diff options
Diffstat (limited to 'llvm/test/Transforms/Scalarizer')
-rw-r--r-- | llvm/test/Transforms/Scalarizer/basic.ll | 453 | ||||
-rw-r--r-- | llvm/test/Transforms/Scalarizer/cache-bug.ll | 31 | ||||
-rw-r--r-- | llvm/test/Transforms/Scalarizer/crash-bug.ll | 25 | ||||
-rw-r--r-- | llvm/test/Transforms/Scalarizer/dbginfo.ll | 86 | ||||
-rw-r--r-- | llvm/test/Transforms/Scalarizer/dbgloc-bug.ll | 44 | ||||
-rw-r--r-- | llvm/test/Transforms/Scalarizer/intrinsics.ll | 110 | ||||
-rw-r--r-- | llvm/test/Transforms/Scalarizer/order-bug.ll | 24 | ||||
-rw-r--r-- | llvm/test/Transforms/Scalarizer/phi-bug.ll | 25 | ||||
-rw-r--r-- | llvm/test/Transforms/Scalarizer/store-bug.ll | 26 | ||||
-rw-r--r-- | llvm/test/Transforms/Scalarizer/vector-gep.ll | 123 |
10 files changed, 0 insertions, 947 deletions
diff --git a/llvm/test/Transforms/Scalarizer/basic.ll b/llvm/test/Transforms/Scalarizer/basic.ll deleted file mode 100644 index 29a82fd8090..00000000000 --- a/llvm/test/Transforms/Scalarizer/basic.ll +++ /dev/null @@ -1,453 +0,0 @@ -; RUN: opt %s -scalarizer -scalarize-load-store -dce -S | FileCheck %s -; RUN: opt %s -passes='function(scalarizer,dce)' -scalarize-load-store -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" - -declare <4 x float> @ext(<4 x float>) -@g = global <4 x float> zeroinitializer - -define void @f1(<4 x float> %init, <4 x float> *%base, i32 %count) { -; CHECK-LABEL: @f1( -; CHECK: entry: -; CHECK: %init.i0 = extractelement <4 x float> %init, i32 0 -; CHECK: %init.i1 = extractelement <4 x float> %init, i32 1 -; CHECK: %init.i2 = extractelement <4 x float> %init, i32 2 -; CHECK: %init.i3 = extractelement <4 x float> %init, i32 3 -; CHECK: br label %loop -; CHECK: loop: -; CHECK: %i = phi i32 [ %count, %entry ], [ %nexti, %loop ] -; CHECK: %acc.i0 = phi float [ %init.i0, %entry ], [ %sel.i0, %loop ] -; CHECK: %acc.i1 = phi float [ %init.i1, %entry ], [ %sel.i1, %loop ] -; CHECK: %acc.i2 = phi float [ %init.i2, %entry ], [ %sel.i2, %loop ] -; CHECK: %acc.i3 = phi float [ %init.i3, %entry ], [ %sel.i3, %loop ] -; CHECK: %nexti = sub i32 %i, 1 -; CHECK: %ptr = getelementptr <4 x float>, <4 x float>* %base, i32 %i -; CHECK: %ptr.i0 = bitcast <4 x float>* %ptr to float* -; CHECK: %val.i0 = load float, float* %ptr.i0, align 16 -; CHECK: %ptr.i1 = getelementptr float, float* %ptr.i0, i32 1 -; CHECK: %val.i1 = load float, float* %ptr.i1, align 4 -; CHECK: %ptr.i2 = getelementptr float, float* %ptr.i0, i32 2 -; CHECK: %val.i2 = load float, float* %ptr.i2, align 8 -; CHECK: %ptr.i3 = getelementptr float, float* %ptr.i0, i32 3 -; CHECK: %val.i3 = load float, float* %ptr.i3, align 4 -; CHECK: %add.i0 = fadd float %val.i0, %val.i2 -; CHECK: %add.i1 = fadd float %val.i1, %val.i3 -; CHECK: %add.i2 = fadd float %acc.i0, %acc.i2 -; CHECK: %add.i3 = fadd float %acc.i1, %acc.i3 -; CHECK: %add.upto0 = insertelement <4 x float> undef, float %add.i0, i32 0 -; CHECK: %add.upto1 = insertelement <4 x float> %add.upto0, float %add.i1, i32 1 -; CHECK: %add.upto2 = insertelement <4 x float> %add.upto1, float %add.i2, i32 2 -; CHECK: %add = insertelement <4 x float> %add.upto2, float %add.i3, i32 3 -; CHECK: %call = call <4 x float> @ext(<4 x float> %add) -; CHECK: %call.i0 = extractelement <4 x float> %call, i32 0 -; CHECK: %cmp.i0 = fcmp ogt float %call.i0, 1.0 -; CHECK: %call.i1 = extractelement <4 x float> %call, i32 1 -; CHECK: %cmp.i1 = fcmp ogt float %call.i1, 2.0 -; CHECK: %call.i2 = extractelement <4 x float> %call, i32 2 -; CHECK: %cmp.i2 = fcmp ogt float %call.i2, 3.0 -; CHECK: %call.i3 = extractelement <4 x float> %call, i32 3 -; CHECK: %cmp.i3 = fcmp ogt float %call.i3, 4.0 -; CHECK: %sel.i0 = select i1 %cmp.i0, float %call.i0, float 5.0 -; CHECK: %sel.i1 = select i1 %cmp.i1, float %call.i1, float 6.0 -; CHECK: %sel.i2 = select i1 %cmp.i2, float %call.i2, float 7.0 -; CHECK: %sel.i3 = select i1 %cmp.i3, float %call.i3, float 8.0 -; CHECK: store float %sel.i0, float* %ptr.i0 -; CHECK: store float %sel.i1, float* %ptr.i1 -; CHECK: store float %sel.i2, float* %ptr.i2 -; CHECK: store float %sel.i3, float* %ptr.i3 -; CHECK: %test = icmp eq i32 %nexti, 0 -; CHECK: br i1 %test, label %loop, label %exit -; CHECK: exit: -; CHECK: ret void -entry: - br label %loop - -loop: - %i = phi i32 [ %count, %entry ], [ %nexti, %loop ] - %acc = phi <4 x float> [ %init, %entry ], [ %sel, %loop ] - %nexti = sub i32 %i, 1 - - %ptr = getelementptr <4 x float>, <4 x float> *%base, i32 %i - %val = load <4 x float> , <4 x float> *%ptr - %dval = bitcast <4 x float> %val to <2 x double> - %dacc = bitcast <4 x float> %acc to <2 x double> - %shuffle1 = shufflevector <2 x double> %dval, <2 x double> %dacc, - <2 x i32> <i32 0, i32 2> - %shuffle2 = shufflevector <2 x double> %dval, <2 x double> %dacc, - <2 x i32> <i32 1, i32 3> - %f1 = bitcast <2 x double> %shuffle1 to <4 x float> - %f2 = bitcast <2 x double> %shuffle2 to <4 x float> - %add = fadd <4 x float> %f1, %f2 - %call = call <4 x float> @ext(<4 x float> %add) - %cmp = fcmp ogt <4 x float> %call, - <float 1.0, float 2.0, float 3.0, float 4.0> - %sel = select <4 x i1> %cmp, <4 x float> %call, - <4 x float> <float 5.0, float 6.0, float 7.0, float 8.0> - store <4 x float> %sel, <4 x float> *%ptr - - %test = icmp eq i32 %nexti, 0 - br i1 %test, label %loop, label %exit - -exit: - ret void -} - -define void @f2(<4 x i32> %init, <4 x i8> *%base, i32 %count) { -; CHECK-LABEL: define void @f2(<4 x i32> %init, <4 x i8>* %base, i32 %count) { -; CHECK: entry: -; CHECK: %init.i0 = extractelement <4 x i32> %init, i32 0 -; CHECK: %init.i1 = extractelement <4 x i32> %init, i32 1 -; CHECK: %init.i2 = extractelement <4 x i32> %init, i32 2 -; CHECK: %init.i3 = extractelement <4 x i32> %init, i32 3 -; CHECK: br label %loop -; CHECK: loop: -; CHECK: %i = phi i32 [ %count, %entry ], [ %nexti, %loop ] -; CHECK: %acc.i0 = phi i32 [ %init.i0, %entry ], [ %sel.i0, %loop ] -; CHECK: %acc.i1 = phi i32 [ %init.i1, %entry ], [ %sel.i1, %loop ] -; CHECK: %acc.i2 = phi i32 [ %init.i2, %entry ], [ %sel.i2, %loop ] -; CHECK: %acc.i3 = phi i32 [ %init.i3, %entry ], [ %sel.i3, %loop ] -; CHECK: %nexti = sub i32 %i, 1 -; CHECK: %ptr = getelementptr <4 x i8>, <4 x i8>* %base, i32 %i -; CHECK: %ptr.i0 = bitcast <4 x i8>* %ptr to i8* -; CHECK: %val.i0 = load i8, i8* %ptr.i0, align 4 -; CHECK: %ptr.i1 = getelementptr i8, i8* %ptr.i0, i32 1 -; CHECK: %val.i1 = load i8, i8* %ptr.i1, align 1 -; CHECK: %ptr.i2 = getelementptr i8, i8* %ptr.i0, i32 2 -; CHECK: %val.i2 = load i8, i8* %ptr.i2, align 2 -; CHECK: %ptr.i3 = getelementptr i8, i8* %ptr.i0, i32 3 -; CHECK: %val.i3 = load i8, i8* %ptr.i3, align 1 -; CHECK: %ext.i0 = sext i8 %val.i0 to i32 -; CHECK: %ext.i1 = sext i8 %val.i1 to i32 -; CHECK: %ext.i2 = sext i8 %val.i2 to i32 -; CHECK: %ext.i3 = sext i8 %val.i3 to i32 -; CHECK: %add.i0 = add i32 %ext.i0, %acc.i0 -; CHECK: %add.i1 = add i32 %ext.i1, %acc.i1 -; CHECK: %add.i2 = add i32 %ext.i2, %acc.i2 -; CHECK: %add.i3 = add i32 %ext.i3, %acc.i3 -; CHECK: %cmp.i0 = icmp slt i32 %add.i0, -10 -; CHECK: %cmp.i1 = icmp slt i32 %add.i1, -11 -; CHECK: %cmp.i2 = icmp slt i32 %add.i2, -12 -; CHECK: %cmp.i3 = icmp slt i32 %add.i3, -13 -; CHECK: %sel.i0 = select i1 %cmp.i0, i32 %add.i0, i32 %i -; CHECK: %sel.i1 = select i1 %cmp.i1, i32 %add.i1, i32 %i -; CHECK: %sel.i2 = select i1 %cmp.i2, i32 %add.i2, i32 %i -; CHECK: %sel.i3 = select i1 %cmp.i3, i32 %add.i3, i32 %i -; CHECK: %trunc.i0 = trunc i32 %sel.i0 to i8 -; CHECK: %trunc.i1 = trunc i32 %sel.i1 to i8 -; CHECK: %trunc.i2 = trunc i32 %sel.i2 to i8 -; CHECK: %trunc.i3 = trunc i32 %sel.i3 to i8 -; CHECK: store i8 %trunc.i0, i8* %ptr.i0, align 4 -; CHECK: store i8 %trunc.i1, i8* %ptr.i1, align 1 -; CHECK: store i8 %trunc.i2, i8* %ptr.i2, align 2 -; CHECK: store i8 %trunc.i3, i8* %ptr.i3, align 1 -; CHECK: %test = icmp eq i32 %nexti, 0 -; CHECK: br i1 %test, label %loop, label %exit -; CHECK: exit: -; CHECK: ret void -entry: - br label %loop - -loop: - %i = phi i32 [ %count, %entry ], [ %nexti, %loop ] - %acc = phi <4 x i32> [ %init, %entry ], [ %sel, %loop ] - %nexti = sub i32 %i, 1 - - %ptr = getelementptr <4 x i8>, <4 x i8> *%base, i32 %i - %val = load <4 x i8> , <4 x i8> *%ptr - %ext = sext <4 x i8> %val to <4 x i32> - %add = add <4 x i32> %ext, %acc - %cmp = icmp slt <4 x i32> %add, <i32 -10, i32 -11, i32 -12, i32 -13> - %single = insertelement <4 x i32> undef, i32 %i, i32 0 - %limit = shufflevector <4 x i32> %single, <4 x i32> undef, - <4 x i32> zeroinitializer - %sel = select <4 x i1> %cmp, <4 x i32> %add, <4 x i32> %limit - %trunc = trunc <4 x i32> %sel to <4 x i8> - store <4 x i8> %trunc, <4 x i8> *%ptr - - %test = icmp eq i32 %nexti, 0 - br i1 %test, label %loop, label %exit - -exit: - ret void -} - -; Check that !tbaa information is preserved. -define void @f3(<4 x i32> *%src, <4 x i32> *%dst) { -; CHECK-LABEL: @f3( -; CHECK: %val.i0 = load i32, i32* %src.i0, align 16, !tbaa ![[TAG:[0-9]*]] -; CHECK: %val.i1 = load i32, i32* %src.i1, align 4, !tbaa ![[TAG]] -; CHECK: %val.i2 = load i32, i32* %src.i2, align 8, !tbaa ![[TAG]] -; CHECK: %val.i3 = load i32, i32* %src.i3, align 4, !tbaa ![[TAG]] -; CHECK: store i32 %add.i0, i32* %dst.i0, align 16, !tbaa ![[TAG:[0-9]*]] -; CHECK: store i32 %add.i1, i32* %dst.i1, align 4, !tbaa ![[TAG]] -; CHECK: store i32 %add.i2, i32* %dst.i2, align 8, !tbaa ![[TAG]] -; CHECK: store i32 %add.i3, i32* %dst.i3, align 4, !tbaa ![[TAG]] -; CHECK: ret void - %val = load <4 x i32> , <4 x i32> *%src, !tbaa !1 - %add = add <4 x i32> %val, %val - store <4 x i32> %add, <4 x i32> *%dst, !tbaa !2 - ret void -} - -; Check that !tbaa.struct information is preserved. -define void @f4(<4 x i32> *%src, <4 x i32> *%dst) { -; CHECK-LABEL: @f4( -; CHECK: %val.i0 = load i32, i32* %src.i0, align 16, !tbaa.struct ![[TAG:[0-9]*]] -; CHECK: %val.i1 = load i32, i32* %src.i1, align 4, !tbaa.struct ![[TAG]] -; CHECK: %val.i2 = load i32, i32* %src.i2, align 8, !tbaa.struct ![[TAG]] -; CHECK: %val.i3 = load i32, i32* %src.i3, align 4, !tbaa.struct ![[TAG]] -; CHECK: store i32 %add.i0, i32* %dst.i0, align 16, !tbaa.struct ![[TAG]] -; CHECK: store i32 %add.i1, i32* %dst.i1, align 4, !tbaa.struct ![[TAG]] -; CHECK: store i32 %add.i2, i32* %dst.i2, align 8, !tbaa.struct ![[TAG]] -; CHECK: store i32 %add.i3, i32* %dst.i3, align 4, !tbaa.struct ![[TAG]] -; CHECK: ret void - %val = load <4 x i32> , <4 x i32> *%src, !tbaa.struct !5 - %add = add <4 x i32> %val, %val - store <4 x i32> %add, <4 x i32> *%dst, !tbaa.struct !5 - ret void -} - -; Check that llvm.access.group information is preserved. -define void @f5(i32 %count, <4 x i32> *%src, <4 x i32> *%dst) { -; CHECK-LABEL: @f5( -; CHECK: %val.i0 = load i32, i32* %this_src.i0, align 16, !llvm.access.group ![[TAG:[0-9]*]] -; CHECK: %val.i1 = load i32, i32* %this_src.i1, align 4, !llvm.access.group ![[TAG]] -; CHECK: %val.i2 = load i32, i32* %this_src.i2, align 8, !llvm.access.group ![[TAG]] -; CHECK: %val.i3 = load i32, i32* %this_src.i3, align 4, !llvm.access.group ![[TAG]] -; CHECK: store i32 %add.i0, i32* %this_dst.i0, align 16, !llvm.access.group ![[TAG]] -; CHECK: store i32 %add.i1, i32* %this_dst.i1, align 4, !llvm.access.group ![[TAG]] -; CHECK: store i32 %add.i2, i32* %this_dst.i2, align 8, !llvm.access.group ![[TAG]] -; CHECK: store i32 %add.i3, i32* %this_dst.i3, align 4, !llvm.access.group ![[TAG]] -; CHECK: ret void -entry: - br label %loop - -loop: - %index = phi i32 [ 0, %entry ], [ %next_index, %loop ] - %this_src = getelementptr <4 x i32>, <4 x i32> *%src, i32 %index - %this_dst = getelementptr <4 x i32>, <4 x i32> *%dst, i32 %index - %val = load <4 x i32> , <4 x i32> *%this_src, !llvm.access.group !13 - %add = add <4 x i32> %val, %val - store <4 x i32> %add, <4 x i32> *%this_dst, !llvm.access.group !13 - %next_index = add i32 %index, -1 - %continue = icmp ne i32 %next_index, %count - br i1 %continue, label %loop, label %end, !llvm.loop !3 - -end: - ret void -} - -; Check that fpmath information is preserved. -define <4 x float> @f6(<4 x float> %x) { -; CHECK-LABEL: @f6( -; CHECK: %x.i0 = extractelement <4 x float> %x, i32 0 -; CHECK: %res.i0 = fadd float %x.i0, 1.0{{[e+0]*}}, !fpmath ![[TAG:[0-9]*]] -; CHECK: %x.i1 = extractelement <4 x float> %x, i32 1 -; CHECK: %res.i1 = fadd float %x.i1, 2.0{{[e+0]*}}, !fpmath ![[TAG]] -; CHECK: %x.i2 = extractelement <4 x float> %x, i32 2 -; CHECK: %res.i2 = fadd float %x.i2, 3.0{{[e+0]*}}, !fpmath ![[TAG]] -; CHECK: %x.i3 = extractelement <4 x float> %x, i32 3 -; CHECK: %res.i3 = fadd float %x.i3, 4.0{{[e+0]*}}, !fpmath ![[TAG]] -; CHECK: %res.upto0 = insertelement <4 x float> undef, float %res.i0, i32 0 -; CHECK: %res.upto1 = insertelement <4 x float> %res.upto0, float %res.i1, i32 1 -; CHECK: %res.upto2 = insertelement <4 x float> %res.upto1, float %res.i2, i32 2 -; CHECK: %res = insertelement <4 x float> %res.upto2, float %res.i3, i32 3 -; CHECK: ret <4 x float> %res - %res = fadd <4 x float> %x, <float 1.0, float 2.0, float 3.0, float 4.0>, - !fpmath !4 - ret <4 x float> %res -} - -; Check that random metadata isn't kept. -define void @f7(<4 x i32> *%src, <4 x i32> *%dst) { -; CHECK-LABEL: @f7( -; CHECK-NOT: !foo -; CHECK: ret void - %val = load <4 x i32> , <4 x i32> *%src, !foo !5 - %add = add <4 x i32> %val, %val - store <4 x i32> %add, <4 x i32> *%dst, !foo !5 - ret void -} - -; Test GEP with vectors. -define void @f8(<4 x float *> *%dest, <4 x float *> %ptr0, <4 x i32> %i0, - float *%other) { -; CHECK-LABEL: @f8( -; CHECK: %dest.i0 = bitcast <4 x float*>* %dest to float** -; CHECK: %dest.i1 = getelementptr float*, float** %dest.i0, i32 1 -; CHECK: %dest.i2 = getelementptr float*, float** %dest.i0, i32 2 -; CHECK: %dest.i3 = getelementptr float*, float** %dest.i0, i32 3 -; CHECK: %i0.i1 = extractelement <4 x i32> %i0, i32 1 -; CHECK: %i0.i3 = extractelement <4 x i32> %i0, i32 3 -; CHECK: %ptr0.i0 = extractelement <4 x float*> %ptr0, i32 0 -; CHECK: %val.i0 = getelementptr float, float* %ptr0.i0, i32 100 -; CHECK: %val.i1 = getelementptr float, float* %other, i32 %i0.i1 -; CHECK: %ptr0.i2 = extractelement <4 x float*> %ptr0, i32 2 -; CHECK: %val.i2 = getelementptr float, float* %ptr0.i2, i32 100 -; CHECK: %ptr0.i3 = extractelement <4 x float*> %ptr0, i32 3 -; CHECK: %val.i3 = getelementptr float, float* %ptr0.i3, i32 %i0.i3 -; CHECK: store float* %val.i0, float** %dest.i0, align 32 -; CHECK: store float* %val.i1, float** %dest.i1, align 8 -; CHECK: store float* %val.i2, float** %dest.i2, align 16 -; CHECK: store float* %val.i3, float** %dest.i3, align 8 -; CHECK: ret void - %i1 = insertelement <4 x i32> %i0, i32 100, i32 0 - %i2 = insertelement <4 x i32> %i1, i32 100, i32 2 - %ptr1 = insertelement <4 x float *> %ptr0, float *%other, i32 1 - %val = getelementptr float, <4 x float *> %ptr1, <4 x i32> %i2 - store <4 x float *> %val, <4 x float *> *%dest - ret void -} - -; Test the handling of unaligned loads. -define void @f9(<4 x float> *%dest, <4 x float> *%src) { -; CHECK: @f9( -; CHECK: %dest.i0 = bitcast <4 x float>* %dest to float* -; CHECK: %dest.i1 = getelementptr float, float* %dest.i0, i32 1 -; CHECK: %dest.i2 = getelementptr float, float* %dest.i0, i32 2 -; CHECK: %dest.i3 = getelementptr float, float* %dest.i0, i32 3 -; CHECK: %src.i0 = bitcast <4 x float>* %src to float* -; CHECK: %val.i0 = load float, float* %src.i0, align 4 -; CHECK: %src.i1 = getelementptr float, float* %src.i0, i32 1 -; CHECK: %val.i1 = load float, float* %src.i1, align 4 -; CHECK: %src.i2 = getelementptr float, float* %src.i0, i32 2 -; CHECK: %val.i2 = load float, float* %src.i2, align 4 -; CHECK: %src.i3 = getelementptr float, float* %src.i0, i32 3 -; CHECK: %val.i3 = load float, float* %src.i3, align 4 -; CHECK: store float %val.i0, float* %dest.i0, align 8 -; CHECK: store float %val.i1, float* %dest.i1, align 4 -; CHECK: store float %val.i2, float* %dest.i2, align 8 -; CHECK: store float %val.i3, float* %dest.i3, align 4 -; CHECK: ret void - %val = load <4 x float> , <4 x float> *%src, align 4 - store <4 x float> %val, <4 x float> *%dest, align 8 - ret void -} - -; ...and again with subelement alignment. -define void @f10(<4 x float> *%dest, <4 x float> *%src) { -; CHECK: @f10( -; CHECK: %dest.i0 = bitcast <4 x float>* %dest to float* -; CHECK: %dest.i1 = getelementptr float, float* %dest.i0, i32 1 -; CHECK: %dest.i2 = getelementptr float, float* %dest.i0, i32 2 -; CHECK: %dest.i3 = getelementptr float, float* %dest.i0, i32 3 -; CHECK: %src.i0 = bitcast <4 x float>* %src to float* -; CHECK: %val.i0 = load float, float* %src.i0, align 1 -; CHECK: %src.i1 = getelementptr float, float* %src.i0, i32 1 -; CHECK: %val.i1 = load float, float* %src.i1, align 1 -; CHECK: %src.i2 = getelementptr float, float* %src.i0, i32 2 -; CHECK: %val.i2 = load float, float* %src.i2, align 1 -; CHECK: %src.i3 = getelementptr float, float* %src.i0, i32 3 -; CHECK: %val.i3 = load float, float* %src.i3, align 1 -; CHECK: store float %val.i0, float* %dest.i0, align 2 -; CHECK: store float %val.i1, float* %dest.i1, align 2 -; CHECK: store float %val.i2, float* %dest.i2, align 2 -; CHECK: store float %val.i3, float* %dest.i3, align 2 -; CHECK: ret void - %val = load <4 x float> , <4 x float> *%src, align 1 - store <4 x float> %val, <4 x float> *%dest, align 2 - ret void -} - -; Test that sub-byte loads aren't scalarized. -define void @f11(<32 x i1> *%dest, <32 x i1> *%src0) { -; CHECK: @f11( -; CHECK: %val0 = load <32 x i1>, <32 x i1>* %src0 -; CHECK: %val1 = load <32 x i1>, <32 x i1>* %src1 -; CHECK: store <32 x i1> %and, <32 x i1>* %dest -; CHECK: ret void - %src1 = getelementptr <32 x i1>, <32 x i1> *%src0, i32 1 - %val0 = load <32 x i1> , <32 x i1> *%src0 - %val1 = load <32 x i1> , <32 x i1> *%src1 - %and = and <32 x i1> %val0, %val1 - store <32 x i1> %and, <32 x i1> *%dest - ret void -} - -; Test that variable inserts aren't scalarized. -define void @f12(<4 x i32> *%dest, <4 x i32> *%src, i32 %index) { -; CHECK: @f12( -; CHECK: %val1 = insertelement <4 x i32> %val0, i32 1, i32 %index -; CHECK-DAG: %val1.i0 = extractelement <4 x i32> %val1, i32 0 -; CHECK-DAG: %val1.i1 = extractelement <4 x i32> %val1, i32 1 -; CHECK-DAG: %val1.i2 = extractelement <4 x i32> %val1, i32 2 -; CHECK-DAG: %val1.i3 = extractelement <4 x i32> %val1, i32 3 -; CHECK-DAG: %val2.i0 = shl i32 1, %val1.i0 -; CHECK-DAG: %val2.i1 = shl i32 2, %val1.i1 -; CHECK-DAG: %val2.i2 = shl i32 3, %val1.i2 -; CHECK-DAG: %val2.i3 = shl i32 4, %val1.i3 -; CHECK: ret void - %val0 = load <4 x i32> , <4 x i32> *%src - %val1 = insertelement <4 x i32> %val0, i32 1, i32 %index - %val2 = shl <4 x i32> <i32 1, i32 2, i32 3, i32 4>, %val1 - store <4 x i32> %val2, <4 x i32> *%dest - ret void -} - -; Test vector GEPs with more than one index. -define void @f13(<4 x float *> *%dest, <4 x [4 x float] *> %ptr, <4 x i32> %i, - float *%other) { -; CHECK-LABEL: @f13( -; CHECK: %dest.i0 = bitcast <4 x float*>* %dest to float** -; CHECK: %dest.i1 = getelementptr float*, float** %dest.i0, i32 1 -; CHECK: %dest.i2 = getelementptr float*, float** %dest.i0, i32 2 -; CHECK: %dest.i3 = getelementptr float*, float** %dest.i0, i32 3 -; CHECK: %i.i0 = extractelement <4 x i32> %i, i32 0 -; CHECK: %ptr.i0 = extractelement <4 x [4 x float]*> %ptr, i32 0 -; CHECK: %val.i0 = getelementptr inbounds [4 x float], [4 x float]* %ptr.i0, i32 0, i32 %i.i0 -; CHECK: %i.i1 = extractelement <4 x i32> %i, i32 1 -; CHECK: %ptr.i1 = extractelement <4 x [4 x float]*> %ptr, i32 1 -; CHECK: %val.i1 = getelementptr inbounds [4 x float], [4 x float]* %ptr.i1, i32 1, i32 %i.i1 -; CHECK: %i.i2 = extractelement <4 x i32> %i, i32 2 -; CHECK: %ptr.i2 = extractelement <4 x [4 x float]*> %ptr, i32 2 -; CHECK: %val.i2 = getelementptr inbounds [4 x float], [4 x float]* %ptr.i2, i32 2, i32 %i.i2 -; CHECK: %i.i3 = extractelement <4 x i32> %i, i32 3 -; CHECK: %ptr.i3 = extractelement <4 x [4 x float]*> %ptr, i32 3 -; CHECK: %val.i3 = getelementptr inbounds [4 x float], [4 x float]* %ptr.i3, i32 3, i32 %i.i3 -; CHECK: store float* %val.i0, float** %dest.i0, align 32 -; CHECK: store float* %val.i1, float** %dest.i1, align 8 -; CHECK: store float* %val.i2, float** %dest.i2, align 16 -; CHECK: store float* %val.i3, float** %dest.i3, align 8 -; CHECK: ret void - %val = getelementptr inbounds [4 x float], <4 x [4 x float] *> %ptr, - <4 x i32> <i32 0, i32 1, i32 2, i32 3>, - <4 x i32> %i - store <4 x float *> %val, <4 x float *> *%dest - ret void -} - -; Test combinations of vector and non-vector PHIs. -define <4 x float> @f14(<4 x float> %acc, i32 %count) { -; CHECK-LABEL: @f14( -; CHECK: %this_acc.i0 = phi float [ %acc.i0, %entry ], [ %next_acc.i0, %loop ] -; CHECK: %this_acc.i1 = phi float [ %acc.i1, %entry ], [ %next_acc.i1, %loop ] -; CHECK: %this_acc.i2 = phi float [ %acc.i2, %entry ], [ %next_acc.i2, %loop ] -; CHECK: %this_acc.i3 = phi float [ %acc.i3, %entry ], [ %next_acc.i3, %loop ] -; CHECK: %this_count = phi i32 [ %count, %entry ], [ %next_count, %loop ] -; CHECK: %this_acc.upto0 = insertelement <4 x float> undef, float %this_acc.i0, i32 0 -; CHECK: %this_acc.upto1 = insertelement <4 x float> %this_acc.upto0, float %this_acc.i1, i32 1 -; CHECK: %this_acc.upto2 = insertelement <4 x float> %this_acc.upto1, float %this_acc.i2, i32 2 -; CHECK: %this_acc = insertelement <4 x float> %this_acc.upto2, float %this_acc.i3, i32 3 -; CHECK: ret <4 x float> %next_acc -entry: - br label %loop - -loop: - %this_acc = phi <4 x float> [ %acc, %entry ], [ %next_acc, %loop ] - %this_count = phi i32 [ %count, %entry ], [ %next_count, %loop ] - %foo = call <4 x float> @ext(<4 x float> %this_acc) - %next_acc = fadd <4 x float> %this_acc, %foo - %next_count = sub i32 %this_count, 1 - %cmp = icmp eq i32 %next_count, 0 - br i1 %cmp, label %loop, label %exit - -exit: - ret <4 x float> %next_acc -} - -!0 = !{ !"root" } -!1 = !{ !"set1", !0 } -!2 = !{ !"set2", !0 } -!3 = !{ !3, !{!"llvm.loop.parallel_accesses", !13} } -!4 = !{ float 4.0 } -!5 = !{ i64 0, i64 8, null } -!13 = distinct !{} diff --git a/llvm/test/Transforms/Scalarizer/cache-bug.ll b/llvm/test/Transforms/Scalarizer/cache-bug.ll deleted file mode 100644 index cfb4140e41c..00000000000 --- a/llvm/test/Transforms/Scalarizer/cache-bug.ll +++ /dev/null @@ -1,31 +0,0 @@ -; RUN: opt -scalarizer -S < %s | FileCheck %s -; RUN: opt -passes='function(scalarizer)' -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" - - -; Check that vector element 1 is scalarized correctly from a chain of -; insertelement instructions -define void @func(i32 %x) { -; CHECK-LABEL: @func( -; CHECK-NOT: phi i32 [ %x, %entry ], [ %inc.pos.y, %loop ] -; CHECK: phi i32 [ %inc, %entry ], [ %inc.pos.y, %loop ] -; CHECK: ret void -entry: - %vecinit = insertelement <2 x i32> <i32 0, i32 0>, i32 %x, i32 1 - %inc = add i32 %x, 1 - %0 = insertelement <2 x i32> %vecinit, i32 %inc, i32 1 - br label %loop - -loop: - %pos = phi <2 x i32> [ %0, %entry ], [ %new.pos.y, %loop ] - %i = phi i32 [ 0, %entry ], [ %new.i, %loop ] - %pos.y = extractelement <2 x i32> %pos, i32 1 - %inc.pos.y = add i32 %pos.y, 1 - %new.pos.y = insertelement <2 x i32> %pos, i32 %inc.pos.y, i32 1 - %new.i = add i32 %i, 1 - %cmp2 = icmp slt i32 %new.i, 1 - br i1 %cmp2, label %loop, label %exit - -exit: - ret void -} diff --git a/llvm/test/Transforms/Scalarizer/crash-bug.ll b/llvm/test/Transforms/Scalarizer/crash-bug.ll deleted file mode 100644 index d0d01956497..00000000000 --- a/llvm/test/Transforms/Scalarizer/crash-bug.ll +++ /dev/null @@ -1,25 +0,0 @@ -; RUN: opt %s -scalarizer -S -o - | FileCheck %s -; RUN: opt %s -passes='function(scalarizer)' -S -o - | FileCheck %s - -; Don't crash - -define void @foo() { - br label %bb1 - -bb2: ; preds = %bb1 - %bb2_vec = shufflevector <2 x i16> <i16 0, i16 10000>, - <2 x i16> %bb1_vec, - <2 x i32> <i32 0, i32 3> - br label %bb1 - -bb1: ; preds = %bb2, %0 - %bb1_vec = phi <2 x i16> [ <i16 100, i16 200>, %0 ], [ %bb2_vec, %bb2 ] -;CHECK: bb1: -;CHECK: %bb1_vec.i0 = phi i16 [ 100, %0 ], [ 0, %bb2 ] -;CHECK: %bb2_vec.i1 = phi i16 [ 200, %0 ], [ %bb2_vec.i1, %bb2 ] - br i1 undef, label %bb3, label %bb2 - -bb3: - ret void -} - diff --git a/llvm/test/Transforms/Scalarizer/dbginfo.ll b/llvm/test/Transforms/Scalarizer/dbginfo.ll deleted file mode 100644 index 37452ec70a9..00000000000 --- a/llvm/test/Transforms/Scalarizer/dbginfo.ll +++ /dev/null @@ -1,86 +0,0 @@ -; RUN: opt %s -scalarizer -scalarize-load-store -S | FileCheck %s -; RUN: opt %s -passes='function(scalarizer)' -scalarize-load-store -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" - -; Function Attrs: nounwind uwtable -define void @f1(<4 x i32>* nocapture %a, <4 x i32>* nocapture readonly %b, <4 x i32>* nocapture readonly %c) #0 !dbg !4 { -; CHECK: @f1( -; CHECK: %a.i0 = bitcast <4 x i32>* %a to i32* -; CHECK: %a.i1 = getelementptr i32, i32* %a.i0, i32 1 -; CHECK: %a.i2 = getelementptr i32, i32* %a.i0, i32 2 -; CHECK: %a.i3 = getelementptr i32, i32* %a.i0, i32 3 -; CHECK: %c.i0 = bitcast <4 x i32>* %c to i32* -; CHECK: %c.i1 = getelementptr i32, i32* %c.i0, i32 1 -; CHECK: %c.i2 = getelementptr i32, i32* %c.i0, i32 2 -; CHECK: %c.i3 = getelementptr i32, i32* %c.i0, i32 3 -; CHECK: %b.i0 = bitcast <4 x i32>* %b to i32* -; CHECK: %b.i1 = getelementptr i32, i32* %b.i0, i32 1 -; CHECK: %b.i2 = getelementptr i32, i32* %b.i0, i32 2 -; CHECK: %b.i3 = getelementptr i32, i32* %b.i0, i32 3 -; CHECK: tail call void @llvm.dbg.value(metadata <4 x i32>* %a, metadata !{{[0-9]+}}, metadata {{.*}}), !dbg !{{[0-9]+}} -; CHECK: tail call void @llvm.dbg.value(metadata <4 x i32>* %b, metadata !{{[0-9]+}}, metadata {{.*}}), !dbg !{{[0-9]+}} -; CHECK: tail call void @llvm.dbg.value(metadata <4 x i32>* %c, metadata !{{[0-9]+}}, metadata {{.*}}), !dbg !{{[0-9]+}} -; CHECK: %bval.i0 = load i32, i32* %b.i0, align 16, !dbg ![[TAG1:[0-9]+]], !tbaa ![[TAG2:[0-9]+]] -; CHECK: %bval.i1 = load i32, i32* %b.i1, align 4, !dbg ![[TAG1]], !tbaa ![[TAG2]] -; CHECK: %bval.i2 = load i32, i32* %b.i2, align 8, !dbg ![[TAG1]], !tbaa ![[TAG2]] -; CHECK: %bval.i3 = load i32, i32* %b.i3, align 4, !dbg ![[TAG1]], !tbaa ![[TAG2]] -; CHECK: %cval.i0 = load i32, i32* %c.i0, align 16, !dbg ![[TAG1]], !tbaa ![[TAG2]] -; CHECK: %cval.i1 = load i32, i32* %c.i1, align 4, !dbg ![[TAG1]], !tbaa ![[TAG2]] -; CHECK: %cval.i2 = load i32, i32* %c.i2, align 8, !dbg ![[TAG1]], !tbaa ![[TAG2]] -; CHECK: %cval.i3 = load i32, i32* %c.i3, align 4, !dbg ![[TAG1]], !tbaa ![[TAG2]] -; CHECK: %add.i0 = add i32 %bval.i0, %cval.i0, !dbg ![[TAG1]] -; CHECK: %add.i1 = add i32 %bval.i1, %cval.i1, !dbg ![[TAG1]] -; CHECK: %add.i2 = add i32 %bval.i2, %cval.i2, !dbg ![[TAG1]] -; CHECK: %add.i3 = add i32 %bval.i3, %cval.i3, !dbg ![[TAG1]] -; CHECK: store i32 %add.i0, i32* %a.i0, align 16, !dbg ![[TAG1]], !tbaa ![[TAG2]] -; CHECK: store i32 %add.i1, i32* %a.i1, align 4, !dbg ![[TAG1]], !tbaa ![[TAG2]] -; CHECK: store i32 %add.i2, i32* %a.i2, align 8, !dbg ![[TAG1]], !tbaa ![[TAG2]] -; CHECK: store i32 %add.i3, i32* %a.i3, align 4, !dbg ![[TAG1]], !tbaa ![[TAG2]] -; CHECK: ret void -entry: - tail call void @llvm.dbg.value(metadata <4 x i32>* %a, metadata !15, metadata !DIExpression()), !dbg !20 - tail call void @llvm.dbg.value(metadata <4 x i32>* %b, metadata !16, metadata !DIExpression()), !dbg !20 - tail call void @llvm.dbg.value(metadata <4 x i32>* %c, metadata !17, metadata !DIExpression()), !dbg !20 - %bval = load <4 x i32>, <4 x i32>* %b, align 16, !dbg !21, !tbaa !22 - %cval = load <4 x i32>, <4 x i32>* %c, align 16, !dbg !21, !tbaa !22 - %add = add <4 x i32> %bval, %cval, !dbg !21 - store <4 x i32> %add, <4 x i32>* %a, align 16, !dbg !21, !tbaa !22 - ret void, !dbg !25 -} - -; Function Attrs: nounwind readnone -declare void @llvm.dbg.value(metadata, metadata, metadata) #1 - -attributes #0 = { nounwind uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" } -attributes #1 = { nounwind readnone } - -!llvm.dbg.cu = !{!0} -!llvm.module.flags = !{!18, !26} -!llvm.ident = !{!19} - -!0 = distinct !DICompileUnit(language: DW_LANG_C99, producer: "clang version 3.4 (trunk 194134) (llvm/trunk 194126)", isOptimized: true, emissionKind: FullDebug, file: !1, enums: !2, retainedTypes: !2, globals: !2, imports: !2) -!1 = !DIFile(filename: "/tmp/add.c", directory: "/home/richards/llvm/build") -!2 = !{} -!4 = distinct !DISubprogram(name: "f1", line: 3, isLocal: false, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: true, unit: !0, scopeLine: 4, file: !1, scope: !5, type: !6, retainedNodes: !14) -!5 = !DIFile(filename: "/tmp/add.c", directory: "/home/richards/llvm/build") -!6 = !DISubroutineType(types: !7) -!7 = !{null, !8, !8, !8} -!8 = !DIDerivedType(tag: DW_TAG_pointer_type, size: 64, align: 64, baseType: !9) -!9 = !DIDerivedType(tag: DW_TAG_typedef, name: "V4SI", line: 1, file: !1, baseType: !10) -!10 = !DICompositeType(tag: DW_TAG_array_type, size: 128, align: 128, flags: DIFlagVector, baseType: !11, elements: !12) -!11 = !DIBasicType(tag: DW_TAG_base_type, name: "int", size: 32, align: 32, encoding: DW_ATE_signed) -!12 = !{!13} -!13 = !DISubrange(count: 4) -!14 = !{!15, !16, !17} -!15 = !DILocalVariable(name: "a", line: 3, arg: 1, scope: !4, file: !5, type: !8) -!16 = !DILocalVariable(name: "b", line: 3, arg: 2, scope: !4, file: !5, type: !8) -!17 = !DILocalVariable(name: "c", line: 3, arg: 3, scope: !4, file: !5, type: !8) -!18 = !{i32 2, !"Dwarf Version", i32 4} -!19 = !{!"clang version 3.4 (trunk 194134) (llvm/trunk 194126)"} -!20 = !DILocation(line: 3, scope: !4) -!21 = !DILocation(line: 5, scope: !4) -!22 = !{!23, !23, i64 0} -!23 = !{!"omnipotent char", !24, i64 0} -!24 = !{!"Simple C/C++ TBAA"} -!25 = !DILocation(line: 6, scope: !4) -!26 = !{i32 1, !"Debug Info Version", i32 3} diff --git a/llvm/test/Transforms/Scalarizer/dbgloc-bug.ll b/llvm/test/Transforms/Scalarizer/dbgloc-bug.ll deleted file mode 100644 index 7c627ee78a3..00000000000 --- a/llvm/test/Transforms/Scalarizer/dbgloc-bug.ll +++ /dev/null @@ -1,44 +0,0 @@ -; RUN: opt -S -march=x86 -scalarizer %s | FileCheck %s -; RUN: opt -S -march=x86 -passes='function(scalarizer)' %s | FileCheck %s - -; Reproducer for pr27938 -; https://llvm.org/bugs/show_bug.cgi?id=27938 - -define i16 @f1() !dbg !5 { - ret i16 undef, !dbg !9 -} - -define void @f2() !dbg !10 { -bb1: - %_tmp7 = tail call i16 @f1(), !dbg !13 -; CHECK: call i16 @f1(), !dbg !13 - %broadcast.splatinsert5 = insertelement <4 x i16> undef, i16 %_tmp7, i32 0 - %broadcast.splat6 = shufflevector <4 x i16> %broadcast.splatinsert5, <4 x i16> undef, <4 x i32> zeroinitializer - br label %vector.body - -vector.body: - br i1 undef, label %middle.block, label %vector.body - -middle.block: - ret void, !dbg !15 -} - -!llvm.dbg.cu = !{!0} -!llvm.module.flags = !{!3, !4} - -!0 = distinct !DICompileUnit(language: DW_LANG_C, file: !1, isOptimized: true, runtimeVersion: 0, emissionKind: LineTablesOnly, enums: !2, retainedTypes: !2) -!1 = !DIFile(filename: "dbgloc-bug.c", directory: ".") -!2 = !{} -!3 = !{i32 2, !"Dwarf Version", i32 4} -!4 = !{i32 2, !"Debug Info Version", i32 3} -!5 = distinct !DISubprogram(name: "f1", scope: !1, file: !1, line: 9, type: !6, isLocal: false, isDefinition: true, scopeLine: 10, isOptimized: true, unit: !0, retainedNodes: !2) -!6 = !DISubroutineType(types: !7) -!7 = !{!8} -!8 = !DIBasicType(name: "short", size: 16, align: 16, encoding: DW_ATE_signed) -!9 = !DILocation(line: 11, column: 5, scope: !5) -!10 = distinct !DISubprogram(name: "f2", scope: !1, file: !1, line: 14, type: !11, isLocal: false, isDefinition: true, scopeLine: 15, isOptimized: true, unit: !0, retainedNodes: !2) -!11 = !DISubroutineType(types: !12) -!12 = !{null} -!13 = !DILocation(line: 24, column: 9, scope: !14) -!14 = !DILexicalBlock(scope: !10, file: !1, line: 17, column: 5) -!15 = !DILocation(line: 28, column: 1, scope: !10) diff --git a/llvm/test/Transforms/Scalarizer/intrinsics.ll b/llvm/test/Transforms/Scalarizer/intrinsics.ll deleted file mode 100644 index 7cd324122d9..00000000000 --- a/llvm/test/Transforms/Scalarizer/intrinsics.ll +++ /dev/null @@ -1,110 +0,0 @@ -; RUN: opt -S -scalarizer %s | FileCheck %s -; RUN: opt -S -passes='function(scalarizer)' %s | FileCheck %s - -; Unary fp -declare <2 x float> @llvm.sqrt.v2f32(<2 x float>) - -; Binary fp -declare <2 x float> @llvm.minnum.v2f32(<2 x float>, <2 x float>) -declare <2 x float> @llvm.minimum.v2f32(<2 x float>, <2 x float>) -declare <2 x float> @llvm.maximum.v2f32(<2 x float>, <2 x float>) - -; Ternary fp -declare <2 x float> @llvm.fma.v2f32(<2 x float>, <2 x float>, <2 x float>) - -; Binary int -declare <2 x i32> @llvm.bswap.v2i32(<2 x i32>) - -; Unary int plus constant scalar operand -declare <2 x i32> @llvm.ctlz.v2i32(<2 x i32>, i1) - -; Unary fp plus any scalar operand -declare <2 x float> @llvm.powi.v2f32(<2 x float>, i32) - -; CHECK-LABEL: @scalarize_sqrt_v2f32( -; CHECK: %sqrt.i0 = call float @llvm.sqrt.f32(float %x.i0) -; CHECK: %sqrt.i1 = call float @llvm.sqrt.f32(float %x.i1) -; CHECK: %sqrt.upto0 = insertelement <2 x float> undef, float %sqrt.i0, i32 0 -; CHECK: %sqrt = insertelement <2 x float> %sqrt.upto0, float %sqrt.i1, i32 1 -; CHECK: ret <2 x float> %sqrt -define <2 x float> @scalarize_sqrt_v2f32(<2 x float> %x) #0 { - %sqrt = call <2 x float> @llvm.sqrt.v2f32(<2 x float> %x) - ret <2 x float> %sqrt -} - -; CHECK-LABEL: @scalarize_minnum_v2f32( -; CHECK: %minnum.i0 = call float @llvm.minnum.f32(float %x.i0, float %y.i0) -; CHECK: %minnum.i1 = call float @llvm.minnum.f32(float %x.i1, float %y.i1) -; CHECK: %minnum.upto0 = insertelement <2 x float> undef, float %minnum.i0, i32 0 -; CHECK: %minnum = insertelement <2 x float> %minnum.upto0, float %minnum.i1, i32 1 -; CHECK: ret <2 x float> %minnum -define <2 x float> @scalarize_minnum_v2f32(<2 x float> %x, <2 x float> %y) #0 { - %minnum = call <2 x float> @llvm.minnum.v2f32(<2 x float> %x, <2 x float> %y) - ret <2 x float> %minnum -} - -; CHECK-LABEL: @scalarize_minimum_v2f32( -; CHECK: %minimum.i0 = call float @llvm.minimum.f32(float %x.i0, float %y.i0) -; CHECK: %minimum.i1 = call float @llvm.minimum.f32(float %x.i1, float %y.i1) -; CHECK: %minimum.upto0 = insertelement <2 x float> undef, float %minimum.i0, i32 0 -; CHECK: %minimum = insertelement <2 x float> %minimum.upto0, float %minimum.i1, i32 1 -; CHECK: ret <2 x float> %minimum -define <2 x float> @scalarize_minimum_v2f32(<2 x float> %x, <2 x float> %y) #0 { - %minimum = call <2 x float> @llvm.minimum.v2f32(<2 x float> %x, <2 x float> %y) - ret <2 x float> %minimum -} - -; CHECK-LABEL: @scalarize_maximum_v2f32( -; CHECK: %maximum.i0 = call float @llvm.maximum.f32(float %x.i0, float %y.i0) -; CHECK: %maximum.i1 = call float @llvm.maximum.f32(float %x.i1, float %y.i1) -; CHECK: %maximum.upto0 = insertelement <2 x float> undef, float %maximum.i0, i32 0 -; CHECK: %maximum = insertelement <2 x float> %maximum.upto0, float %maximum.i1, i32 1 -; CHECK: ret <2 x float> %maximum -define <2 x float> @scalarize_maximum_v2f32(<2 x float> %x, <2 x float> %y) #0 { - %maximum = call <2 x float> @llvm.maximum.v2f32(<2 x float> %x, <2 x float> %y) - ret <2 x float> %maximum -} - -; CHECK-LABEL: @scalarize_fma_v2f32( -; CHECK: %fma.i0 = call float @llvm.fma.f32(float %x.i0, float %y.i0, float %z.i0) -; CHECK: %fma.i1 = call float @llvm.fma.f32(float %x.i1, float %y.i1, float %z.i1) -; CHECK: %fma.upto0 = insertelement <2 x float> undef, float %fma.i0, i32 0 -; CHECK: %fma = insertelement <2 x float> %fma.upto0, float %fma.i1, i32 1 -; CHECK: ret <2 x float> %fma -define <2 x float> @scalarize_fma_v2f32(<2 x float> %x, <2 x float> %y, <2 x float> %z) #0 { - %fma = call <2 x float> @llvm.fma.v2f32(<2 x float> %x, <2 x float> %y, <2 x float> %z) - ret <2 x float> %fma -} - -; CHECK-LABEL: @scalarize_bswap_v2i32( -; CHECK: %bswap.i0 = call i32 @llvm.bswap.i32(i32 %x.i0) -; CHECK: %bswap.i1 = call i32 @llvm.bswap.i32(i32 %x.i1) -; CHECK: %bswap.upto0 = insertelement <2 x i32> undef, i32 %bswap.i0, i32 0 -; CHECK: %bswap = insertelement <2 x i32> %bswap.upto0, i32 %bswap.i1, i32 1 -; CHECK: ret <2 x i32> %bswap -define <2 x i32> @scalarize_bswap_v2i32(<2 x i32> %x) #0 { - %bswap = call <2 x i32> @llvm.bswap.v2i32(<2 x i32> %x) - ret <2 x i32> %bswap -} - -; CHECK-LABEL: @scalarize_ctlz_v2i32( -; CHECK: %ctlz.i0 = call i32 @llvm.ctlz.i32(i32 %x.i0, i1 true) -; CHECK: %ctlz.i1 = call i32 @llvm.ctlz.i32(i32 %x.i1, i1 true) -; CHECK: %ctlz.upto0 = insertelement <2 x i32> undef, i32 %ctlz.i0, i32 0 -; CHECK: %ctlz = insertelement <2 x i32> %ctlz.upto0, i32 %ctlz.i1, i32 1 -; CHECK: ret <2 x i32> %ctlz -define <2 x i32> @scalarize_ctlz_v2i32(<2 x i32> %x) #0 { - %ctlz = call <2 x i32> @llvm.ctlz.v2i32(<2 x i32> %x, i1 true) - ret <2 x i32> %ctlz -} - -; CHECK-LABEL: @scalarize_powi_v2f32( -; CHECK: %powi.i0 = call float @llvm.powi.f32(float %x.i0, i32 %y) -; CHECK: %powi.i1 = call float @llvm.powi.f32(float %x.i1, i32 %y) -; CHECK: %powi.upto0 = insertelement <2 x float> undef, float %powi.i0, i32 0 -; CHECK: %powi = insertelement <2 x float> %powi.upto0, float %powi.i1, i32 1 -; CHECK: ret <2 x float> %powi -define <2 x float> @scalarize_powi_v2f32(<2 x float> %x, i32 %y) #0 { - %powi = call <2 x float> @llvm.powi.v2f32(<2 x float> %x, i32 %y) - ret <2 x float> %powi -} diff --git a/llvm/test/Transforms/Scalarizer/order-bug.ll b/llvm/test/Transforms/Scalarizer/order-bug.ll deleted file mode 100644 index 1265bb07bf1..00000000000 --- a/llvm/test/Transforms/Scalarizer/order-bug.ll +++ /dev/null @@ -1,24 +0,0 @@ -; RUN: opt %s -scalarizer -S -o - | FileCheck %s -; RUN: opt %s -passes='function(scalarizer)' -S -o - | FileCheck %s - -; This input caused the scalarizer to replace & erase gathered results when -; future gathered results depended on them being alive - -define dllexport spir_func <4 x i32> @main(float %a) { -entry: - %i = insertelement <4 x float> undef, float %a, i32 0 - br label %z - -y: -; CHECK: %f.upto0 = insertelement <4 x i32> undef, i32 %b.i0, i32 0 -; CHECK: %f.upto1 = insertelement <4 x i32> %f.upto0, i32 %b.i0, i32 1 -; CHECK: %f.upto2 = insertelement <4 x i32> %f.upto1, i32 %b.i0, i32 2 -; CHECK: %f = insertelement <4 x i32> %f.upto2, i32 %b.i0, i32 3 - %f = shufflevector <4 x i32> %b, <4 x i32> undef, <4 x i32> zeroinitializer - ret <4 x i32> %f - -z: -; CHECK: %b.i0 = bitcast float %a to i32 - %b = bitcast <4 x float> %i to <4 x i32> - br label %y -} diff --git a/llvm/test/Transforms/Scalarizer/phi-bug.ll b/llvm/test/Transforms/Scalarizer/phi-bug.ll deleted file mode 100644 index 3fd08130c53..00000000000 --- a/llvm/test/Transforms/Scalarizer/phi-bug.ll +++ /dev/null @@ -1,25 +0,0 @@ -; RUN: opt %s -scalarizer -verify -S -o - | FileCheck %s -; RUN: opt %s -passes='function(scalarizer,verify)' -S -o - | FileCheck %s - -define void @f3() local_unnamed_addr { -bb1: - br label %bb2 - -bb3: -; CHECK-LABEL: bb3: -; CHECK-NEXT: br label %bb4 - %h.10.0.vec.insert = shufflevector <1 x i16> %h.10.1, <1 x i16> undef, <1 x i32> <i32 0> - br label %bb4 - -bb2: -; CHECK-LABEL: bb2: -; CHECK: phi i16 - %h.10.1 = phi <1 x i16> [ undef, %bb1 ] - br label %bb3 - -bb4: -; CHECK-LABEL: bb4: -; CHECK: phi i16 - %h.10.2 = phi <1 x i16> [ %h.10.0.vec.insert, %bb3 ] - ret void -} diff --git a/llvm/test/Transforms/Scalarizer/store-bug.ll b/llvm/test/Transforms/Scalarizer/store-bug.ll deleted file mode 100644 index 8f4d30db1a8..00000000000 --- a/llvm/test/Transforms/Scalarizer/store-bug.ll +++ /dev/null @@ -1,26 +0,0 @@ -; RUN: opt -scalarizer -scalarize-load-store -S < %s | FileCheck %s -; RUN: opt -passes='function(scalarizer)' -scalarize-load-store -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" - -; This input caused the scalarizer not to clear cached results -; properly. -; -; Any regressions should trigger an assert in the scalarizer. - -define void @func(<4 x float> %val, <4 x float> *%ptr) { - store <4 x float> %val, <4 x float> *%ptr - ret void -; CHECK: store float %val.i0, float* %ptr.i0, align 16 -; CHECK: store float %val.i1, float* %ptr.i1, align 4 -; CHECK: store float %val.i2, float* %ptr.i2, align 8 -; CHECK: store float %val.i3, float* %ptr.i3, align 4 -} - -define void @func.copy(<4 x float> %val, <4 x float> *%ptr) { - store <4 x float> %val, <4 x float> *%ptr - ret void -; CHECK: store float %val.i0, float* %ptr.i0, align 16 -; CHECK: store float %val.i1, float* %ptr.i1, align 4 -; CHECK: store float %val.i2, float* %ptr.i2, align 8 -; CHECK: store float %val.i3, float* %ptr.i3, align 4 -} diff --git a/llvm/test/Transforms/Scalarizer/vector-gep.ll b/llvm/test/Transforms/Scalarizer/vector-gep.ll deleted file mode 100644 index 81566067401..00000000000 --- a/llvm/test/Transforms/Scalarizer/vector-gep.ll +++ /dev/null @@ -1,123 +0,0 @@ -; RUN: opt -S -scalarizer %s | FileCheck %s -; RUN: opt -S -passes='function(scalarizer)' %s | FileCheck %s - -; Check that the scalarizer can handle vector GEPs with scalar indices - -@vec = global <4 x i16*> <i16* null, i16* null, i16* null, i16* null> -@index = global i16 1 -@ptr = global [4 x i16] [i16 1, i16 2, i16 3, i16 4] -@ptrptr = global i16* null - -; constant index -define void @test1() { -bb: - %0 = load <4 x i16*>, <4 x i16*>* @vec - %1 = getelementptr i16, <4 x i16*> %0, i16 1 - - ret void -} - -;CHECK-LABEL: @test1 -;CHECK: %[[I0:.i[0-9]*]] = extractelement <4 x i16*> %0, i32 0 -;CHECK: getelementptr i16, i16* %[[I0]], i16 1 -;CHECK: %[[I1:.i[0-9]*]] = extractelement <4 x i16*> %0, i32 1 -;CHECK: getelementptr i16, i16* %[[I1]], i16 1 -;CHECK: %[[I2:.i[0-9]*]] = extractelement <4 x i16*> %0, i32 2 -;CHECK: getelementptr i16, i16* %[[I2]], i16 1 -;CHECK: %[[I3:.i[0-9]*]] = extractelement <4 x i16*> %0, i32 3 -;CHECK: getelementptr i16, i16* %[[I3]], i16 1 - -; non-constant index -define void @test2() { -bb: - %0 = load <4 x i16*>, <4 x i16*>* @vec - %index = load i16, i16* @index - %1 = getelementptr i16, <4 x i16*> %0, i16 %index - - ret void -} - -;CHECK-LABEL: @test2 -;CHECK: %0 = load <4 x i16*>, <4 x i16*>* @vec -;CHECK: %[[I0:.i[0-9]*]] = extractelement <4 x i16*> %0, i32 0 -;CHECK: %[[I1:.i[0-9]*]] = extractelement <4 x i16*> %0, i32 1 -;CHECK: %[[I2:.i[0-9]*]] = extractelement <4 x i16*> %0, i32 2 -;CHECK: %[[I3:.i[0-9]*]] = extractelement <4 x i16*> %0, i32 3 -;CHECK: %index = load i16, i16* @index -;CHECK: %.splatinsert = insertelement <4 x i16> undef, i16 %index, i32 0 -;CHECK: %.splat = shufflevector <4 x i16> %.splatinsert, <4 x i16> undef, <4 x i32> zeroinitializer -;CHECK: %.splat[[I0]] = extractelement <4 x i16> %.splat, i32 0 -;CHECK: getelementptr i16, i16* %[[I0]], i16 %.splat[[I0]] -;CHECK: %.splat[[I1]] = extractelement <4 x i16> %.splat, i32 1 -;CHECK: getelementptr i16, i16* %[[I1]], i16 %.splat[[I1]] -;CHECK: %.splat[[I2]] = extractelement <4 x i16> %.splat, i32 2 -;CHECK: getelementptr i16, i16* %[[I2]], i16 %.splat[[I2]] -;CHECK: %.splat[[I3]] = extractelement <4 x i16> %.splat, i32 3 -;CHECK: getelementptr i16, i16* %[[I3]], i16 %.splat[[I3]] - - -; Check that the scalarizer can handle vector GEPs with scalar pointer - -; constant pointer -define void @test3() { -bb: - %0 = bitcast [4 x i16]* @ptr to i16* - %1 = getelementptr i16, i16* %0, <4 x i16> <i16 0, i16 1, i16 2, i16 3> - - ret void -} - -;CHECK-LABEL: @test3 -;CHECK: %0 = bitcast [4 x i16]* @ptr to i16* -;CHECK: %.splatinsert = insertelement <4 x i16*> undef, i16* %0, i32 0 -;CHECK: %.splat = shufflevector <4 x i16*> %.splatinsert, <4 x i16*> undef, <4 x i32> zeroinitializer -;CHECK: %.splat[[I0:.i[0-9]*]] = extractelement <4 x i16*> %.splat, i32 0 -;CHECK: getelementptr i16, i16* %.splat[[I0]], i16 0 -;CHECK: %.splat[[I1:.i[0-9]*]] = extractelement <4 x i16*> %.splat, i32 1 -;CHECK: getelementptr i16, i16* %.splat[[I1]], i16 1 -;CHECK: %.splat[[I2:.i[0-9]*]] = extractelement <4 x i16*> %.splat, i32 2 -;CHECK: getelementptr i16, i16* %.splat[[I2]], i16 2 -;CHECK: %.splat[[I3:.i[0-9]*]] = extractelement <4 x i16*> %.splat, i32 3 -;CHECK: getelementptr i16, i16* %.splat[[I3]], i16 3 - -; non-constant pointer -define void @test4() { -bb: - %0 = load i16*, i16** @ptrptr - %1 = getelementptr i16, i16* %0, <4 x i16> <i16 0, i16 1, i16 2, i16 3> - - ret void -} - -;CHECK-LABEL: @test4 -;CHECK: %0 = load i16*, i16** @ptrptr -;CHECK: %.splatinsert = insertelement <4 x i16*> undef, i16* %0, i32 0 -;CHECK: %.splat = shufflevector <4 x i16*> %.splatinsert, <4 x i16*> undef, <4 x i32> zeroinitializer -;CHECK: %.splat[[I0:.i[0-9]*]] = extractelement <4 x i16*> %.splat, i32 0 -;CHECK: getelementptr i16, i16* %.splat[[I0]], i16 0 -;CHECK: %.splat[[I1:.i[0-9]*]] = extractelement <4 x i16*> %.splat, i32 1 -;CHECK: getelementptr i16, i16* %.splat[[I1]], i16 1 -;CHECK: %.splat[[I2:.i[0-9]*]] = extractelement <4 x i16*> %.splat, i32 2 -;CHECK: getelementptr i16, i16* %.splat[[I2]], i16 2 -;CHECK: %.splat[[I3:.i[0-9]*]] = extractelement <4 x i16*> %.splat, i32 3 -;CHECK: getelementptr i16, i16* %.splat[[I3]], i16 3 - -; constant index, inbounds -define void @test5() { -bb: - %0 = load <4 x i16*>, <4 x i16*>* @vec - %1 = getelementptr inbounds i16, <4 x i16*> %0, i16 1 - - ret void -} - -;CHECK-LABEL: @test5 -;CHECK: %[[I0:.i[0-9]*]] = extractelement <4 x i16*> %0, i32 0 -;CHECK: getelementptr inbounds i16, i16* %[[I0]], i16 1 -;CHECK: %[[I1:.i[0-9]*]] = extractelement <4 x i16*> %0, i32 1 -;CHECK: getelementptr inbounds i16, i16* %[[I1]], i16 1 -;CHECK: %[[I2:.i[0-9]*]] = extractelement <4 x i16*> %0, i32 2 -;CHECK: getelementptr inbounds i16, i16* %[[I2]], i16 1 -;CHECK: %[[I3:.i[0-9]*]] = extractelement <4 x i16*> %0, i32 3 -;CHECK: getelementptr inbounds i16, i16* %[[I3]], i16 1 - |