should be taken at this point");
> > + if (Decision == CM_Scalarize)
> > + Width = 1;
> > + }
> > + VectorTy = ToVectorTy(getMemInstValueType(I), Width);
> > return getMemoryInstructionCost(I, VF);
> > }
> > case Instruction::ZExt:
> >
> > Added:
> > llvm/trunk/test/Transforms/LoopVectorize/AArch64/no_
> vector_instructions.ll
> > URL: http://llvm.org/viewvc/llvm-
> > project/llvm/trunk/test/Transforms/LoopVectorize/
> AArch64/no_vector_instruction
> > s.ll?rev=303763&view=auto
> > ============================================================
> ==================
> > --- llvm/trunk/test/Transforms/LoopVectorize/AArch64/no_
> vector_instructions.ll
> > (added)
> > +++ llvm/trunk/test/Transforms/LoopVectorize/AArch64/no_vector_instructi
> > +++ ons.ll Wed May 24 10:26:15 2017
> > @@ -0,0 +1,26 @@
> > +; REQUIRES: asserts
> > +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -S
> > +-debug-only=loop-vectorize 2>&1 | FileCheck %s
> > +
> > +target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:
> 64-i128:128-n32:64-S128"
> > +target triple = "aarch64--linux-gnu"
> > +
> > +; CHECK-LABEL: all_scalar
> > +; CHECK: LV: Found scalar instruction: %i.next = add nuw nsw i64
> %i, 2
> > +; CHECK: LV: Found an estimated cost of 2 for VF 2 For
> instruction:
> > %i.next = add nuw nsw i64 %i, 2
> > +; CHECK: LV: Not considering vector loop of width 2 because it
> will not
> > generate any vector instructions
> > +;
> > +define void @all_scalar(i64* %a, i64 %n) {
> > +entry:
> > + br label %for.body
> > +
> > +for.body:
> > + %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
> > + %tmp0 = getelementptr i64, i64* %a, i64 %i
> > + store i64 0, i64* %tmp0, align 1
> > + %i.next = add nuw nsw i64 %i, 2
> > + %cond = icmp eq i64 %i.next, %n
> > + br i1 %cond, label %for.end, label %for.body
> > +
> > +for.end:
> > + ret void
> > +}
> >
> >
> > _______________________________________________
> > llvm-commits mailing list
> > llvm-commits at lists.llvm.org
> > http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-commits
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at lists.llvm.org
> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-commits
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170529/ea4bde31/attachment.html>
More information about the llvm-commits
mailing list