[llvm] r218607 - [AArch64] Improve cost model to handle sdiv by a pow-of-two.

[Jim Grosbach]

Woot! Thanks, Chad.

-Jim

> On Sep 29, 2014, at 6:59 AM, Chad Rosier <mcrosier at codeaurora.org> wrote:
> 
> Author: mcrosier
> Date: Mon Sep 29 08:59:31 2014
> New Revision: 218607
> 
> URL: http://llvm.org/viewvc/llvm-project?rev=218607&view=rev
> Log:
> [AArch64] Improve cost model to handle sdiv by a pow-of-two.
> 
> This patch improves the target-specific cost model to better handle signed
> division by a power of two. The immediate result is that this enables the SLP
> vectorizer to do a better job.
> 
> http://reviews.llvm.org/D5469
> PR20714
> 
> Added:
>    llvm/trunk/test/Transforms/SLPVectorizer/AArch64/sdiv-pow2.ll
> Modified:
>    llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
> 
> Modified: llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp?rev=218607&r1=218606&r2=218607&view=diff
> ==============================================================================
> --- llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp (original)
> +++ llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp Mon Sep 29 08:59:31 2014
> @@ -413,6 +413,29 @@ unsigned AArch64TTI::getArithmeticInstrC
> 
>   int ISD = TLI->InstructionOpcodeToISD(Opcode);
> 
> +  if (ISD == ISD::SDIV &&
> +      Opd2Info == TargetTransformInfo::OK_UniformConstantValue &&
> +      Opd2PropInfo == TargetTransformInfo::OP_PowerOf2) {
> +    // On AArch64, scalar signed division by constants power-of-two are
> +    // normally expanded to the sequence ADD + CMP + SELECT + SRA.
> +    // The OperandValue properties many not be same as that of previous
> +    // operation; conservatively assume OP_None.
> +    unsigned Cost =
> +      getArithmeticInstrCost(Instruction::Add, Ty, Opd1Info, Opd2Info,
> +                             TargetTransformInfo::OP_None,
> +                             TargetTransformInfo::OP_None);
> +    Cost += getArithmeticInstrCost(Instruction::Sub, Ty, Opd1Info, Opd2Info,
> +                                   TargetTransformInfo::OP_None,
> +                                   TargetTransformInfo::OP_None);
> +    Cost += getArithmeticInstrCost(Instruction::Select, Ty, Opd1Info, Opd2Info,
> +                                   TargetTransformInfo::OP_None,
> +                                   TargetTransformInfo::OP_None);
> +    Cost += getArithmeticInstrCost(Instruction::AShr, Ty, Opd1Info, Opd2Info,
> +                                   TargetTransformInfo::OP_None,
> +                                   TargetTransformInfo::OP_None);
> +    return Cost;
> +  }
> +
>   switch (ISD) {
>   default:
>     return TargetTransformInfo::getArithmeticInstrCost(
> 
> Added: llvm/trunk/test/Transforms/SLPVectorizer/AArch64/sdiv-pow2.ll
> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/SLPVectorizer/AArch64/sdiv-pow2.ll?rev=218607&view=auto
> ==============================================================================
> --- llvm/trunk/test/Transforms/SLPVectorizer/AArch64/sdiv-pow2.ll (added)
> +++ llvm/trunk/test/Transforms/SLPVectorizer/AArch64/sdiv-pow2.ll Mon Sep 29 08:59:31 2014
> @@ -0,0 +1,42 @@
> +; RUN: opt < %s -basicaa -slp-vectorizer -S -mtriple=aarch64-unknown-linux-gnu -mcpu=cortex-a57 | FileCheck %s
> +target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
> +target triple = "aarch64--linux-gnu"
> +
> +; CHECK-LABEL: @test1
> +; CHECK: load <4 x i32>
> +; CHECK: add nsw <4 x i32>
> +; CHECK: sdiv <4 x i32>
> +
> +define void @test1(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32* noalias nocapture readonly %c) {
> +entry:
> +  %0 = load i32* %b, align 4
> +  %1 = load i32* %c, align 4
> +  %add = add nsw i32 %1, %0
> +  %div = sdiv i32 %add, 2
> +  store i32 %div, i32* %a, align 4
> +  %arrayidx3 = getelementptr inbounds i32* %b, i64 1
> +  %2 = load i32* %arrayidx3, align 4
> +  %arrayidx4 = getelementptr inbounds i32* %c, i64 1
> +  %3 = load i32* %arrayidx4, align 4
> +  %add5 = add nsw i32 %3, %2
> +  %div6 = sdiv i32 %add5, 2
> +  %arrayidx7 = getelementptr inbounds i32* %a, i64 1
> +  store i32 %div6, i32* %arrayidx7, align 4
> +  %arrayidx8 = getelementptr inbounds i32* %b, i64 2
> +  %4 = load i32* %arrayidx8, align 4
> +  %arrayidx9 = getelementptr inbounds i32* %c, i64 2
> +  %5 = load i32* %arrayidx9, align 4
> +  %add10 = add nsw i32 %5, %4
> +  %div11 = sdiv i32 %add10, 2
> +  %arrayidx12 = getelementptr inbounds i32* %a, i64 2
> +  store i32 %div11, i32* %arrayidx12, align 4
> +  %arrayidx13 = getelementptr inbounds i32* %b, i64 3
> +  %6 = load i32* %arrayidx13, align 4
> +  %arrayidx14 = getelementptr inbounds i32* %c, i64 3
> +  %7 = load i32* %arrayidx14, align 4
> +  %add15 = add nsw i32 %7, %6
> +  %div16 = sdiv i32 %add15, 2
> +  %arrayidx17 = getelementptr inbounds i32* %a, i64 3
> +  store i32 %div16, i32* %arrayidx17, align 4
> +  ret void
> +}
> 
> 
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits