[LoopVectorize] Fix zext/sext cost calculations when types are shrunk

In getInstructionCost if we know a zext/sext is going to be shrunk
we should only be changing the destination type, and leave the
source type unchanged. For example, we may change a zext from

  zext <16 x i8> %a to <16 x i32>

to

  zext <16 x i8> %a to <16 x i16>

However, we were previously calculating the cost for doing

  zext <16 x i16> %a to <16 x i16>

which is incorrect.

Differential Revision: https://reviews.llvm.org/D147152

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index fd8596a..e686508 100644 (file)
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -7371,7 +7371,8 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, ElementCount VF,
         VectorTy =
             largestIntegerVectorType(ToVectorTy(I->getType(), VF), MinVecTy);
       } else if (Opcode == Instruction::ZExt || Opcode == Instruction::SExt) {
-        SrcVecTy = largestIntegerVectorType(SrcVecTy, MinVecTy);
+        // Leave SrcVecTy unchanged - we only shrink the destination element
+        // type.
         VectorTy =
             smallestIntegerVectorType(ToVectorTy(I->getType(), VF), MinVecTy);
       }

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/type-shrinkage-zext-costs.ll b/llvm/test/Transforms/LoopVectorize/AArch64/type-shrinkage-zext-costs.ll
index 091c571..34de689 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/type-shrinkage-zext-costs.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/type-shrinkage-zext-costs.ll
@@ -16,7 +16,8 @@ define void @zext_i8_i16(ptr noalias nocapture readonly %p, ptr noalias nocaptur
 ; CHECK-COST: LV: Found an estimated cost of 1 for VF vscale x 1 For instruction:   %conv = zext i8 %0 to i32
 ; CHECK-COST: LV: Found an estimated cost of 1 for VF vscale x 2 For instruction:   %conv = zext i8 %0 to i32
 ; CHECK-COST: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction:   %conv = zext i8 %0 to i32
-; CHECK-COST: LV: Found an estimated cost of 1 for VF vscale x 8 For instruction:   %conv = zext i8 %0 to i32
+; CHECK-COST: LV: Found an estimated cost of 0 for VF vscale x 8 For instruction:   %conv = zext i8 %0 to i32
+
 ; CHECK-LABEL: define void @zext_i8_i16
 ; CHECK-SAME: (ptr noalias nocapture readonly [[P:%.*]], ptr noalias nocapture [[Q:%.*]], i32 [[LEN:%.*]]) #[[ATTR0:[0-9]+]] {
 ; CHECK-NEXT:  entry:
@@ -99,7 +100,8 @@ define void @sext_i8_i16(ptr noalias nocapture readonly %p, ptr noalias nocaptur
 ; CHECK-COST: LV: Found an estimated cost of 1 for VF vscale x 1 For instruction:   %conv = sext i8 %0 to i32
 ; CHECK-COST: LV: Found an estimated cost of 1 for VF vscale x 2 For instruction:   %conv = sext i8 %0 to i32
 ; CHECK-COST: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction:   %conv = sext i8 %0 to i32
-; CHECK-COST: LV: Found an estimated cost of 1 for VF vscale x 8 For instruction:   %conv = sext i8 %0 to i32
+; CHECK-COST: LV: Found an estimated cost of 0 for VF vscale x 8 For instruction:   %conv = sext i8 %0 to i32
+
 ; CHECK-LABEL: define void @sext_i8_i16
 ; CHECK-SAME: (ptr noalias nocapture readonly [[P:%.*]], ptr noalias nocapture [[Q:%.*]], i32 [[LEN:%.*]]) #[[ATTR0]] {
 ; CHECK-NEXT:  entry: