[LV] Reapply r303763 with fix for PR33193

r303763 caused build failures in some out-of-tree tests due to an assertion in
TTI. The original patch updated cost estimates for induction variable update
instructions marked for scalarization. However, it didn't consider that the
incoming value of an induction variable phi node could be a cast instruction.
This caused queries for cast instruction costs with a mix of vector and scalar
types. This patch includes a fix for cast instructions and the test case from
PR33193.

The fix was suggested by Jonas Paulsson <paulsson@linux.vnet.ibm.com>.

Reference: https://bugs.llvm.org/show_bug.cgi?id=33193
Original Differential Revision: https://reviews.llvm.org/D33457

llvm-svn: 304235

2 files changed, 68 insertions, 10 deletions

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 2b83b8426d1..8b9a64c220c 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -7170,10 +7170,8 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, unsigned VF) {
   Type *VectorTy;
   unsigned C = getInstructionCost(I, VF, VectorTy);
 
-  // Note: Even if all instructions are scalarized, return true if any memory
-  // accesses appear in the loop to get benefits from address folding etc.
   bool TypeNotScalarized =
-      VF > 1 && !VectorTy->isVoidTy() && TTI.getNumberOfParts(VectorTy) < VF;
+      VF > 1 && VectorTy->isVectorTy() && TTI.getNumberOfParts(VectorTy) < VF;
   return VectorizationCostTy(C, TypeNotScalarized);
 }
 
@@ -7312,7 +7310,7 @@ unsigned LoopVectorizationCostModel::getInstructionCost(Instruction *I,
   Type *RetTy = I->getType();
   if (canTruncateToMinimalBitwidth(I, VF))
     RetTy = IntegerType::get(RetTy->getContext(), MinBWs[I]);
-  VectorTy = ToVectorTy(RetTy, VF);
+  VectorTy = isScalarAfterVectorization(I, VF) ? RetTy : ToVectorTy(RetTy, VF);
   auto SE = PSE.getSE();
 
   // TODO: We need to estimate the cost of intrinsic calls.
@@ -7445,9 +7443,10 @@ unsigned LoopVectorizationCostModel::getInstructionCost(Instruction *I,
     } else if (Legal->isUniform(Op2)) {
       Op2VK = TargetTransformInfo::OK_UniformValue;
     }
-    SmallVector<const Value *, 4> Operands(I->operand_values()); 
-    return TTI.getArithmeticInstrCost(I->getOpcode(), VectorTy, Op1VK,
-                                      Op2VK, Op1VP, Op2VP, Operands);
+    SmallVector<const Value *, 4> Operands(I->operand_values());
+    unsigned N = isScalarAfterVectorization(I, VF) ? VF : 1;
+    return N * TTI.getArithmeticInstrCost(I->getOpcode(), VectorTy, Op1VK,
+                                          Op2VK, Op1VP, Op2VP, Operands);
   }
   case Instruction::Select: {
     SelectInst *SI = cast<SelectInst>(I);
@@ -7470,7 +7469,15 @@ unsigned LoopVectorizationCostModel::getInstructionCost(Instruction *I,
   }
   case Instruction::Store:
   case Instruction::Load: {
-    VectorTy = ToVectorTy(getMemInstValueType(I), VF);
+    unsigned Width = VF;
+    if (Width > 1) {
+      InstWidening Decision = getWideningDecision(I, Width);
+      assert(Decision != CM_Unknown &&
+             "CM decision should be taken at this point");
+      if (Decision == CM_Scalarize)
+        Width = 1;
+    }
+    VectorTy = ToVectorTy(getMemInstValueType(I), Width);
     return getMemoryInstructionCost(I, VF);
   }
   case Instruction::ZExt:
@@ -7495,7 +7502,8 @@ unsigned LoopVectorizationCostModel::getInstructionCost(Instruction *I,
     }
 
     Type *SrcScalarTy = I->getOperand(0)->getType();
-    Type *SrcVecTy = ToVectorTy(SrcScalarTy, VF);
+    Type *SrcVecTy =
+        VectorTy->isVectorTy() ? ToVectorTy(SrcScalarTy, VF) : SrcScalarTy;
     if (canTruncateToMinimalBitwidth(I, VF)) {
       // This cast is going to be shrunk. This may remove the cast or it might
       // turn it into slightly different cast. For example, if MinBW == 16,
@@ -7515,7 +7523,8 @@ unsigned LoopVectorizationCostModel::getInstructionCost(Instruction *I,
       }
     }
 
-    return TTI.getCastInstrCost(I->getOpcode(), VectorTy, SrcVecTy, I);
+    unsigned N = isScalarAfterVectorization(I, VF) ? VF : 1;
+    return N * TTI.getCastInstrCost(I->getOpcode(), VectorTy, SrcVecTy, I);
   }
   case Instruction::Call: {
     bool NeedToScalarize;
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll b/llvm/test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll
new file mode 100644
index 00000000000..247ea35ff5d
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll
@@ -0,0 +1,49 @@
+; REQUIRES: asserts
+; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -S -debug-only=loop-vectorize 2>&1 | FileCheck %s
+
+target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
+target triple = "aarch64--linux-gnu"
+
+; CHECK-LABEL: all_scalar
+; CHECK:       LV: Found scalar instruction: %i.next = add nuw nsw i64 %i, 2
+; CHECK:       LV: Found an estimated cost of 2 for VF 2 For instruction: %i.next = add nuw nsw i64 %i, 2
+; CHECK:       LV: Not considering vector loop of width 2 because it will not generate any vector instructions
+;
+define void @all_scalar(i64* %a, i64 %n) {
+entry:
+  br label %for.body
+
+for.body:
+  %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
+  %tmp0 = getelementptr i64, i64* %a, i64 %i
+  store i64 0, i64* %tmp0, align 1
+  %i.next = add nuw nsw i64 %i, 2
+  %cond = icmp eq i64 %i.next, %n
+  br i1 %cond, label %for.end, label %for.body
+
+for.end:
+  ret void
+}
+
+; CHECK-LABEL: PR33193
+; CHECK:       LV: Found scalar instruction: %i.next = zext i32 %j.next to i64
+; CHECK:       LV: Found an estimated cost of 0 for VF 8 For instruction: %i.next = zext i32 %j.next to i64
+; CHECK:       LV: Not considering vector loop of width 8 because it will not generate any vector instructions
+%struct.a = type { i32, i8 }
+define void @PR33193(%struct.a* %a, i64 %n) {
+entry:
+  br label %for.body
+
+for.body:
+  %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
+  %j = phi i32 [ 0, %entry ], [ %j.next, %for.body ]
+  %tmp0 = getelementptr inbounds %struct.a, %struct.a* %a, i64 %i, i32 1
+  store i8 0, i8* %tmp0, align 4
+  %j.next = add i32 %j, 1
+  %i.next = zext i32 %j.next to i64
+  %cond = icmp ugt i64 %n, %i.next
+  br i1 %cond, label %for.body, label %for.end
+
+for.end:
+  ret void
+}