[CostModel][X86] Fix overcounting arithmetic cost in illegal types getArithmeticReductionCost

[craig.topper]

Summary

We were overcounting the number of arithmetic operations needed at each level before we reach a legal type. We were using the full vector type for that level, but we are going to split the input vector at that level in half. So the effective arithmetic operation cost at that level is half the width.

So for example on 8i32 on an sse target. Were were calculating the cost of an 8i32 op which is likely 2 for basic integer. Then after the loop we count 2 more v4i32 ops. For a total arith cost of 4. But if you look at the assembly there would only be 3 arithmetic ops.

There are still more bugs in this code that I'm going to work on next. The non pairwise code shouldn't count extract subvectors in the loop. There are no extracts, the types are split in registers. For pairwise we need to use 2 two src permute shuffles.

[craig.topper]

Do the same thing to the min/max reduction cost.

[RKSimon]

Nice catch! LGTM

include/llvm/CodeGen/BasicTTIImpl.h

unsigned MVTLen =
         LT.second.isVector() ? LT.second.getVectorNumElements() : 1;
     while (NumVecElts > MVTLen) {
       NumVecElts /= 2;
       Type *SubTy = VectorType::get(ScalarTy, NumVecElts);
       // Assume the pairwise shuffles add a cost.
       ShuffleCost += (IsPairwise + 1) *
                      ConcreteTTI->getShuffleCost(TTI::SK_ExtractSubvector, Ty,
                                                  NumVecElts, SubTy);
-      ArithCost += ConcreteTTI->getArithmeticInstrCost(Opcode, Ty);
+      ArithCost += ConcreteTTI->getArithmeticInstrCost(Opcode, SubTy);
       Ty = SubTy;
       ++LongVectorCount;
     }
     // The minimal length of the vector is limited by the real length of vector
     // operations performed on the current platform. That's why several final
     // reduction operations are performed on the vectors with the same
     // architecture-dependent length.
     ShuffleCost += (NumReduxLevels - LongVectorCount) * (IsPairwise + 1) *

test/Analysis/CostModel/X86/reduce-add-widen.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+ssse3 | FileCheck %s --check-prefixes=CHECK,SSE,SSSE3
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BW
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512dq | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512DQ
 
 define i32 @reduce_i64(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i64'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.i64.v2i64(<2 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i64'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.i64.v2i64(<2 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i64'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.i64.v2i64(<2 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX-LABEL: 'reduce_i64'
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.i64.v2i64(<2 x i64> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'reduce_i64'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.i64.v2i64(<2 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1  = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> undef)
   %V2  = call i64 @llvm.experimental.vector.reduce.add.i64.v2i64(<2 x i64> undef)
   %V4  = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef)
   %V8  = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef)
   %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i32(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i32'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.i32.v2i32(<2 x i32> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.i32.v4i32(<4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i32'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.i32.v2i32(<2 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.i32.v4i32(<4 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i32'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.i32.v2i32(<2 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.i32.v4i32(<4 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX-LABEL: 'reduce_i32'
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.i32.v2i32(<2 x i32> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.i32.v4i32(<4 x i32> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'reduce_i32'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.i32.v2i32(<2 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.i32.v4i32(<4 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i32 @llvm.experimental.vector.reduce.add.i32.v2i32(<2 x i32> undef)
   %V4  = call i32 @llvm.experimental.vector.reduce.add.i32.v4i32(<4 x i32> undef)
   %V8  = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef)
   %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef)
   %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i16(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i16'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i16'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i16'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i16'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 73 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 53 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 61 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i16'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i16'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i16'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i16'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef)
   %V4  = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef)
   %V8  = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef)
   %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
   %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
   %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i8(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i8'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i8'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i8'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i8'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 61 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 85 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 65 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 73 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i8'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i8'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i8'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i8'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2   = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef)
   %V4   = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef)
   %V8   = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef)
   %V16  = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef)
   %V32  = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
   %V64  = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)

test/Analysis/CostModel/X86/reduce-add.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+ssse3 | FileCheck %s --check-prefixes=CHECK,SSE,SSSE3
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BW
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512dq | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512DQ
 
 define i32 @reduce_i64(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i64'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.i64.v2i64(<2 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i64'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.i64.v2i64(<2 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i64'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.i64.v2i64(<2 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX-LABEL: 'reduce_i64'
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.i64.v2i64(<2 x i64> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'reduce_i64'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.add.i64.v2i64(<2 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1  = call i64 @llvm.experimental.vector.reduce.add.i64.v1i64(<1 x i64> undef)
   %V2  = call i64 @llvm.experimental.vector.reduce.add.i64.v2i64(<2 x i64> undef)
   %V4  = call i64 @llvm.experimental.vector.reduce.add.i64.v4i64(<4 x i64> undef)
   %V8  = call i64 @llvm.experimental.vector.reduce.add.i64.v8i64(<8 x i64> undef)
   %V16 = call i64 @llvm.experimental.vector.reduce.add.i64.v16i64(<16 x i64> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i32(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i32'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.i32.v2i32(<2 x i32> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.i32.v4i32(<4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i32'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.i32.v2i32(<2 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.i32.v4i32(<4 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i32'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.i32.v2i32(<2 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.i32.v4i32(<4 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX-LABEL: 'reduce_i32'
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.i32.v2i32(<2 x i32> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.i32.v4i32(<4 x i32> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef)
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'reduce_i32'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.add.i32.v2i32(<2 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.add.i32.v4i32(<4 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i32 @llvm.experimental.vector.reduce.add.i32.v2i32(<2 x i32> undef)
   %V4  = call i32 @llvm.experimental.vector.reduce.add.i32.v4i32(<4 x i32> undef)
   %V8  = call i32 @llvm.experimental.vector.reduce.add.i32.v8i32(<8 x i32> undef)
   %V16 = call i32 @llvm.experimental.vector.reduce.add.i32.v16i32(<16 x i32> undef)
   %V32 = call i32 @llvm.experimental.vector.reduce.add.i32.v32i32(<32 x i32> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i16(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i16'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i16'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i16'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i16'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 73 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 53 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 61 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i16'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i16'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i16'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i16'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i16 @llvm.experimental.vector.reduce.add.i16.v2i16(<2 x i16> undef)
   %V4  = call i16 @llvm.experimental.vector.reduce.add.i16.v4i16(<4 x i16> undef)
   %V8  = call i16 @llvm.experimental.vector.reduce.add.i16.v8i16(<8 x i16> undef)
   %V16 = call i16 @llvm.experimental.vector.reduce.add.i16.v16i16(<16 x i16> undef)
   %V32 = call i16 @llvm.experimental.vector.reduce.add.i16.v32i16(<32 x i16> undef)
   %V64 = call i16 @llvm.experimental.vector.reduce.add.i16.v64i16(<64 x i16> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i8(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i8'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i8'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i8'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i8'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 61 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 85 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 65 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 73 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i8'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i8'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i8'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i8'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.add.i8.v128i8(<128 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2   = call i8 @llvm.experimental.vector.reduce.add.i8.v2i8(<2 x i8> undef)
   %V4   = call i8 @llvm.experimental.vector.reduce.add.i8.v4i8(<4 x i8> undef)
   %V8   = call i8 @llvm.experimental.vector.reduce.add.i8.v8i8(<8 x i8> undef)
   %V16  = call i8 @llvm.experimental.vector.reduce.add.i8.v16i8(<16 x i8> undef)
   %V32  = call i8 @llvm.experimental.vector.reduce.add.i8.v32i8(<32 x i8> undef)
   %V64  = call i8 @llvm.experimental.vector.reduce.add.i8.v64i8(<64 x i8> undef)

test/Analysis/CostModel/X86/reduce-and-widen.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+ssse3 | FileCheck %s --check-prefixes=CHECK,SSE,SSSE3
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BW
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512dq | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512DQ
 
 define i32 @reduce_i64(i32 %arg) {
 ; SSE-LABEL: 'reduce_i64'
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i64'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i64'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'reduce_i64'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1  = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef)
   %V2  = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef)
   %V4  = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef)
   %V8  = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
   %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i32(i32 %arg) {
 ; SSE-LABEL: 'reduce_i32'
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i32'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i32'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'reduce_i32'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef)
   %V4  = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef)
   %V8  = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef)
   %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
   %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i16(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i16'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i16'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i16'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i16'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i16'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i16'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i16'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i16'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef)
   %V4  = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
   %V8  = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
   %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
   %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
   %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i8(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i8'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i8'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i8'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i8'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i8'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i8'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i8'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i8'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2   = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef)
   %V4   = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef)
   %V8   = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
   %V16  = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
   %V32  = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
   %V64  = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
   %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i1(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i1'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i1'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i1'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i1'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i1'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i1'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i1'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 326 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 775 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 777 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 776 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i1'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1   = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
   %V2   = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
   %V4   = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
   %V8   = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
   %V16  = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
   %V32  = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)

test/Analysis/CostModel/X86/reduce-and.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+ssse3 | FileCheck %s --check-prefixes=CHECK,SSE,SSSE3
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BW
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512dq | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512DQ
 
 define i32 @reduce_i64(i32 %arg) {
 ; SSE-LABEL: 'reduce_i64'
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i64'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i64'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'reduce_i64'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1  = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef)
   %V2  = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef)
   %V4  = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef)
   %V8  = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
   %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i32(i32 %arg) {
 ; SSE-LABEL: 'reduce_i32'
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i32'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i32'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'reduce_i32'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef)
   %V4  = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef)
   %V8  = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef)
   %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
   %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i16(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i16'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i16'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i16'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i16'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i16'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i16'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i16'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i16'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i16 @llvm.experimental.vector.reduce.and.i16.v2i16(<2 x i16> undef)
   %V4  = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
   %V8  = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
   %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
   %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
   %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i8(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i8'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i8'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i8'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i8'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i8'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i8'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i8'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i8'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2   = call i8 @llvm.experimental.vector.reduce.and.i8.v2i8(<2 x i8> undef)
   %V4   = call i8 @llvm.experimental.vector.reduce.and.i8.v4i8(<4 x i8> undef)
   %V8   = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
   %V16  = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
   %V32  = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
   %V64  = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
   %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i1(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i1'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i1'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i1'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i1'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i1'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i1'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i1'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 326 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 775 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 777 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 776 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i1'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1   = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
   %V2   = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
   %V4   = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
   %V8   = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
   %V16  = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
   %V32  = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)

test/Analysis/CostModel/X86/reduce-mul-widen.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+ssse3 | FileCheck %s --check-prefixes=CHECK,SSE,SSSE3
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BW
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512dq | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512DQ
 
 define i32 @reduce_i64(i32 %arg) {
 ; SSE-LABEL: 'reduce_i64'
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 122 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i64'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 41 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 77 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 149 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i64'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 67 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i64'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i64'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i64'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1  = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef)
   %V2  = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef)
   %V4  = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef)
   %V8  = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
   %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i32(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i32'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 99 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i32'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 99 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i32'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i32'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i32'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'reduce_i32'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef)
   %V4  = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef)
   %V8  = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
   %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
   %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i16(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i16'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i16'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i16'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i16'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 73 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 53 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 61 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i16'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i16'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i16'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i16'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef)
   %V4  = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef)
   %V8  = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef)
   %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
   %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
   %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i8(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i8'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 67 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 89 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 113 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 161 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 257 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 101 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 125 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 173 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i8'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 53 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 77 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 125 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 221 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 65 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 89 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 137 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i8'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 53 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 77 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 125 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 221 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 65 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 89 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 137 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i8'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 53 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 171 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 223 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 327 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 197 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 249 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i8'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 106 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 123 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 157 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i8'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 164 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 99 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 125 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i8'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 115 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 137 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 126 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i8'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 164 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 99 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 125 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2   = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef)
   %V4   = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef)
   %V8   = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef)
   %V16  = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef)
   %V32  = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
   %V64  = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)

test/Analysis/CostModel/X86/reduce-mul.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+ssse3 | FileCheck %s --check-prefixes=CHECK,SSE,SSSE3
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BW
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512dq | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512DQ
 
 define i32 @reduce_i64(i32 %arg) {
 ; SSE-LABEL: 'reduce_i64'
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 122 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i64'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 41 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 77 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 149 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i64'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 67 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i64'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i64'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i64'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1  = call i64 @llvm.experimental.vector.reduce.mul.i64.v1i64(<1 x i64> undef)
   %V2  = call i64 @llvm.experimental.vector.reduce.mul.i64.v2i64(<2 x i64> undef)
   %V4  = call i64 @llvm.experimental.vector.reduce.mul.i64.v4i64(<4 x i64> undef)
   %V8  = call i64 @llvm.experimental.vector.reduce.mul.i64.v8i64(<8 x i64> undef)
   %V16 = call i64 @llvm.experimental.vector.reduce.mul.i64.v16i64(<16 x i64> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i32(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i32'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 99 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i32'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 99 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i32'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i32'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i32'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i32'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i32'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i32'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i32 @llvm.experimental.vector.reduce.mul.i32.v2i32(<2 x i32> undef)
   %V4  = call i32 @llvm.experimental.vector.reduce.mul.i32.v4i32(<4 x i32> undef)
   %V8  = call i32 @llvm.experimental.vector.reduce.mul.i32.v8i32(<8 x i32> undef)
   %V16 = call i32 @llvm.experimental.vector.reduce.mul.i32.v16i32(<16 x i32> undef)
   %V32 = call i32 @llvm.experimental.vector.reduce.mul.i32.v32i32(<32 x i32> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i16(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i16'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i16'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i16'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i16'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 73 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 53 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 61 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i16'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i16'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i16'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i16'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i16 @llvm.experimental.vector.reduce.mul.i16.v2i16(<2 x i16> undef)
   %V4  = call i16 @llvm.experimental.vector.reduce.mul.i16.v4i16(<4 x i16> undef)
   %V8  = call i16 @llvm.experimental.vector.reduce.mul.i16.v8i16(<8 x i16> undef)
   %V16 = call i16 @llvm.experimental.vector.reduce.mul.i16.v16i16(<16 x i16> undef)
   %V32 = call i16 @llvm.experimental.vector.reduce.mul.i16.v32i16(<32 x i16> undef)
   %V64 = call i16 @llvm.experimental.vector.reduce.mul.i16.v64i16(<64 x i16> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i8(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i8'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 89 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 113 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 161 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 257 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 101 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 125 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 173 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i8'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 53 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 77 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 125 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 221 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 65 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 89 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 137 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i8'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 53 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 77 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 125 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 221 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 65 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 89 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 137 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i8'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 53 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 171 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 223 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 327 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 197 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 249 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i8'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 106 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 123 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 157 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i8'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 164 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 99 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 125 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i8'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 115 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 137 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 126 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i8'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 164 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 99 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 125 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.mul.i8.v128i8(<128 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2   = call i8 @llvm.experimental.vector.reduce.mul.i8.v2i8(<2 x i8> undef)
   %V4   = call i8 @llvm.experimental.vector.reduce.mul.i8.v4i8(<4 x i8> undef)
   %V8   = call i8 @llvm.experimental.vector.reduce.mul.i8.v8i8(<8 x i8> undef)
   %V16  = call i8 @llvm.experimental.vector.reduce.mul.i8.v16i8(<16 x i8> undef)
   %V32  = call i8 @llvm.experimental.vector.reduce.mul.i8.v32i8(<32 x i8> undef)
   %V64  = call i8 @llvm.experimental.vector.reduce.mul.i8.v64i8(<64 x i8> undef)

test/Analysis/CostModel/X86/reduce-or-widen.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+ssse3 | FileCheck %s --check-prefixes=CHECK,SSE,SSSE3
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BW
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512dq | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512DQ
 
 define i32 @reduce_i64(i32 %arg) {
 ; SSE-LABEL: 'reduce_i64'
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.or.i64.v1i64(<1 x i64> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.i64.v2i64(<2 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i64'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.or.i64.v1i64(<1 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.i64.v2i64(<2 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i64'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.or.i64.v1i64(<1 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.i64.v2i64(<2 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'reduce_i64'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.or.i64.v1i64(<1 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.i64.v2i64(<2 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1  = call i64 @llvm.experimental.vector.reduce.or.i64.v1i64(<1 x i64> undef)
   %V2  = call i64 @llvm.experimental.vector.reduce.or.i64.v2i64(<2 x i64> undef)
   %V4  = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef)
   %V8  = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef)
   %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i32(i32 %arg) {
 ; SSE-LABEL: 'reduce_i32'
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.or.i32.v2i32(<2 x i32> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.i32.v4i32(<4 x i32> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i32'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.or.i32.v2i32(<2 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.i32.v4i32(<4 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i32'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.or.i32.v2i32(<2 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.i32.v4i32(<4 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'reduce_i32'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.or.i32.v2i32(<2 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.i32.v4i32(<4 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i32 @llvm.experimental.vector.reduce.or.i32.v2i32(<2 x i32> undef)
   %V4  = call i32 @llvm.experimental.vector.reduce.or.i32.v4i32(<4 x i32> undef)
   %V8  = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef)
   %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef)
   %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i16(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i16'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i16'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i16'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i16'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i16'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i16'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i16'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i16'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef)
   %V4  = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef)
   %V8  = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef)
   %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
   %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
   %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i8(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i8'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i8'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i8'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i8'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i8'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i8'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i8'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i8'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2   = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef)
   %V4   = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef)
   %V8   = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef)
   %V16  = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef)
   %V32  = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
   %V64  = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
   %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i1(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i1'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.or.i1.v2i1(<2 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i1'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.or.i1.v2i1(<2 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i1'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.or.i1.v2i1(<2 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i1'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.or.i1.v2i1(<2 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i1'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.or.i1.v2i1(<2 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i1'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.or.i1.v2i1(<2 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i1'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.or.i1.v2i1(<2 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 326 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 775 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 777 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 776 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i1'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.or.i1.v2i1(<2 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1   = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef)
   %V2   = call i1 @llvm.experimental.vector.reduce.or.i1.v2i1(<2 x i1> undef)
   %V4   = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef)
   %V8   = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef)
   %V16  = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef)
   %V32  = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)

test/Analysis/CostModel/X86/reduce-or.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+ssse3 | FileCheck %s --check-prefixes=CHECK,SSE,SSSE3
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BW
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512dq | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512DQ
 
 define i32 @reduce_i64(i32 %arg) {
 ; SSE-LABEL: 'reduce_i64'
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.or.i64.v1i64(<1 x i64> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.i64.v2i64(<2 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i64'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.or.i64.v1i64(<1 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.i64.v2i64(<2 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i64'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.or.i64.v1i64(<1 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.i64.v2i64(<2 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'reduce_i64'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.or.i64.v1i64(<1 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.or.i64.v2i64(<2 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1  = call i64 @llvm.experimental.vector.reduce.or.i64.v1i64(<1 x i64> undef)
   %V2  = call i64 @llvm.experimental.vector.reduce.or.i64.v2i64(<2 x i64> undef)
   %V4  = call i64 @llvm.experimental.vector.reduce.or.i64.v4i64(<4 x i64> undef)
   %V8  = call i64 @llvm.experimental.vector.reduce.or.i64.v8i64(<8 x i64> undef)
   %V16 = call i64 @llvm.experimental.vector.reduce.or.i64.v16i64(<16 x i64> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i32(i32 %arg) {
 ; SSE-LABEL: 'reduce_i32'
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.or.i32.v2i32(<2 x i32> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.i32.v4i32(<4 x i32> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i32'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.or.i32.v2i32(<2 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.i32.v4i32(<4 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i32'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.or.i32.v2i32(<2 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.i32.v4i32(<4 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'reduce_i32'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.or.i32.v2i32(<2 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.or.i32.v4i32(<4 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i32 @llvm.experimental.vector.reduce.or.i32.v2i32(<2 x i32> undef)
   %V4  = call i32 @llvm.experimental.vector.reduce.or.i32.v4i32(<4 x i32> undef)
   %V8  = call i32 @llvm.experimental.vector.reduce.or.i32.v8i32(<8 x i32> undef)
   %V16 = call i32 @llvm.experimental.vector.reduce.or.i32.v16i32(<16 x i32> undef)
   %V32 = call i32 @llvm.experimental.vector.reduce.or.i32.v32i32(<32 x i32> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i16(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i16'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i16'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i16'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i16'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i16'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i16'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i16'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i16'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i16 @llvm.experimental.vector.reduce.or.i16.v2i16(<2 x i16> undef)
   %V4  = call i16 @llvm.experimental.vector.reduce.or.i16.v4i16(<4 x i16> undef)
   %V8  = call i16 @llvm.experimental.vector.reduce.or.i16.v8i16(<8 x i16> undef)
   %V16 = call i16 @llvm.experimental.vector.reduce.or.i16.v16i16(<16 x i16> undef)
   %V32 = call i16 @llvm.experimental.vector.reduce.or.i16.v32i16(<32 x i16> undef)
   %V64 = call i16 @llvm.experimental.vector.reduce.or.i16.v64i16(<64 x i16> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i8(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i8'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i8'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i8'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i8'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i8'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i8'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i8'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i8'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2   = call i8 @llvm.experimental.vector.reduce.or.i8.v2i8(<2 x i8> undef)
   %V4   = call i8 @llvm.experimental.vector.reduce.or.i8.v4i8(<4 x i8> undef)
   %V8   = call i8 @llvm.experimental.vector.reduce.or.i8.v8i8(<8 x i8> undef)
   %V16  = call i8 @llvm.experimental.vector.reduce.or.i8.v16i8(<16 x i8> undef)
   %V32  = call i8 @llvm.experimental.vector.reduce.or.i8.v32i8(<32 x i8> undef)
   %V64  = call i8 @llvm.experimental.vector.reduce.or.i8.v64i8(<64 x i8> undef)
   %V128 = call i8 @llvm.experimental.vector.reduce.or.i8.v128i8(<128 x i8> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i1(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i1'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.or.i1.v2i1(<2 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i1'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.or.i1.v2i1(<2 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i1'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.or.i1.v2i1(<2 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i1'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.or.i1.v2i1(<2 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i1'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.or.i1.v2i1(<2 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i1'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.or.i1.v2i1(<2 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i1'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.or.i1.v2i1(<2 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 326 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 775 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 777 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 776 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i1'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.or.i1.v2i1(<2 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.or.i1.v64i1(<64 x i1> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.or.i1.v128i1(<128 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1   = call i1 @llvm.experimental.vector.reduce.or.i1.v1i1(<1 x i1> undef)
   %V2   = call i1 @llvm.experimental.vector.reduce.or.i1.v2i1(<2 x i1> undef)
   %V4   = call i1 @llvm.experimental.vector.reduce.or.i1.v4i1(<4 x i1> undef)
   %V8   = call i1 @llvm.experimental.vector.reduce.or.i1.v8i1(<8 x i1> undef)
   %V16  = call i1 @llvm.experimental.vector.reduce.or.i1.v16i1(<16 x i1> undef)
   %V32  = call i1 @llvm.experimental.vector.reduce.or.i1.v32i1(<32 x i1> undef)

test/Analysis/CostModel/X86/reduce-xor-widen.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+ssse3 | FileCheck %s --check-prefixes=CHECK,SSE,SSSE3
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BW
 ; RUN: opt < %s -x86-experimental-vector-widening-legalization -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512dq | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512DQ
 
 define i32 @reduce_i64(i32 %arg) {
 ; SSE-LABEL: 'reduce_i64'
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.xor.i64.v1i64(<1 x i64> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.i64.v2i64(<2 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i64'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.xor.i64.v1i64(<1 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.i64.v2i64(<2 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i64'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.xor.i64.v1i64(<1 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.i64.v2i64(<2 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'reduce_i64'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.xor.i64.v1i64(<1 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.i64.v2i64(<2 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1  = call i64 @llvm.experimental.vector.reduce.xor.i64.v1i64(<1 x i64> undef)
   %V2  = call i64 @llvm.experimental.vector.reduce.xor.i64.v2i64(<2 x i64> undef)
   %V4  = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef)
   %V8  = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef)
   %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i32(i32 %arg) {
 ; SSE-LABEL: 'reduce_i32'
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.xor.i32.v2i32(<2 x i32> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.i32.v4i32(<4 x i32> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i32'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.xor.i32.v2i32(<2 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.i32.v4i32(<4 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i32'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.xor.i32.v2i32(<2 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.i32.v4i32(<4 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'reduce_i32'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.xor.i32.v2i32(<2 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.i32.v4i32(<4 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i32 @llvm.experimental.vector.reduce.xor.i32.v2i32(<2 x i32> undef)
   %V4  = call i32 @llvm.experimental.vector.reduce.xor.i32.v4i32(<4 x i32> undef)
   %V8  = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef)
   %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef)
   %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i16(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i16'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i16'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i16'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i16'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i16'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i16'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i16'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i16'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef)
   %V4  = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef)
   %V8  = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef)
   %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
   %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
   %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i8(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i8'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i8'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i8'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i8'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i8'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i8'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i8'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i8'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2   = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef)
   %V4   = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef)
   %V8   = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef)
   %V16  = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef)
   %V32  = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
   %V64  = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
   %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i1(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i1'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.xor.i1.v2i1(<2 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i1'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.xor.i1.v2i1(<2 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i1'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.xor.i1.v2i1(<2 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i1'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.xor.i1.v2i1(<2 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i1'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.xor.i1.v2i1(<2 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i1'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.xor.i1.v2i1(<2 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i1'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.xor.i1.v2i1(<2 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 326 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 775 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 777 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 776 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i1'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.xor.i1.v2i1(<2 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1   = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef)
   %V2   = call i1 @llvm.experimental.vector.reduce.xor.i1.v2i1(<2 x i1> undef)
   %V4   = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef)
   %V8   = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef)
   %V16  = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef)
   %V32  = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)

test/Analysis/CostModel/X86/reduce-xor.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+ssse3 | FileCheck %s --check-prefixes=CHECK,SSE,SSSE3
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BW
 ; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512dq | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512DQ
 
 define i32 @reduce_i64(i32 %arg) {
 ; SSE-LABEL: 'reduce_i64'
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.xor.i64.v1i64(<1 x i64> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.i64.v2i64(<2 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i64'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.xor.i64.v1i64(<1 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.i64.v2i64(<2 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i64'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.xor.i64.v1i64(<1 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.i64.v2i64(<2 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'reduce_i64'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.xor.i64.v1i64(<1 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.xor.i64.v2i64(<2 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1  = call i64 @llvm.experimental.vector.reduce.xor.i64.v1i64(<1 x i64> undef)
   %V2  = call i64 @llvm.experimental.vector.reduce.xor.i64.v2i64(<2 x i64> undef)
   %V4  = call i64 @llvm.experimental.vector.reduce.xor.i64.v4i64(<4 x i64> undef)
   %V8  = call i64 @llvm.experimental.vector.reduce.xor.i64.v8i64(<8 x i64> undef)
   %V16 = call i64 @llvm.experimental.vector.reduce.xor.i64.v16i64(<16 x i64> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i32(i32 %arg) {
 ; SSE-LABEL: 'reduce_i32'
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.xor.i32.v2i32(<2 x i32> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.i32.v4i32(<4 x i32> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef)
-; SSE-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef)
+; SSE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef)
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i32'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.xor.i32.v2i32(<2 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.i32.v4i32(<4 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i32'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.xor.i32.v2i32(<2 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.i32.v4i32(<4 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'reduce_i32'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.xor.i32.v2i32(<2 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.xor.i32.v4i32(<4 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef)
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef)
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef)
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i32 @llvm.experimental.vector.reduce.xor.i32.v2i32(<2 x i32> undef)
   %V4  = call i32 @llvm.experimental.vector.reduce.xor.i32.v4i32(<4 x i32> undef)
   %V8  = call i32 @llvm.experimental.vector.reduce.xor.i32.v8i32(<8 x i32> undef)
   %V16 = call i32 @llvm.experimental.vector.reduce.xor.i32.v16i32(<16 x i32> undef)
   %V32 = call i32 @llvm.experimental.vector.reduce.xor.i32.v32i32(<32 x i32> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i16(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i16'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i16'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i16'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i16'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i16'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i16'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i16'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i16'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2  = call i16 @llvm.experimental.vector.reduce.xor.i16.v2i16(<2 x i16> undef)
   %V4  = call i16 @llvm.experimental.vector.reduce.xor.i16.v4i16(<4 x i16> undef)
   %V8  = call i16 @llvm.experimental.vector.reduce.xor.i16.v8i16(<8 x i16> undef)
   %V16 = call i16 @llvm.experimental.vector.reduce.xor.i16.v16i16(<16 x i16> undef)
   %V32 = call i16 @llvm.experimental.vector.reduce.xor.i16.v32i16(<32 x i16> undef)
   %V64 = call i16 @llvm.experimental.vector.reduce.xor.i16.v64i16(<64 x i16> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i8(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i8'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i8'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i8'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i8'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i8'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i8'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i8'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 55 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i8'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V2   = call i8 @llvm.experimental.vector.reduce.xor.i8.v2i8(<2 x i8> undef)
   %V4   = call i8 @llvm.experimental.vector.reduce.xor.i8.v4i8(<4 x i8> undef)
   %V8   = call i8 @llvm.experimental.vector.reduce.xor.i8.v8i8(<8 x i8> undef)
   %V16  = call i8 @llvm.experimental.vector.reduce.xor.i8.v16i8(<16 x i8> undef)
   %V32  = call i8 @llvm.experimental.vector.reduce.xor.i8.v32i8(<32 x i8> undef)
   %V64  = call i8 @llvm.experimental.vector.reduce.xor.i8.v64i8(<64 x i8> undef)
   %V128 = call i8 @llvm.experimental.vector.reduce.xor.i8.v128i8(<128 x i8> undef)
   ret i32 undef
 }
 
 define i32 @reduce_i1(i32 %arg) {
 ; SSE2-LABEL: 'reduce_i1'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.xor.i1.v2i1(<2 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 45 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSSE3-LABEL: 'reduce_i1'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.xor.i1.v2i1(<2 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'reduce_i1'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.xor.i1.v2i1(<2 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
+; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'reduce_i1'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.xor.i1.v2i1(<2 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
+; AVX1-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'reduce_i1'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.xor.i1.v2i1(<2 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
+; AVX2-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'reduce_i1'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.xor.i1.v2i1(<2 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'reduce_i1'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.xor.i1.v2i1(<2 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 326 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 775 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 777 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 776 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'reduce_i1'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.xor.i1.v2i1(<2 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 135 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 139 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 147 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 134 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.xor.i1.v64i1(<64 x i1> undef)
+; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.xor.i1.v128i1(<128 x i1> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %V1   = call i1 @llvm.experimental.vector.reduce.xor.i1.v1i1(<1 x i1> undef)
   %V2   = call i1 @llvm.experimental.vector.reduce.xor.i1.v2i1(<2 x i1> undef)
   %V4   = call i1 @llvm.experimental.vector.reduce.xor.i1.v4i1(<4 x i1> undef)
   %V8   = call i1 @llvm.experimental.vector.reduce.xor.i1.v8i1(<8 x i1> undef)
   %V16  = call i1 @llvm.experimental.vector.reduce.xor.i1.v16i1(<16 x i1> undef)
   %V32  = call i1 @llvm.experimental.vector.reduce.xor.i1.v32i1(<32 x i1> undef)

test/Analysis/CostModel/X86/reduction.ll

;
   %rdx.shuf7 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
   %bin.rdx8 = fadd <4 x float> %bin.rdx, %rdx.shuf7
 
   %r = extractelement <4 x float> %bin.rdx8, i32 0
   ret float %r
 }
 
 define fastcc i32 @reduction_cost_int(<8 x i32> %rdx) {
-; SSE2-LABEL: 'reduction_cost_int'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx, %rdx.shuf
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.2 = add <8 x i32> %bin.rdx, %rdx.shuf.2
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.3 = shufflevector <8 x i32> %bin.rdx.2, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.3 = add <8 x i32> %bin.rdx.2, %rdx.shuf.3
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <8 x i32> %bin.rdx.3, i32 0
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
-;
-; SSSE3-LABEL: 'reduction_cost_int'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx, %rdx.shuf
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.2 = add <8 x i32> %bin.rdx, %rdx.shuf.2
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.3 = shufflevector <8 x i32> %bin.rdx.2, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.3 = add <8 x i32> %bin.rdx.2, %rdx.shuf.3
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <8 x i32> %bin.rdx.3, i32 0
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
-;
-; SSE42-LABEL: 'reduction_cost_int'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx, %rdx.shuf
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.2 = add <8 x i32> %bin.rdx, %rdx.shuf.2
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.3 = shufflevector <8 x i32> %bin.rdx.2, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.3 = add <8 x i32> %bin.rdx.2, %rdx.shuf.3
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx.3, i32 0
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
+; SSE-LABEL: 'reduction_cost_int'
+; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx, %rdx.shuf
+; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.2 = add <8 x i32> %bin.rdx, %rdx.shuf.2
+; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.3 = shufflevector <8 x i32> %bin.rdx.2, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.3 = add <8 x i32> %bin.rdx.2, %rdx.shuf.3
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx.3, i32 0
+; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
 ;
 ; AVX1-LABEL: 'reduction_cost_int'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = add <8 x i32> %rdx, %rdx.shuf
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx.2 = add <8 x i32> %bin.rdx, %rdx.shuf.2
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.3 = shufflevector <8 x i32> %bin.rdx.2, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx.3 = add <8 x i32> %bin.rdx.2, %rdx.shuf.3

 }
 
 define fastcc double @no_pairwise_reduction4double(<4 x double> %rdx, double %f1) {
 ; SSE2-LABEL: 'no_pairwise_reduction4double'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <4 x double> %rdx, %rdx.shuf
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %bin.rdx, %rdx.shuf7
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret double %r
 ;
 ; SSSE3-LABEL: 'no_pairwise_reduction4double'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <4 x double> %rdx, %rdx.shuf
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %bin.rdx, %rdx.shuf7
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret double %r
 ;
 ; SSE42-LABEL: 'no_pairwise_reduction4double'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <4 x double> %rdx, %rdx.shuf
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <4 x double> %bin.rdx, %rdx.shuf7
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0

 define fastcc float @no_pairwise_reduction8float(<8 x float> %rdx, float %f1) {
 ; SSE2-LABEL: 'no_pairwise_reduction8float'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx4 = fadd <8 x float> %rdx, %rdx.shuf3
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x float> %bin.rdx4, <8 x float> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <8 x float> %bin.rdx4, %rdx.shuf
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <8 x float> %bin.rdx, %rdx.shuf7
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret float %r
 ;
 ; SSSE3-LABEL: 'no_pairwise_reduction8float'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx4 = fadd <8 x float> %rdx, %rdx.shuf3
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x float> %bin.rdx4, <8 x float> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <8 x float> %bin.rdx4, %rdx.shuf
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <8 x float> %bin.rdx, %rdx.shuf7
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret float %r
 ;
 ; SSE42-LABEL: 'no_pairwise_reduction8float'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx4 = fadd <8 x float> %rdx, %rdx.shuf3
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x float> %bin.rdx4, <8 x float> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <8 x float> %bin.rdx4, %rdx.shuf
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
;
   %rdx.shuf7 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
   %bin.rdx8 = add <4 x i32> %bin.rdx, %rdx.shuf7
 
   %r = extractelement <4 x i32> %bin.rdx8, i32 0
   ret i32 %r
 }
 
 define fastcc i64 @no_pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) {
-; SSE2-LABEL: 'no_pairwise_reduction4i64'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <4 x i64> %rdx, %rdx.shuf
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <4 x i64> %bin.rdx, %rdx.shuf7
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
-;
-; SSSE3-LABEL: 'no_pairwise_reduction4i64'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <4 x i64> %rdx, %rdx.shuf
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <4 x i64> %bin.rdx, %rdx.shuf7
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
-;
-; SSE42-LABEL: 'no_pairwise_reduction4i64'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <4 x i64> %rdx, %rdx.shuf
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <4 x i64> %bin.rdx, %rdx.shuf7
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
+; SSE-LABEL: 'no_pairwise_reduction4i64'
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <4 x i64> %rdx, %rdx.shuf
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <4 x i64> %bin.rdx, %rdx.shuf7
+; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
+; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
 ;
 ; AVX1-LABEL: 'no_pairwise_reduction4i64'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = add <4 x i64> %rdx, %rdx.shuf
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = add <4 x i64> %bin.rdx, %rdx.shuf7
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
;
   %rdx.shuf7 = shufflevector <8 x i16> %bin.rdx, <8 x i16> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
   %bin.rdx8 = add <8 x i16> %bin.rdx, %rdx.shuf7
 
   %r = extractelement <8 x i16> %bin.rdx8, i32 0
   ret i16 %r
 }
 
 define fastcc i32 @no_pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) {
-; SSE2-LABEL: 'no_pairwise_reduction8i32'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx4 = add <8 x i32> %rdx, %rdx.shuf3
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %bin.rdx4, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %bin.rdx4, %rdx.shuf
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %bin.rdx, %rdx.shuf7
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <8 x i32> %bin.rdx8, i32 0
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
-;
-; SSSE3-LABEL: 'no_pairwise_reduction8i32'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx4 = add <8 x i32> %rdx, %rdx.shuf3
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %bin.rdx4, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %bin.rdx4, %rdx.shuf
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %bin.rdx, %rdx.shuf7
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <8 x i32> %bin.rdx8, i32 0
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
-;
-; SSE42-LABEL: 'no_pairwise_reduction8i32'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx4 = add <8 x i32> %rdx, %rdx.shuf3
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %bin.rdx4, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %bin.rdx4, %rdx.shuf
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %bin.rdx, %rdx.shuf7
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx8, i32 0
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
+; SSE-LABEL: 'no_pairwise_reduction8i32'
+; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx4 = add <8 x i32> %rdx, %rdx.shuf3
+; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %bin.rdx4, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %bin.rdx4, %rdx.shuf
+; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %bin.rdx, %rdx.shuf7
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx8, i32 0
+; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
 ;
 ; AVX1-LABEL: 'no_pairwise_reduction8i32'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx4 = add <8 x i32> %rdx, %rdx.shuf3
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %bin.rdx4, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = add <8 x i32> %bin.rdx4, %rdx.shuf
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = add <8 x i32> %bin.rdx, %rdx.shuf7

 define fastcc double @pairwise_reduction4double(<4 x double> %rdx, double %f1) {
 ; SSE2-LABEL: 'pairwise_reduction4double'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <4 x double> %rdx.shuf.0.0, %rdx.shuf.0.1
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %rdx.shuf.1.0, %rdx.shuf.1.1
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret double %r
 ;
 ; SSSE3-LABEL: 'pairwise_reduction4double'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <4 x double> %rdx.shuf.0.0, %rdx.shuf.0.1
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %rdx.shuf.1.0, %rdx.shuf.1.1
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret double %r
 ;
 ; SSE42-LABEL: 'pairwise_reduction4double'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <4 x double> %rdx.shuf.0.0, %rdx.shuf.0.1
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>

 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.1 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <8 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.0 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.1 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> <i32 1, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <8 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx9 = fadd <8 x float> %rdx.shuf.2.0, %rdx.shuf.2.1
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret float %r
 ;
 ; SSSE3-LABEL: 'pairwise_reduction8float'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.0 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.1 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <8 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.0 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.1 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> <i32 1, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <8 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx9 = fadd <8 x float> %rdx.shuf.2.0, %rdx.shuf.2.1
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret float %r
 ;
 ; SSE42-LABEL: 'pairwise_reduction8float'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.0 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.1 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <8 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.0 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.1 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> <i32 1, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>

 define fastcc i64 @pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) {
 ; SSE2-LABEL: 'pairwise_reduction4i64'
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <4 x i64> %rdx.shuf.0.0, %rdx.shuf.0.1
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <4 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
 ;
 ; SSSE3-LABEL: 'pairwise_reduction4i64'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <4 x i64> %rdx.shuf.0.0, %rdx.shuf.0.1
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <4 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
 ;
 ; SSE42-LABEL: 'pairwise_reduction4i64'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <4 x i64> %rdx.shuf.0.0, %rdx.shuf.0.1
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>

 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.1 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.0 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.1 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = add <8 x i32> %rdx.shuf.2.0, %rdx.shuf.2.1
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
+; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
 ; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
 ;
 ; SSSE3-LABEL: 'pairwise_reduction8i32'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.0 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.1 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.0 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.1 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = add <8 x i32> %rdx.shuf.2.0, %rdx.shuf.2.1
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
+; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
 ;
 ; SSE42-LABEL: 'pairwise_reduction8i32'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.0 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.1 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.0 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.1 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>

test/Transforms/SLPVectorizer/X86/reduction_unrolled.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -slp-vectorizer -slp-vectorize-hor -S -mtriple=x86_64-unknown-linux-gnu -mcpu=bdver2 -debug < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX
 ; RUN: opt -slp-vectorizer -slp-vectorize-hor -S -mtriple=x86_64-unknown-linux-gnu -mcpu=core2 -debug < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE
 ; REQUIRES: asserts
 
 ; int test_add(unsigned int *p) {
 ;   int result = 0;
 ;   for (int i = 0; i < 8; i++)
 ;     result += p[i];
 ;   return result;
 ; }
 
 ; Vector cost is 5, Scalar cost is 7
 ; AVX: Adding cost -2 for reduction that starts with   %7 = load i32, i32* %arrayidx.7, align 4 (It is a splitting reduction)
-; Vector cost is 7, Scalar cost is 7
-; SSE: Adding cost 0 for reduction that starts with   %7 = load i32, i32* %arrayidx.7, align 4 (It is a splitting reduction)
+; Vector cost is 6, Scalar cost is 7
+; SSE: Adding cost -1 for reduction that starts with   %7 = load i32, i32* %arrayidx.7, align 4 (It is a splitting reduction)
 define i32 @test_add(i32* nocapture readonly %p) {
 ; CHECK-LABEL: @test_add(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[ARRAYIDX_1:%.*]] = getelementptr inbounds i32, i32* [[P:%.*]], i64 1
 ; CHECK-NEXT:    [[ARRAYIDX_2:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 2
 ; CHECK-NEXT:    [[ARRAYIDX_3:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 3
 ; CHECK-NEXT:    [[ARRAYIDX_4:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 4
 ; CHECK-NEXT:    [[ARRAYIDX_5:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 5