[LV] Update type in cost model for scalarization

For non-uniform instructions marked for scalarization, we should update
`VectorTy` when computing instruction costs to reflect the scalar type. In
addition to determining instruction costs, this type is also used to signal
that all instructions in the loop will be scalarized. This currently affects
memory instructions and non-pointer induction variables and their updates. (We
also mark GEPs scalar after vectorization, but their cost is computed together
with memory instructions.) For scalarized induction updates, this patch also
scales the scalar cost by the vectorization factor, corresponding to each
induction step.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@303763 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Vectorize/LoopVectorize.cpp b/lib/Transforms/Vectorize/LoopVectorize.cpp
index 2b83b84..3b036a6 100644 (file)
--- a/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -7173,7 +7173,7 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, unsigned VF) {
   // 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 +7312,7 @@ 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 +7445,10 @@ 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 +7471,15 @@ 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:

diff --git a/test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll b/test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll
new file mode 100644 (file)
index 0000000..a7f414b
--- /dev/null
+++ b/test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll
@@ -0,0 +1,26 @@
+; 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
+}