[LV] Scalarize instructions marked scalar after vectorization

This patch ensures that we actually scalarize instructions marked scalar after
vectorization. Previously, such instructions may have been vectorized instead.

Differential Revision: https://reviews.llvm.org/D23889

llvm-svn: 282418

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -4506,6 +4506,15 @@ static bool mayDivideByZero(Instruction &I) {
 void InnerLoopVectorizer::vectorizeBlockInLoop(BasicBlock *BB, PhiVector *PV) {
   // For each instruction in the old loop.
   for (Instruction &I : *BB) {
+
+    // Scalarize instructions that should remain scalar after vectorization.
+    if (!(isa<BranchInst>(&I) || isa<PHINode>(&I) ||
+          isa<DbgInfoIntrinsic>(&I)) &&
+        Legal->isScalarAfterVectorization(&I)) {
+      scalarizeInstruction(&I);
+      continue;
+    }
+
     switch (I.getOpcode()) {
     case Instruction::Br:
       // Nothing to do for PHIs and BR, since we already took care of the

llvm/test/Transforms/LoopVectorize/PowerPC/small-loop-rdx.ll

@@ -1,5 +1,6 @@
 ; RUN: opt < %s -loop-vectorize -S | FileCheck %s
 
+; CHECK: vector.body:
 ; CHECK: fadd
 ; CHECK-NEXT: fadd
 ; CHECK-NEXT: fadd
@@ -12,9 +13,8 @@
 ; CHECK-NEXT: fadd
 ; CHECK-NEXT: fadd
 ; CHECK-NEXT: fadd
-; CHECK-NEXT: =
 ; CHECK-NOT: fadd
-; CHECK-SAME: >
+; CHECK: middle.block
 
 target datalayout = "e-m:e-i64:64-n32:64"
 target triple = "powerpc64le-ibm-linux-gnu"

llvm/test/Transforms/LoopVectorize/PowerPC/vsx-tsvc-s173.ll

@@ -43,7 +43,7 @@ for.end12:                                        ; preds = %for.end, %entry
 
 ; CHECK-LABEL: @s173
 ; CHECK: load <4 x float>, <4 x float>*
-; CHECK: add i64 %index, 16000
+; CHECK: add nsw i64 %index, 16000
 ; CHECK: ret i32 0
 }
 

llvm/test/Transforms/LoopVectorize/global_alias.ll

@@ -387,7 +387,7 @@ for.end:                                          ; preds = %for.cond
 ;   return Foo.A[a];
 ; }
 ; CHECK-LABEL: define i32 @noAlias08(
-; CHECK: sub <4 x i32>
+; CHECK: load <4 x i32>
 ; CHECK: ret
 
 define i32 @noAlias08(i32 %a) #0 {
@@ -439,7 +439,7 @@ for.end:                                          ; preds = %for.cond
 ;   return Foo.A[a];
 ; }
 ; CHECK-LABEL: define i32 @noAlias09(
-; CHECK: sub <4 x i32>
+; CHECK: load <4 x i32>
 ; CHECK: ret
 
 define i32 @noAlias09(i32 %a) #0 {
@@ -721,7 +721,7 @@ for.end:                                          ; preds = %for.cond
 ;   return Foo.A[a];
 ; }
 ; CHECK-LABEL: define i32 @noAlias14(
-; CHECK: sub <4 x i32>
+; CHECK: load <4 x i32>
 ; CHECK: ret
 
 define i32 @noAlias14(i32 %a) #0 {

llvm/test/Transforms/LoopVectorize/induction_plus.ll

@@ -9,7 +9,9 @@ target triple = "x86_64-apple-macosx10.8.0"
 ;CHECK: %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
 ;CHECK: %vec.ind = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, %vector.ph ], [ %vec.ind.next, %vector.body ]
 ;CHECK: %vec.ind1 = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, %vector.ph ], [ %vec.ind.next2, %vector.body ]
-;CHECK: add nsw <4 x i64> %vec.ind, <i64 12, i64 12, i64 12, i64 12>
+;CHECK: %[[T1:.+]] = add i64 %index, 0
+;CHECK: %[[T2:.+]] = add nsw i64 %[[T1]], 12
+;CHECK: getelementptr inbounds [1024 x i32], [1024 x i32]* @array, i64 0, i64 %[[T2]]
 ;CHECK: %vec.ind.next = add <4 x i64> %vec.ind, <i64 4, i64 4, i64 4, i64 4>
 ;CHECK: %vec.ind.next2 = add <4 x i32> %vec.ind1, <i32 4, i32 4, i32 4, i32 4>
 ;CHECK: ret i32

llvm/test/Transforms/LoopVectorize/scalar_after_vectorization.ll

@@ -0,0 +1,74 @@
+; RUN: opt < %s -force-vector-width=4 -force-vector-interleave=2 -loop-vectorize -instcombine -S | FileCheck %s
+; RUN: opt < %s -force-vector-width=4 -force-vector-interleave=2 -loop-vectorize -S | FileCheck %s --check-prefix=NO-IC
+
+target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
+
+; CHECK-LABEL: @scalar_after_vectorization_0
+;
+; CHECK: vector.body:
+; CHECK:   %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
+; CHECK:   %offset.idx = or i64 %index, 1
+; CHECK:   %[[T2:.+]] = add nuw nsw i64 %offset.idx, %tmp0
+; CHECK:   %[[T3:.+]] = sub nsw i64 %[[T2]], %x
+; CHECK:   %[[T4:.+]] = getelementptr inbounds i32, i32* %a, i64 %[[T3]]
+; CHECK:   %[[T5:.+]] = bitcast i32* %[[T4]] to <4 x i32>*
+; CHECK:   load <4 x i32>, <4 x i32>* %[[T5]], align 4
+; CHECK:   %[[T6:.+]] = getelementptr i32, i32* %[[T4]], i64 4
+; CHECK:   %[[T7:.+]] = bitcast i32* %[[T6]] to <4 x i32>*
+; CHECK:   load <4 x i32>, <4 x i32>* %[[T7]], align 4
+; CHECK:   br {{.*}}, label %middle.block, label %vector.body
+;
+; NO-IC-LABEL: @scalar_after_vectorization_0
+;
+; NO-IC: vector.body:
+; NO-IC:   %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
+; NO-IC:   %offset.idx = add i64 1, %index
+; NO-IC:   %[[T2:.+]] = add i64 %offset.idx, 0
+; NO-IC:   %[[T3:.+]] = add i64 %offset.idx, 4
+; NO-IC:   %[[T4:.+]] = add nuw nsw i64 %[[T2]], %tmp0
+; NO-IC:   %[[T5:.+]] = add nuw nsw i64 %[[T3]], %tmp0
+; NO-IC:   %[[T6:.+]] = sub nsw i64 %[[T4]], %x
+; NO-IC:   %[[T7:.+]] = sub nsw i64 %[[T5]], %x
+; NO-IC:   %[[T8:.+]] = getelementptr inbounds i32, i32* %a, i64 %[[T6]]
+; NO-IC:   %[[T9:.+]] = getelementptr inbounds i32, i32* %a, i64 %[[T7]]
+; NO-IC:   %[[T10:.+]] = getelementptr i32, i32* %[[T8]], i32 0
+; NO-IC:   %[[T11:.+]] = bitcast i32* %[[T10]] to <4 x i32>*
+; NO-IC:   load <4 x i32>, <4 x i32>* %[[T11]], align 4
+; NO-IC:   %[[T12:.+]] = getelementptr i32, i32* %[[T8]], i32 4
+; NO-IC:   %[[T13:.+]] = bitcast i32* %[[T12]] to <4 x i32>*
+; NO-IC:   load <4 x i32>, <4 x i32>* %[[T13]], align 4
+; NO-IC:   br {{.*}}, label %middle.block, label %vector.body
+;
+define void @scalar_after_vectorization_0(i32* noalias %a, i32* noalias %b, i64 %x, i64 %y) {
+
+outer.ph:
+  br label %outer.body
+
+outer.body:
+  %i = phi i64 [ 1, %outer.ph ], [ %i.next, %inner.end ]
+  %tmp0 = mul nuw nsw i64 %i, %x
+  br label %inner.ph
+
+inner.ph:
+  br label %inner.body
+
+inner.body:
+  %j = phi i64 [ 1, %inner.ph ], [ %j.next, %inner.body ]
+  %tmp1 = add nuw nsw i64 %j, %tmp0
+  %tmp2 = sub nsw i64 %tmp1, %x
+  %tmp3 = getelementptr inbounds i32, i32* %a, i64 %tmp2
+  %tmp4 = load i32, i32* %tmp3, align 4
+  %tmp5 = getelementptr inbounds i32, i32* %b, i64 %tmp1
+  store i32 %tmp4, i32* %tmp5, align 4
+  %j.next = add i64 %j, 1
+  %cond.j = icmp slt i64 %j.next, %y
+  br i1 %cond.j, label %inner.body, label %inner.end
+
+inner.end:
+  %i.next = add i64 %i, 1
+  %cond.i = icmp slt i64 %i.next, %y
+  br i1 %cond.i, label %outer.body, label %outer.end
+
+outer.end:
+  ret void
+}