diff options
Diffstat (limited to 'llvm/test/Transforms/LoopVectorize/PowerPC')
8 files changed, 456 insertions, 0 deletions
diff --git a/llvm/test/Transforms/LoopVectorize/PowerPC/agg-interleave-a2.ll b/llvm/test/Transforms/LoopVectorize/PowerPC/agg-interleave-a2.ll new file mode 100644 index 00000000000..3491e08bbaa --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/PowerPC/agg-interleave-a2.ll @@ -0,0 +1,40 @@ +; RUN: opt -S -basicaa -loop-vectorize < %s | FileCheck %s +target datalayout = "E-m:e-i64:64-n32:64" +target triple = "powerpc64-unknown-linux-gnu" + +; Function Attrs: nounwind +define void @foo(double* noalias nocapture %a, double* noalias nocapture readonly %b, double* noalias nocapture readonly %c) #0 { +entry: + br label %for.body + +; CHECK-LABEL: @foo +; CHECK: fmul <4 x double> %{{[^,]+}}, <double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00> +; CHECK-NEXT: fmul <4 x double> %{{[^,]+}}, <double 2.000000e+00, double 2.000000e+00, double 2.000000e+00, double 2.000000e+00> + +for.cond.cleanup: ; preds = %for.body + ret void + +for.body: ; preds = %for.body, %entry + %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ] + %arrayidx = getelementptr inbounds double, double* %b, i64 %indvars.iv + %0 = load double, double* %arrayidx, align 8 + %mul = fmul double %0, 2.000000e+00 + %mul3 = fmul double %0, %mul + %arrayidx5 = getelementptr inbounds double, double* %c, i64 %indvars.iv + %1 = load double, double* %arrayidx5, align 8 + %mul6 = fmul double %1, 3.000000e+00 + %mul9 = fmul double %1, %mul6 + %add = fadd double %mul3, %mul9 + %mul12 = fmul double %0, 4.000000e+00 + %mul15 = fmul double %mul12, %1 + %add16 = fadd double %mul15, %add + %add17 = fadd double %add16, 1.000000e+00 + %arrayidx19 = getelementptr inbounds double, double* %a, i64 %indvars.iv + store double %add17, double* %arrayidx19, align 8 + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + %exitcond = icmp eq i64 %indvars.iv.next, 1600 + br i1 %exitcond, label %for.cond.cleanup, label %for.body +} + +attributes #0 = { nounwind "target-cpu"="a2q" } + diff --git a/llvm/test/Transforms/LoopVectorize/PowerPC/large-loop-rdx.ll b/llvm/test/Transforms/LoopVectorize/PowerPC/large-loop-rdx.ll new file mode 100644 index 00000000000..c88b496e4e9 --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/PowerPC/large-loop-rdx.ll @@ -0,0 +1,75 @@ +; RUN: opt < %s -loop-vectorize -S | FileCheck %s + +; CHECK: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: = +; CHECK-NOT: fadd +; CHECK-SAME: > + +target datalayout = "e-m:e-i64:64-n32:64" +target triple = "powerpc64le-ibm-linux-gnu" + +define void @QLA_F3_r_veq_norm2_V(float* noalias nocapture %r, [3 x { float, float }]* noalias nocapture readonly %a, i32 signext %n) #0 { +entry: + %cmp24 = icmp sgt i32 %n, 0 + br i1 %cmp24, label %for.cond1.preheader.preheader, label %for.end13 + +for.cond1.preheader.preheader: ; preds = %entry + br label %for.cond1.preheader + +for.cond1.preheader: ; preds = %for.cond1.preheader.preheader, %for.cond1.preheader + %indvars.iv = phi i64 [ %indvars.iv.next, %for.cond1.preheader ], [ 0, %for.cond1.preheader.preheader ] + %sum.026 = phi double [ %add10.2, %for.cond1.preheader ], [ 0.000000e+00, %for.cond1.preheader.preheader ] + %arrayidx5.realp = getelementptr inbounds [3 x { float, float }], [3 x { float, float }]* %a, i64 %indvars.iv, i64 0, i32 0 + %arrayidx5.real = load float, float* %arrayidx5.realp, align 8 + %arrayidx5.imagp = getelementptr inbounds [3 x { float, float }], [3 x { float, float }]* %a, i64 %indvars.iv, i64 0, i32 1 + %arrayidx5.imag = load float, float* %arrayidx5.imagp, align 8 + %mul = fmul fast float %arrayidx5.real, %arrayidx5.real + %mul9 = fmul fast float %arrayidx5.imag, %arrayidx5.imag + %add = fadd fast float %mul9, %mul + %conv = fpext float %add to double + %add10 = fadd fast double %conv, %sum.026 + %arrayidx5.realp.1 = getelementptr inbounds [3 x { float, float }], [3 x { float, float }]* %a, i64 %indvars.iv, i64 1, i32 0 + %arrayidx5.real.1 = load float, float* %arrayidx5.realp.1, align 8 + %arrayidx5.imagp.1 = getelementptr inbounds [3 x { float, float }], [3 x { float, float }]* %a, i64 %indvars.iv, i64 1, i32 1 + %arrayidx5.imag.1 = load float, float* %arrayidx5.imagp.1, align 8 + %mul.1 = fmul fast float %arrayidx5.real.1, %arrayidx5.real.1 + %mul9.1 = fmul fast float %arrayidx5.imag.1, %arrayidx5.imag.1 + %add.1 = fadd fast float %mul9.1, %mul.1 + %conv.1 = fpext float %add.1 to double + %add10.1 = fadd fast double %conv.1, %add10 + %arrayidx5.realp.2 = getelementptr inbounds [3 x { float, float }], [3 x { float, float }]* %a, i64 %indvars.iv, i64 2, i32 0 + %arrayidx5.real.2 = load float, float* %arrayidx5.realp.2, align 8 + %arrayidx5.imagp.2 = getelementptr inbounds [3 x { float, float }], [3 x { float, float }]* %a, i64 %indvars.iv, i64 2, i32 1 + %arrayidx5.imag.2 = load float, float* %arrayidx5.imagp.2, align 8 + %mul.2 = fmul fast float %arrayidx5.real.2, %arrayidx5.real.2 + %mul9.2 = fmul fast float %arrayidx5.imag.2, %arrayidx5.imag.2 + %add.2 = fadd fast float %mul9.2, %mul.2 + %conv.2 = fpext float %add.2 to double + %add10.2 = fadd fast double %conv.2, %add10.1 + %indvars.iv.next = add nuw nsw 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.cond.for.end13_crit_edge, label %for.cond1.preheader + +for.cond.for.end13_crit_edge: ; preds = %for.cond1.preheader + %add10.2.lcssa = phi double [ %add10.2, %for.cond1.preheader ] + %phitmp = fptrunc double %add10.2.lcssa to float + br label %for.end13 + +for.end13: ; preds = %for.cond.for.end13_crit_edge, %entry + %sum.0.lcssa = phi float [ %phitmp, %for.cond.for.end13_crit_edge ], [ 0.000000e+00, %entry ] + store float %sum.0.lcssa, float* %r, align 4 + ret void +} + diff --git a/llvm/test/Transforms/LoopVectorize/PowerPC/lit.local.cfg b/llvm/test/Transforms/LoopVectorize/PowerPC/lit.local.cfg new file mode 100644 index 00000000000..5d33887ff0a --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/PowerPC/lit.local.cfg @@ -0,0 +1,3 @@ +if not 'PowerPC' in config.root.targets: + config.unsupported = True + diff --git a/llvm/test/Transforms/LoopVectorize/PowerPC/pr30990.ll b/llvm/test/Transforms/LoopVectorize/PowerPC/pr30990.ll new file mode 100644 index 00000000000..d3cdabd26f5 --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/PowerPC/pr30990.ll @@ -0,0 +1,140 @@ +; RUN: opt < %s -loop-vectorize -mcpu=pwr8 -mattr=+vsx -force-vector-interleave=1 -vectorizer-maximize-bandwidth=0 -S | FileCheck %s + +target triple = "powerpc64-unknown-linux-gnu" + +define signext i32 @foo(i8* readonly %ptr, i32 signext %l) { +entry: + %idx.ext = sext i32 %l to i64 + %add.ptr = getelementptr inbounds i8, i8* %ptr, i64 %idx.ext + %cmp7 = icmp sgt i32 %l, 0 + br i1 %cmp7, label %while.body.preheader, label %while.end + +while.body.preheader: ; preds = %entry + br label %while.body + +while.body: ; preds = %while.body.preheader, %while.body + %count.09 = phi i32 [ %add, %while.body ], [ 0, %while.body.preheader ] + %ptr.addr.08 = phi i8* [ %incdec.ptr, %while.body ], [ %ptr, %while.body.preheader ] + %0 = load i8, i8* %ptr.addr.08, align 1 + %cmp1 = icmp slt i8 %0, -64 + %cond = zext i1 %cmp1 to i32 + %add = add nsw i32 %cond, %count.09 + %incdec.ptr = getelementptr inbounds i8, i8* %ptr.addr.08, i64 1 + %cmp = icmp ult i8* %incdec.ptr, %add.ptr + br i1 %cmp, label %while.body, label %while.end.loopexit + +while.end.loopexit: ; preds = %while.body + %add.lcssa = phi i32 [ %add, %while.body ] + br label %while.end + +while.end: ; preds = %while.end.loopexit, %entry + %count.0.lcssa = phi i32 [ 0, %entry ], [ %add.lcssa, %while.end.loopexit ] + ret i32 %count.0.lcssa + +; CHECK: load <4 x i8> +; CHECK: icmp slt <4 x i8> +} + + +define signext i16 @foo2(i8* readonly %ptr, i32 signext %l) { +entry: + %idx.ext = sext i32 %l to i64 + %add.ptr = getelementptr inbounds i8, i8* %ptr, i64 %idx.ext + %cmp7 = icmp sgt i32 %l, 0 + br i1 %cmp7, label %while.body.preheader, label %while.end + +while.body.preheader: ; preds = %entry + br label %while.body + +while.body: ; preds = %while.body.preheader, %while.body + %count.09 = phi i16 [ %add, %while.body ], [ 0, %while.body.preheader ] + %ptr.addr.08 = phi i8* [ %incdec.ptr, %while.body ], [ %ptr, %while.body.preheader ] + %0 = load i8, i8* %ptr.addr.08, align 1 + %cmp1 = icmp slt i8 %0, -64 + %cond = zext i1 %cmp1 to i16 + %add = add nsw i16 %cond, %count.09 + %incdec.ptr = getelementptr inbounds i8, i8* %ptr.addr.08, i64 1 + %cmp = icmp ult i8* %incdec.ptr, %add.ptr + br i1 %cmp, label %while.body, label %while.end.loopexit + +while.end.loopexit: ; preds = %while.body + %add.lcssa = phi i16 [ %add, %while.body ] + br label %while.end + +while.end: ; preds = %while.end.loopexit, %entry + %count.0.lcssa = phi i16 [ 0, %entry ], [ %add.lcssa, %while.end.loopexit ] + ret i16 %count.0.lcssa + +; CHECK-LABEL: foo2 +; CHECK: load <8 x i8> +; CHECK: icmp slt <8 x i8> +} + +define signext i32 @foo3(i16* readonly %ptr, i32 signext %l) { +entry: + %idx.ext = sext i32 %l to i64 + %add.ptr = getelementptr inbounds i16, i16* %ptr, i64 %idx.ext + %cmp7 = icmp sgt i32 %l, 0 + br i1 %cmp7, label %while.body.preheader, label %while.end + +while.body.preheader: ; preds = %entry + br label %while.body + +while.body: ; preds = %while.body.preheader, %while.body + %count.09 = phi i32 [ %add, %while.body ], [ 0, %while.body.preheader ] + %ptr.addr.16 = phi i16* [ %incdec.ptr, %while.body ], [ %ptr, %while.body.preheader ] + %0 = load i16, i16* %ptr.addr.16, align 1 + %cmp1 = icmp slt i16 %0, -64 + %cond = zext i1 %cmp1 to i32 + %add = add nsw i32 %cond, %count.09 + %incdec.ptr = getelementptr inbounds i16, i16* %ptr.addr.16, i64 1 + %cmp = icmp ult i16* %incdec.ptr, %add.ptr + br i1 %cmp, label %while.body, label %while.end.loopexit + +while.end.loopexit: ; preds = %while.body + %add.lcssa = phi i32 [ %add, %while.body ] + br label %while.end + +while.end: ; preds = %while.end.loopexit, %entry + %count.0.lcssa = phi i32 [ 0, %entry ], [ %add.lcssa, %while.end.loopexit ] + ret i32 %count.0.lcssa + +; CHECK-LABEL: foo3 +; CHECK: load <4 x i16> +; CHECK: icmp slt <4 x i16> +} + +define i64 @foo4(i16* readonly %ptr, i32 signext %l) { +entry: + %idx.ext = sext i32 %l to i64 + %add.ptr = getelementptr inbounds i16, i16* %ptr, i64 %idx.ext + %cmp7 = icmp sgt i32 %l, 0 + br i1 %cmp7, label %while.body.preheader, label %while.end + +while.body.preheader: ; preds = %entry + br label %while.body + +while.body: ; preds = %while.body.preheader, %while.body + %count.09 = phi i64 [ %add, %while.body ], [ 0, %while.body.preheader ] + %ptr.addr.16 = phi i16* [ %incdec.ptr, %while.body ], [ %ptr, %while.body.preheader ] + %0 = load i16, i16* %ptr.addr.16, align 1 + %cmp1 = icmp slt i16 %0, -64 + %cond = zext i1 %cmp1 to i64 + %add = add nsw i64 %cond, %count.09 + %incdec.ptr = getelementptr inbounds i16, i16* %ptr.addr.16, i64 1 + %cmp = icmp ult i16* %incdec.ptr, %add.ptr + br i1 %cmp, label %while.body, label %while.end.loopexit + +while.end.loopexit: ; preds = %while.body + %add.lcssa = phi i64 [ %add, %while.body ] + br label %while.end + +while.end: ; preds = %while.end.loopexit, %entry + %count.0.lcssa = phi i64 [ 0, %entry ], [ %add.lcssa, %while.end.loopexit ] + ret i64 %count.0.lcssa + +; CHECK-LABEL: foo4 +; CHECK: load <2 x i16> +; CHECK: icmp slt <2 x i16> +} + diff --git a/llvm/test/Transforms/LoopVectorize/PowerPC/small-loop-rdx.ll b/llvm/test/Transforms/LoopVectorize/PowerPC/small-loop-rdx.ll new file mode 100644 index 00000000000..76864bc4629 --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/PowerPC/small-loop-rdx.ll @@ -0,0 +1,49 @@ +; RUN: opt < %s -loop-vectorize -S | FileCheck %s + +; CHECK: vector.body: +; CHECK: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NEXT: fadd +; CHECK-NOT: fadd +; CHECK: middle.block + +target datalayout = "e-m:e-i64:64-n32:64" +target triple = "powerpc64le-ibm-linux-gnu" + +define void @test(double* nocapture readonly %arr, i32 signext %len) #0 { +entry: + %cmp4 = icmp sgt i32 %len, 0 + br i1 %cmp4, label %for.body.lr.ph, label %for.end + +for.body.lr.ph: ; preds = %entry + %0 = add i32 %len, -1 + br label %for.body + +for.body: ; preds = %for.body, %for.body.lr.ph + %indvars.iv = phi i64 [ 0, %for.body.lr.ph ], [ %indvars.iv.next, %for.body ] + %redx.05 = phi double [ 0.000000e+00, %for.body.lr.ph ], [ %add, %for.body ] + %arrayidx = getelementptr inbounds double, double* %arr, i64 %indvars.iv + %1 = load double, double* %arrayidx, align 8 + %add = fadd fast double %1, %redx.05 + %indvars.iv.next = add i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv to i32 + %exitcond = icmp eq i32 %lftr.wideiv, %0 + br i1 %exitcond, label %for.end.loopexit, label %for.body + +for.end.loopexit: ; preds = %for.body + %add.lcssa = phi double [ %add, %for.body ] + br label %for.end + +for.end: ; preds = %for.end.loopexit, %entry + %redx.0.lcssa = phi double [ 0.000000e+00, %entry ], [ %add.lcssa, %for.end.loopexit ] + ret void +} diff --git a/llvm/test/Transforms/LoopVectorize/PowerPC/stride-vectorization.ll b/llvm/test/Transforms/LoopVectorize/PowerPC/stride-vectorization.ll new file mode 100644 index 00000000000..f6f2609e8fb --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/PowerPC/stride-vectorization.ll @@ -0,0 +1,36 @@ +; RUN: opt -S -basicaa -loop-vectorize < %s | FileCheck %s +target datalayout = "E-m:e-i64:64-n32:64" +target triple = "powerpc64-unknown-linux-gnu" + +; Function Attrs: nounwind +define void @foo(double* noalias nocapture %a, double* noalias nocapture readonly %b) #0 { +entry: + br label %for.body + +; CHECK-LABEL: @foo +; CHECK: <2 x double> + +for.cond.cleanup: ; preds = %for.body + ret void + +for.body: ; preds = %for.body, %entry + %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ] + %0 = shl nsw i64 %indvars.iv, 1 + %odd.idx = add nsw i64 %0, 1 + + %arrayidx = getelementptr inbounds double, double* %b, i64 %0 + %arrayidx.odd = getelementptr inbounds double, double* %b, i64 %odd.idx + + %1 = load double, double* %arrayidx, align 8 + %2 = load double, double* %arrayidx.odd, align 8 + + %add = fadd double %1, %2 + %arrayidx2 = getelementptr inbounds double, double* %a, i64 %indvars.iv + store double %add, double* %arrayidx2, align 8 + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + %exitcond = icmp eq i64 %indvars.iv.next, 1600 + br i1 %exitcond, label %for.cond.cleanup, label %for.body +} + +attributes #0 = { nounwind "target-cpu"="pwr8" } + diff --git a/llvm/test/Transforms/LoopVectorize/PowerPC/vectorize-only-for-real.ll b/llvm/test/Transforms/LoopVectorize/PowerPC/vectorize-only-for-real.ll new file mode 100644 index 00000000000..8abc25ece35 --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/PowerPC/vectorize-only-for-real.ll @@ -0,0 +1,62 @@ +; RUN: opt -S -loop-vectorize < %s | FileCheck %s +target datalayout = "E-m:e-i64:64-n32:64" +target triple = "powerpc64-bgq-linux" + +; Function Attrs: nounwind +define zeroext i32 @test() #0 { +; CHECK-LABEL: @test +; CHECK-NOT: x i32> + +entry: + %a = alloca [1600 x i32], align 4 + %c = alloca [1600 x i32], align 4 + %0 = bitcast [1600 x i32]* %a to i8* + call void @llvm.lifetime.start(i64 6400, i8* %0) #3 + br label %for.body + +for.cond.cleanup: ; preds = %for.body + %1 = bitcast [1600 x i32]* %c to i8* + call void @llvm.lifetime.start(i64 6400, i8* %1) #3 + %arraydecay = getelementptr inbounds [1600 x i32], [1600 x i32]* %a, i64 0, i64 0 + %arraydecay1 = getelementptr inbounds [1600 x i32], [1600 x i32]* %c, i64 0, i64 0 + %call = call signext i32 @bar(i32* %arraydecay, i32* %arraydecay1) #3 + br label %for.body6 + +for.body: ; preds = %for.body, %entry + %indvars.iv25 = phi i64 [ 0, %entry ], [ %indvars.iv.next26, %for.body ] + %arrayidx = getelementptr inbounds [1600 x i32], [1600 x i32]* %a, i64 0, i64 %indvars.iv25 + %2 = trunc i64 %indvars.iv25 to i32 + store i32 %2, i32* %arrayidx, align 4 + %indvars.iv.next26 = add nuw nsw i64 %indvars.iv25, 1 + %exitcond27 = icmp eq i64 %indvars.iv.next26, 1600 + br i1 %exitcond27, label %for.cond.cleanup, label %for.body + +for.cond.cleanup5: ; preds = %for.body6 + call void @llvm.lifetime.end(i64 6400, i8* nonnull %1) #3 + call void @llvm.lifetime.end(i64 6400, i8* %0) #3 + ret i32 %add + +for.body6: ; preds = %for.body6, %for.cond.cleanup + %indvars.iv = phi i64 [ 0, %for.cond.cleanup ], [ %indvars.iv.next, %for.body6 ] + %s.022 = phi i32 [ 0, %for.cond.cleanup ], [ %add, %for.body6 ] + %arrayidx8 = getelementptr inbounds [1600 x i32], [1600 x i32]* %c, i64 0, i64 %indvars.iv + %3 = load i32, i32* %arrayidx8, align 4 + %add = add i32 %3, %s.022 + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + %exitcond = icmp eq i64 %indvars.iv.next, 1600 + br i1 %exitcond, label %for.cond.cleanup5, label %for.body6 +} + +; Function Attrs: argmemonly nounwind +declare void @llvm.lifetime.start(i64, i8* nocapture) #1 + +; Function Attrs: argmemonly nounwind +declare void @llvm.lifetime.end(i64, i8* nocapture) #1 + +declare signext i32 @bar(i32*, i32*) #2 + +attributes #0 = { nounwind "target-cpu"="a2q" "target-features"="+qpx,-altivec,-bpermd,-crypto,-direct-move,-extdiv,-power8-vector,-vsx" } +attributes #1 = { argmemonly nounwind } +attributes #2 = { "target-cpu"="a2q" "target-features"="+qpx,-altivec,-bpermd,-crypto,-direct-move,-extdiv,-power8-vector,-vsx" } +attributes #3 = { nounwind } + diff --git a/llvm/test/Transforms/LoopVectorize/PowerPC/vsx-tsvc-s173.ll b/llvm/test/Transforms/LoopVectorize/PowerPC/vsx-tsvc-s173.ll new file mode 100644 index 00000000000..15aec0d3539 --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/PowerPC/vsx-tsvc-s173.ll @@ -0,0 +1,51 @@ +; RUN: opt < %s -mcpu=pwr7 -mattr=+vsx -loop-vectorize -instcombine -S | FileCheck %s +target datalayout = "E-m:e-i64:64-n32:64" +target triple = "powerpc64-unknown-linux-gnu" + +%struct.GlobalData = type { [32000 x float], [3 x i32], [4 x i8], [32000 x float], [5 x i32], [12 x i8], [32000 x float], [7 x i32], [4 x i8], [32000 x float], [11 x i32], [4 x i8], [32000 x float], [13 x i32], [12 x i8], [256 x [256 x float]], [17 x i32], [12 x i8], [256 x [256 x float]], [19 x i32], [4 x i8], [256 x [256 x float]], [23 x i32], [4 x i8], [256 x [256 x float]] } + +@global_data = external global %struct.GlobalData, align 16 +@ntimes = external hidden unnamed_addr global i32, align 4 + +define signext i32 @s173() #0 { +entry: + %0 = load i32, i32* @ntimes, align 4 + %cmp21 = icmp sgt i32 %0, 0 + br i1 %cmp21, label %for.cond1.preheader, label %for.end12 + +for.cond1.preheader: ; preds = %for.end, %entry + %nl.022 = phi i32 [ %inc11, %for.end ], [ 0, %entry ] + br label %for.body3 + +for.body3: ; preds = %for.body3, %for.cond1.preheader + %indvars.iv = phi i64 [ 0, %for.cond1.preheader ], [ %indvars.iv.next, %for.body3 ] + %arrayidx = getelementptr inbounds %struct.GlobalData, %struct.GlobalData* @global_data, i64 0, i32 0, i64 %indvars.iv + %1 = load float, float* %arrayidx, align 4 + %arrayidx5 = getelementptr inbounds %struct.GlobalData, %struct.GlobalData* @global_data, i64 0, i32 3, i64 %indvars.iv + %2 = load float, float* %arrayidx5, align 4 + %add = fadd float %1, %2 + %3 = add nsw i64 %indvars.iv, 16000 + %arrayidx8 = getelementptr inbounds %struct.GlobalData, %struct.GlobalData* @global_data, i64 0, i32 0, i64 %3 + store float %add, float* %arrayidx8, align 4 + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + %exitcond = icmp eq i64 %indvars.iv.next, 16000 + br i1 %exitcond, label %for.end, label %for.body3 + +for.end: ; preds = %for.body3 + %inc11 = add nsw i32 %nl.022, 1 + %4 = load i32, i32* @ntimes, align 4 + %mul = mul nsw i32 %4, 10 + %cmp = icmp slt i32 %inc11, %mul + br i1 %cmp, label %for.cond1.preheader, label %for.end12 + +for.end12: ; preds = %for.end, %entry + ret i32 0 + +; CHECK-LABEL: @s173 +; CHECK: load <4 x float>, <4 x float>* +; CHECK: add nsw i64 %index, 16000 +; CHECK: ret i32 0 +} + +attributes #0 = { nounwind } + |
