diff options
Diffstat (limited to 'test/Transforms/LoopVectorize')
101 files changed, 1161 insertions, 359 deletions
diff --git a/test/Transforms/LoopVectorize/12-12-11-if-conv.ll b/test/Transforms/LoopVectorize/12-12-11-if-conv.ll index 1e1396f800851..a292afbd58820 100644 --- a/test/Transforms/LoopVectorize/12-12-11-if-conv.ll +++ b/test/Transforms/LoopVectorize/12-12-11-if-conv.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -enable-if-conversion -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -enable-if-conversion -dce -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/2012-10-20-infloop.ll b/test/Transforms/LoopVectorize/2012-10-20-infloop.ll index aa7cc0ee325d4..b3eae690423d9 100644 --- a/test/Transforms/LoopVectorize/2012-10-20-infloop.ll +++ b/test/Transforms/LoopVectorize/2012-10-20-infloop.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce ; Check that we don't fall into an infinite loop. define void @test() nounwind { diff --git a/test/Transforms/LoopVectorize/2012-10-22-isconsec.ll b/test/Transforms/LoopVectorize/2012-10-22-isconsec.ll index ae9f998fee268..16d64eab25c3f 100644 --- a/test/Transforms/LoopVectorize/2012-10-22-isconsec.ll +++ b/test/Transforms/LoopVectorize/2012-10-22-isconsec.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -dce -force-vector-unroll=1 -force-vector-width=4 +; RUN: opt < %s -loop-vectorize -dce -force-vector-interleave=1 -force-vector-width=4 ; Check that we don't crash. diff --git a/test/Transforms/LoopVectorize/AArch64/sdiv-pow2.ll b/test/Transforms/LoopVectorize/AArch64/sdiv-pow2.ll new file mode 100644 index 0000000000000..a01d54312a60e --- /dev/null +++ b/test/Transforms/LoopVectorize/AArch64/sdiv-pow2.ll @@ -0,0 +1,31 @@ +; RUN: opt < %s -loop-vectorize -mtriple=aarch64-unknown-linux-gnu -mcpu=cortex-a57 -S | FileCheck %s +target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128" +target triple = "aarch64--linux-gnu" + +%struct.anon = type { [100 x i32], i32, [100 x i32] } + +@Foo = common global %struct.anon zeroinitializer, align 4 + +; CHECK-LABEL: @foo( +; CHECK: load <4 x i32>* +; CHECK: sdiv <4 x i32> +; CHECK: store <4 x i32> + +define void @foo(){ +entry: + br label %for.body + +for.body: ; preds = %for.body, %entry + %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ] + %arrayidx = getelementptr inbounds %struct.anon* @Foo, i64 0, i32 2, i64 %indvars.iv + %0 = load i32* %arrayidx, align 4 + %div = sdiv i32 %0, 2 + %arrayidx2 = getelementptr inbounds %struct.anon* @Foo, i64 0, i32 0, i64 %indvars.iv + store i32 %div, i32* %arrayidx2, align 4 + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + %exitcond = icmp eq i64 %indvars.iv.next, 100 + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body + ret void +} diff --git a/test/Transforms/LoopVectorize/X86/already-vectorized.ll b/test/Transforms/LoopVectorize/X86/already-vectorized.ll index 9c69ba87f392d..29d74a0645e8d 100644 --- a/test/Transforms/LoopVectorize/X86/already-vectorized.ll +++ b/test/Transforms/LoopVectorize/X86/already-vectorized.ll @@ -39,8 +39,8 @@ for.end: ; preds = %for.body } ; Now, we check for the Hint metadata -; CHECK: [[vect]] = metadata !{metadata [[vect]], metadata [[width:![0-9]+]], metadata [[unroll:![0-9]+]]} -; CHECK: [[width]] = metadata !{metadata !"llvm.loop.vectorize.width", i32 1} -; CHECK: [[unroll]] = metadata !{metadata !"llvm.loop.interleave.count", i32 1} -; CHECK: [[scalar]] = metadata !{metadata [[scalar]], metadata [[width]], metadata [[unroll]]} +; CHECK: [[vect]] = distinct !{[[vect]], [[width:![0-9]+]], [[unroll:![0-9]+]]} +; CHECK: [[width]] = !{!"llvm.loop.vectorize.width", i32 1} +; CHECK: [[unroll]] = !{!"llvm.loop.interleave.count", i32 1} +; CHECK: [[scalar]] = distinct !{[[scalar]], [[width]], [[unroll]]} diff --git a/test/Transforms/LoopVectorize/X86/assume.ll b/test/Transforms/LoopVectorize/X86/assume.ll new file mode 100644 index 0000000000000..a94e24dd7e9cf --- /dev/null +++ b/test/Transforms/LoopVectorize/X86/assume.ll @@ -0,0 +1,100 @@ +; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7 -S | FileCheck %s +target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" +target triple = "x86_64-unknown-linux-gnu" + +; Function Attrs: nounwind uwtable +define void @test1(float* noalias nocapture %a, float* noalias nocapture readonly %b) #0 { +entry: + br label %for.body + +; CHECK-LABEL: @test1 +; CHECK: vector.body: +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: for.body: +; CHECK: ret void + +for.body: ; preds = %for.body, %entry + %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ] + %arrayidx = getelementptr inbounds float* %b, i64 %indvars.iv + %0 = load float* %arrayidx, align 4 + %cmp1 = fcmp ogt float %0, 1.000000e+02 + tail call void @llvm.assume(i1 %cmp1) + %add = fadd float %0, 1.000000e+00 + %arrayidx5 = getelementptr inbounds float* %a, i64 %indvars.iv + store float %add, float* %arrayidx5, align 4 + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + %exitcond = icmp eq i64 %indvars.iv, 1599 + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body + ret void +} + +; Function Attrs: nounwind +declare void @llvm.assume(i1) #1 + +attributes #0 = { nounwind uwtable } +attributes #1 = { nounwind } + +%struct.data = type { float*, float* } + +; Function Attrs: nounwind uwtable +define void @test2(%struct.data* nocapture readonly %d) #0 { +entry: + %b = getelementptr inbounds %struct.data* %d, i64 0, i32 1 + %0 = load float** %b, align 8 + %ptrint = ptrtoint float* %0 to i64 + %maskedptr = and i64 %ptrint, 31 + %maskcond = icmp eq i64 %maskedptr, 0 + %a = getelementptr inbounds %struct.data* %d, i64 0, i32 0 + %1 = load float** %a, align 8 + %ptrint2 = ptrtoint float* %1 to i64 + %maskedptr3 = and i64 %ptrint2, 31 + %maskcond4 = icmp eq i64 %maskedptr3, 0 + br label %for.body + +; CHECK-LABEL: @test2 +; CHECK: vector.body: +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: @llvm.assume +; CHECK: for.body: +; CHECK: ret void + +for.body: ; preds = %for.body, %entry + %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ] + tail call void @llvm.assume(i1 %maskcond) + %arrayidx = getelementptr inbounds float* %0, i64 %indvars.iv + %2 = load float* %arrayidx, align 4 + %add = fadd float %2, 1.000000e+00 + tail call void @llvm.assume(i1 %maskcond4) + %arrayidx5 = getelementptr inbounds float* %1, i64 %indvars.iv + store float %add, float* %arrayidx5, align 4 + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + %exitcond = icmp eq i64 %indvars.iv, 1599 + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body + ret void +} + diff --git a/test/Transforms/LoopVectorize/X86/gcc-examples.ll b/test/Transforms/LoopVectorize/X86/gcc-examples.ll index e1113fdd911c0..05403cd5b61b1 100644 --- a/test/Transforms/LoopVectorize/X86/gcc-examples.ll +++ b/test/Transforms/LoopVectorize/X86/gcc-examples.ll @@ -1,5 +1,5 @@ ; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7 -dce -instcombine -S | FileCheck %s -; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7 -force-vector-unroll=0 -dce -instcombine -S | FileCheck %s -check-prefix=UNROLL +; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7 -force-vector-interleave=0 -dce -instcombine -S | FileCheck %s -check-prefix=UNROLL 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll b/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll index d6120e76cc0b7..46efaf0e85311 100644 --- a/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll +++ b/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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" @@ -50,7 +50,7 @@ for.end15: ; preds = %for.end.us, %entry attributes #0 = { nounwind uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-frame-pointer-elim-non-leaf"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" } -!3 = metadata !{metadata !4, metadata !5} -!4 = metadata !{metadata !4} -!5 = metadata !{metadata !5} +!3 = !{!4, !5} +!4 = !{!4} +!5 = !{!5} diff --git a/test/Transforms/LoopVectorize/X86/masked_load_store.ll b/test/Transforms/LoopVectorize/X86/masked_load_store.ll new file mode 100644 index 0000000000000..0708471e643ad --- /dev/null +++ b/test/Transforms/LoopVectorize/X86/masked_load_store.ll @@ -0,0 +1,420 @@ +; RUN: opt < %s -O3 -mcpu=corei7-avx -S | FileCheck %s -check-prefix=AVX1 +; RUN: opt < %s -O3 -mcpu=core-avx2 -S | FileCheck %s -check-prefix=AVX2 +; RUN: opt < %s -O3 -mcpu=knl -S | FileCheck %s -check-prefix=AVX512 + +;AVX1-NOT: llvm.masked + +target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" +target triple = "x86_64-pc_linux" + +; The source code: +; +;void foo1(int *A, int *B, int *trigger) { +; +; for (int i=0; i<10000; i++) { +; if (trigger[i] < 100) { +; A[i] = B[i] + trigger[i]; +; } +; } +;} + +;AVX2-LABEL: @foo1 +;AVX2: icmp slt <8 x i32> %wide.load, <i32 100, i32 100, i32 100 +;AVX2: call <8 x i32> @llvm.masked.load.v8i32 +;AVX2: add nsw <8 x i32> +;AVX2: call void @llvm.masked.store.v8i32 +;AVX2: ret void + +;AVX512-LABEL: @foo1 +;AVX512: icmp slt <16 x i32> %wide.load, <i32 100, i32 100, i32 100 +;AVX512: call <16 x i32> @llvm.masked.load.v16i32 +;AVX512: add nsw <16 x i32> +;AVX512: call void @llvm.masked.store.v16i32 +;AVX512: ret void + +; Function Attrs: nounwind uwtable +define void @foo1(i32* %A, i32* %B, i32* %trigger) { +entry: + %A.addr = alloca i32*, align 8 + %B.addr = alloca i32*, align 8 + %trigger.addr = alloca i32*, align 8 + %i = alloca i32, align 4 + store i32* %A, i32** %A.addr, align 8 + store i32* %B, i32** %B.addr, align 8 + store i32* %trigger, i32** %trigger.addr, align 8 + store i32 0, i32* %i, align 4 + br label %for.cond + +for.cond: ; preds = %for.inc, %entry + %0 = load i32* %i, align 4 + %cmp = icmp slt i32 %0, 10000 + br i1 %cmp, label %for.body, label %for.end + +for.body: ; preds = %for.cond + %1 = load i32* %i, align 4 + %idxprom = sext i32 %1 to i64 + %2 = load i32** %trigger.addr, align 8 + %arrayidx = getelementptr inbounds i32* %2, i64 %idxprom + %3 = load i32* %arrayidx, align 4 + %cmp1 = icmp slt i32 %3, 100 + br i1 %cmp1, label %if.then, label %if.end + +if.then: ; preds = %for.body + %4 = load i32* %i, align 4 + %idxprom2 = sext i32 %4 to i64 + %5 = load i32** %B.addr, align 8 + %arrayidx3 = getelementptr inbounds i32* %5, i64 %idxprom2 + %6 = load i32* %arrayidx3, align 4 + %7 = load i32* %i, align 4 + %idxprom4 = sext i32 %7 to i64 + %8 = load i32** %trigger.addr, align 8 + %arrayidx5 = getelementptr inbounds i32* %8, i64 %idxprom4 + %9 = load i32* %arrayidx5, align 4 + %add = add nsw i32 %6, %9 + %10 = load i32* %i, align 4 + %idxprom6 = sext i32 %10 to i64 + %11 = load i32** %A.addr, align 8 + %arrayidx7 = getelementptr inbounds i32* %11, i64 %idxprom6 + store i32 %add, i32* %arrayidx7, align 4 + br label %if.end + +if.end: ; preds = %if.then, %for.body + br label %for.inc + +for.inc: ; preds = %if.end + %12 = load i32* %i, align 4 + %inc = add nsw i32 %12, 1 + store i32 %inc, i32* %i, align 4 + br label %for.cond + +for.end: ; preds = %for.cond + ret void +} + +; The source code: +; +;void foo2(float *A, float *B, int *trigger) { +; +; for (int i=0; i<10000; i++) { +; if (trigger[i] < 100) { +; A[i] = B[i] + trigger[i]; +; } +; } +;} + +;AVX2-LABEL: @foo2 +;AVX2: icmp slt <8 x i32> %wide.load, <i32 100, i32 100, i32 100 +;AVX2: call <8 x float> @llvm.masked.load.v8f32 +;AVX2: fadd <8 x float> +;AVX2: call void @llvm.masked.store.v8f32 +;AVX2: ret void + +;AVX512-LABEL: @foo2 +;AVX512: icmp slt <16 x i32> %wide.load, <i32 100, i32 100, i32 100 +;AVX512: call <16 x float> @llvm.masked.load.v16f32 +;AVX512: fadd <16 x float> +;AVX512: call void @llvm.masked.store.v16f32 +;AVX512: ret void + +; Function Attrs: nounwind uwtable +define void @foo2(float* %A, float* %B, i32* %trigger) { +entry: + %A.addr = alloca float*, align 8 + %B.addr = alloca float*, align 8 + %trigger.addr = alloca i32*, align 8 + %i = alloca i32, align 4 + store float* %A, float** %A.addr, align 8 + store float* %B, float** %B.addr, align 8 + store i32* %trigger, i32** %trigger.addr, align 8 + store i32 0, i32* %i, align 4 + br label %for.cond + +for.cond: ; preds = %for.inc, %entry + %0 = load i32* %i, align 4 + %cmp = icmp slt i32 %0, 10000 + br i1 %cmp, label %for.body, label %for.end + +for.body: ; preds = %for.cond + %1 = load i32* %i, align 4 + %idxprom = sext i32 %1 to i64 + %2 = load i32** %trigger.addr, align 8 + %arrayidx = getelementptr inbounds i32* %2, i64 %idxprom + %3 = load i32* %arrayidx, align 4 + %cmp1 = icmp slt i32 %3, 100 + br i1 %cmp1, label %if.then, label %if.end + +if.then: ; preds = %for.body + %4 = load i32* %i, align 4 + %idxprom2 = sext i32 %4 to i64 + %5 = load float** %B.addr, align 8 + %arrayidx3 = getelementptr inbounds float* %5, i64 %idxprom2 + %6 = load float* %arrayidx3, align 4 + %7 = load i32* %i, align 4 + %idxprom4 = sext i32 %7 to i64 + %8 = load i32** %trigger.addr, align 8 + %arrayidx5 = getelementptr inbounds i32* %8, i64 %idxprom4 + %9 = load i32* %arrayidx5, align 4 + %conv = sitofp i32 %9 to float + %add = fadd float %6, %conv + %10 = load i32* %i, align 4 + %idxprom6 = sext i32 %10 to i64 + %11 = load float** %A.addr, align 8 + %arrayidx7 = getelementptr inbounds float* %11, i64 %idxprom6 + store float %add, float* %arrayidx7, align 4 + br label %if.end + +if.end: ; preds = %if.then, %for.body + br label %for.inc + +for.inc: ; preds = %if.end + %12 = load i32* %i, align 4 + %inc = add nsw i32 %12, 1 + store i32 %inc, i32* %i, align 4 + br label %for.cond + +for.end: ; preds = %for.cond + ret void +} + +; The source code: +; +;void foo3(double *A, double *B, int *trigger) { +; +; for (int i=0; i<10000; i++) { +; if (trigger[i] < 100) { +; A[i] = B[i] + trigger[i]; +; } +; } +;} + +;AVX2-LABEL: @foo3 +;AVX2: icmp slt <4 x i32> %wide.load, <i32 100, i32 100, +;AVX2: call <4 x double> @llvm.masked.load.v4f64 +;AVX2: sitofp <4 x i32> %wide.load to <4 x double> +;AVX2: fadd <4 x double> +;AVX2: call void @llvm.masked.store.v4f64 +;AVX2: ret void + +;AVX512-LABEL: @foo3 +;AVX512: icmp slt <8 x i32> %wide.load, <i32 100, i32 100, +;AVX512: call <8 x double> @llvm.masked.load.v8f64 +;AVX512: sitofp <8 x i32> %wide.load to <8 x double> +;AVX512: fadd <8 x double> +;AVX512: call void @llvm.masked.store.v8f64 +;AVX512: ret void + + +; Function Attrs: nounwind uwtable +define void @foo3(double* %A, double* %B, i32* %trigger) #0 { +entry: + %A.addr = alloca double*, align 8 + %B.addr = alloca double*, align 8 + %trigger.addr = alloca i32*, align 8 + %i = alloca i32, align 4 + store double* %A, double** %A.addr, align 8 + store double* %B, double** %B.addr, align 8 + store i32* %trigger, i32** %trigger.addr, align 8 + store i32 0, i32* %i, align 4 + br label %for.cond + +for.cond: ; preds = %for.inc, %entry + %0 = load i32* %i, align 4 + %cmp = icmp slt i32 %0, 10000 + br i1 %cmp, label %for.body, label %for.end + +for.body: ; preds = %for.cond + %1 = load i32* %i, align 4 + %idxprom = sext i32 %1 to i64 + %2 = load i32** %trigger.addr, align 8 + %arrayidx = getelementptr inbounds i32* %2, i64 %idxprom + %3 = load i32* %arrayidx, align 4 + %cmp1 = icmp slt i32 %3, 100 + br i1 %cmp1, label %if.then, label %if.end + +if.then: ; preds = %for.body + %4 = load i32* %i, align 4 + %idxprom2 = sext i32 %4 to i64 + %5 = load double** %B.addr, align 8 + %arrayidx3 = getelementptr inbounds double* %5, i64 %idxprom2 + %6 = load double* %arrayidx3, align 8 + %7 = load i32* %i, align 4 + %idxprom4 = sext i32 %7 to i64 + %8 = load i32** %trigger.addr, align 8 + %arrayidx5 = getelementptr inbounds i32* %8, i64 %idxprom4 + %9 = load i32* %arrayidx5, align 4 + %conv = sitofp i32 %9 to double + %add = fadd double %6, %conv + %10 = load i32* %i, align 4 + %idxprom6 = sext i32 %10 to i64 + %11 = load double** %A.addr, align 8 + %arrayidx7 = getelementptr inbounds double* %11, i64 %idxprom6 + store double %add, double* %arrayidx7, align 8 + br label %if.end + +if.end: ; preds = %if.then, %for.body + br label %for.inc + +for.inc: ; preds = %if.end + %12 = load i32* %i, align 4 + %inc = add nsw i32 %12, 1 + store i32 %inc, i32* %i, align 4 + br label %for.cond + +for.end: ; preds = %for.cond + ret void +} + +; The source code: +; +;void foo4(double *A, double *B, int *trigger) { +; +; for (int i=0; i<10000; i++) { +; if (trigger[i] < 100) { +; A[i] = B[i*2] + trigger[i]; << non-cosecutive access +; } +; } +;} + +;AVX2-LABEL: @foo4 +;AVX2-NOT: llvm.masked +;AVX2: ret void + +;AVX512-LABEL: @foo4 +;AVX512-NOT: llvm.masked +;AVX512: ret void + +; Function Attrs: nounwind uwtable +define void @foo4(double* %A, double* %B, i32* %trigger) { +entry: + %A.addr = alloca double*, align 8 + %B.addr = alloca double*, align 8 + %trigger.addr = alloca i32*, align 8 + %i = alloca i32, align 4 + store double* %A, double** %A.addr, align 8 + store double* %B, double** %B.addr, align 8 + store i32* %trigger, i32** %trigger.addr, align 8 + store i32 0, i32* %i, align 4 + br label %for.cond + +for.cond: ; preds = %for.inc, %entry + %0 = load i32* %i, align 4 + %cmp = icmp slt i32 %0, 10000 + br i1 %cmp, label %for.body, label %for.end + +for.body: ; preds = %for.cond + %1 = load i32* %i, align 4 + %idxprom = sext i32 %1 to i64 + %2 = load i32** %trigger.addr, align 8 + %arrayidx = getelementptr inbounds i32* %2, i64 %idxprom + %3 = load i32* %arrayidx, align 4 + %cmp1 = icmp slt i32 %3, 100 + br i1 %cmp1, label %if.then, label %if.end + +if.then: ; preds = %for.body + %4 = load i32* %i, align 4 + %mul = mul nsw i32 %4, 2 + %idxprom2 = sext i32 %mul to i64 + %5 = load double** %B.addr, align 8 + %arrayidx3 = getelementptr inbounds double* %5, i64 %idxprom2 + %6 = load double* %arrayidx3, align 8 + %7 = load i32* %i, align 4 + %idxprom4 = sext i32 %7 to i64 + %8 = load i32** %trigger.addr, align 8 + %arrayidx5 = getelementptr inbounds i32* %8, i64 %idxprom4 + %9 = load i32* %arrayidx5, align 4 + %conv = sitofp i32 %9 to double + %add = fadd double %6, %conv + %10 = load i32* %i, align 4 + %idxprom6 = sext i32 %10 to i64 + %11 = load double** %A.addr, align 8 + %arrayidx7 = getelementptr inbounds double* %11, i64 %idxprom6 + store double %add, double* %arrayidx7, align 8 + br label %if.end + +if.end: ; preds = %if.then, %for.body + br label %for.inc + +for.inc: ; preds = %if.end + %12 = load i32* %i, align 4 + %inc = add nsw i32 %12, 1 + store i32 %inc, i32* %i, align 4 + br label %for.cond + +for.end: ; preds = %for.cond + ret void +} + +@a = common global [1 x i32*] zeroinitializer, align 8 +@c = common global i32* null, align 8 + +; The loop here should not be vectorized due to trapping +; constant expression +;AVX2-LABEL: @foo5 +;AVX2-NOT: llvm.masked +;AVX2: store i32 sdiv +;AVX2: ret void + +;AVX512-LABEL: @foo5 +;AVX512-NOT: llvm.masked +;AVX512: store i32 sdiv +;AVX512: ret void + +; Function Attrs: nounwind uwtable +define void @foo5(i32* %A, i32* %B, i32* %trigger) { +entry: + %A.addr = alloca i32*, align 8 + %B.addr = alloca i32*, align 8 + %trigger.addr = alloca i32*, align 8 + %i = alloca i32, align 4 + store i32* %A, i32** %A.addr, align 8 + store i32* %B, i32** %B.addr, align 8 + store i32* %trigger, i32** %trigger.addr, align 8 + store i32 0, i32* %i, align 4 + br label %for.cond + +for.cond: ; preds = %for.inc, %entry + %0 = load i32* %i, align 4 + %cmp = icmp slt i32 %0, 10000 + br i1 %cmp, label %for.body, label %for.end + +for.body: ; preds = %for.cond + %1 = load i32* %i, align 4 + %idxprom = sext i32 %1 to i64 + %2 = load i32** %trigger.addr, align 8 + %arrayidx = getelementptr inbounds i32* %2, i64 %idxprom + %3 = load i32* %arrayidx, align 4 + %cmp1 = icmp slt i32 %3, 100 + br i1 %cmp1, label %if.then, label %if.end + +if.then: ; preds = %for.body + %4 = load i32* %i, align 4 + %idxprom2 = sext i32 %4 to i64 + %5 = load i32** %B.addr, align 8 + %arrayidx3 = getelementptr inbounds i32* %5, i64 %idxprom2 + %6 = load i32* %arrayidx3, align 4 + %7 = load i32* %i, align 4 + %idxprom4 = sext i32 %7 to i64 + %8 = load i32** %trigger.addr, align 8 + %arrayidx5 = getelementptr inbounds i32* %8, i64 %idxprom4 + %9 = load i32* %arrayidx5, align 4 + %add = add nsw i32 %6, %9 + %10 = load i32* %i, align 4 + %idxprom6 = sext i32 %10 to i64 + %11 = load i32** %A.addr, align 8 + %arrayidx7 = getelementptr inbounds i32* %11, i64 %idxprom6 + store i32 sdiv (i32 1, i32 zext (i1 icmp eq (i32** getelementptr inbounds ([1 x i32*]* @a, i64 0, i64 1), i32** @c) to i32)), i32* %arrayidx7, align 4 + br label %if.end + +if.end: ; preds = %if.then, %for.body + br label %for.inc + +for.inc: ; preds = %if.end + %12 = load i32* %i, align 4 + %inc = add nsw i32 %12, 1 + store i32 %inc, i32* %i, align 4 + br label %for.cond + +for.end: ; preds = %for.cond + ret void +} + diff --git a/test/Transforms/LoopVectorize/X86/metadata-enable.ll b/test/Transforms/LoopVectorize/X86/metadata-enable.ll index 8e0ca417b404f..7feb66ce6a984 100644 --- a/test/Transforms/LoopVectorize/X86/metadata-enable.ll +++ b/test/Transforms/LoopVectorize/X86/metadata-enable.ll @@ -170,7 +170,7 @@ for.end: ; preds = %for.body ret i32 %1 } -!0 = metadata !{metadata !0, metadata !1} -!1 = metadata !{metadata !"llvm.loop.vectorize.enable", i1 1} -!2 = metadata !{metadata !2, metadata !3} -!3 = metadata !{metadata !"llvm.loop.vectorize.enable", i1 0} +!0 = !{!0, !1} +!1 = !{!"llvm.loop.vectorize.enable", i1 1} +!2 = !{!2, !3} +!3 = !{!"llvm.loop.vectorize.enable", i1 0} diff --git a/test/Transforms/LoopVectorize/X86/min-trip-count-switch.ll b/test/Transforms/LoopVectorize/X86/min-trip-count-switch.ll index 8716cff77789a..fd69dc46070ef 100644 --- a/test/Transforms/LoopVectorize/X86/min-trip-count-switch.ll +++ b/test/Transforms/LoopVectorize/X86/min-trip-count-switch.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -vectorizer-min-trip-count=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -vectorizer-min-trip-count=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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" diff --git a/test/Transforms/LoopVectorize/X86/parallel-loops-after-reg2mem.ll b/test/Transforms/LoopVectorize/X86/parallel-loops-after-reg2mem.ll index 2c47fcb4d3890..ad010443a5e05 100644 --- a/test/Transforms/LoopVectorize/X86/parallel-loops-after-reg2mem.ll +++ b/test/Transforms/LoopVectorize/X86/parallel-loops-after-reg2mem.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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" @@ -46,4 +46,4 @@ for.end: ; preds = %for.body ret void } -!3 = metadata !{metadata !3} +!3 = !{!3} diff --git a/test/Transforms/LoopVectorize/X86/parallel-loops.ll b/test/Transforms/LoopVectorize/X86/parallel-loops.ll index 7e156a9edad4d..22ab521574987 100644 --- a/test/Transforms/LoopVectorize/X86/parallel-loops.ll +++ b/test/Transforms/LoopVectorize/X86/parallel-loops.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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" @@ -104,8 +104,8 @@ for.end: ; preds = %for.body ret void } -!3 = metadata !{metadata !3} -!4 = metadata !{metadata !4} -!5 = metadata !{metadata !3, metadata !4} -!6 = metadata !{metadata !6} -!7 = metadata !{metadata !7} +!3 = !{!3} +!4 = !{!4} +!5 = !{!3, !4} +!6 = !{!6} +!7 = !{!7} diff --git a/test/Transforms/LoopVectorize/X86/powof2div.ll b/test/Transforms/LoopVectorize/X86/powof2div.ll new file mode 100644 index 0000000000000..054da8ed20ae4 --- /dev/null +++ b/test/Transforms/LoopVectorize/X86/powof2div.ll @@ -0,0 +1,32 @@ +; RUN: opt < %s -loop-vectorize -mtriple=x86_64-unknown-linux-gnu -S | FileCheck %s +target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" +target triple = "x86_64-unknown-linux-gnu" + +%struct.anon = type { [100 x i32], i32, [100 x i32] } + +@Foo = common global %struct.anon zeroinitializer, align 4 + +;CHECK-LABEL: @foo( +;CHECK: load <4 x i32>* +;CHECK: sdiv <4 x i32> +;CHECK: store <4 x i32> + +define void @foo(){ +entry: + br label %for.body + +for.body: ; preds = %for.body, %entry + %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ] + %arrayidx = getelementptr inbounds %struct.anon* @Foo, i64 0, i32 2, i64 %indvars.iv + %0 = load i32* %arrayidx, align 4 + %div = sdiv i32 %0, 2 + %arrayidx2 = getelementptr inbounds %struct.anon* @Foo, i64 0, i32 0, i64 %indvars.iv + store i32 %div, i32* %arrayidx2, align 4 + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + %exitcond = icmp eq i64 %indvars.iv.next, 100 + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body + ret void +} + diff --git a/test/Transforms/LoopVectorize/X86/small-size.ll b/test/Transforms/LoopVectorize/X86/small-size.ll index bcf16aa5db139..8c7a881be46f2 100644 --- a/test/Transforms/LoopVectorize/X86/small-size.ll +++ b/test/Transforms/LoopVectorize/X86/small-size.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -basicaa -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -loop-vectorize-with-block-frequency -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -basicaa -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -loop-vectorize-with-block-frequency -dce -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" @@ -139,7 +139,7 @@ define void @example4(i32 %n, i32* noalias nocapture %p, i32* noalias nocapture ret void } -!0 = metadata !{metadata !"branch_weights", i32 64, i32 4} +!0 = !{!"branch_weights", i32 64, i32 4} ; We can't vectorize this one because we need a runtime ptr check. ;CHECK-LABEL: @example23( diff --git a/test/Transforms/LoopVectorize/X86/tripcount.ll b/test/Transforms/LoopVectorize/X86/tripcount.ll index 6b38bacf88884..a4ec6948a2f0b 100644 --- a/test/Transforms/LoopVectorize/X86/tripcount.ll +++ b/test/Transforms/LoopVectorize/X86/tripcount.ll @@ -1,4 +1,4 @@ -; RUN: opt -S -loop-vectorize -force-vector-width=2 -force-vector-unroll=1 -mcpu=prescott < %s | FileCheck %s +; RUN: opt -S -loop-vectorize -force-vector-width=2 -force-vector-interleave=1 -mcpu=prescott < %s | FileCheck %s target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:32:32-n8:16:32-S128" target triple = "i386-unknown-freebsd11.0" diff --git a/test/Transforms/LoopVectorize/X86/unroll-small-loops.ll b/test/Transforms/LoopVectorize/X86/unroll-small-loops.ll index d5024bb132100..716dc08a55ace 100644 --- a/test/Transforms/LoopVectorize/X86/unroll-small-loops.ll +++ b/test/Transforms/LoopVectorize/X86/unroll-small-loops.ll @@ -1,6 +1,6 @@ -; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -force-vector-width=4 -force-vector-unroll=0 -dce -S \ +; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -force-vector-width=4 -force-vector-interleave=0 -dce -S \ ; RUN: | FileCheck %s --check-prefix=CHECK-VECTOR -; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -force-vector-width=1 -force-vector-unroll=0 -dce -S \ +; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -force-vector-width=1 -force-vector-interleave=0 -dce -S \ ; RUN: | FileCheck %s --check-prefix=CHECK-SCALAR 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" diff --git a/test/Transforms/LoopVectorize/X86/unroll_selection.ll b/test/Transforms/LoopVectorize/X86/unroll_selection.ll index 2d7b663804f5c..c684b4e79b143 100644 --- a/test/Transforms/LoopVectorize/X86/unroll_selection.ll +++ b/test/Transforms/LoopVectorize/X86/unroll_selection.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -force-vector-width=4 -force-vector-unroll=0 -dce -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -force-vector-width=4 -force-vector-interleave=0 -dce -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/X86/vect.omp.force.ll b/test/Transforms/LoopVectorize/X86/vect.omp.force.ll index 074313bde6f53..a781fbedb404f 100644 --- a/test/Transforms/LoopVectorize/X86/vect.omp.force.ll +++ b/test/Transforms/LoopVectorize/X86/vect.omp.force.ll @@ -52,8 +52,8 @@ for.end: ret void } -!1 = metadata !{metadata !1, metadata !2} -!2 = metadata !{metadata !"llvm.loop.vectorize.enable", i1 true} +!1 = !{!1, !2} +!2 = !{!"llvm.loop.vectorize.enable", i1 true} ; ; This method will not be vectorized, as scalar cost is lower than any of vector costs. @@ -89,5 +89,5 @@ for.end: declare float @llvm.sin.f32(float) nounwind readnone ; Dummy metadata -!3 = metadata !{metadata !3} +!3 = !{!3} diff --git a/test/Transforms/LoopVectorize/X86/vect.omp.force.small-tc.ll b/test/Transforms/LoopVectorize/X86/vect.omp.force.small-tc.ll index 97c31a148e3ac..e39e6b57dd96b 100644 --- a/test/Transforms/LoopVectorize/X86/vect.omp.force.small-tc.ll +++ b/test/Transforms/LoopVectorize/X86/vect.omp.force.small-tc.ll @@ -43,8 +43,8 @@ for.end: ret void } -!1 = metadata !{metadata !1, metadata !2} -!2 = metadata !{metadata !"llvm.loop.vectorize.enable", i1 true} +!1 = !{!1, !2} +!2 = !{!"llvm.loop.vectorize.enable", i1 true} ; ; This loop will not be vectorized as the trip count is below the threshold. @@ -69,5 +69,5 @@ for.end: ret void } -!3 = metadata !{metadata !3} +!3 = !{!3} diff --git a/test/Transforms/LoopVectorize/X86/vectorization-remarks-missed.ll b/test/Transforms/LoopVectorize/X86/vectorization-remarks-missed.ll index 93f24cbf49091..011ce8eac5566 100644 --- a/test/Transforms/LoopVectorize/X86/vectorization-remarks-missed.ll +++ b/test/Transforms/LoopVectorize/X86/vectorization-remarks-missed.ll @@ -24,10 +24,10 @@ ; File, line, and column should match those specified in the metadata ; CHECK: remark: source.cpp:4:5: loop not vectorized: could not determine number of loop iterations -; CHECK: remark: source.cpp:4:5: loop not vectorized: vectorization was not specified +; CHECK: remark: source.cpp:4:5: loop not vectorized: use -Rpass-analysis=loop-vectorize for more info ; CHECK: remark: source.cpp:13:5: loop not vectorized: vector width and interleave count are explicitly set to 1 ; CHECK: remark: source.cpp:19:5: loop not vectorized: cannot identify array bounds -; CHECK: remark: source.cpp:19:5: loop not vectorized: vectorization is explicitly enabled +; CHECK: remark: source.cpp:19:5: loop not vectorized: use -Rpass-analysis=loop-vectorize for more info ; CHECK: warning: source.cpp:19:5: loop not vectorized: failed explicitly specified loop vectorization ; CHECK: _Z4testPii @@ -122,40 +122,40 @@ attributes #0 = { nounwind } !llvm.module.flags = !{!9, !10} !llvm.ident = !{!11} -!0 = metadata !{i32 786449, metadata !1, i32 4, metadata !"clang version 3.5.0", i1 true, metadata !"", i32 0, metadata !2, metadata !2, metadata !3, metadata !2, metadata !2, metadata !"", i32 2} -!1 = metadata !{metadata !"source.cpp", metadata !"."} -!2 = metadata !{} -!3 = metadata !{metadata !4, metadata !7, metadata !8} -!4 = metadata !{i32 786478, metadata !1, metadata !5, metadata !"test", metadata !"test", metadata !"", i32 1, metadata !6, i1 false, i1 true, i32 0, i32 0, null, i32 256, i1 true, void (i32*, i32)* @_Z4testPii, null, null, metadata !2, i32 1} -!5 = metadata !{i32 786473, metadata !1} -!6 = metadata !{i32 786453, i32 0, null, metadata !"", i32 0, i64 0, i64 0, i64 0, i32 0, null, metadata !2, i32 0, null, null, null} -!7 = metadata !{i32 786478, metadata !1, metadata !5, metadata !"test_disabled", metadata !"test_disabled", metadata !"", i32 10, metadata !6, i1 false, i1 true, i32 0, i32 0, null, i32 256, i1 true, void (i32*, i32)* @_Z13test_disabledPii, null, null, metadata !2, i32 10} -!8 = metadata !{i32 786478, metadata !1, metadata !5, metadata !"test_array_bounds", metadata !"test_array_bounds", metadata !"", i32 16, metadata !6, i1 false, i1 true, i32 0, i32 0, null, i32 256, i1 true, void (i32*, i32*, i32)* @_Z17test_array_boundsPiS_i, null, null, metadata !2, i32 16} -!9 = metadata !{i32 2, metadata !"Dwarf Version", i32 2} -!10 = metadata !{i32 2, metadata !"Debug Info Version", i32 1} -!11 = metadata !{metadata !"clang version 3.5.0"} -!12 = metadata !{i32 3, i32 8, metadata !13, null} -!13 = metadata !{i32 786443, metadata !1, metadata !4, i32 3, i32 3, i32 0, i32 0} -!14 = metadata !{metadata !14, metadata !15, metadata !15} -!15 = metadata !{metadata !"llvm.loop.vectorize.enable", i1 true} -!16 = metadata !{i32 4, i32 5, metadata !17, null} -!17 = metadata !{i32 786443, metadata !1, metadata !13, i32 3, i32 36, i32 0, i32 1} -!18 = metadata !{metadata !19, metadata !19, i64 0} -!19 = metadata !{metadata !"int", metadata !20, i64 0} -!20 = metadata !{metadata !"omnipotent char", metadata !21, i64 0} -!21 = metadata !{metadata !"Simple C/C++ TBAA"} -!22 = metadata !{i32 5, i32 9, metadata !23, null} -!23 = metadata !{i32 786443, metadata !1, metadata !17, i32 5, i32 9, i32 0, i32 2} -!24 = metadata !{i32 8, i32 1, metadata !4, null} -!25 = metadata !{i32 12, i32 8, metadata !26, null} -!26 = metadata !{i32 786443, metadata !1, metadata !7, i32 12, i32 3, i32 0, i32 3} -!27 = metadata !{metadata !27, metadata !28, metadata !29} -!28 = metadata !{metadata !"llvm.loop.interleave.count", i32 1} -!29 = metadata !{metadata !"llvm.loop.vectorize.width", i32 1} -!30 = metadata !{i32 13, i32 5, metadata !26, null} -!31 = metadata !{i32 14, i32 1, metadata !7, null} -!32 = metadata !{i32 18, i32 8, metadata !33, null} -!33 = metadata !{i32 786443, metadata !1, metadata !8, i32 18, i32 3, i32 0, i32 4} -!34 = metadata !{metadata !34, metadata !15} -!35 = metadata !{i32 19, i32 5, metadata !33, null} -!36 = metadata !{i32 20, i32 1, metadata !8, null} +!0 = !{!"0x11\004\00clang version 3.5.0\001\00\006\00\002", !1, !2, !2, !3, !2, !2} ; [ DW_TAG_compile_unit ] [./source.cpp] [DW_LANG_C_plus_plus] +!1 = !{!"source.cpp", !"."} +!2 = !{} +!3 = !{!4, !7, !8} +!4 = !{!"0x2e\00test\00test\00\001\000\001\000\006\00256\001\001", !1, !5, !6, null, void (i32*, i32)* @_Z4testPii, null, null, !2} ; [ DW_TAG_subprogram ] [line 1] [def] [test] +!5 = !{!"0x29", !1} ; [ DW_TAG_file_type ] [./source.cpp] +!6 = !{!"0x15\00\000\000\000\000\000\000", i32 0, null, null, !2, null, null, null} ; [ DW_TAG_subroutine_type ] [line 0, size 0, align 0, offset 0] [from ] +!7 = !{!"0x2e\00test_disabled\00test_disabled\00\0010\000\001\000\006\00256\001\0010", !1, !5, !6, null, void (i32*, i32)* @_Z13test_disabledPii, null, null, !2} ; [ DW_TAG_subprogram ] [line 10] [def] [test_disabled] +!8 = !{!"0x2e\00test_array_bounds\00test_array_bounds\00\0016\000\001\000\006\00256\001\0016", !1, !5, !6, null, void (i32*, i32*, i32)* @_Z17test_array_boundsPiS_i, null, null, !2} ; [ DW_TAG_subprogram ] [line 16] [def] [test_array_bounds] +!9 = !{i32 2, !"Dwarf Version", i32 2} +!10 = !{i32 2, !"Debug Info Version", i32 2} +!11 = !{!"clang version 3.5.0"} +!12 = !MDLocation(line: 3, column: 8, scope: !13) +!13 = !{!"0xb\003\003\000", !1, !4} ; [ DW_TAG_lexical_block ] +!14 = !{!14, !15, !15} +!15 = !{!"llvm.loop.vectorize.enable", i1 true} +!16 = !MDLocation(line: 4, column: 5, scope: !17) +!17 = !{!"0xb\003\0036\000", !1, !13} ; [ DW_TAG_lexical_block ] +!18 = !{!19, !19, i64 0} +!19 = !{!"int", !20, i64 0} +!20 = !{!"omnipotent char", !21, i64 0} +!21 = !{!"Simple C/C++ TBAA"} +!22 = !MDLocation(line: 5, column: 9, scope: !23) +!23 = !{!"0xb\005\009\000", !1, !17} ; [ DW_TAG_lexical_block ] +!24 = !MDLocation(line: 8, column: 1, scope: !4) +!25 = !MDLocation(line: 12, column: 8, scope: !26) +!26 = !{!"0xb\0012\003\000", !1, !7} ; [ DW_TAG_lexical_block ] +!27 = !{!27, !28, !29} +!28 = !{!"llvm.loop.interleave.count", i32 1} +!29 = !{!"llvm.loop.vectorize.width", i32 1} +!30 = !MDLocation(line: 13, column: 5, scope: !26) +!31 = !MDLocation(line: 14, column: 1, scope: !7) +!32 = !MDLocation(line: 18, column: 8, scope: !33) +!33 = !{!"0xb\0018\003\000", !1, !8} ; [ DW_TAG_lexical_block ] +!34 = !{!34, !15} +!35 = !MDLocation(line: 19, column: 5, scope: !33) +!36 = !MDLocation(line: 20, column: 1, scope: !8) diff --git a/test/Transforms/LoopVectorize/X86/vectorization-remarks.ll b/test/Transforms/LoopVectorize/X86/vectorization-remarks.ll index f6834477ff512..16fe370464b0d 100644 --- a/test/Transforms/LoopVectorize/X86/vectorization-remarks.ll +++ b/test/Transforms/LoopVectorize/X86/vectorization-remarks.ll @@ -1,6 +1,6 @@ ; RUN: opt < %s -loop-vectorize -mtriple=x86_64-unknown-linux -S -pass-remarks='loop-vectorize' 2>&1 | FileCheck -check-prefix=VECTORIZED %s -; RUN: opt < %s -loop-vectorize -force-vector-width=1 -force-vector-unroll=4 -mtriple=x86_64-unknown-linux -S -pass-remarks='loop-vectorize' 2>&1 | FileCheck -check-prefix=UNROLLED %s -; RUN: opt < %s -loop-vectorize -force-vector-width=1 -force-vector-unroll=1 -mtriple=x86_64-unknown-linux -S -pass-remarks-analysis='loop-vectorize' 2>&1 | FileCheck -check-prefix=NONE %s +; RUN: opt < %s -loop-vectorize -force-vector-width=1 -force-vector-interleave=4 -mtriple=x86_64-unknown-linux -S -pass-remarks='loop-vectorize' 2>&1 | FileCheck -check-prefix=UNROLLED %s +; RUN: opt < %s -loop-vectorize -force-vector-width=1 -force-vector-interleave=1 -mtriple=x86_64-unknown-linux -S -pass-remarks-analysis='loop-vectorize' 2>&1 | FileCheck -check-prefix=NONE %s ; This code has all the !dbg annotations needed to track source line information, ; but is missing the llvm.dbg.cu annotation. This prevents code generation from @@ -49,26 +49,26 @@ declare void @ibar(i32*) #1 !llvm.module.flags = !{!7, !8} !llvm.ident = !{!9} -!1 = metadata !{metadata !"vectorization-remarks.c", metadata !"."} -!2 = metadata !{} -!3 = metadata !{metadata !4} -!4 = metadata !{i32 786478, metadata !1, metadata !5, metadata !"foo", metadata !"foo", metadata !"", i32 5, metadata !6, i1 false, i1 true, i32 0, i32 0, null, i32 256, i1 true, i32 (i32)* @foo, null, null, metadata !2, i32 6} ; [ DW_TAG_subprogram ] [line 5] [def] [scope 6] [foo] -!5 = metadata !{i32 786473, metadata !1} ; [ DW_TAG_file_type ] [./vectorization-remarks.c] -!6 = metadata !{i32 786453, i32 0, null, metadata !"", i32 0, i64 0, i64 0, i64 0, i32 0, null, metadata !2, i32 0, null, null, null} ; [ DW_TAG_subroutine_type ] [line 0, size 0, align 0, offset 0] [from ] -!7 = metadata !{i32 2, metadata !"Dwarf Version", i32 4} -!8 = metadata !{i32 1, metadata !"Debug Info Version", i32 1} -!9 = metadata !{metadata !"clang version 3.5.0 "} -!10 = metadata !{i32 8, i32 3, metadata !4, null} ; [ DW_TAG_imported_declaration ] -!11 = metadata !{metadata !12, metadata !12, i64 0} -!12 = metadata !{metadata !"int", metadata !13, i64 0} -!13 = metadata !{metadata !"omnipotent char", metadata !14, i64 0} -!14 = metadata !{metadata !"Simple C/C++ TBAA"} -!15 = metadata !{i32 17, i32 8, metadata !16, null} -!16 = metadata !{i32 786443, metadata !1, metadata !17, i32 17, i32 8, i32 2, i32 3} ; [ DW_TAG_lexical_block ] [./vectorization-remarks.c] -!17 = metadata !{i32 786443, metadata !1, metadata !18, i32 17, i32 8, i32 1, i32 2} ; [ DW_TAG_lexical_block ] [./vectorization-remarks.c] -!18 = metadata !{i32 786443, metadata !1, metadata !4, i32 17, i32 3, i32 0, i32 0} ; [ DW_TAG_lexical_block ] [./vectorization-remarks.c] -!19 = metadata !{i32 18, i32 5, metadata !20, null} -!20 = metadata !{i32 786443, metadata !1, metadata !18, i32 17, i32 27, i32 0, i32 1} ; [ DW_TAG_lexical_block ] [./vectorization-remarks.c] -!21 = metadata !{metadata !13, metadata !13, i64 0} -!22 = metadata !{i32 20, i32 3, metadata !4, null} -!23 = metadata !{i32 21, i32 3, metadata !4, null} +!1 = !{!"vectorization-remarks.c", !"."} +!2 = !{} +!3 = !{!4} +!4 = !{!"0x2e\00foo\00foo\00\005\000\001\000\006\00256\001\006", !1, !5, !6, null, i32 (i32)* @foo, null, null, !2} ; [ DW_TAG_subprogram ] [line 5] [def] [scope 6] [foo] +!5 = !{!"0x29", !1} ; [ DW_TAG_file_type ] [./vectorization-remarks.c] +!6 = !{!"0x15\00\000\000\000\000\000\000", i32 0, null, null, !2, null, null, null} ; [ DW_TAG_subroutine_type ] [line 0, size 0, align 0, offset 0] [from ] +!7 = !{i32 2, !"Dwarf Version", i32 4} +!8 = !{i32 1, !"Debug Info Version", i32 2} +!9 = !{!"clang version 3.5.0 "} +!10 = !MDLocation(line: 8, column: 3, scope: !4) +!11 = !{!12, !12, i64 0} +!12 = !{!"int", !13, i64 0} +!13 = !{!"omnipotent char", !14, i64 0} +!14 = !{!"Simple C/C++ TBAA"} +!15 = !MDLocation(line: 17, column: 8, scope: !16) +!16 = !{!"0xb\0017\008\002", !1, !17} ; [ DW_TAG_lexical_block ] [./vectorization-remarks.c] +!17 = !{!"0xb\0017\008\001", !1, !18} ; [ DW_TAG_lexical_block ] [./vectorization-remarks.c] +!18 = !{!"0xb\0017\003\000", !1, !4} ; [ DW_TAG_lexical_block ] [./vectorization-remarks.c] +!19 = !MDLocation(line: 18, column: 5, scope: !20) +!20 = !{!"0xb\0017\0027\000", !1, !18} ; [ DW_TAG_lexical_block ] [./vectorization-remarks.c] +!21 = !{!13, !13, i64 0} +!22 = !MDLocation(line: 20, column: 3, scope: !4) +!23 = !MDLocation(line: 21, column: 3, scope: !4) diff --git a/test/Transforms/LoopVectorize/X86/x86_fp80-vector-store.ll b/test/Transforms/LoopVectorize/X86/x86_fp80-vector-store.ll index efc93d94a7c51..d8e5403d2d4ea 100644 --- a/test/Transforms/LoopVectorize/X86/x86_fp80-vector-store.ll +++ b/test/Transforms/LoopVectorize/X86/x86_fp80-vector-store.ll @@ -1,4 +1,4 @@ -; RUN: opt -O3 -loop-vectorize -force-vector-unroll=1 -force-vector-width=2 -S < %s | FileCheck %s +; RUN: opt -O3 -loop-vectorize -force-vector-interleave=1 -force-vector-width=2 -S < %s | FileCheck %s 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-apple-macosx10.7.0" diff --git a/test/Transforms/LoopVectorize/XCore/no-vector-registers.ll b/test/Transforms/LoopVectorize/XCore/no-vector-registers.ll index a099daa740e56..cab333d064066 100644 --- a/test/Transforms/LoopVectorize/XCore/no-vector-registers.ll +++ b/test/Transforms/LoopVectorize/XCore/no-vector-registers.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-width=4 -force-vector-unroll=2 -S -mtriple=xcore | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-width=4 -force-vector-interleave=2 -S -mtriple=xcore | FileCheck %s target datalayout = "e-p:32:32:32-a0:0:32-n32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:32-f16:16:32-f32:32:32-f64:32:32" target triple = "xcore" diff --git a/test/Transforms/LoopVectorize/align.ll b/test/Transforms/LoopVectorize/align.ll index 84b03615d374c..f2fb8b91b46ec 100644 --- a/test/Transforms/LoopVectorize/align.ll +++ b/test/Transforms/LoopVectorize/align.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/bsd_regex.ll b/test/Transforms/LoopVectorize/bsd_regex.ll index 7b712729a1cd6..7a3e79893da3b 100644 --- a/test/Transforms/LoopVectorize/bsd_regex.ll +++ b/test/Transforms/LoopVectorize/bsd_regex.ll @@ -1,4 +1,4 @@ -; RUN: opt -S -loop-vectorize -dce -instcombine -force-vector-width=2 -force-vector-unroll=2 < %s | FileCheck %s +; RUN: opt -S -loop-vectorize -dce -instcombine -force-vector-width=2 -force-vector-interleave=2 < %s | FileCheck %s 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" diff --git a/test/Transforms/LoopVectorize/bzip_reverse_loops.ll b/test/Transforms/LoopVectorize/bzip_reverse_loops.ll index 2648bbea80357..d7cbad06ddf0d 100644 --- a/test/Transforms/LoopVectorize/bzip_reverse_loops.ll +++ b/test/Transforms/LoopVectorize/bzip_reverse_loops.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S -enable-if-conversion | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S -enable-if-conversion | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/calloc.ll b/test/Transforms/LoopVectorize/calloc.ll index 55c0a605450f9..5f441f3e238f9 100644 --- a/test/Transforms/LoopVectorize/calloc.ll +++ b/test/Transforms/LoopVectorize/calloc.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -basicaa -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -basicaa -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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-apple-macosx10.9.0" diff --git a/test/Transforms/LoopVectorize/cast-induction.ll b/test/Transforms/LoopVectorize/cast-induction.ll index 255ce9c77eafc..4f92d33ff5286 100644 --- a/test/Transforms/LoopVectorize/cast-induction.ll +++ b/test/Transforms/LoopVectorize/cast-induction.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s ; rdar://problem/12848162 diff --git a/test/Transforms/LoopVectorize/conditional-assignment.ll b/test/Transforms/LoopVectorize/conditional-assignment.ll new file mode 100644 index 0000000000000..38e9c4f9a61c1 --- /dev/null +++ b/test/Transforms/LoopVectorize/conditional-assignment.ll @@ -0,0 +1,58 @@ +; RUN: opt < %s -loop-vectorize -S -pass-remarks-missed='loop-vectorize' -pass-remarks-analysis='loop-vectorize' 2>&1 | FileCheck %s + +; CHECK: remark: source.c:2:8: loop not vectorized: store that is conditionally executed prevents vectorization + +target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" +target triple = "x86_64-apple-macosx10.9.0" + +; Function Attrs: nounwind ssp uwtable +define void @conditional_store(i32* noalias nocapture %indices) #0 { +entry: + br label %for.body, !dbg !10 + +for.body: ; preds = %for.inc, %entry + %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.inc ] + %arrayidx = getelementptr inbounds i32* %indices, i64 %indvars.iv, !dbg !12 + %0 = load i32* %arrayidx, align 4, !dbg !12, !tbaa !14 + %cmp1 = icmp eq i32 %0, 1024, !dbg !12 + br i1 %cmp1, label %if.then, label %for.inc, !dbg !12 + +if.then: ; preds = %for.body + store i32 0, i32* %arrayidx, align 4, !dbg !18, !tbaa !14 + br label %for.inc, !dbg !18 + +for.inc: ; preds = %for.body, %if.then + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1, !dbg !10 + %exitcond = icmp eq i64 %indvars.iv.next, 4096, !dbg !10 + br i1 %exitcond, label %for.end, label %for.body, !dbg !10 + +for.end: ; preds = %for.inc + ret void, !dbg !19 +} + +attributes #0 = { nounwind } + +!llvm.dbg.cu = !{!0} +!llvm.module.flags = !{!7, !8} +!llvm.ident = !{!9} + +!0 = !{!"0x11\0012\00clang version 3.6.0\001\00\000\00\002", !1, !2, !2, !3, !2, !2} ; [ DW_TAG_compile_unit ] +!1 = !{!"source.c", !"."} +!2 = !{} +!3 = !{!4} +!4 = !{!"0x2e\00conditional_store\00conditional_store\00\001\000\001\000\006\00256\001\001", !1, !5, !6, null, void (i32*)* @conditional_store, null, null, !2} ; [ DW_TAG_subprogram ] +!5 = !{!"0x29", !1} ; [ DW_TAG_file_type ] +!6 = !{!"0x15\00\000\000\000\000\000\000", i32 0, null, null, !2, null, null, null} ; [ DW_TAG_subroutine_type ] +!7 = !{i32 2, !"Dwarf Version", i32 2} +!8 = !{i32 2, !"Debug Info Version", i32 2} +!9 = !{!"clang version 3.6.0"} +!10 = !MDLocation(line: 2, column: 8, scope: !11) +!11 = !{!"0xb\002\003\000", !1, !4} ; [ DW_TAG_lexical_block ] +!12 = !MDLocation(line: 3, column: 9, scope: !13) +!13 = !{!"0xb\003\009\000", !1, !11} ; [ DW_TAG_lexical_block ] +!14 = !{!15, !15, i64 0} +!15 = !{!"int", !16, i64 0} +!16 = !{!"omnipotent char", !17, i64 0} +!17 = !{!"Simple C/C++ TBAA"} +!18 = !MDLocation(line: 3, column: 29, scope: !13) +!19 = !MDLocation(line: 4, column: 1, scope: !4) diff --git a/test/Transforms/LoopVectorize/control-flow.ll b/test/Transforms/LoopVectorize/control-flow.ll index e4ba77fa3daaa..1882c3ff9a830 100644 --- a/test/Transforms/LoopVectorize/control-flow.ll +++ b/test/Transforms/LoopVectorize/control-flow.ll @@ -11,7 +11,7 @@ ; } ; CHECK: remark: source.cpp:5:9: loop not vectorized: loop control flow is not understood by vectorizer -; CHECK: remark: source.cpp:5:9: loop not vectorized: vectorization was not specified +; CHECK: remark: source.cpp:5:9: loop not vectorized: use -Rpass-analysis=loop-vectorize for more info ; CHECK: _Z4testPii ; CHECK-NOT: x i32> @@ -55,24 +55,24 @@ attributes #0 = { nounwind } !llvm.module.flags = !{!7, !8} !llvm.ident = !{!9} -!0 = metadata !{i32 786449, metadata !1, i32 4, metadata !"clang version 3.5.0", i1 true, metadata !"", i32 0, metadata !2, metadata !2, metadata !3, metadata !2, metadata !2, metadata !"", i32 2} -!1 = metadata !{metadata !"source.cpp", metadata !"."} -!2 = metadata !{} -!3 = metadata !{metadata !4} -!4 = metadata !{i32 786478, metadata !1, metadata !5, metadata !"test", metadata !"test", metadata !"", i32 1, metadata !6, i1 false, i1 true, i32 0, i32 0, null, i32 256, i1 true, i32 (i32*, i32)* @_Z4testPii, null, null, metadata !2, i32 2} -!5 = metadata !{i32 786473, metadata !1} -!6 = metadata !{i32 786453, i32 0, null, metadata !"", i32 0, i64 0, i64 0, i64 0, i32 0, null, metadata !2, i32 0, null, null, null} -!7 = metadata !{i32 2, metadata !"Dwarf Version", i32 2} -!8 = metadata !{i32 2, metadata !"Debug Info Version", i32 1} -!9 = metadata !{metadata !"clang version 3.5.0"} -!10 = metadata !{i32 3, i32 8, metadata !11, null} -!11 = metadata !{i32 786443, metadata !1, metadata !4, i32 3, i32 3, i32 0, i32 0} -!12 = metadata !{i32 5, i32 9, metadata !13, null} -!13 = metadata !{i32 786443, metadata !1, metadata !14, i32 5, i32 9, i32 0, i32 2} -!14 = metadata !{i32 786443, metadata !1, metadata !11, i32 4, i32 3, i32 0, i32 1} -!15 = metadata !{metadata !16, metadata !16, i64 0} -!16 = metadata !{metadata !"int", metadata !17, i64 0} -!17 = metadata !{metadata !"omnipotent char", metadata !18, i64 0} -!18 = metadata !{metadata !"Simple C/C++ TBAA"} -!19 = metadata !{i32 8, i32 7, metadata !13, null} -!20 = metadata !{i32 12, i32 3, metadata !4, null} +!0 = !{!"0x11\004\00clang version 3.5.0\001\00\006\00\002", !1, !2, !2, !3, !2, !2} ; [ DW_TAG_compile_unit ] [./source.cpp] [DW_LANG_C_plus_plus] +!1 = !{!"source.cpp", !"."} +!2 = !{} +!3 = !{!4} +!4 = !{!"0x2e\00test\00test\00\001\000\001\000\006\00256\001\002", !1, !5, !6, null, i32 (i32*, i32)* @_Z4testPii, null, null, !2} ; [ DW_TAG_subprogram ] [line 1] [def] [scope 2] [test] +!5 = !{!"0x29", !1} ; [ DW_TAG_file_type ] [./source.cpp] +!6 = !{!"0x15\00\000\000\000\000\000\000", i32 0, null, null, !2, null, null, null} ; [ DW_TAG_subroutine_type ] [line 0, size 0, align 0, offset 0] [from ] +!7 = !{i32 2, !"Dwarf Version", i32 2} +!8 = !{i32 2, !"Debug Info Version", i32 2} +!9 = !{!"clang version 3.5.0"} +!10 = !MDLocation(line: 3, column: 8, scope: !11) +!11 = !{!"0xb\003\003\000", !1, !4} ; [ DW_TAG_lexical_block ] +!12 = !MDLocation(line: 5, column: 9, scope: !13) +!13 = !{!"0xb\005\009\000", !1, !14} ; [ DW_TAG_lexical_block ] +!14 = !{!"0xb\004\003\000", !1, !11} ; [ DW_TAG_lexical_block ] +!15 = !{!16, !16, i64 0} +!16 = !{!"int", !17, i64 0} +!17 = !{!"omnipotent char", !18, i64 0} +!18 = !{!"Simple C/C++ TBAA"} +!19 = !MDLocation(line: 8, column: 7, scope: !13) +!20 = !MDLocation(line: 12, column: 3, scope: !4) diff --git a/test/Transforms/LoopVectorize/cpp-new-array.ll b/test/Transforms/LoopVectorize/cpp-new-array.ll index c8215a107de7a..f32f610b1cd6e 100644 --- a/test/Transforms/LoopVectorize/cpp-new-array.ll +++ b/test/Transforms/LoopVectorize/cpp-new-array.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/dbg.value.ll b/test/Transforms/LoopVectorize/dbg.value.ll index 2497b25ea1da9..92d3154812661 100644 --- a/test/Transforms/LoopVectorize/dbg.value.ll +++ b/test/Transforms/LoopVectorize/dbg.value.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -S -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine | FileCheck %s +; RUN: opt < %s -S -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine | FileCheck %s ; Make sure we vectorize with debugging turned on. 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" @@ -11,7 +11,7 @@ target triple = "x86_64-apple-macosx10.8.0" ; CHECK-LABEL: @test( define i32 @test() #0 { entry: - tail call void @llvm.dbg.value(metadata !1, i64 0, metadata !9), !dbg !18 + tail call void @llvm.dbg.value(metadata i32 0, i64 0, metadata !9, metadata !{}), !dbg !18 br label %for.body, !dbg !18 for.body: @@ -25,7 +25,7 @@ for.body: %arrayidx4 = getelementptr inbounds [1024 x i32]* @A, i64 0, i64 %indvars.iv, !dbg !19 store i32 %add, i32* %arrayidx4, align 4, !dbg !19 %indvars.iv.next = add i64 %indvars.iv, 1, !dbg !18 - tail call void @llvm.dbg.value(metadata !{null}, i64 0, metadata !9), !dbg !18 + tail call void @llvm.dbg.value(metadata !{null}, i64 0, metadata !9, metadata !{}), !dbg !18 %lftr.wideiv = trunc i64 %indvars.iv.next to i32, !dbg !18 %exitcond = icmp ne i32 %lftr.wideiv, 1024, !dbg !18 br i1 %exitcond, label %for.body, label %for.end, !dbg !18 @@ -34,9 +34,9 @@ for.end: ret i32 0, !dbg !24 } -declare void @llvm.dbg.declare(metadata, metadata) #1 +declare void @llvm.dbg.declare(metadata, metadata, metadata) #1 -declare void @llvm.dbg.value(metadata, i64, metadata) #1 +declare void @llvm.dbg.value(metadata, i64, metadata, metadata) #1 attributes #0 = { nounwind ssp uwtable "fp-contract-model"="standard" "no-frame-pointer-elim" "no-frame-pointer-elim-non-leaf" "relocation-model"="pic" "ssp-buffers-size"="8" } attributes #1 = { nounwind readnone } @@ -44,27 +44,27 @@ attributes #1 = { nounwind readnone } !llvm.dbg.cu = !{!0} !llvm.module.flags = !{!26} -!0 = metadata !{i32 786449, metadata !25, i32 4, metadata !"clang", i1 true, metadata !"", i32 0, metadata !1, metadata !1, metadata !2, metadata !11, null, metadata !""} -!1 = metadata !{i32 0} -!2 = metadata !{metadata !3} -!3 = metadata !{i32 786478, metadata !25, metadata !4, metadata !"test", metadata !"test", metadata !"test", i32 5, metadata !5, i1 false, i1 true, i32 0, i32 0, null, i32 256, i1 true, i32 ()* @test, null, null, metadata !8, i32 5} -!4 = metadata !{i32 786473, metadata !25} -!5 = metadata !{i32 786453, i32 0, null, i32 0, i32 0, i64 0, i64 0, i64 0, i32 0, null, metadata !6, i32 0, null, null, null} ; [ DW_TAG_subroutine_type ] [line 0, size 0, align 0, offset 0] [from ] -!6 = metadata !{metadata !7} -!7 = metadata !{i32 786468, null, null, metadata !"int", i32 0, i64 32, i64 32, i64 0, i32 0, i32 5} -!8 = metadata !{metadata !9} -!9 = metadata !{i32 786688, metadata !10, metadata !"i", metadata !4, i32 6, metadata !7, i32 0, i32 0} -!10 = metadata !{i32 786443, metadata !25, metadata !3, i32 6, i32 0, i32 0} -!11 = metadata !{metadata !12, metadata !16, metadata !17} -!12 = metadata !{i32 786484, i32 0, null, metadata !"A", metadata !"A", metadata !"", metadata !4, i32 1, metadata !13, i32 0, i32 1, [1024 x i32]* @A, null} -!13 = metadata !{i32 786433, null, null, null, i32 0, i64 32768, i64 32, i32 0, i32 0, metadata !7, metadata !14, i32 0, null, null, null} ; [ DW_TAG_array_type ] [line 0, size 32768, align 32, offset 0] [from int] -!14 = metadata !{metadata !15} -!15 = metadata !{i32 786465, i64 0, i64 1024} -!16 = metadata !{i32 786484, i32 0, null, metadata !"B", metadata !"B", metadata !"", metadata !4, i32 2, metadata !13, i32 0, i32 1, [1024 x i32]* @B, null} -!17 = metadata !{i32 786484, i32 0, null, metadata !"C", metadata !"C", metadata !"", metadata !4, i32 3, metadata !13, i32 0, i32 1, [1024 x i32]* @C, null} -!18 = metadata !{i32 6, i32 0, metadata !10, null} -!19 = metadata !{i32 7, i32 0, metadata !20, null} -!20 = metadata !{i32 786443, metadata !25, metadata !10, i32 6, i32 0, i32 1} -!24 = metadata !{i32 9, i32 0, metadata !3, null} -!25 = metadata !{metadata !"test", metadata !"/path/to/somewhere"} -!26 = metadata !{i32 1, metadata !"Debug Info Version", i32 1} +!0 = !{!"0x11\004\00clang\001\00\000\00\000", !25, !1, !1, !2, !11, null} ; [ DW_TAG_compile_unit ] +!1 = !{i32 0} +!2 = !{!3} +!3 = !{!"0x2e\00test\00test\00test\005\000\001\000\006\00256\001\005", !25, !4, !5, null, i32 ()* @test, null, null, !8} ; [ DW_TAG_subprogram ] +!4 = !{!"0x29", !25} ; [ DW_TAG_file_type ] +!5 = !{!"0x15\00\000\000\000\000\000\000", i32 0, null, null, !6, null, null, null} ; [ DW_TAG_subroutine_type ] [line 0, size 0, align 0, offset 0] [from ] +!6 = !{!7} +!7 = !{!"0x24\00int\000\0032\0032\000\000\005", null, null} ; [ DW_TAG_base_type ] +!8 = !{!9} +!9 = !{!"0x100\00i\006\000", !10, !4, !7} ; [ DW_TAG_auto_variable ] +!10 = !{!"0xb\006\000\000", !25, !3} ; [ DW_TAG_lexical_block ] +!11 = !{!12, !16, !17} +!12 = !{!"0x34\00A\00A\00\001\000\001", null, !4, !13, [1024 x i32]* @A, null} ; [ DW_TAG_variable ] +!13 = !{!"0x1\00\000\0032768\0032\000\000", null, null, !7, !14, i32 0, null, null, null} ; [ DW_TAG_array_type ] [line 0, size 32768, align 32, offset 0] [from int] +!14 = !{!15} +!15 = !{i32 786465, i64 0, i64 1024} +!16 = !{!"0x34\00B\00B\00\002\000\001", null, !4, !13, [1024 x i32]* @B, null} ; [ DW_TAG_variable ] +!17 = !{!"0x34\00C\00C\00\003\000\001", null, !4, !13, [1024 x i32]* @C, null} ; [ DW_TAG_variable ] +!18 = !MDLocation(line: 6, scope: !10) +!19 = !MDLocation(line: 7, scope: !20) +!20 = !{!"0xb\006\000\001", !25, !10} ; [ DW_TAG_lexical_block ] +!24 = !MDLocation(line: 9, scope: !3) +!25 = !{!"test", !"/path/to/somewhere"} +!26 = !{i32 1, !"Debug Info Version", i32 2} diff --git a/test/Transforms/LoopVectorize/debugloc.ll b/test/Transforms/LoopVectorize/debugloc.ll index bf0b4184b7a13..634bf79ddf0e3 100644 --- a/test/Transforms/LoopVectorize/debugloc.ll +++ b/test/Transforms/LoopVectorize/debugloc.ll @@ -1,4 +1,4 @@ -; RUN: opt -S < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=2 | FileCheck %s +; RUN: opt -S < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=2 | FileCheck %s 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" @@ -19,10 +19,10 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f3 define i32 @f(i32* nocapture %a, i32 %size) #0 { entry: - tail call void @llvm.dbg.value(metadata !{i32* %a}, i64 0, metadata !13), !dbg !19 - tail call void @llvm.dbg.value(metadata !{i32 %size}, i64 0, metadata !14), !dbg !19 - tail call void @llvm.dbg.value(metadata !2, i64 0, metadata !15), !dbg !20 - tail call void @llvm.dbg.value(metadata !2, i64 0, metadata !16), !dbg !21 + tail call void @llvm.dbg.value(metadata i32* %a, i64 0, metadata !13, metadata !{}), !dbg !19 + tail call void @llvm.dbg.value(metadata i32 %size, i64 0, metadata !14, metadata !{}), !dbg !19 + tail call void @llvm.dbg.value(metadata i32 0, i64 0, metadata !15, metadata !{}), !dbg !20 + tail call void @llvm.dbg.value(metadata i32 0, i64 0, metadata !16, metadata !{}), !dbg !21 %cmp4 = icmp eq i32 %size, 0, !dbg !21 br i1 %cmp4, label %for.end, label %for.body.lr.ph, !dbg !21 @@ -35,9 +35,9 @@ for.body: ; preds = %for.body.lr.ph, %fo %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv, !dbg !22 %0 = load i32* %arrayidx, align 4, !dbg !22 %add = add i32 %0, %sum.05, !dbg !22 - tail call void @llvm.dbg.value(metadata !{i32 %add.lcssa}, i64 0, metadata !15), !dbg !22 + tail call void @llvm.dbg.value(metadata i32 %add.lcssa, i64 0, metadata !15, metadata !{}), !dbg !22 %indvars.iv.next = add i64 %indvars.iv, 1, !dbg !21 - tail call void @llvm.dbg.value(metadata !{null}, i64 0, metadata !16), !dbg !21 + tail call void @llvm.dbg.value(metadata !{null}, i64 0, metadata !16, metadata !{}), !dbg !21 %lftr.wideiv = trunc i64 %indvars.iv.next to i32, !dbg !21 %exitcond = icmp ne i32 %lftr.wideiv, %size, !dbg !21 br i1 %exitcond, label %for.body, label %for.cond.for.end_crit_edge, !dbg !21 @@ -52,10 +52,10 @@ for.end: ; preds = %entry, %for.cond.fo } ; Function Attrs: nounwind readnone -declare void @llvm.dbg.declare(metadata, metadata) #1 +declare void @llvm.dbg.declare(metadata, metadata, metadata) #1 ; Function Attrs: nounwind readnone -declare void @llvm.dbg.value(metadata, i64, metadata) #1 +declare void @llvm.dbg.value(metadata, i64, metadata, metadata) #1 attributes #0 = { nounwind readonly ssp uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf"="true" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "unsafe-fp-math"="true" "use-soft-float"="false" } attributes #1 = { nounwind readnone } @@ -63,28 +63,28 @@ attributes #1 = { nounwind readnone } !llvm.dbg.cu = !{!0} !llvm.module.flags = !{!18, !27} -!0 = metadata !{i32 786449, metadata !1, i32 12, metadata !"clang version 3.4 (trunk 185038) (llvm/trunk 185097)", i1 true, metadata !"", i32 0, metadata !2, metadata !2, metadata !3, metadata !2, metadata !2, metadata !""} ; [ DW_TAG_compile_unit ] [/Volumes/Data/backedup/dev/os/llvm/debug/-] [DW_LANG_C99] -!1 = metadata !{metadata !"-", metadata !"/Volumes/Data/backedup/dev/os/llvm/debug"} -!2 = metadata !{i32 0} -!3 = metadata !{metadata !4} -!4 = metadata !{i32 786478, metadata !5, metadata !6, metadata !"f", metadata !"f", metadata !"", i32 3, metadata !7, i1 false, i1 true, i32 0, i32 0, null, i32 256, i1 true, i32 (i32*, i32)* @f, null, null, metadata !12, i32 3} ; [ DW_TAG_subprogram ] [line 3] [def] [f] -!5 = metadata !{metadata !"<stdin>", metadata !"/Volumes/Data/backedup/dev/os/llvm/debug"} -!6 = metadata !{i32 786473, metadata !5} ; [ DW_TAG_file_type ] [/Volumes/Data/backedup/dev/os/llvm/debug/<stdin>] -!7 = metadata !{i32 786453, i32 0, null, metadata !"", i32 0, i64 0, i64 0, i64 0, i32 0, null, metadata !8, i32 0, null, null, null} ; [ DW_TAG_subroutine_type ] [line 0, size 0, align 0, offset 0] [from ] -!8 = metadata !{metadata !9, metadata !10, metadata !11} -!9 = metadata !{i32 786468, null, null, metadata !"int", i32 0, i64 32, i64 32, i64 0, i32 0, i32 5} ; [ DW_TAG_base_type ] [int] [line 0, size 32, align 32, offset 0, enc DW_ATE_signed] -!10 = metadata !{i32 786447, null, null, metadata !"", i32 0, i64 64, i64 64, i64 0, i32 0, metadata !9} ; [ DW_TAG_pointer_type ] [line 0, size 64, align 64, offset 0] [from int] -!11 = metadata !{i32 786468, null, null, metadata !"unsigned int", i32 0, i64 32, i64 32, i64 0, i32 0, i32 7} ; [ DW_TAG_base_type ] [unsigned int] [line 0, size 32, align 32, offset 0, enc DW_ATE_unsigned] -!12 = metadata !{metadata !13, metadata !14, metadata !15, metadata !16} -!13 = metadata !{i32 786689, metadata !4, metadata !"a", metadata !6, i32 16777219, metadata !10, i32 0, i32 0} ; [ DW_TAG_arg_variable ] [a] [line 3] -!14 = metadata !{i32 786689, metadata !4, metadata !"size", metadata !6, i32 33554435, metadata !11, i32 0, i32 0} ; [ DW_TAG_arg_variable ] [size] [line 3] -!15 = metadata !{i32 786688, metadata !4, metadata !"sum", metadata !6, i32 4, metadata !11, i32 0, i32 0} ; [ DW_TAG_auto_variable ] [sum] [line 4] -!16 = metadata !{i32 786688, metadata !17, metadata !"i", metadata !6, i32 5, metadata !11, i32 0, i32 0} ; [ DW_TAG_auto_variable ] [i] [line 5] -!17 = metadata !{i32 786443, metadata !5, metadata !4, i32 5, i32 0, i32 0} ; [ DW_TAG_lexical_block ] [/Volumes/Data/backedup/dev/os/llvm/debug/<stdin>] -!18 = metadata !{i32 2, metadata !"Dwarf Version", i32 3} -!19 = metadata !{i32 3, i32 0, metadata !4, null} -!20 = metadata !{i32 4, i32 0, metadata !4, null} -!21 = metadata !{i32 5, i32 0, metadata !17, null} -!22 = metadata !{i32 6, i32 0, metadata !17, null} -!26 = metadata !{i32 7, i32 0, metadata !4, null} -!27 = metadata !{i32 1, metadata !"Debug Info Version", i32 1} +!0 = !{!"0x11\0012\00clang version 3.4 (trunk 185038) (llvm/trunk 185097)\001\00\000\00\000", !1, !2, !2, !3, !2, !2} ; [ DW_TAG_compile_unit ] [/Volumes/Data/backedup/dev/os/llvm/debug/-] [DW_LANG_C99] +!1 = !{!"-", !"/Volumes/Data/backedup/dev/os/llvm/debug"} +!2 = !{i32 0} +!3 = !{!4} +!4 = !{!"0x2e\00f\00f\00\003\000\001\000\006\00256\001\003", !5, !6, !7, null, i32 (i32*, i32)* @f, null, null, !12} ; [ DW_TAG_subprogram ] [line 3] [def] [f] +!5 = !{!"<stdin>", !"/Volumes/Data/backedup/dev/os/llvm/debug"} +!6 = !{!"0x29", !5} ; [ DW_TAG_file_type ] [/Volumes/Data/backedup/dev/os/llvm/debug/<stdin>] +!7 = !{!"0x15\00\000\000\000\000\000\000", i32 0, null, null, !8, null, null, null} ; [ DW_TAG_subroutine_type ] [line 0, size 0, align 0, offset 0] [from ] +!8 = !{!9, !10, !11} +!9 = !{!"0x24\00int\000\0032\0032\000\000\005", null, null} ; [ DW_TAG_base_type ] [int] [line 0, size 32, align 32, offset 0, enc DW_ATE_signed] +!10 = !{!"0xf\00\000\0064\0064\000\000", null, null, !9} ; [ DW_TAG_pointer_type ] [line 0, size 64, align 64, offset 0] [from int] +!11 = !{!"0x24\00unsigned int\000\0032\0032\000\000\007", null, null} ; [ DW_TAG_base_type ] [unsigned int] [line 0, size 32, align 32, offset 0, enc DW_ATE_unsigned] +!12 = !{!13, !14, !15, !16} +!13 = !{!"0x101\00a\0016777219\000", !4, !6, !10} ; [ DW_TAG_arg_variable ] [a] [line 3] +!14 = !{!"0x101\00size\0033554435\000", !4, !6, !11} ; [ DW_TAG_arg_variable ] [size] [line 3] +!15 = !{!"0x100\00sum\004\000", !4, !6, !11} ; [ DW_TAG_auto_variable ] [sum] [line 4] +!16 = !{!"0x100\00i\005\000", !17, !6, !11} ; [ DW_TAG_auto_variable ] [i] [line 5] +!17 = !{!"0xb\005\000\000", !5, !4} ; [ DW_TAG_lexical_block ] [/Volumes/Data/backedup/dev/os/llvm/debug/<stdin>] +!18 = !{i32 2, !"Dwarf Version", i32 3} +!19 = !MDLocation(line: 3, scope: !4) +!20 = !MDLocation(line: 4, scope: !4) +!21 = !MDLocation(line: 5, scope: !17) +!22 = !MDLocation(line: 6, scope: !17) +!26 = !MDLocation(line: 7, scope: !4) +!27 = !{i32 1, !"Debug Info Version", i32 2} diff --git a/test/Transforms/LoopVectorize/duplicated-metadata.ll b/test/Transforms/LoopVectorize/duplicated-metadata.ll new file mode 100644 index 0000000000000..bf2f899dff041 --- /dev/null +++ b/test/Transforms/LoopVectorize/duplicated-metadata.ll @@ -0,0 +1,30 @@ +; RUN: opt < %s -loop-vectorize -S 2>&1 | FileCheck %s +target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" +target triple = "x86_64-unknown-linux-gnu" + +; This test makes sure we don't duplicate the loop vectorizer's metadata +; while marking them as already vectorized (by setting width = 1), even +; at lower optimization levels, where no extra cleanup is done + +define void @_Z3fooPf(float* %a) { +entry: + br label %for.body + +for.body: ; preds = %for.body, %entry + %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ] + %arrayidx = getelementptr inbounds float* %a, i64 %indvars.iv + %p = load float* %arrayidx, align 4 + %mul = fmul float %p, 2.000000e+00 + store float %mul, float* %arrayidx, align 4 + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + %exitcond = icmp eq i64 %indvars.iv.next, 1024 + br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0 + +for.end: ; preds = %for.body + ret void +} + +!0 = !{!0, !1} +!1 = !{!"llvm.loop.vectorize.width", i32 4} +; CHECK-NOT: !{metadata !"llvm.loop.vectorize.width", i32 4} +; CHECK: !{!"llvm.loop.interleave.count", i32 1} diff --git a/test/Transforms/LoopVectorize/ee-crash.ll b/test/Transforms/LoopVectorize/ee-crash.ll index 8a4f8ce3c122d..a3c0bb89b1282 100644 --- a/test/Transforms/LoopVectorize/ee-crash.ll +++ b/test/Transforms/LoopVectorize/ee-crash.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/exact.ll b/test/Transforms/LoopVectorize/exact.ll new file mode 100644 index 0000000000000..0a8fbf337347e --- /dev/null +++ b/test/Transforms/LoopVectorize/exact.ll @@ -0,0 +1,24 @@ +; RUN: opt < %s -loop-vectorize -force-vector-width=4 -S | FileCheck %s + +target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" +target triple = "x86_64-apple-macosx10.9.0" + +; CHECK-LABEL: @lshr_exact( +; CHECK: lshr exact <4 x i32> +define void @lshr_exact(i32* %x) { +entry: + br label %for.body + +for.body: + %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ] + %arrayidx = getelementptr inbounds i32* %x, i64 %iv + %0 = load i32* %arrayidx, align 4 + %conv1 = lshr exact i32 %0, 1 + store i32 %conv1, i32* %arrayidx, align 4 + %iv.next = add nuw nsw i64 %iv, 1 + %exitcond = icmp eq i64 %iv.next, 256 + br i1 %exitcond, label %for.end, label %for.body + +for.end: + ret void +} diff --git a/test/Transforms/LoopVectorize/flags.ll b/test/Transforms/LoopVectorize/flags.ll index 21d09372d546a..0fc55c8973104 100644 --- a/test/Transforms/LoopVectorize/flags.ll +++ b/test/Transforms/LoopVectorize/flags.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/float-reduction.ll b/test/Transforms/LoopVectorize/float-reduction.ll index 0dfbab07279ac..0f064ee2dc851 100644 --- a/test/Transforms/LoopVectorize/float-reduction.ll +++ b/test/Transforms/LoopVectorize/float-reduction.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" @@ -23,3 +23,25 @@ for.body: ; preds = %for.body, %entry for.end: ; preds = %for.body ret float %add } + +;CHECK-LABEL: @foosub( +;CHECK: fsub fast <4 x float> +;CHECK: ret +define float @foosub(float* nocapture %A, i32* nocapture %n) nounwind uwtable readonly ssp { +entry: + br label %for.body + +for.body: ; preds = %for.body, %entry + %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ] + %sum.04 = phi float [ 0.000000e+00, %entry ], [ %sub, %for.body ] + %arrayidx = getelementptr inbounds float* %A, i64 %indvars.iv + %0 = load float* %arrayidx, align 4 + %sub = fsub fast float %sum.04, %0 + %indvars.iv.next = add i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 + %exitcond = icmp eq i32 %lftr.wideiv, 200 + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body + ret float %sub +} diff --git a/test/Transforms/LoopVectorize/funcall.ll b/test/Transforms/LoopVectorize/funcall.ll index f1f068c43db30..e03534fbac370 100644 --- a/test/Transforms/LoopVectorize/funcall.ll +++ b/test/Transforms/LoopVectorize/funcall.ll @@ -1,4 +1,4 @@ -; RUN: opt -S -loop-vectorize -force-vector-width=2 -force-vector-unroll=1 < %s | FileCheck %s +; RUN: opt -S -loop-vectorize -force-vector-width=2 -force-vector-interleave=1 < %s | FileCheck %s 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" diff --git a/test/Transforms/LoopVectorize/gcc-examples.ll b/test/Transforms/LoopVectorize/gcc-examples.ll index b6cde5d00f5e8..6c8af0bcd7c9f 100644 --- a/test/Transforms/LoopVectorize/gcc-examples.ll +++ b/test/Transforms/LoopVectorize/gcc-examples.ll @@ -1,5 +1,5 @@ -; RUN: opt < %s -basicaa -loop-vectorize -force-vector-width=4 -force-vector-unroll=1 -dce -instcombine -S | FileCheck %s -; RUN: opt < %s -basicaa -loop-vectorize -force-vector-width=4 -force-vector-unroll=4 -dce -instcombine -S | FileCheck %s -check-prefix=UNROLL +; RUN: opt < %s -basicaa -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -basicaa -loop-vectorize -force-vector-width=4 -force-vector-interleave=4 -dce -instcombine -S | FileCheck %s -check-prefix=UNROLL 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/global_alias.ll b/test/Transforms/LoopVectorize/global_alias.ll index d64d67f6a5b1b..3f11ce8bf2130 100644 --- a/test/Transforms/LoopVectorize/global_alias.ll +++ b/test/Transforms/LoopVectorize/global_alias.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -O1 -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -O1 -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:64:128-a0:0:64-n32-S64" diff --git a/test/Transforms/LoopVectorize/hoist-loads.ll b/test/Transforms/LoopVectorize/hoist-loads.ll index 765e14d6985ba..d0b27f1eae7ce 100644 --- a/test/Transforms/LoopVectorize/hoist-loads.ll +++ b/test/Transforms/LoopVectorize/hoist-loads.ll @@ -1,4 +1,4 @@ -; RUN: opt -loop-vectorize -force-vector-width=2 -force-vector-unroll=1 -S < %s | FileCheck %s +; RUN: opt -loop-vectorize -force-vector-width=2 -force-vector-interleave=1 -S < %s | FileCheck %s 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" diff --git a/test/Transforms/LoopVectorize/i8-induction.ll b/test/Transforms/LoopVectorize/i8-induction.ll index 2a0e826454940..90e3ec00cde21 100644 --- a/test/Transforms/LoopVectorize/i8-induction.ll +++ b/test/Transforms/LoopVectorize/i8-induction.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/if-conv-crash.ll b/test/Transforms/LoopVectorize/if-conv-crash.ll index f8f2cf1fff4bb..67910bf6d5445 100644 --- a/test/Transforms/LoopVectorize/if-conv-crash.ll +++ b/test/Transforms/LoopVectorize/if-conv-crash.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -enable-if-conversion +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -enable-if-conversion 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/if-conversion-nest.ll b/test/Transforms/LoopVectorize/if-conversion-nest.ll index 92cb06e5e5251..b5ac8fca23b33 100644 --- a/test/Transforms/LoopVectorize/if-conversion-nest.ll +++ b/test/Transforms/LoopVectorize/if-conversion-nest.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -enable-if-conversion -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -enable-if-conversion -dce -instcombine -S | FileCheck %s 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" diff --git a/test/Transforms/LoopVectorize/if-conversion-reduction.ll b/test/Transforms/LoopVectorize/if-conversion-reduction.ll index 8cb703cdfa4b6..455699c78030d 100644 --- a/test/Transforms/LoopVectorize/if-conversion-reduction.ll +++ b/test/Transforms/LoopVectorize/if-conversion-reduction.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -enable-if-conversion -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -enable-if-conversion -dce -instcombine -S | FileCheck %s 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-apple-macosx10.9.0" diff --git a/test/Transforms/LoopVectorize/if-conversion.ll b/test/Transforms/LoopVectorize/if-conversion.ll index 6e3e8ed27853e..9e185284919a6 100644 --- a/test/Transforms/LoopVectorize/if-conversion.ll +++ b/test/Transforms/LoopVectorize/if-conversion.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -enable-if-conversion -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -enable-if-conversion -dce -instcombine -S | FileCheck %s 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-apple-macosx10.9.0" diff --git a/test/Transforms/LoopVectorize/if-pred-stores.ll b/test/Transforms/LoopVectorize/if-pred-stores.ll index 7b0e181c845fe..c6067e01ee21a 100644 --- a/test/Transforms/LoopVectorize/if-pred-stores.ll +++ b/test/Transforms/LoopVectorize/if-pred-stores.ll @@ -1,5 +1,5 @@ -; RUN: opt -S -vectorize-num-stores-pred=1 -force-vector-width=1 -force-vector-unroll=2 -loop-vectorize < %s | FileCheck %s --check-prefix=UNROLL -; RUN: opt -S -vectorize-num-stores-pred=1 -force-vector-width=2 -force-vector-unroll=1 -loop-vectorize -enable-cond-stores-vec < %s | FileCheck %s --check-prefix=VEC +; RUN: opt -S -vectorize-num-stores-pred=1 -force-vector-width=1 -force-vector-interleave=2 -loop-vectorize < %s | FileCheck %s --check-prefix=UNROLL +; RUN: opt -S -vectorize-num-stores-pred=1 -force-vector-width=2 -force-vector-interleave=1 -loop-vectorize -enable-cond-stores-vec < %s | FileCheck %s --check-prefix=VEC target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" target triple = "x86_64-apple-macosx10.9.0" diff --git a/test/Transforms/LoopVectorize/incorrect-dom-info.ll b/test/Transforms/LoopVectorize/incorrect-dom-info.ll index 624ee7e50597a..b8624fd007747 100644 --- a/test/Transforms/LoopVectorize/incorrect-dom-info.ll +++ b/test/Transforms/LoopVectorize/incorrect-dom-info.ll @@ -139,4 +139,4 @@ attributes #0 = { nounwind ssp uwtable "less-precise-fpmad"="false" "no-frame-po !llvm.ident = !{!0} -!0 = metadata !{metadata !"clang version 3.6.0 "} +!0 = !{!"clang version 3.6.0 "} diff --git a/test/Transforms/LoopVectorize/increment.ll b/test/Transforms/LoopVectorize/increment.ll index 71bedb7334ac7..067a76b51ad01 100644 --- a/test/Transforms/LoopVectorize/increment.ll +++ b/test/Transforms/LoopVectorize/increment.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/induction.ll b/test/Transforms/LoopVectorize/induction.ll index 7dabcb2ba04fc..3f3491835b54d 100644 --- a/test/Transforms/LoopVectorize/induction.ll +++ b/test/Transforms/LoopVectorize/induction.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=2 -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=2 -S | FileCheck %s 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" @@ -28,7 +28,7 @@ for.end: ret void } -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=2 -instcombine -S | FileCheck %s --check-prefix=IND +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=2 -instcombine -S | FileCheck %s --check-prefix=IND ; Make sure we remove unneeded vectorization of induction variables. ; In order for instcombine to cleanup the vectorized induction variables that we diff --git a/test/Transforms/LoopVectorize/induction_plus.ll b/test/Transforms/LoopVectorize/induction_plus.ll index 9c8201ab78053..ce64c5b620d5a 100644 --- a/test/Transforms/LoopVectorize/induction_plus.ll +++ b/test/Transforms/LoopVectorize/induction_plus.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/intrinsic.ll b/test/Transforms/LoopVectorize/intrinsic.ll index 7dfaf03b0f2d7..d48731a074366 100644 --- a/test/Transforms/LoopVectorize/intrinsic.ll +++ b/test/Transforms/LoopVectorize/intrinsic.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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" @@ -1192,3 +1192,59 @@ for.body: ; preds = %entry, %for.body for.end: ; preds = %for.body, %entry ret void } + +declare float @llvm.minnum.f32(float, float) nounwind readnone + +;CHECK-LABEL: @minnum_f32( +;CHECK: llvm.minnum.v4f32 +;CHECK: ret void +define void @minnum_f32(i32 %n, float* noalias %y, float* noalias %x, float* noalias %z) nounwind uwtable { +entry: + %cmp9 = icmp sgt i32 %n, 0 + br i1 %cmp9, label %for.body, label %for.end + +for.body: ; preds = %entry, %for.body + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ] + %arrayidx = getelementptr inbounds float* %y, i64 %indvars.iv + %0 = load float* %arrayidx, align 4 + %arrayidx2 = getelementptr inbounds float* %z, i64 %indvars.iv + %1 = load float* %arrayidx2, align 4 + %call = tail call float @llvm.minnum.f32(float %0, float %1) nounwind readnone + %arrayidx4 = getelementptr inbounds float* %x, i64 %indvars.iv + store float %call, float* %arrayidx4, align 4 + %indvars.iv.next = add i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 + %exitcond = icmp eq i32 %lftr.wideiv, %n + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body, %entry + ret void +} + +declare float @llvm.maxnum.f32(float, float) nounwind readnone + +;CHECK-LABEL: @maxnum_f32( +;CHECK: llvm.maxnum.v4f32 +;CHECK: ret void +define void @maxnum_f32(i32 %n, float* noalias %y, float* noalias %x, float* noalias %z) nounwind uwtable { +entry: + %cmp9 = icmp sgt i32 %n, 0 + br i1 %cmp9, label %for.body, label %for.end + +for.body: ; preds = %entry, %for.body + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ] + %arrayidx = getelementptr inbounds float* %y, i64 %indvars.iv + %0 = load float* %arrayidx, align 4 + %arrayidx2 = getelementptr inbounds float* %z, i64 %indvars.iv + %1 = load float* %arrayidx2, align 4 + %call = tail call float @llvm.maxnum.f32(float %0, float %1) nounwind readnone + %arrayidx4 = getelementptr inbounds float* %x, i64 %indvars.iv + store float %call, float* %arrayidx4, align 4 + %indvars.iv.next = add i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 + %exitcond = icmp eq i32 %lftr.wideiv, %n + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body, %entry + ret void +} diff --git a/test/Transforms/LoopVectorize/lcssa-crash.ll b/test/Transforms/LoopVectorize/lcssa-crash.ll index de6be548490c5..68cc74ed70980 100644 --- a/test/Transforms/LoopVectorize/lcssa-crash.ll +++ b/test/Transforms/LoopVectorize/lcssa-crash.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 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" diff --git a/test/Transforms/LoopVectorize/lifetime.ll b/test/Transforms/LoopVectorize/lifetime.ll index 4f6f3b820a437..ba36cc4f7aa4e 100644 --- a/test/Transforms/LoopVectorize/lifetime.ll +++ b/test/Transforms/LoopVectorize/lifetime.ll @@ -1,4 +1,4 @@ -; RUN: opt -S -loop-vectorize -force-vector-width=2 -force-vector-unroll=1 < %s | FileCheck %s +; RUN: opt -S -loop-vectorize -force-vector-width=2 -force-vector-interleave=1 < %s | FileCheck %s 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" diff --git a/test/Transforms/LoopVectorize/loop-vect-memdep.ll b/test/Transforms/LoopVectorize/loop-vect-memdep.ll new file mode 100644 index 0000000000000..e2c7524238d17 --- /dev/null +++ b/test/Transforms/LoopVectorize/loop-vect-memdep.ll @@ -0,0 +1,26 @@ +target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" + +; RUN: opt < %s -S -loop-vectorize -debug-only=loop-vectorize 2>&1 | FileCheck %s +; REQUIRES: asserts +; CHECK: LV: Can't vectorize due to memory conflicts + +define void @test_loop_novect(double** %arr, i64 %n) { +for.body.lr.ph: + %t = load double** %arr, align 8 + br label %for.body + +for.body: ; preds = %for.body, %for.body.lr.ph + %i = phi i64 [ 0, %for.body.lr.ph ], [ %i.next, %for.body ] + %a = getelementptr inbounds double* %t, i64 %i + %i.next = add nuw nsw i64 %i, 1 + %a.next = getelementptr inbounds double* %t, i64 %i.next + %t1 = load double* %a, align 8 + %t2 = load double* %a.next, align 8 + store double %t1, double* %a.next, align 8 + store double %t2, double* %a, align 8 + %c = icmp eq i64 %i, %n + br i1 %c, label %final, label %for.body + +final: ; preds = %for.body + ret void +} diff --git a/test/Transforms/LoopVectorize/memdep.ll b/test/Transforms/LoopVectorize/memdep.ll index 21cb703ba47c0..f857e800bea7b 100644 --- a/test/Transforms/LoopVectorize/memdep.ll +++ b/test/Transforms/LoopVectorize/memdep.ll @@ -1,5 +1,5 @@ -; RUN: opt < %s -loop-vectorize -force-vector-width=2 -force-vector-unroll=1 -S | FileCheck %s -; RUN: opt < %s -loop-vectorize -force-vector-width=4 -force-vector-unroll=1 -S | FileCheck %s -check-prefix=WIDTH +; RUN: opt < %s -loop-vectorize -force-vector-width=2 -force-vector-interleave=1 -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -S | FileCheck %s -check-prefix=WIDTH 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" diff --git a/test/Transforms/LoopVectorize/metadata-unroll.ll b/test/Transforms/LoopVectorize/metadata-unroll.ll index 848f1f9601b9c..36a231454f084 100644 --- a/test/Transforms/LoopVectorize/metadata-unroll.ll +++ b/test/Transforms/LoopVectorize/metadata-unroll.ll @@ -37,5 +37,5 @@ define void @inc(i32 %n) nounwind uwtable noinline ssp { ret void } -!0 = metadata !{metadata !0, metadata !1} -!1 = metadata !{metadata !"llvm.loop.interleave.count", i32 2} +!0 = !{!0, !1} +!1 = !{!"llvm.loop.interleave.count", i32 2} diff --git a/test/Transforms/LoopVectorize/metadata-width.ll b/test/Transforms/LoopVectorize/metadata-width.ll index 87de655da6f20..dee4feedd6b83 100644 --- a/test/Transforms/LoopVectorize/metadata-width.ll +++ b/test/Transforms/LoopVectorize/metadata-width.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -dce -instcombine -S | FileCheck %s 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" @@ -27,5 +27,5 @@ for.end: ; preds = %for.body, %entry attributes #0 = { nounwind uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-frame-pointer-elim-non-leaf"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" } -!0 = metadata !{metadata !0, metadata !1} -!1 = metadata !{metadata !"llvm.loop.vectorize.width", i32 8} +!0 = !{!0, !1} +!1 = !{!"llvm.loop.vectorize.width", i32 8} diff --git a/test/Transforms/LoopVectorize/metadata.ll b/test/Transforms/LoopVectorize/metadata.ll index bdcf1c9fb2290..a258f7c06c072 100644 --- a/test/Transforms/LoopVectorize/metadata.ll +++ b/test/Transforms/LoopVectorize/metadata.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -S | FileCheck %s target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" target triple = "x86_64-unknown-linux-gnu" @@ -27,18 +27,18 @@ for.end: ; preds = %for.body ; CHECK: store <4 x i32> %{{.*}}, <4 x i32>* %{{.*}}, align 4, !tbaa ![[TINT:[0-9]+]] ; CHECK: ret i32 0 -; CHECK-DAG: ![[TFLT]] = metadata !{metadata ![[TFLT1:[0-9]+]] -; CHECK-DAG: ![[TFLT1]] = metadata !{metadata !"float" +; CHECK-DAG: ![[TFLT]] = !{![[TFLT1:[0-9]+]] +; CHECK-DAG: ![[TFLT1]] = !{!"float" -; CHECK-DAG: ![[TINT]] = metadata !{metadata ![[TINT1:[0-9]+]] -; CHECK-DAG: ![[TINT1]] = metadata !{metadata !"int" +; CHECK-DAG: ![[TINT]] = !{![[TINT1:[0-9]+]] +; CHECK-DAG: ![[TINT1]] = !{!"int" attributes #0 = { nounwind uwtable } -!0 = metadata !{metadata !1, metadata !1, i64 0} -!1 = metadata !{metadata !"float", metadata !2, i64 0} -!2 = metadata !{metadata !"omnipotent char", metadata !3, i64 0} -!3 = metadata !{metadata !"Simple C/C++ TBAA"} -!4 = metadata !{metadata !5, metadata !5, i64 0} -!5 = metadata !{metadata !"int", metadata !2, i64 0} +!0 = !{!1, !1, i64 0} +!1 = !{!"float", !2, i64 0} +!2 = !{!"omnipotent char", !3, i64 0} +!3 = !{!"Simple C/C++ TBAA"} +!4 = !{!5, !5, i64 0} +!5 = !{!"int", !2, i64 0} diff --git a/test/Transforms/LoopVectorize/minmax_reduction.ll b/test/Transforms/LoopVectorize/minmax_reduction.ll index 0e47260984f22..1984cdd892d14 100644 --- a/test/Transforms/LoopVectorize/minmax_reduction.ll +++ b/test/Transforms/LoopVectorize/minmax_reduction.ll @@ -1,4 +1,4 @@ -; RUN: opt -S -loop-vectorize -dce -instcombine -force-vector-width=2 -force-vector-unroll=1 < %s | FileCheck %s +; RUN: opt -S -loop-vectorize -dce -instcombine -force-vector-width=2 -force-vector-interleave=1 < %s | FileCheck %s 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" @@ -516,7 +516,7 @@ for.end: } ; CHECK-LABEL: @unordered_max_red_float( -; CHECK: fcmp ugt <2 x float> +; CHECK: fcmp ole <2 x float> ; CHECK: select <2 x i1> ; CHECK: middle.block ; CHECK: fcmp ogt <2 x float> @@ -542,7 +542,7 @@ for.end: } ; CHECK-LABEL: @unordered_max_red_float_ge( -; CHECK: fcmp uge <2 x float> +; CHECK: fcmp olt <2 x float> ; CHECK: select <2 x i1> ; CHECK: middle.block ; CHECK: fcmp ogt <2 x float> @@ -568,7 +568,7 @@ for.end: } ; CHECK-LABEL: @inverted_unordered_max_red_float( -; CHECK: fcmp ult <2 x float> +; CHECK: fcmp oge <2 x float> ; CHECK: select <2 x i1> ; CHECK: middle.block ; CHECK: fcmp ogt <2 x float> @@ -594,7 +594,7 @@ for.end: } ; CHECK-LABEL: @inverted_unordered_max_red_float_le( -; CHECK: fcmp ule <2 x float> +; CHECK: fcmp ogt <2 x float> ; CHECK: select <2 x i1> ; CHECK: middle.block ; CHECK: fcmp ogt <2 x float> @@ -727,7 +727,7 @@ for.end: } ; CHECK-LABEL: @unordered_min_red_float( -; CHECK: fcmp ult <2 x float> +; CHECK: fcmp oge <2 x float> ; CHECK: select <2 x i1> ; CHECK: middle.block ; CHECK: fcmp olt <2 x float> @@ -753,7 +753,7 @@ for.end: } ; CHECK-LABEL: @unordered_min_red_float_le( -; CHECK: fcmp ule <2 x float> +; CHECK: fcmp ogt <2 x float> ; CHECK: select <2 x i1> ; CHECK: middle.block ; CHECK: fcmp olt <2 x float> @@ -779,7 +779,7 @@ for.end: } ; CHECK-LABEL: @inverted_unordered_min_red_float( -; CHECK: fcmp ugt <2 x float> +; CHECK: fcmp ole <2 x float> ; CHECK: select <2 x i1> ; CHECK: middle.block ; CHECK: fcmp olt <2 x float> @@ -805,7 +805,7 @@ for.end: } ; CHECK-LABEL: @inverted_unordered_min_red_float_ge( -; CHECK: fcmp uge <2 x float> +; CHECK: fcmp olt <2 x float> ; CHECK: select <2 x i1> ; CHECK: middle.block ; CHECK: fcmp olt <2 x float> diff --git a/test/Transforms/LoopVectorize/multi-use-reduction-bug.ll b/test/Transforms/LoopVectorize/multi-use-reduction-bug.ll index 88a29c50df5a8..cd022adc9399d 100644 --- a/test/Transforms/LoopVectorize/multi-use-reduction-bug.ll +++ b/test/Transforms/LoopVectorize/multi-use-reduction-bug.ll @@ -1,4 +1,4 @@ -; RUN: opt -indvars -loop-vectorize -force-vector-width=2 -force-vector-unroll=1 -S < %s | FileCheck %s +; RUN: opt -indvars -loop-vectorize -force-vector-width=2 -force-vector-interleave=1 -S < %s | FileCheck %s target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" target triple = "x86_64-apple-macosx10.9.0" diff --git a/test/Transforms/LoopVectorize/multiple-address-spaces.ll b/test/Transforms/LoopVectorize/multiple-address-spaces.ll index d64662838e008..bb2af1e57ccce 100644 --- a/test/Transforms/LoopVectorize/multiple-address-spaces.ll +++ b/test/Transforms/LoopVectorize/multiple-address-spaces.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -basicaa -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -basicaa -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s ; From a simple program with two address spaces: ; char Y[4*10000] __attribute__((address_space(1))); diff --git a/test/Transforms/LoopVectorize/no_array_bounds.ll b/test/Transforms/LoopVectorize/no_array_bounds.ll index 240b1b5d49dcb..d3bd755e6cf11 100644 --- a/test/Transforms/LoopVectorize/no_array_bounds.ll +++ b/test/Transforms/LoopVectorize/no_array_bounds.ll @@ -72,30 +72,30 @@ attributes #0 = { nounwind } !llvm.module.flags = !{!7, !8} !llvm.ident = !{!9} -!0 = metadata !{i32 786449, metadata !1, i32 4, metadata !"clang version 3.5.0", i1 true, metadata !"", i32 0, metadata !2, metadata !2, metadata !3, metadata !2, metadata !2, metadata !"", i32 2} -!1 = metadata !{metadata !"no_array_bounds.cpp", metadata !"."} -!2 = metadata !{} -!3 = metadata !{metadata !4} -!4 = metadata !{i32 786478, metadata !1, metadata !5, metadata !"test", metadata !"test", metadata !"", i32 1, metadata !6, i1 false, i1 true, i32 0, i32 0, null, i32 256, i1 true, void (i32*, i32*, i32)* @_Z4testPiS_i, null, null, metadata !2, i32 2} -!5 = metadata !{i32 786473, metadata !1} -!6 = metadata !{i32 786453, i32 0, null, metadata !"", i32 0, i64 0, i64 0, i64 0, i32 0, null, metadata !2, i32 0, null, null, null} -!7 = metadata !{i32 2, metadata !"Dwarf Version", i32 2} -!8 = metadata !{i32 2, metadata !"Debug Info Version", i32 1} -!9 = metadata !{metadata !"clang version 3.5.0"} -!10 = metadata !{i32 4, i32 8, metadata !11, null} -!11 = metadata !{i32 786443, metadata !1, metadata !4, i32 4, i32 3, i32 0, i32 0} -!12 = metadata !{metadata !12, metadata !13} -!13 = metadata !{metadata !"llvm.loop.vectorize.enable", i1 true} -!14 = metadata !{i32 5, i32 5, metadata !15, null} -!15 = metadata !{i32 786443, metadata !1, metadata !11, i32 4, i32 36, i32 0, i32 1} -!16 = metadata !{i32 9, i32 8, metadata !17, null} -!17 = metadata !{i32 786443, metadata !1, metadata !4, i32 9, i32 3, i32 0, i32 2} -!18 = metadata !{metadata !18, metadata !13, metadata !19} -!19 = metadata !{metadata !"llvm.loop.vectorize.width", i32 1} -!20 = metadata !{i32 10, i32 5, metadata !21, null} -!21 = metadata !{i32 786443, metadata !1, metadata !17, i32 9, i32 36, i32 0, i32 3} -!22 = metadata !{metadata !23, metadata !23, i64 0} -!23 = metadata !{metadata !"int", metadata !24, i64 0} -!24 = metadata !{metadata !"omnipotent char", metadata !25, i64 0} -!25 = metadata !{metadata !"Simple C/C++ TBAA"} -!26 = metadata !{i32 12, i32 1, metadata !4, null} +!0 = !{!"0x11\004\00clang version 3.5.0\001\00\000\00\002", !1, !2, !2, !3, !2, !2} ; [ DW_TAG_compile_unit ] +!1 = !{!"no_array_bounds.cpp", !"."} +!2 = !{} +!3 = !{!4} +!4 = !{!"0x2e\00test\00test\00\001\000\001\000\006\00256\001\002", !1, !5, !6, null, void (i32*, i32*, i32)* @_Z4testPiS_i, null, null, !2} ; [ DW_TAG_subprogram ] +!5 = !{!"0x29", !1} ; [ DW_TAG_file_type ] +!6 = !{!"0x15\00\000\000\000\000\000\000", i32 0, null, null, !2, null, null, null} ; [ DW_TAG_subroutine_type ] +!7 = !{i32 2, !"Dwarf Version", i32 2} +!8 = !{i32 2, !"Debug Info Version", i32 2} +!9 = !{!"clang version 3.5.0"} +!10 = !MDLocation(line: 4, column: 8, scope: !11) +!11 = !{!"0xb\004\003\000", !1, !4} ; [ DW_TAG_lexical_block ] +!12 = !{!12, !13} +!13 = !{!"llvm.loop.vectorize.enable", i1 true} +!14 = !MDLocation(line: 5, column: 5, scope: !15) +!15 = !{!"0xb\004\0036\000", !1, !11} ; [ DW_TAG_lexical_block ] +!16 = !MDLocation(line: 9, column: 8, scope: !17) +!17 = !{!"0xb\009\003\000", !1, !4} ; [ DW_TAG_lexical_block ] +!18 = !{!18, !13, !19} +!19 = !{!"llvm.loop.vectorize.width", i32 1} +!20 = !MDLocation(line: 10, column: 5, scope: !21) +!21 = !{!"0xb\009\0036\000", !1, !17} ; [ DW_TAG_lexical_block ] +!22 = !{!23, !23, i64 0} +!23 = !{!"int", !24, i64 0} +!24 = !{!"omnipotent char", !25, i64 0} +!25 = !{!"Simple C/C++ TBAA"} +!26 = !MDLocation(line: 12, column: 1, scope: !4) diff --git a/test/Transforms/LoopVectorize/no_idiv_reduction.ll b/test/Transforms/LoopVectorize/no_idiv_reduction.ll index 295fcabb0b291..5c721a6806d99 100644 --- a/test/Transforms/LoopVectorize/no_idiv_reduction.ll +++ b/test/Transforms/LoopVectorize/no_idiv_reduction.ll @@ -1,4 +1,4 @@ -; RUN: opt -loop-vectorize -force-vector-width=2 -force-vector-unroll=1 -S < %s | FileCheck %s +; RUN: opt -loop-vectorize -force-vector-width=2 -force-vector-interleave=1 -S < %s | FileCheck %s @a = common global [128 x i32] zeroinitializer, align 16 ;; Must not vectorize division reduction. Division is lossy. diff --git a/test/Transforms/LoopVectorize/no_int_induction.ll b/test/Transforms/LoopVectorize/no_int_induction.ll index e572d1a884cad..1275915f5e368 100644 --- a/test/Transforms/LoopVectorize/no_int_induction.ll +++ b/test/Transforms/LoopVectorize/no_int_induction.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s ; int __attribute__((noinline)) sum_array(int *A, int n) { ; return std::accumulate(A, A + n, 0); diff --git a/test/Transforms/LoopVectorize/no_outside_user.ll b/test/Transforms/LoopVectorize/no_outside_user.ll index 1f891ad2c4fa1..bcd29c1a439a0 100644 --- a/test/Transforms/LoopVectorize/no_outside_user.ll +++ b/test/Transforms/LoopVectorize/no_outside_user.ll @@ -1,4 +1,7 @@ -; RUN: opt -S -loop-vectorize -force-vector-unroll=1 -force-vector-width=2 < %s | FileCheck %s +; RUN: opt -S -loop-vectorize -force-vector-interleave=1 -force-vector-width=2 -pass-remarks-analysis=loop-vectorize < %s 2>&1 | FileCheck %s + +; CHECK: remark: {{.*}}: loop not vectorized: value could not be identified as an induction or reduction variable +; CHECK: remark: {{.*}}: loop not vectorized: use of induction value outside of the loop is not handled by vectorizer target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:32:32-n8:16:32-S128" diff --git a/test/Transforms/LoopVectorize/no_switch.ll b/test/Transforms/LoopVectorize/no_switch.ll index 8f654e41d4c87..64aab37592f6d 100644 --- a/test/Transforms/LoopVectorize/no_switch.ll +++ b/test/Transforms/LoopVectorize/no_switch.ll @@ -1,7 +1,7 @@ ; RUN: opt < %s -loop-vectorize -force-vector-width=4 -S -pass-remarks-missed='loop-vectorize' -pass-remarks-analysis='loop-vectorize' 2>&1 | FileCheck %s ; CHECK: remark: source.cpp:4:5: loop not vectorized: loop contains a switch statement -; CHECK: remark: source.cpp:4:5: loop not vectorized: vectorization is explicitly enabled with width 4 +; CHECK: remark: source.cpp:4:5: loop not vectorized: use -Rpass-analysis=loop-vectorize for more info (Force=true, Vector Width=4) ; CHECK: warning: source.cpp:4:5: loop not vectorized: failed explicitly specified loop vectorization ; CHECK: _Z11test_switchPii @@ -59,28 +59,28 @@ attributes #0 = { nounwind } !llvm.module.flags = !{!7, !8} !llvm.ident = !{!9} -!0 = metadata !{i32 786449, metadata !1, i32 4, metadata !"clang version 3.5.0", i1 true, metadata !"", i32 0, metadata !2, metadata !2, metadata !3, metadata !2, metadata !2, metadata !"", i32 2} -!1 = metadata !{metadata !"source.cpp", metadata !"."} -!2 = metadata !{} -!3 = metadata !{metadata !4} -!4 = metadata !{i32 786478, metadata !1, metadata !5, metadata !"test_switch", metadata !"test_switch", metadata !"", i32 1, metadata !6, i1 false, i1 true, i32 0, i32 0, null, i32 256, i1 true, void (i32*, i32)* @_Z11test_switchPii, null, null, metadata !2, i32 1} -!5 = metadata !{i32 786473, metadata !1} -!6 = metadata !{i32 786453, i32 0, null, metadata !"", i32 0, i64 0, i64 0, i64 0, i32 0, null, metadata !2, i32 0, null, null, null} -!7 = metadata !{i32 2, metadata !"Dwarf Version", i32 2} -!8 = metadata !{i32 2, metadata !"Debug Info Version", i32 1} -!9 = metadata !{metadata !"clang version 3.5.0"} -!10 = metadata !{i32 3, i32 8, metadata !11, null} -!11 = metadata !{i32 786443, metadata !1, metadata !4, i32 3, i32 3, i32 0, i32 0} -!12 = metadata !{metadata !12, metadata !13, metadata !13} -!13 = metadata !{metadata !"llvm.loop.vectorize.enable", i1 true} -!14 = metadata !{i32 4, i32 5, metadata !15, null} -!15 = metadata !{i32 786443, metadata !1, metadata !11, i32 3, i32 36, i32 0, i32 1} -!16 = metadata !{metadata !17, metadata !17, i64 0} -!17 = metadata !{metadata !"int", metadata !18, i64 0} -!18 = metadata !{metadata !"omnipotent char", metadata !19, i64 0} -!19 = metadata !{metadata !"Simple C/C++ TBAA"} -!20 = metadata !{i32 6, i32 7, metadata !21, null} -!21 = metadata !{i32 786443, metadata !1, metadata !15, i32 4, i32 18, i32 0, i32 2} -!22 = metadata !{i32 7, i32 5, metadata !21, null} -!23 = metadata !{i32 9, i32 7, metadata !21, null} -!24 = metadata !{i32 14, i32 1, metadata !4, null} +!0 = !{!"0x11\004\00clang version 3.5.0\001\00\006\00\002", !1, !2, !2, !3, !2, !2} ; [ DW_TAG_compile_unit ] [./source.cpp] [DW_LANG_C_plus_plus] +!1 = !{!"source.cpp", !"."} +!2 = !{} +!3 = !{!4} +!4 = !{!"0x2e\00test_switch\00test_switch\00\001\000\001\000\006\00256\001\001", !1, !5, !6, null, void (i32*, i32)* @_Z11test_switchPii, null, null, !2} ; [ DW_TAG_subprogram ] [line 1] [def] [test_switch] +!5 = !{!"0x29", !1} ; [ DW_TAG_file_type ] [./source.cpp] +!6 = !{!"0x15\00\000\000\000\000\000\000", i32 0, null, null, !2, null, null, null} ; [ DW_TAG_subroutine_type ] [line 0, size 0, align 0, offset 0] [from ] +!7 = !{i32 2, !"Dwarf Version", i32 2} +!8 = !{i32 2, !"Debug Info Version", i32 2} +!9 = !{!"clang version 3.5.0"} +!10 = !MDLocation(line: 3, column: 8, scope: !11) +!11 = !{!"0xb\003\003\000", !1, !4} ; [ DW_TAG_lexical_block ] +!12 = !{!12, !13, !13} +!13 = !{!"llvm.loop.vectorize.enable", i1 true} +!14 = !MDLocation(line: 4, column: 5, scope: !15) +!15 = !{!"0xb\003\0036\000", !1, !11} ; [ DW_TAG_lexical_block ] +!16 = !{!17, !17, i64 0} +!17 = !{!"int", !18, i64 0} +!18 = !{!"omnipotent char", !19, i64 0} +!19 = !{!"Simple C/C++ TBAA"} +!20 = !MDLocation(line: 6, column: 7, scope: !21) +!21 = !{!"0xb\004\0018\000", !1, !15} ; [ DW_TAG_lexical_block ] +!22 = !MDLocation(line: 7, column: 5, scope: !21) +!23 = !MDLocation(line: 9, column: 7, scope: !21) +!24 = !MDLocation(line: 14, column: 1, scope: !4) diff --git a/test/Transforms/LoopVectorize/nofloat.ll b/test/Transforms/LoopVectorize/nofloat.ll index c3c81b6f84509..e9f4c5f23e08f 100644 --- a/test/Transforms/LoopVectorize/nofloat.ll +++ b/test/Transforms/LoopVectorize/nofloat.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s ; Make sure that we don't vectorize functions with 'noimplicitfloat' attributes. diff --git a/test/Transforms/LoopVectorize/non-const-n.ll b/test/Transforms/LoopVectorize/non-const-n.ll index 0c54a2b01226a..b03d4f05e16f2 100644 --- a/test/Transforms/LoopVectorize/non-const-n.ll +++ b/test/Transforms/LoopVectorize/non-const-n.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/nsw-crash.ll b/test/Transforms/LoopVectorize/nsw-crash.ll index e5fad14d0dda5..68d993340bdb7 100644 --- a/test/Transforms/LoopVectorize/nsw-crash.ll +++ b/test/Transforms/LoopVectorize/nsw-crash.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 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" diff --git a/test/Transforms/LoopVectorize/opt.ll b/test/Transforms/LoopVectorize/opt.ll index 27030a2ff2a97..a9be80fbfee60 100644 --- a/test/Transforms/LoopVectorize/opt.ll +++ b/test/Transforms/LoopVectorize/opt.ll @@ -1,5 +1,5 @@ -; RUN: opt -S -O3 -force-vector-width=2 -force-vector-unroll=1 < %s | FileCheck --check-prefix=LOOPVEC %s -; RUN: opt -S -O3 -disable-loop-vectorization -force-vector-width=2 -force-vector-unroll=1 < %s | FileCheck --check-prefix=NOLOOPVEC %s +; RUN: opt -S -O3 -force-vector-width=2 -force-vector-interleave=1 < %s | FileCheck --check-prefix=LOOPVEC %s +; RUN: opt -S -O3 -disable-loop-vectorization -force-vector-width=2 -force-vector-interleave=1 < %s | FileCheck --check-prefix=NOLOOPVEC %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/ptr_loops.ll b/test/Transforms/LoopVectorize/ptr_loops.ll index 1259e21ebf2ee..3fb38fe1ef132 100644 --- a/test/Transforms/LoopVectorize/ptr_loops.ll +++ b/test/Transforms/LoopVectorize/ptr_loops.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -basicaa -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S -enable-if-conversion | FileCheck %s +; RUN: opt < %s -basicaa -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S -enable-if-conversion | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/read-only.ll b/test/Transforms/LoopVectorize/read-only.ll index fc8f0a5482f0b..2f7a96a09d227 100644 --- a/test/Transforms/LoopVectorize/read-only.ll +++ b/test/Transforms/LoopVectorize/read-only.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/reduction.ll b/test/Transforms/LoopVectorize/reduction.ll index 791fce1562202..5e6b7fa332b22 100644 --- a/test/Transforms/LoopVectorize/reduction.ll +++ b/test/Transforms/LoopVectorize/reduction.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/reverse_induction.ll b/test/Transforms/LoopVectorize/reverse_induction.ll index 65ef95dcb1210..da02d01706ca1 100644 --- a/test/Transforms/LoopVectorize/reverse_induction.ll +++ b/test/Transforms/LoopVectorize/reverse_induction.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=2 -force-vector-width=4 -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=2 -force-vector-width=4 -S | FileCheck %s 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" diff --git a/test/Transforms/LoopVectorize/reverse_iter.ll b/test/Transforms/LoopVectorize/reverse_iter.ll index f803120c4d570..13172bb17aeb6 100644 --- a/test/Transforms/LoopVectorize/reverse_iter.ll +++ b/test/Transforms/LoopVectorize/reverse_iter.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/runtime-check-address-space.ll b/test/Transforms/LoopVectorize/runtime-check-address-space.ll index 848ffc428c5ff..ec56f80144c44 100644 --- a/test/Transforms/LoopVectorize/runtime-check-address-space.ll +++ b/test/Transforms/LoopVectorize/runtime-check-address-space.ll @@ -1,4 +1,4 @@ -; RUN: opt -S -march=r600 -mcpu=cayman -basicaa -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine < %s | FileCheck %s +; RUN: opt -S -march=r600 -mcpu=cayman -basicaa -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine < %s | FileCheck %s ; Check vectorization that would ordinarily require a runtime bounds ; check on the pointers when mixing address spaces. For now we cannot diff --git a/test/Transforms/LoopVectorize/runtime-check-readonly-address-space.ll b/test/Transforms/LoopVectorize/runtime-check-readonly-address-space.ll index 4e98ec504f5bb..12ba3ce6c667d 100644 --- a/test/Transforms/LoopVectorize/runtime-check-readonly-address-space.ll +++ b/test/Transforms/LoopVectorize/runtime-check-readonly-address-space.ll @@ -1,4 +1,4 @@ -; RUN: opt -S -march=r600 -mcpu=cayman -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine < %s | FileCheck %s +; RUN: opt -S -march=r600 -mcpu=cayman -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine < %s | FileCheck %s ; Artificial datalayout target datalayout = "e-p:32:32:32-p1:16:16:16-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-v16:16:16-v24:32:32-v32:32:32-v48:64:64-v64:64:64-v96:128:128-v128:128:128-v192:256:256-v256:256:256-v512:512:512-v1024:1024:1024-v2048:2048:2048-n32:64" diff --git a/test/Transforms/LoopVectorize/runtime-check-readonly.ll b/test/Transforms/LoopVectorize/runtime-check-readonly.ll index 73b28301b7e73..9d02a6accd67f 100644 --- a/test/Transforms/LoopVectorize/runtime-check-readonly.ll +++ b/test/Transforms/LoopVectorize/runtime-check-readonly.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/runtime-check.ll b/test/Transforms/LoopVectorize/runtime-check.ll index d15479d202b7d..1edafb4ed7a90 100644 --- a/test/Transforms/LoopVectorize/runtime-check.ll +++ b/test/Transforms/LoopVectorize/runtime-check.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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-apple-macosx10.9.0" diff --git a/test/Transforms/LoopVectorize/runtime-limit.ll b/test/Transforms/LoopVectorize/runtime-limit.ll index 7370a6fb93c56..324949dafd0a0 100644 --- a/test/Transforms/LoopVectorize/runtime-limit.ll +++ b/test/Transforms/LoopVectorize/runtime-limit.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/safegep.ll b/test/Transforms/LoopVectorize/safegep.ll index c9508601e2c1f..f853afd2bba63 100644 --- a/test/Transforms/LoopVectorize/safegep.ll +++ b/test/Transforms/LoopVectorize/safegep.ll @@ -1,4 +1,4 @@ -; RUN: opt -S -loop-vectorize -force-vector-width=4 -force-vector-unroll=1 < %s | FileCheck %s +; RUN: opt -S -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 < %s | FileCheck %s target datalayout = "e-p:32:32:32-S128-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f16:16:16-f32:32:32-f64:32:64-f128:128:128-v64:64:64-v128:128:128-a0:0:64-f80:32:32-n8:16:32" diff --git a/test/Transforms/LoopVectorize/same-base-access.ll b/test/Transforms/LoopVectorize/same-base-access.ll index d623a34690966..d19458f4aa922 100644 --- a/test/Transforms/LoopVectorize/same-base-access.ll +++ b/test/Transforms/LoopVectorize/same-base-access.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S -enable-if-conversion | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S -enable-if-conversion | FileCheck %s 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-apple-macosx10.9.0" diff --git a/test/Transforms/LoopVectorize/scalar-select.ll b/test/Transforms/LoopVectorize/scalar-select.ll index 257c7bebe4d54..6b37cc23ae319 100644 --- a/test/Transforms/LoopVectorize/scalar-select.ll +++ b/test/Transforms/LoopVectorize/scalar-select.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/scev-exitlim-crash.ll b/test/Transforms/LoopVectorize/scev-exitlim-crash.ll index 683621a6f69bb..5154771807722 100644 --- a/test/Transforms/LoopVectorize/scev-exitlim-crash.ll +++ b/test/Transforms/LoopVectorize/scev-exitlim-crash.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=2 -force-vector-width=8 -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=2 -force-vector-width=8 -S | FileCheck %s 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-apple-macosx" @@ -106,9 +106,9 @@ declare i32 @fn2(double) #1 attributes #0 = { nounwind ssp uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf"="true" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" } attributes #1 = { "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf"="true" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" } -!0 = metadata !{metadata !"int", metadata !1} -!1 = metadata !{metadata !"omnipotent char", metadata !2} -!2 = metadata !{metadata !"Simple C/C++ TBAA"} -!3 = metadata !{metadata !"double", metadata !1} -!4 = metadata !{metadata !0, metadata !0, i64 0} -!5 = metadata !{metadata !3, metadata !3, i64 0} +!0 = !{!"int", !1} +!1 = !{!"omnipotent char", !2} +!2 = !{!"Simple C/C++ TBAA"} +!3 = !{!"double", !1} +!4 = !{!0, !0, i64 0} +!5 = !{!3, !3, i64 0} diff --git a/test/Transforms/LoopVectorize/simple-unroll.ll b/test/Transforms/LoopVectorize/simple-unroll.ll index 83f35ffb609b7..8bf680ac7c5fd 100644 --- a/test/Transforms/LoopVectorize/simple-unroll.ll +++ b/test/Transforms/LoopVectorize/simple-unroll.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-width=4 -force-vector-unroll=2 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-width=4 -force-vector-interleave=2 -dce -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/small-loop.ll b/test/Transforms/LoopVectorize/small-loop.ll index 49ce5c539727a..1d30102c3f977 100644 --- a/test/Transforms/LoopVectorize/small-loop.ll +++ b/test/Transforms/LoopVectorize/small-loop.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/start-non-zero.ll b/test/Transforms/LoopVectorize/start-non-zero.ll index 8f675afd80cbc..cc474945a9d07 100644 --- a/test/Transforms/LoopVectorize/start-non-zero.ll +++ b/test/Transforms/LoopVectorize/start-non-zero.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/store-shuffle-bug.ll b/test/Transforms/LoopVectorize/store-shuffle-bug.ll index 26f4d156df614..6d3d11349b14a 100644 --- a/test/Transforms/LoopVectorize/store-shuffle-bug.ll +++ b/test/Transforms/LoopVectorize/store-shuffle-bug.ll @@ -1,4 +1,4 @@ -; RUN: opt -S -basicaa -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine < %s | FileCheck %s +; RUN: opt -S -basicaa -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine < %s | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/struct_access.ll b/test/Transforms/LoopVectorize/struct_access.ll index 75beae82f170a..cf6f325ae3064 100644 --- a/test/Transforms/LoopVectorize/struct_access.ll +++ b/test/Transforms/LoopVectorize/struct_access.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -instcombine -S | FileCheck %s 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-apple-macosx10.9.0" diff --git a/test/Transforms/LoopVectorize/tbaa-nodep.ll b/test/Transforms/LoopVectorize/tbaa-nodep.ll index f31b3072bc6c5..be3e74f5d68a2 100644 --- a/test/Transforms/LoopVectorize/tbaa-nodep.ll +++ b/test/Transforms/LoopVectorize/tbaa-nodep.ll @@ -1,5 +1,5 @@ -; RUN: opt < %s -tbaa -basicaa -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -simplifycfg -S | FileCheck %s -; RUN: opt < %s -basicaa -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -simplifycfg -S | FileCheck %s --check-prefix=CHECK-NOTBAA +; RUN: opt < %s -tbaa -basicaa -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -simplifycfg -S | FileCheck %s +; RUN: opt < %s -basicaa -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -simplifycfg -S | FileCheck %s --check-prefix=CHECK-NOTBAA target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" target triple = "x86_64-unknown-linux-gnu" @@ -93,10 +93,10 @@ for.end: ; preds = %for.body attributes #0 = { nounwind uwtable } -!0 = metadata !{metadata !1, metadata !1, i64 0} -!1 = metadata !{metadata !"float", metadata !2, i64 0} -!2 = metadata !{metadata !"omnipotent char", metadata !3, i64 0} -!3 = metadata !{metadata !"Simple C/C++ TBAA"} -!4 = metadata !{metadata !5, metadata !5, i64 0} -!5 = metadata !{metadata !"int", metadata !2, i64 0} +!0 = !{!1, !1, i64 0} +!1 = !{!"float", !2, i64 0} +!2 = !{!"omnipotent char", !3, i64 0} +!3 = !{!"Simple C/C++ TBAA"} +!4 = !{!5, !5, i64 0} +!5 = !{!"int", !2, i64 0} diff --git a/test/Transforms/LoopVectorize/undef-inst-bug.ll b/test/Transforms/LoopVectorize/undef-inst-bug.ll index ed60e801afde3..0444fe894ed4a 100644 --- a/test/Transforms/LoopVectorize/undef-inst-bug.ll +++ b/test/Transforms/LoopVectorize/undef-inst-bug.ll @@ -1,4 +1,4 @@ -; RUN: opt -S -loop-vectorize -force-vector-width=4 -force-vector-unroll=1 < %s | FileCheck %s +; RUN: opt -S -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 < %s | FileCheck %s 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" diff --git a/test/Transforms/LoopVectorize/unroll_novec.ll b/test/Transforms/LoopVectorize/unroll_novec.ll index 89f4678526de2..257b4e63a9159 100644 --- a/test/Transforms/LoopVectorize/unroll_novec.ll +++ b/test/Transforms/LoopVectorize/unroll_novec.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-width=1 -force-target-num-scalar-regs=16 -force-target-max-scalar-unroll=8 -force-target-instruction-cost=1 -small-loop-cost=40 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-width=1 -force-target-num-scalar-regs=16 -force-target-max-scalar-interleave=8 -force-target-instruction-cost=1 -small-loop-cost=40 -dce -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" diff --git a/test/Transforms/LoopVectorize/value-ptr-bug.ll b/test/Transforms/LoopVectorize/value-ptr-bug.ll index 6b06afaf0de25..7fb9095b7c103 100644 --- a/test/Transforms/LoopVectorize/value-ptr-bug.ll +++ b/test/Transforms/LoopVectorize/value-ptr-bug.ll @@ -1,4 +1,4 @@ -; RUN: opt -S -loop-vectorize -force-vector-width=4 -force-vector-unroll=1 -dce -instcombine < %s | FileCheck %s +; RUN: opt -S -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -dce -instcombine < %s | FileCheck %s 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" diff --git a/test/Transforms/LoopVectorize/vect.omp.persistence.ll b/test/Transforms/LoopVectorize/vect.omp.persistence.ll index f6465677839e1..ea7be9c106b35 100644 --- a/test/Transforms/LoopVectorize/vect.omp.persistence.ll +++ b/test/Transforms/LoopVectorize/vect.omp.persistence.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -O2 -force-vector-unroll=2 -force-vector-width=4 -debug-only=loop-vectorize -stats -S 2>&1 | FileCheck %s +; RUN: opt < %s -O2 -force-vector-interleave=2 -force-vector-width=4 -debug-only=loop-vectorize -stats -S 2>&1 | FileCheck %s ; REQUIRES: asserts ; Loop from "rotated" @@ -61,8 +61,8 @@ for.end: ret void } -!1 = metadata !{metadata !1, metadata !2} -!2 = metadata !{metadata !"llvm.loop.vectorize.enable", i1 true} +!1 = !{!1, !2} +!2 = !{!"llvm.loop.vectorize.enable", i1 true} ; ; Test #2 @@ -84,5 +84,5 @@ return: ret i32 0 } -!3 = metadata !{metadata !3, metadata !4} -!4 = metadata !{metadata !"llvm.loop.vectorize.enable", i1 true} +!3 = !{!3, !4} +!4 = !{!"llvm.loop.vectorize.enable", i1 true} diff --git a/test/Transforms/LoopVectorize/vect.stats.ll b/test/Transforms/LoopVectorize/vect.stats.ll index 9adf2bb6cf14f..c5b6e64bc9fb7 100644 --- a/test/Transforms/LoopVectorize/vect.stats.ll +++ b/test/Transforms/LoopVectorize/vect.stats.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=4 -force-vector-width=4 -debug-only=loop-vectorize -stats -S 2>&1 | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=4 -force-vector-width=4 -debug-only=loop-vectorize -stats -S 2>&1 | FileCheck %s ; REQUIRES: asserts ; @@ -56,4 +56,4 @@ for.body: ; preds = %entry, %for.body for.end: ; preds = %entry, %for.body ret void -}
\ No newline at end of file +} diff --git a/test/Transforms/LoopVectorize/vectorize-once.ll b/test/Transforms/LoopVectorize/vectorize-once.ll index 97654f4950182..a9b2a53f74b31 100644 --- a/test/Transforms/LoopVectorize/vectorize-once.ll +++ b/test/Transforms/LoopVectorize/vectorize-once.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S -simplifycfg | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S -simplifycfg | FileCheck %s 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-apple-macosx10.8.0" @@ -68,10 +68,10 @@ _ZSt10accumulateIPiiET0_T_S2_S1_.exit: ; preds = %for.body.i, %entry attributes #0 = { nounwind readonly ssp uwtable "fp-contract-model"="standard" "no-frame-pointer-elim" "no-frame-pointer-elim-non-leaf" "realign-stack" "relocation-model"="pic" "ssp-buffers-size"="8" } -; CHECK: !0 = metadata !{metadata !0, metadata !1, metadata !2} -; CHECK: !1 = metadata !{metadata !"llvm.loop.vectorize.width", i32 1} -; CHECK: !2 = metadata !{metadata !"llvm.loop.interleave.count", i32 1} -; CHECK: !3 = metadata !{metadata !3, metadata !1, metadata !2} +; CHECK: !0 = distinct !{!0, !1, !2} +; CHECK: !1 = !{!"llvm.loop.vectorize.width", i32 1} +; CHECK: !2 = !{!"llvm.loop.interleave.count", i32 1} +; CHECK: !3 = distinct !{!3, !1, !2} -!0 = metadata !{metadata !0, metadata !1} -!1 = metadata !{metadata !"llvm.loop.vectorize.width", i32 1} +!0 = !{!0, !1} +!1 = !{!"llvm.loop.vectorize.width", i32 1} diff --git a/test/Transforms/LoopVectorize/version-mem-access.ll b/test/Transforms/LoopVectorize/version-mem-access.ll index 51d20e227ddfa..7ac2fca2533f9 100644 --- a/test/Transforms/LoopVectorize/version-mem-access.ll +++ b/test/Transforms/LoopVectorize/version-mem-access.ll @@ -1,4 +1,4 @@ -; RUN: opt -basicaa -loop-vectorize -enable-mem-access-versioning -force-vector-width=2 -force-vector-unroll=1 < %s -S | FileCheck %s +; RUN: opt -basicaa -loop-vectorize -enable-mem-access-versioning -force-vector-width=2 -force-vector-interleave=1 < %s -S | FileCheck %s target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" diff --git a/test/Transforms/LoopVectorize/write-only.ll b/test/Transforms/LoopVectorize/write-only.ll index 71a9cd0dc5bec..2f100de82370e 100644 --- a/test/Transforms/LoopVectorize/write-only.ll +++ b/test/Transforms/LoopVectorize/write-only.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s 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-apple-macosx10.8.0" |