replica
/
hanchenye-llvm-project
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[CostModel] Treat Identity shuffle masks as zero cost 

As discussed on D47985, identity shuffle masks should probably be free.

I've limited this to the case where the input and output types all match - but we could probably accept all cases.

Differential Revision: https://reviews.llvm.org/D47986

llvm-svn: 334506
This commit is contained in:
Simon Pilgrim 2018-06-12 14:47:13 +00:00
parent 76969eaf3d
commit 0783921987
3 changed files with 76 additions and 92 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
llvm/lib/Analysis/TargetTransformInfo.cpp
View File

@ -658,6 +658,22 @@ static bool isZeroEltBroadcastVectorMask(ArrayRef<int> Mask) {
return true;
}
static bool isIdentityVectorMask(ArrayRef<int> Mask) {
bool IdentityLHS = true;
bool IdentityRHS = true;
unsigned MaskSize = Mask.size();
// Example: shufflevector A, B, <0,1,u,3>
// Example: shufflevector A, B, <4,u,6,u>
for (unsigned i = 0; i < MaskSize && (IdentityLHS || IdentityRHS); ++i) {
if (Mask[i] < 0)
continue;
IdentityLHS &= (Mask[i] == i);
IdentityRHS &= (Mask[i] == (i + MaskSize));
}
return IdentityLHS || IdentityRHS;
}
static bool isAlternateVectorMask(ArrayRef<int> Mask) {
bool isAlternate = true;
unsigned MaskSize = Mask.size();
@ -1213,9 +1229,13 @@ int TargetTransformInfo::getInstructionThroughput(const Instruction *I) const {
SmallVector<int, 16> Mask = Shuffle->getShuffleMask();
if (NumVecElems == Mask.size()) {
if (isIdentityVectorMask(Mask))
return 0;
if (isReverseVectorMask(Mask))
return TTIImpl->getShuffleCost(TargetTransformInfo::SK_Reverse,
VecTypOp0, 0, nullptr);
if (isAlternateVectorMask(Mask))
return TTIImpl->getShuffleCost(TargetTransformInfo::SK_Alternate,
VecTypOp0, 0, nullptr);

96
llvm/test/Analysis/CostModel/X86/reduction.ll
View File

@ -124,7 +124,7 @@ define fastcc float @pairwise_hadd(<4 x float> %rdx, float %f1) {
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> 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.0 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> 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.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSE2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
@ -135,7 +135,7 @@ define fastcc float @pairwise_hadd(<4 x float> %rdx, float %f1) {
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> 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.0 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> 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.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
@ -146,7 +146,7 @@ define fastcc float @pairwise_hadd(<4 x float> %rdx, float %f1) {
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.0 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
@ -157,7 +157,7 @@ define fastcc float @pairwise_hadd(<4 x float> %rdx, float %f1) {
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.0 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
@ -185,7 +185,7 @@ define fastcc float @pairwise_hadd_assoc(<4 x float> %rdx, float %f1) {
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> 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.0 = fadd <4 x float> %rdx.shuf.0.1, %rdx.shuf.0.0
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> 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.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSE2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
@ -196,7 +196,7 @@ define fastcc float @pairwise_hadd_assoc(<4 x float> %rdx, float %f1) {
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> 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.0 = fadd <4 x float> %rdx.shuf.0.1, %rdx.shuf.0.0
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> 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.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
@ -207,7 +207,7 @@ define fastcc float @pairwise_hadd_assoc(<4 x float> %rdx, float %f1) {
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.0 = fadd <4 x float> %rdx.shuf.0.1, %rdx.shuf.0.0
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
@ -218,7 +218,7 @@ define fastcc float @pairwise_hadd_assoc(<4 x float> %rdx, float %f1) {
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.0 = fadd <4 x float> %rdx.shuf.0.1, %rdx.shuf.0.0
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0
@ -722,28 +722,28 @@ define fastcc i32 @no_pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) {
define fastcc double @pairwise_reduction2double(<2 x double> %rdx, double %f1) {
; SSE2-LABEL: 'pairwise_reduction2double'
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 0, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 0, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 1, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <2 x double> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <2 x double> %bin.rdx8, i32 0
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r
;
; SSSE3-LABEL: 'pairwise_reduction2double'
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 0, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 0, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 1, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <2 x double> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <2 x double> %bin.rdx8, i32 0
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r
;
; SSE42-LABEL: 'pairwise_reduction2double'
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 0, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 0, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 1, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = fadd <2 x double> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = extractelement <2 x double> %bin.rdx8, i32 0
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r
;
; AVX-LABEL: 'pairwise_reduction2double'
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 0, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 0, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 1, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = fadd <2 x double> %rdx.shuf.1.0, %rdx.shuf.1.1
; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = extractelement <2 x double> %bin.rdx8, i32 0
@ -762,7 +762,7 @@ define fastcc float @pairwise_reduction4float(<4 x float> %rdx, float %f1) {
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> 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 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx, <4 x float> 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 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSE2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
@ -772,7 +772,7 @@ define fastcc float @pairwise_reduction4float(<4 x float> %rdx, float %f1) {
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> 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 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx, <4 x float> 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 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSSE3-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
@ -782,7 +782,7 @@ define fastcc float @pairwise_reduction4float(<4 x float> %rdx, float %f1) {
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
@ -792,7 +792,7 @@ define fastcc float @pairwise_reduction4float(<4 x float> %rdx, float %f1) {
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0
@ -814,7 +814,7 @@ define fastcc double @pairwise_reduction4double(<4 x double> %rdx, double %f1) {
; 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 2 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 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 11 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
@ -824,7 +824,7 @@ define fastcc double @pairwise_reduction4double(<4 x double> %rdx, double %f1) {
; 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 2 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 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 11 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
@ -834,7 +834,7 @@ define fastcc double @pairwise_reduction4double(<4 x double> %rdx, double %f1) {
; 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 2 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 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>
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <4 x double> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
@ -844,7 +844,7 @@ define fastcc double @pairwise_reduction4double(<4 x double> %rdx, double %f1) {
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 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>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 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>
; AVX1-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
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX1-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>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 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>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <4 x double> %rdx.shuf.1.0, %rdx.shuf.1.1
; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
@ -854,7 +854,7 @@ define fastcc double @pairwise_reduction4double(<4 x double> %rdx, double %f1) {
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = fadd <4 x double> %rdx.shuf.0.0, %rdx.shuf.0.1
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX2-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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = fadd <4 x double> %rdx.shuf.1.0, %rdx.shuf.1.1
; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
@ -879,7 +879,7 @@ define fastcc float @pairwise_reduction8float(<8 x float> %rdx, float %f1) {
; 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 4 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 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 17 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
@ -892,7 +892,7 @@ define fastcc float @pairwise_reduction8float(<8 x float> %rdx, float %f1) {
; 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 4 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 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 17 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
@ -905,7 +905,7 @@ define fastcc float @pairwise_reduction8float(<8 x float> %rdx, float %f1) {
; 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>
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <8 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 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>
; SSE42-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>
; SSE42-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>
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = fadd <8 x float> %rdx.shuf.2.0, %rdx.shuf.2.1
; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
@ -918,7 +918,7 @@ define fastcc float @pairwise_reduction8float(<8 x float> %rdx, float %f1) {
; AVX1-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>
; AVX1-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>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <8 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX1-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>
; AVX1-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>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = fadd <8 x float> %rdx.shuf.2.0, %rdx.shuf.2.1
; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
@ -931,7 +931,7 @@ define fastcc float @pairwise_reduction8float(<8 x float> %rdx, float %f1) {
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = fadd <8 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX2-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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx9 = fadd <8 x float> %rdx.shuf.2.0, %rdx.shuf.2.1
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
@ -953,28 +953,28 @@ define fastcc float @pairwise_reduction8float(<8 x float> %rdx, float %f1) {
define fastcc i64 @pairwise_reduction2i64(<2 x i64> %rdx, i64 %f1) {
; SSE2-LABEL: 'pairwise_reduction2i64'
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 0, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 0, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 1, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <2 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <2 x i64> %bin.rdx8, i32 0
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
;
; SSSE3-LABEL: 'pairwise_reduction2i64'
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 0, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 0, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 1, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <2 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <2 x i64> %bin.rdx8, i32 0
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
;
; SSE42-LABEL: 'pairwise_reduction2i64'
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 0, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 0, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 1, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <2 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = extractelement <2 x i64> %bin.rdx8, i32 0
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r
;
; AVX-LABEL: 'pairwise_reduction2i64'
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 0, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 0, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 1, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <2 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = extractelement <2 x i64> %bin.rdx8, i32 0
@ -993,7 +993,7 @@ define fastcc i32 @pairwise_reduction4i32(<4 x i32> %rdx, i32 %f1) {
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <4 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <4 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0
@ -1003,7 +1003,7 @@ define fastcc i32 @pairwise_reduction4i32(<4 x i32> %rdx, i32 %f1) {
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <4 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <4 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSSE3-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0
@ -1013,7 +1013,7 @@ define fastcc i32 @pairwise_reduction4i32(<4 x i32> %rdx, i32 %f1) {
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <4 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <4 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0
@ -1023,7 +1023,7 @@ define fastcc i32 @pairwise_reduction4i32(<4 x i32> %rdx, i32 %f1) {
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <4 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <4 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1
; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0
@ -1045,7 +1045,7 @@ define fastcc i64 @pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) {
; 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 2 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 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 9 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
@ -1055,7 +1055,7 @@ define fastcc i64 @pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) {
; 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 2 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 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 9 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
@ -1065,7 +1065,7 @@ define fastcc i64 @pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) {
; 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 2 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 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>
; SSE42-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
; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
@ -1075,7 +1075,7 @@ define fastcc i64 @pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) {
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 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>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 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>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = add <4 x i64> %rdx.shuf.0.0, %rdx.shuf.0.1
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX1-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>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 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>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = add <4 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1
; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
@ -1085,7 +1085,7 @@ define fastcc i64 @pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) {
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <4 x i64> %rdx.shuf.0.0, %rdx.shuf.0.1
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX2-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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <4 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1
; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0
@ -1110,7 +1110,7 @@ define fastcc i16 @pairwise_reduction8i16(<8 x i16> %rdx, i16 %f1) {
; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %rdx.shuf.1.0 = shufflevector <8 x i16> %bin.rdx, <8 x i16> 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 5 for instruction: %rdx.shuf.1.1 = shufflevector <8 x i16> %bin.rdx, <8 x i16> 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 1 for instruction: %bin.rdx8 = add <8 x i16> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i16> %bin.rdx8, <8 x i16> 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 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i16> %bin.rdx8, <8 x i16> 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 5 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i16> %bin.rdx8, <8 x i16> 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 1 for instruction: %bin.rdx9 = add <8 x i16> %rdx.shuf.2.0, %rdx.shuf.2.1
; SSE2-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %r = extractelement <8 x i16> %bin.rdx9, i32 0
@ -1123,7 +1123,7 @@ define fastcc i16 @pairwise_reduction8i16(<8 x i16> %rdx, i16 %f1) {
; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <8 x i16> %bin.rdx, <8 x i16> 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 1 for instruction: %rdx.shuf.1.1 = shufflevector <8 x i16> %bin.rdx, <8 x i16> 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 1 for instruction: %bin.rdx8 = add <8 x i16> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i16> %bin.rdx8, <8 x i16> 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 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i16> %bin.rdx8, <8 x i16> 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 1 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i16> %bin.rdx8, <8 x i16> 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 1 for instruction: %bin.rdx9 = add <8 x i16> %rdx.shuf.2.0, %rdx.shuf.2.1
; SSSE3-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %r = extractelement <8 x i16> %bin.rdx9, i32 0
@ -1136,7 +1136,7 @@ define fastcc i16 @pairwise_reduction8i16(<8 x i16> %rdx, i16 %f1) {
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <8 x i16> %bin.rdx, <8 x i16> 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 1 for instruction: %rdx.shuf.1.1 = shufflevector <8 x i16> %bin.rdx, <8 x i16> undef, <8 x i32> <i32 1, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <8 x i16> %rdx.shuf.1.0, %rdx.shuf.1.1
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i16> %bin.rdx8, <8 x i16> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i16> %bin.rdx8, <8 x i16> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i16> %bin.rdx8, <8 x i16> 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 1 for instruction: %bin.rdx9 = add <8 x i16> %rdx.shuf.2.0, %rdx.shuf.2.1
; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <8 x i16> %bin.rdx9, i32 0
@ -1149,7 +1149,7 @@ define fastcc i16 @pairwise_reduction8i16(<8 x i16> %rdx, i16 %f1) {
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <8 x i16> %bin.rdx, <8 x i16> undef, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <8 x i16> %bin.rdx, <8 x i16> undef, <8 x i32> <i32 1, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <8 x i16> %rdx.shuf.1.0, %rdx.shuf.1.1
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i16> %bin.rdx8, <8 x i16> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i16> %bin.rdx8, <8 x i16> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i16> %bin.rdx8, <8 x i16> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx9 = add <8 x i16> %rdx.shuf.2.0, %rdx.shuf.2.1
; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <8 x i16> %bin.rdx9, i32 0
@ -1177,7 +1177,7 @@ define fastcc i32 @pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) {
; 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 4 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 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 14 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
@ -1190,7 +1190,7 @@ define fastcc i32 @pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) {
; 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 4 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 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 14 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
@ -1203,7 +1203,7 @@ define fastcc i32 @pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) {
; 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>
; SSE42-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
; SSE42-NEXT: Cost Model: Found an estimated cost of 2 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>
; SSE42-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>
; SSE42-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>
; SSE42-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
; SSE42-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
@ -1216,7 +1216,7 @@ define fastcc i32 @pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) {
; AVX1-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>
; AVX1-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>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = add <8 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX1-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>
; AVX1-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>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx9 = add <8 x i32> %rdx.shuf.2.0, %rdx.shuf.2.1
; AVX1-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
@ -1229,7 +1229,7 @@ define fastcc i32 @pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) {
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <8 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX2-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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 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>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx9 = add <8 x i32> %rdx.shuf.2.0, %rdx.shuf.2.1
; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0

52
llvm/test/Analysis/CostModel/X86/shuffle-single-src.ll
View File

@ -353,52 +353,16 @@ define void @test_vXi8(<16 x i8> %src128, <32 x i8> %src256, <64 x i8> %src512)
;
define void @identity_vXf32(<4 x float> %a128, <4 x float> %b128, <8 x float> %a256, <8 x float> %b256, <16 x float> %a512, <16 x float> %b512) {
; SSE2-LABEL: 'identity_vXf32'
; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <4 x float> %a128, <4 x float> %b128, <4 x i32> <i32 0, i32 undef, i32 2, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <8 x float> %a256, <8 x float> %b256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 undef, i32 undef, i32 undef, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 undef, i32 2, i32 undef, i32 4, i32 undef, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 undef>
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; SSSE3-LABEL: 'identity_vXf32'
; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <4 x float> %a128, <4 x float> %b128, <4 x i32> <i32 0, i32 undef, i32 2, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <8 x float> %a256, <8 x float> %b256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 undef, i32 undef, i32 undef, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 undef, i32 2, i32 undef, i32 4, i32 undef, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 undef>
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; SSE42-LABEL: 'identity_vXf32'
; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <4 x float> %a128, <4 x float> %b128, <4 x i32> <i32 0, i32 undef, i32 2, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <8 x float> %a256, <8 x float> %b256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 undef, i32 undef, i32 undef, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 undef, i32 2, i32 undef, i32 4, i32 undef, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 undef>
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; XOP-LABEL: 'identity_vXf32'
; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <4 x float> %a128, <4 x float> %b128, <4 x i32> <i32 0, i32 undef, i32 2, i32 undef>
; XOP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <8 x float> %a256, <8 x float> %b256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 undef, i32 undef, i32 undef, i32 undef>
; XOP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 undef, i32 2, i32 undef, i32 4, i32 undef, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 undef>
; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX1-LABEL: 'identity_vXf32'
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <4 x float> %a128, <4 x float> %b128, <4 x i32> <i32 0, i32 undef, i32 2, i32 undef>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <8 x float> %a256, <8 x float> %b256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 undef, i32 2, i32 undef, i32 4, i32 undef, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 undef>
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX2-LABEL: 'identity_vXf32'
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <4 x float> %a128, <4 x float> %b128, <4 x i32> <i32 0, i32 undef, i32 2, i32 undef>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256 = shufflevector <8 x float> %a256, <8 x float> %b256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 undef, i32 2, i32 undef, i32 4, i32 undef, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 undef>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512-LABEL: 'identity_vXf32'
; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <4 x float> %a128, <4 x float> %b128, <4 x i32> <i32 0, i32 undef, i32 2, i32 undef>
; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256 = shufflevector <8 x float> %a256, <8 x float> %b256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 undef, i32 2, i32 undef, i32 4, i32 undef, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 undef>
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
; CHECK-LABEL: 'identity_vXf32'
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V128 = shufflevector <4 x float> %a128, <4 x float> %b128, <4 x i32> <i32 0, i32 undef, i32 2, i32 undef>
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V256 = shufflevector <8 x float> %a256, <8 x float> %b256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 undef, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 undef, i32 2, i32 undef, i32 4, i32 undef, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 undef>
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; BTVER2-LABEL: 'identity_vXf32'
; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <4 x float> %a128, <4 x float> %b128, <4 x i32> <i32 0, i32 undef, i32 2, i32 undef>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <8 x float> %a256, <8 x float> %b256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 undef, i32 undef, i32 undef, i32 undef>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 undef, i32 2, i32 undef, i32 4, i32 undef, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 undef>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V128 = shufflevector <4 x float> %a128, <4 x float> %b128, <4 x i32> <i32 0, i32 undef, i32 2, i32 undef>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V256 = shufflevector <8 x float> %a256, <8 x float> %b256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 undef, i32 undef, i32 undef, i32 undef>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 undef, i32 2, i32 undef, i32 4, i32 undef, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 undef>
; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%V128 = shufflevector <4 x float> %a128, <4 x float> %b128, <4 x i32> <i32 0, i32 undef, i32 2, i32 undef>