From ecc69a1d99963b2b1bba92bdcefbfa8a8f1c497a Mon Sep 17 00:00:00 2001 From: Hal Finkel Date: Fri, 26 Oct 2012 19:38:09 +0000 Subject: [PATCH] Move target-specific BBVectorize tests into a separate directory. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166802 91177308-0d34-0410-b5e6-96231b3b80d8 --- test/Transforms/BBVectorize/X86/loop1.ll | 93 +++++++++++++++++++++++ test/Transforms/BBVectorize/X86/simple.ll | 44 +++++++++++ test/Transforms/BBVectorize/lit.local.cfg | 5 ++ test/Transforms/BBVectorize/loop1.ll | 3 - test/Transforms/BBVectorize/simple.ll | 8 -- 5 files changed, 142 insertions(+), 11 deletions(-) create mode 100644 test/Transforms/BBVectorize/X86/loop1.ll create mode 100644 test/Transforms/BBVectorize/X86/simple.ll diff --git a/test/Transforms/BBVectorize/X86/loop1.ll b/test/Transforms/BBVectorize/X86/loop1.ll new file mode 100644 index 00000000000..9d5d9fb6177 --- /dev/null +++ b/test/Transforms/BBVectorize/X86/loop1.ll @@ -0,0 +1,93 @@ +target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128" +target triple = "x86_64-unknown-linux-gnu" +; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7 -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s +; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7 -basicaa -loop-unroll -unroll-threshold=45 -unroll-allow-partial -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s -check-prefix=CHECK-UNRL +; The second check covers the use of alias analysis (with loop unrolling). + +define void @test1(double* noalias %out, double* noalias %in1, double* noalias %in2) nounwind uwtable { +entry: + br label %for.body +; CHECK: @test1 +; CHECK-UNRL: @test1 + +for.body: ; preds = %for.body, %entry + %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ] + %arrayidx = getelementptr inbounds double* %in1, i64 %indvars.iv + %0 = load double* %arrayidx, align 8 + %arrayidx2 = getelementptr inbounds double* %in2, i64 %indvars.iv + %1 = load double* %arrayidx2, align 8 + %mul = fmul double %0, %0 + %mul3 = fmul double %0, %1 + %add = fadd double %mul, %mul3 + %add4 = fadd double %1, %1 + %add5 = fadd double %add4, %0 + %mul6 = fmul double %0, %add5 + %add7 = fadd double %add, %mul6 + %mul8 = fmul double %1, %1 + %add9 = fadd double %0, %0 + %add10 = fadd double %add9, %0 + %mul11 = fmul double %mul8, %add10 + %add12 = fadd double %add7, %mul11 + %arrayidx14 = getelementptr inbounds double* %out, i64 %indvars.iv + store double %add12, double* %arrayidx14, align 8 + %indvars.iv.next = add i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 + %exitcond = icmp eq i32 %lftr.wideiv, 10 + br i1 %exitcond, label %for.end, label %for.body +; CHECK: %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ] +; CHECK: %arrayidx = getelementptr inbounds double* %in1, i64 %indvars.iv +; CHECK: %0 = load double* %arrayidx, align 8 +; CHECK: %arrayidx2 = getelementptr inbounds double* %in2, i64 %indvars.iv +; CHECK: %1 = load double* %arrayidx2, align 8 +; CHECK: %mul = fmul double %0, %0 +; CHECK: %mul3 = fmul double %0, %1 +; CHECK: %add = fadd double %mul, %mul3 +; CHECK: %add4.v.i1.1 = insertelement <2 x double> undef, double %1, i32 0 +; CHECK: %mul8 = fmul double %1, %1 +; CHECK: %add4.v.i1.2 = insertelement <2 x double> %add4.v.i1.1, double %0, i32 1 +; CHECK: %add4 = fadd <2 x double> %add4.v.i1.2, %add4.v.i1.2 +; CHECK: %add5.v.i1.1 = insertelement <2 x double> undef, double %0, i32 0 +; CHECK: %add5.v.i1.2 = insertelement <2 x double> %add5.v.i1.1, double %0, i32 1 +; CHECK: %add5 = fadd <2 x double> %add4, %add5.v.i1.2 +; CHECK: %mul6.v.i0.2 = insertelement <2 x double> %add5.v.i1.1, double %mul8, i32 1 +; CHECK: %mul6 = fmul <2 x double> %mul6.v.i0.2, %add5 +; CHECK: %mul6.v.r1 = extractelement <2 x double> %mul6, i32 0 +; CHECK: %mul6.v.r2 = extractelement <2 x double> %mul6, i32 1 +; CHECK: %add7 = fadd double %add, %mul6.v.r1 +; CHECK: %add12 = fadd double %add7, %mul6.v.r2 +; CHECK: %arrayidx14 = getelementptr inbounds double* %out, i64 %indvars.iv +; CHECK: store double %add12, double* %arrayidx14, align 8 +; CHECK: %indvars.iv.next = add i64 %indvars.iv, 1 +; CHECK: %lftr.wideiv = trunc i64 %indvars.iv.next to i32 +; CHECK: %exitcond = icmp eq i32 %lftr.wideiv, 10 +; CHECK: br i1 %exitcond, label %for.end, label %for.body +; CHECK-UNRL: %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next.1, %for.body ] +; CHECK-UNRL: %arrayidx = getelementptr inbounds double* %in1, i64 %indvars.iv +; CHECK-UNRL: %0 = bitcast double* %arrayidx to <2 x double>* +; CHECK-UNRL: %arrayidx2 = getelementptr inbounds double* %in2, i64 %indvars.iv +; CHECK-UNRL: %1 = bitcast double* %arrayidx2 to <2 x double>* +; CHECK-UNRL: %arrayidx14 = getelementptr inbounds double* %out, i64 %indvars.iv +; CHECK-UNRL: %2 = load <2 x double>* %0, align 8 +; CHECK-UNRL: %3 = load <2 x double>* %1, align 8 +; CHECK-UNRL: %mul = fmul <2 x double> %2, %2 +; CHECK-UNRL: %mul3 = fmul <2 x double> %2, %3 +; CHECK-UNRL: %add = fadd <2 x double> %mul, %mul3 +; CHECK-UNRL: %add4 = fadd <2 x double> %3, %3 +; CHECK-UNRL: %add5 = fadd <2 x double> %add4, %2 +; CHECK-UNRL: %mul6 = fmul <2 x double> %2, %add5 +; CHECK-UNRL: %add7 = fadd <2 x double> %add, %mul6 +; CHECK-UNRL: %mul8 = fmul <2 x double> %3, %3 +; CHECK-UNRL: %add9 = fadd <2 x double> %2, %2 +; CHECK-UNRL: %add10 = fadd <2 x double> %add9, %2 +; CHECK-UNRL: %mul11 = fmul <2 x double> %mul8, %add10 +; CHECK-UNRL: %add12 = fadd <2 x double> %add7, %mul11 +; CHECK-UNRL: %4 = bitcast double* %arrayidx14 to <2 x double>* +; CHECK-UNRL: store <2 x double> %add12, <2 x double>* %4, align 8 +; CHECK-UNRL: %indvars.iv.next.1 = add i64 %indvars.iv, 2 +; CHECK-UNRL: %lftr.wideiv.1 = trunc i64 %indvars.iv.next.1 to i32 +; CHECK-UNRL: %exitcond.1 = icmp eq i32 %lftr.wideiv.1, 10 +; CHECK-UNRL: br i1 %exitcond.1, label %for.end, label %for.body + +for.end: ; preds = %for.body + ret void +} diff --git a/test/Transforms/BBVectorize/X86/simple.ll b/test/Transforms/BBVectorize/X86/simple.ll new file mode 100644 index 00000000000..6450f821f5d --- /dev/null +++ b/test/Transforms/BBVectorize/X86/simple.ll @@ -0,0 +1,44 @@ +target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128" +; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7 -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s + +; Basic depth-3 chain +define double @test1(double %A1, double %A2, double %B1, double %B2) { +; CHECK: @test1 +; CHECK: %X1.v.i1.1 = insertelement <2 x double> undef, double %B1, i32 0 +; CHECK: %X1.v.i0.1 = insertelement <2 x double> undef, double %A1, i32 0 +; CHECK: %X1.v.i1.2 = insertelement <2 x double> %X1.v.i1.1, double %B2, i32 1 +; CHECK: %X1.v.i0.2 = insertelement <2 x double> %X1.v.i0.1, double %A2, i32 1 + %X1 = fsub double %A1, %B1 + %X2 = fsub double %A2, %B2 +; CHECK: %X1 = fsub <2 x double> %X1.v.i0.2, %X1.v.i1.2 + %Y1 = fmul double %X1, %A1 + %Y2 = fmul double %X2, %A2 +; CHECK: %Y1 = fmul <2 x double> %X1, %X1.v.i0.2 + %Z1 = fadd double %Y1, %B1 + %Z2 = fadd double %Y2, %B2 +; CHECK: %Z1 = fadd <2 x double> %Y1, %X1.v.i1.2 + %R = fmul double %Z1, %Z2 +; CHECK: %Z1.v.r1 = extractelement <2 x double> %Z1, i32 0 +; CHECK: %Z1.v.r2 = extractelement <2 x double> %Z1, i32 1 +; CHECK: %R = fmul double %Z1.v.r1, %Z1.v.r2 + ret double %R +; CHECK: ret double %R +} + +; Basic chain with shuffles +define <8 x i8> @test6(<8 x i8> %A1, <8 x i8> %A2, <8 x i8> %B1, <8 x i8> %B2) { + %X1 = sub <8 x i8> %A1, %B1 + %X2 = sub <8 x i8> %A2, %B2 + %Y1 = mul <8 x i8> %X1, %A1 + %Y2 = mul <8 x i8> %X2, %A2 + %Z1 = add <8 x i8> %Y1, %B1 + %Z2 = add <8 x i8> %Y2, %B2 + %Q1 = shufflevector <8 x i8> %Z1, <8 x i8> %Z2, <8 x i32> + %Q2 = shufflevector <8 x i8> %Z2, <8 x i8> %Z2, <8 x i32> + %R = mul <8 x i8> %Q1, %Q2 + ret <8 x i8> %R +; CHECK-TI: @test6 +; CHECK-TI-NOT: sub <16 x i8> +; CHECK-TI: ret <8 x i8> +} + diff --git a/test/Transforms/BBVectorize/lit.local.cfg b/test/Transforms/BBVectorize/lit.local.cfg index 19eebc0ac7a..a8ad0f1a28b 100644 --- a/test/Transforms/BBVectorize/lit.local.cfg +++ b/test/Transforms/BBVectorize/lit.local.cfg @@ -1 +1,6 @@ config.suffixes = ['.ll', '.c', '.cpp'] + +targets = set(config.root.targets_to_build.split()) +if not 'X86' in targets: + config.unsupported = True + diff --git a/test/Transforms/BBVectorize/loop1.ll b/test/Transforms/BBVectorize/loop1.ll index ee38ef43fdc..bebc91ad91a 100644 --- a/test/Transforms/BBVectorize/loop1.ll +++ b/test/Transforms/BBVectorize/loop1.ll @@ -1,11 +1,8 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128" target triple = "x86_64-unknown-linux-gnu" ; RUN: opt < %s -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s -; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7 -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s ; RUN: opt < %s -basicaa -loop-unroll -unroll-threshold=45 -unroll-allow-partial -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s -check-prefix=CHECK-UNRL -; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7 -basicaa -loop-unroll -unroll-threshold=45 -unroll-allow-partial -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s -check-prefix=CHECK-UNRL ; The second check covers the use of alias analysis (with loop unrolling). -; Both checks are run with and without target information. define void @test1(double* noalias %out, double* noalias %in1, double* noalias %in2) nounwind uwtable { entry: diff --git a/test/Transforms/BBVectorize/simple.ll b/test/Transforms/BBVectorize/simple.ll index b6bca5e5193..7cd8133beec 100644 --- a/test/Transforms/BBVectorize/simple.ll +++ b/test/Transforms/BBVectorize/simple.ll @@ -1,6 +1,5 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128" ; RUN: opt < %s -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s -; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7 -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s -check-prefix=CHECK-TI ; Basic depth-3 chain define double @test1(double %A1, double %A2, double %B1, double %B2) { @@ -24,9 +23,6 @@ define double @test1(double %A1, double %A2, double %B1, double %B2) { ; CHECK: %R = fmul double %Z1.v.r1, %Z1.v.r2 ret double %R ; CHECK: ret double %R -; CHECK-TI: @test1 -; CHECK-TI: fsub <2 x double> -; CHECK-TI: ret double } ; Basic depth-3 chain (last pair permuted) @@ -150,9 +146,5 @@ define <8 x i8> @test6(<8 x i8> %A1, <8 x i8> %A2, <8 x i8> %B1, <8 x i8> %B2) { ; CHECK: %R = mul <8 x i8> %Q1.v.r1, %Q1.v.r2 ret <8 x i8> %R ; CHECK: ret <8 x i8> %R -; CHECK-TI: @test6 -; CHECK-TI-NOT: sub <16 x i8> -; CHECK-TI: ret <8 x i8> } -