[llvm] [CostModel][X86] Add initial costs for non-lane-crossing one/two input shuffles (PR #114680)
Simon Pilgrim via llvm-commits
llvm-commits at lists.llvm.org
Sun Nov 3 04:04:21 PST 2024
https://github.com/RKSimon updated https://github.com/llvm/llvm-project/pull/114680
>From 66c2387a7235698790096fe6370552e64291fccf Mon Sep 17 00:00:00 2001
From: Simon Pilgrim <llvm-dev at redking.me.uk>
Date: Wed, 30 Oct 2024 15:52:58 +0000
Subject: [PATCH] [CostModel][X86] Add initial costs for non-lane-crossing
one/two input shuffles
Most of the x86 shuffle instructions operate within each 128-bit subvector lane, but our shuffle costs struggle to handle this and have to fallback to worst case shuffles that reference elements from any lane.
This patch detects shuffle masks that we know are "inlane" and enable us to assume a cheaper shuffle cost.
---
.../lib/Target/X86/X86TargetTransformInfo.cpp | 66 ++++++++++++++++++
llvm/test/Analysis/CostModel/X86/reduction.ll | 32 ++++-----
.../X86/shuffle-extract_subvector-codesize.ll | 4 +-
.../X86/shuffle-extract_subvector-latency.ll | 4 +-
.../shuffle-extract_subvector-sizelatency.ll | 4 +-
.../X86/shuffle-extract_subvector.ll | 4 +-
.../X86/shuffle-insert_subvector-codesize.ll | 40 +++++------
.../X86/shuffle-insert_subvector-latency.ll | 40 +++++------
.../shuffle-insert_subvector-sizelatency.ll | 40 +++++------
.../CostModel/X86/shuffle-insert_subvector.ll | 40 +++++------
.../X86/shuffle-non-pow-2-codesize.ll | 2 +-
.../X86/shuffle-non-pow-2-latency.ll | 2 +-
.../X86/shuffle-non-pow-2-sizelatency.ll | 2 +-
.../CostModel/X86/shuffle-non-pow-2.ll | 2 +-
.../X86/shuffle-transpose-codesize.ll | 68 ++++++++-----------
.../X86/shuffle-transpose-latency.ll | 68 ++++++++-----------
.../X86/shuffle-transpose-sizelatency.ll | 68 ++++++++-----------
.../CostModel/X86/shuffle-transpose.ll | 68 ++++++++-----------
.../X86/horiz-math-inseltpoison.ll | 7 +-
.../PhaseOrdering/X86/horiz-math.ll | 7 +-
.../X86/alternate-calls-inseltpoison.ll | 10 ++-
.../SLPVectorizer/X86/alternate-calls.ll | 10 ++-
22 files changed, 298 insertions(+), 290 deletions(-)
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 520284d1d7a488..c346eb3beb117d 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -1559,6 +1559,23 @@ InstructionCost X86TTIImpl::getShuffleCost(
return TTI::TCC_Free;
}
+ // Attempt to detect a cheaper inlane shuffle, avoiding 128-bit subvector
+ // permutation.
+ bool IsInLaneShuffle = false;
+ if (BaseTp->getPrimitiveSizeInBits() > 0 &&
+ (BaseTp->getPrimitiveSizeInBits() % 128) == 0 &&
+ Mask.size() == BaseTp->getElementCount().getKnownMinValue()) {
+ unsigned NumLanes = BaseTp->getPrimitiveSizeInBits() / 128;
+ unsigned NumEltsPerLane = Mask.size() / NumLanes;
+ if ((Mask.size() % NumLanes) == 0) {
+ IsInLaneShuffle = true;
+ for (auto [I, M] : enumerate(Mask))
+ if (0 <= M)
+ IsInLaneShuffle &=
+ ((M % Mask.size()) / NumEltsPerLane) == (I / NumEltsPerLane);
+ }
+ }
+
// Treat <X x bfloat> shuffles as <X x half>.
if (LT.second.isVector() && LT.second.getScalarType() == MVT::bf16)
LT.second = LT.second.changeVectorElementType(MVT::f16);
@@ -1897,6 +1914,25 @@ InstructionCost X86TTIImpl::getShuffleCost(
if (auto KindCost = Entry->Cost[CostKind])
return LT.first * *KindCost;
+ static const CostTblEntry AVX2InLaneShuffleTbl[] = {
+ {TTI::SK_PermuteSingleSrc, MVT::v16i16, 1}, // vpshufb
+ {TTI::SK_PermuteSingleSrc, MVT::v16f16, 1}, // vpshufb
+ {TTI::SK_PermuteSingleSrc, MVT::v32i8, 1}, // vpshufb
+
+ {TTI::SK_PermuteTwoSrc, MVT::v4f64, 2}, // 2*vshufpd + vblendpd
+ {TTI::SK_PermuteTwoSrc, MVT::v8f32, 2}, // 2*vshufps + vblendps
+ {TTI::SK_PermuteTwoSrc, MVT::v4i64, 2}, // 2*vpshufd + vpblendd
+ {TTI::SK_PermuteTwoSrc, MVT::v8i32, 2}, // 2*vpshufd + vpblendd
+ {TTI::SK_PermuteTwoSrc, MVT::v16i16, 2}, // 2*vpshufb + vpor
+ {TTI::SK_PermuteTwoSrc, MVT::v16f16, 2}, // 2*vpshufb + vpor
+ {TTI::SK_PermuteTwoSrc, MVT::v32i8, 2}, // 2*vpshufb + vpor
+ };
+
+ if (IsInLaneShuffle && ST->hasAVX2())
+ if (const auto *Entry =
+ CostTableLookup(AVX2InLaneShuffleTbl, Kind, LT.second))
+ return LT.first * Entry->Cost;
+
static const CostTblEntry AVX2ShuffleTbl[] = {
{TTI::SK_Broadcast, MVT::v4f64, 1}, // vbroadcastpd
{TTI::SK_Broadcast, MVT::v8f32, 1}, // vbroadcastps
@@ -1973,6 +2009,36 @@ InstructionCost X86TTIImpl::getShuffleCost(
if (const auto *Entry = CostTableLookup(XOPShuffleTbl, Kind, LT.second))
return LT.first * Entry->Cost;
+ static const CostTblEntry AVX1InLaneShuffleTbl[] = {
+ {TTI::SK_PermuteSingleSrc, MVT::v4f64, 1}, // vpermilpd
+ {TTI::SK_PermuteSingleSrc, MVT::v4i64, 1}, // vpermilpd
+ {TTI::SK_PermuteSingleSrc, MVT::v8f32, 1}, // vpermilps
+ {TTI::SK_PermuteSingleSrc, MVT::v8i32, 1}, // vpermilps
+
+ {TTI::SK_PermuteSingleSrc, MVT::v16i16, 4}, // vextractf128 + 2*pshufb
+ // + vpor + vinsertf128
+ {TTI::SK_PermuteSingleSrc, MVT::v16f16, 4}, // vextractf128 + 2*pshufb
+ // + vpor + vinsertf128
+ {TTI::SK_PermuteSingleSrc, MVT::v32i8, 4}, // vextractf128 + 2*pshufb
+ // + vpor + vinsertf128
+
+ {TTI::SK_PermuteTwoSrc, MVT::v4f64, 2}, // 2*vshufpd + vblendpd
+ {TTI::SK_PermuteTwoSrc, MVT::v8f32, 2}, // 2*vshufps + vblendps
+ {TTI::SK_PermuteTwoSrc, MVT::v4i64, 2}, // 2*vpermilpd + vblendpd
+ {TTI::SK_PermuteTwoSrc, MVT::v8i32, 2}, // 2*vpermilps + vblendps
+ {TTI::SK_PermuteTwoSrc, MVT::v16i16, 9}, // 2*vextractf128 + 4*pshufb
+ // + 2*vpor + vinsertf128
+ {TTI::SK_PermuteTwoSrc, MVT::v16f16, 9}, // 2*vextractf128 + 4*pshufb
+ // + 2*vpor + vinsertf128
+ {TTI::SK_PermuteTwoSrc, MVT::v32i8, 9}, // 2*vextractf128 + 4*pshufb
+ // + 2*vpor + vinsertf128
+ };
+
+ if (IsInLaneShuffle && ST->hasAVX())
+ if (const auto *Entry =
+ CostTableLookup(AVX1InLaneShuffleTbl, Kind, LT.second))
+ return LT.first * Entry->Cost;
+
static const CostTblEntry AVX1ShuffleTbl[] = {
{TTI::SK_Broadcast, MVT::v4f64, 2}, // vperm2f128 + vpermilpd
{TTI::SK_Broadcast, MVT::v8f32, 2}, // vperm2f128 + vpermilps
diff --git a/llvm/test/Analysis/CostModel/X86/reduction.ll b/llvm/test/Analysis/CostModel/X86/reduction.ll
index 9fe127a28320a1..e4686f50d22bcf 100644
--- a/llvm/test/Analysis/CostModel/X86/reduction.ll
+++ b/llvm/test/Analysis/CostModel/X86/reduction.ll
@@ -73,9 +73,9 @@ define fastcc i32 @reduction_cost_int(<8 x i32> %rdx) {
; 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 poison, i32 poison, i32 poison, i32 poison>
; 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 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.2 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; 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 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.3 = shufflevector <8 x i32> %bin.rdx.2, <8 x i32> undef, <8 x i32> <i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; 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
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = extractelement <8 x i32> %bin.rdx.3, i32 0
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
@@ -442,7 +442,7 @@ define fastcc double @no_pairwise_reduction4double(<4 x double> %rdx, double %f1
; AVX1-LABEL: 'no_pairwise_reduction4double'
; AVX1-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 poison, i32 poison>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <4 x double> %rdx, %rdx.shuf
-; AVX1-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 poison, i32 poison, i32 poison>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 1, i32 poison, i32 poison, i32 poison>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <4 x double> %bin.rdx, %rdx.shuf7
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r
@@ -506,9 +506,9 @@ define fastcc float @no_pairwise_reduction8float(<8 x float> %rdx, float %f1) {
; AVX1-LABEL: 'no_pairwise_reduction8float'
; AVX1-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 poison, i32 poison, i32 poison, i32 poison>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx4 = fadd <8 x float> %rdx, %rdx.shuf3
-; AVX1-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 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <8 x float> %bin.rdx4, <8 x float> undef, <8 x i32> <i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <8 x float> %bin.rdx4, %rdx.shuf
-; AVX1-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 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> <i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <8 x float> %bin.rdx, %rdx.shuf7
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
@@ -602,7 +602,7 @@ define fastcc i64 @no_pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) {
; 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 poison, i32 poison>
; 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 poison, i32 poison, i32 poison>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 poison, i32 poison, i32 poison>
; 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 1 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
@@ -708,9 +708,9 @@ define fastcc i32 @no_pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) {
; 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 poison, i32 poison, i32 poison, i32 poison>
; 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 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <8 x i32> %bin.rdx4, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; 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 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = add <8 x i32> %bin.rdx, %rdx.shuf7
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = extractelement <8 x i32> %bin.rdx8, i32 0
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
@@ -888,7 +888,7 @@ define fastcc double @pairwise_reduction4double(<4 x double> %rdx, double %f1) {
; AVX1-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 poison, i32 poison>
; 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 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 0, i32 poison, i32 poison, i32 poison>
-; AVX1-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 poison, i32 poison, i32 poison>
+; AVX1-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 poison, i32 poison, i32 poison>
; 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 0 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r
@@ -968,11 +968,11 @@ 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.0.0 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 poison, i32 poison, i32 poison, i32 poison>
; AVX1-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 poison, i32 poison, i32 poison, i32 poison>
; AVX1-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
-; 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 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; 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 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; AVX1-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 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; AVX1-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 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; 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 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> <i32 0, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; 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 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; AVX1-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 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; 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 0 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r
@@ -1088,7 +1088,7 @@ define fastcc i64 @pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) {
; AVX1-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 poison, i32 poison>
; 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 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 0, i32 poison, i32 poison, i32 poison>
-; AVX1-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 poison, i32 poison, i32 poison>
+; AVX1-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 poison, i32 poison, i32 poison>
; 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 1 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
@@ -1222,11 +1222,11 @@ 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.0.0 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 poison, i32 poison, i32 poison, i32 poison>
; AVX1-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 poison, i32 poison, i32 poison, i32 poison>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = add <8 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1
-; 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 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; 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 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; AVX1-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 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; AVX1-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 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; 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 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> <i32 0, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; 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 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; AVX1-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 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; 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 1 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-codesize.ll b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-codesize.ll
index 91314d39690520..adaae37929ee3b 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-codesize.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-codesize.ll
@@ -452,7 +452,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
@@ -511,7 +511,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-latency.ll b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-latency.ll
index 33431083c68bb3..f2e2b3dd394781 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-latency.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-latency.ll
@@ -452,7 +452,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
@@ -511,7 +511,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-sizelatency.ll b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-sizelatency.ll
index 039758e0b6e384..3117d9c280da16 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-sizelatency.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector-sizelatency.ll
@@ -452,7 +452,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
@@ -511,7 +511,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector.ll b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector.ll
index 6a82a4a7432ef8..e91db1b0cb14a3 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector.ll
@@ -452,7 +452,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
@@ -511,7 +511,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-codesize.ll b/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-codesize.ll
index 1af0b9d0fac69a..7f9a84f0cb0f39 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-codesize.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-codesize.ll
@@ -236,13 +236,13 @@ define void @test_vXf32(<2 x float> %src64, <4 x float> %src128, <8 x float> %sr
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <8 x float> %src256, <8 x float> %src128_256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x float> %src256, <8 x float> %src128_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_01 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512_23 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512_23 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512_67 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_89 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -267,13 +267,13 @@ define void @test_vXf32(<2 x float> %src64, <4 x float> %src128, <8 x float> %sr
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_67 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <8 x float> %src256, <8 x float> %src128_256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x float> %src256, <8 x float> %src128_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_01 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512_23 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512_23 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512_67 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_89 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -457,13 +457,13 @@ define void @test_vXi32(<2 x i32> %src64, <4 x i32> %src128, <8 x i32> %src256,
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x i32> %src128, <4 x i32> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <4 x i32> %src128, <4 x i32> %src64_128, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <8 x i32> %src256, <8 x i32> %src128_256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x i32> %src256, <8 x i32> %src128_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_01 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512_67 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_89 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -488,13 +488,13 @@ define void @test_vXi32(<2 x i32> %src64, <4 x i32> %src128, <8 x i32> %src256,
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x i32> %src128, <4 x i32> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <4 x i32> %src128, <4 x i32> %src64_128, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_67 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <8 x i32> %src256, <8 x i32> %src128_256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x i32> %src256, <8 x i32> %src128_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_01 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512_67 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_89 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -700,15 +700,15 @@ define void @test_vXi16(<2 x i16> %src32, <4 x i16> %src64, <8 x i16> %src128, <
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 17, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -735,15 +735,15 @@ define void @test_vXi16(<2 x i16> %src32, <4 x i16> %src64, <8 x i16> %src128, <
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 17, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -770,15 +770,15 @@ define void @test_vXi16(<2 x i16> %src32, <4 x i16> %src64, <8 x i16> %src128, <
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 17, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-latency.ll b/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-latency.ll
index 7a57e57359e9bb..00248958d18620 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-latency.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-latency.ll
@@ -236,13 +236,13 @@ define void @test_vXf32(<2 x float> %src64, <4 x float> %src128, <8 x float> %sr
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <8 x float> %src256, <8 x float> %src128_256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x float> %src256, <8 x float> %src128_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_01 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512_23 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512_23 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512_67 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_89 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -267,13 +267,13 @@ define void @test_vXf32(<2 x float> %src64, <4 x float> %src128, <8 x float> %sr
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_67 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <8 x float> %src256, <8 x float> %src128_256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x float> %src256, <8 x float> %src128_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_01 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512_23 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512_23 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512_67 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_89 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -457,13 +457,13 @@ define void @test_vXi32(<2 x i32> %src64, <4 x i32> %src128, <8 x i32> %src256,
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x i32> %src128, <4 x i32> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <4 x i32> %src128, <4 x i32> %src64_128, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <8 x i32> %src256, <8 x i32> %src128_256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x i32> %src256, <8 x i32> %src128_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_01 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512_67 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_89 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -488,13 +488,13 @@ define void @test_vXi32(<2 x i32> %src64, <4 x i32> %src128, <8 x i32> %src256,
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x i32> %src128, <4 x i32> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <4 x i32> %src128, <4 x i32> %src64_128, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_67 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <8 x i32> %src256, <8 x i32> %src128_256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x i32> %src256, <8 x i32> %src128_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_01 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512_67 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_89 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -700,15 +700,15 @@ define void @test_vXi16(<2 x i16> %src32, <4 x i16> %src64, <8 x i16> %src128, <
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 17, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -735,15 +735,15 @@ define void @test_vXi16(<2 x i16> %src32, <4 x i16> %src64, <8 x i16> %src128, <
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 17, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -770,15 +770,15 @@ define void @test_vXi16(<2 x i16> %src32, <4 x i16> %src64, <8 x i16> %src128, <
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 17, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-sizelatency.ll b/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-sizelatency.ll
index 20ab11c16bbe05..3845d582f8b111 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-sizelatency.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector-sizelatency.ll
@@ -236,13 +236,13 @@ define void @test_vXf32(<2 x float> %src64, <4 x float> %src128, <8 x float> %sr
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <8 x float> %src256, <8 x float> %src128_256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x float> %src256, <8 x float> %src128_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_01 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512_23 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512_23 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512_67 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_89 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -267,13 +267,13 @@ define void @test_vXf32(<2 x float> %src64, <4 x float> %src128, <8 x float> %sr
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_67 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <8 x float> %src256, <8 x float> %src128_256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x float> %src256, <8 x float> %src128_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_01 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512_23 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512_23 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512_67 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_89 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -457,13 +457,13 @@ define void @test_vXi32(<2 x i32> %src64, <4 x i32> %src128, <8 x i32> %src256,
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x i32> %src128, <4 x i32> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <4 x i32> %src128, <4 x i32> %src64_128, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <8 x i32> %src256, <8 x i32> %src128_256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x i32> %src256, <8 x i32> %src128_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_01 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512_67 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_89 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -488,13 +488,13 @@ define void @test_vXi32(<2 x i32> %src64, <4 x i32> %src128, <8 x i32> %src256,
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x i32> %src128, <4 x i32> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <4 x i32> %src128, <4 x i32> %src64_128, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_67 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <8 x i32> %src256, <8 x i32> %src128_256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x i32> %src256, <8 x i32> %src128_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_01 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512_67 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_89 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -700,15 +700,15 @@ define void @test_vXi16(<2 x i16> %src32, <4 x i16> %src64, <8 x i16> %src128, <
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 17, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -735,15 +735,15 @@ define void @test_vXi16(<2 x i16> %src32, <4 x i16> %src64, <8 x i16> %src128, <
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 17, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -770,15 +770,15 @@ define void @test_vXi16(<2 x i16> %src32, <4 x i16> %src64, <8 x i16> %src128, <
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 17, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector.ll b/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector.ll
index 6f4568c1434684..5082eed6fd8794 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector.ll
@@ -236,13 +236,13 @@ define void @test_vXf32(<2 x float> %src64, <4 x float> %src128, <8 x float> %sr
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <8 x float> %src256, <8 x float> %src128_256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x float> %src256, <8 x float> %src128_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_01 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512_23 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512_23 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512_67 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_89 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -267,13 +267,13 @@ define void @test_vXf32(<2 x float> %src64, <4 x float> %src128, <8 x float> %sr
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <4 x float> %src128, <4 x float> %src64_128, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_67 = shufflevector <8 x float> %src256, <8 x float> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <8 x float> %src256, <8 x float> %src128_256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x float> %src256, <8 x float> %src128_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_01 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512_23 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512_23 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512_67 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_89 = shufflevector <16 x float> %src512, <16 x float> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -457,13 +457,13 @@ define void @test_vXi32(<2 x i32> %src64, <4 x i32> %src128, <8 x i32> %src256,
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x i32> %src128, <4 x i32> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <4 x i32> %src128, <4 x i32> %src64_128, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <8 x i32> %src256, <8 x i32> %src128_256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x i32> %src256, <8 x i32> %src128_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_01 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512_67 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_89 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -488,13 +488,13 @@ define void @test_vXi32(<2 x i32> %src64, <4 x i32> %src128, <8 x i32> %src256,
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <4 x i32> %src128, <4 x i32> %src64_128, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <4 x i32> %src128, <4 x i32> %src64_128, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_67 = shufflevector <8 x i32> %src256, <8 x i32> %src64_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <8 x i32> %src256, <8 x i32> %src128_256, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x i32> %src256, <8 x i32> %src128_256, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512_01 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512_67 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V512_89 = shufflevector <16 x i32> %src512, <16 x i32> %src64_512, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -700,15 +700,15 @@ define void @test_vXi16(<2 x i16> %src32, <4 x i16> %src64, <8 x i16> %src128, <
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 17, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -735,15 +735,15 @@ define void @test_vXi16(<2 x i16> %src32, <4 x i16> %src64, <8 x i16> %src128, <
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 17, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -770,15 +770,15 @@ define void @test_vXi16(<2 x i16> %src32, <4 x i16> %src64, <8 x i16> %src128, <
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 17, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-non-pow-2-codesize.ll b/llvm/test/Analysis/CostModel/X86/shuffle-non-pow-2-codesize.ll
index ad7a9bccfc3f88..2ccb97a9ed7a60 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-non-pow-2-codesize.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-non-pow-2-codesize.ll
@@ -22,7 +22,7 @@ define <12 x i64> @foo(<12 x i64> noundef %src) {
; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <12 x i64> %shuffle
;
; AVX-LABEL: 'foo'
-; AVX-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %shuffle = shufflevector <12 x i64> %src, <12 x i64> poison, <12 x i32> <i32 0, i32 3, i32 6, i32 9, i32 1, i32 4, i32 7, i32 10, i32 2, i32 5, i32 8, i32 11>
+; AVX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %shuffle = shufflevector <12 x i64> %src, <12 x i64> poison, <12 x i32> <i32 0, i32 3, i32 6, i32 9, i32 1, i32 4, i32 7, i32 10, i32 2, i32 5, i32 8, i32 11>
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <12 x i64> %shuffle
;
entry:
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-non-pow-2-latency.ll b/llvm/test/Analysis/CostModel/X86/shuffle-non-pow-2-latency.ll
index 2a9edb89467e80..4eeb4e834d339b 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-non-pow-2-latency.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-non-pow-2-latency.ll
@@ -22,7 +22,7 @@ define <12 x i64> @foo(<12 x i64> noundef %src) {
; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <12 x i64> %shuffle
;
; AVX-LABEL: 'foo'
-; AVX-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %shuffle = shufflevector <12 x i64> %src, <12 x i64> poison, <12 x i32> <i32 0, i32 3, i32 6, i32 9, i32 1, i32 4, i32 7, i32 10, i32 2, i32 5, i32 8, i32 11>
+; AVX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %shuffle = shufflevector <12 x i64> %src, <12 x i64> poison, <12 x i32> <i32 0, i32 3, i32 6, i32 9, i32 1, i32 4, i32 7, i32 10, i32 2, i32 5, i32 8, i32 11>
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <12 x i64> %shuffle
;
entry:
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-non-pow-2-sizelatency.ll b/llvm/test/Analysis/CostModel/X86/shuffle-non-pow-2-sizelatency.ll
index bfaf594e276c3c..13e846950721a0 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-non-pow-2-sizelatency.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-non-pow-2-sizelatency.ll
@@ -22,7 +22,7 @@ define <12 x i64> @foo(<12 x i64> noundef %src) {
; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret <12 x i64> %shuffle
;
; AVX-LABEL: 'foo'
-; AVX-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %shuffle = shufflevector <12 x i64> %src, <12 x i64> poison, <12 x i32> <i32 0, i32 3, i32 6, i32 9, i32 1, i32 4, i32 7, i32 10, i32 2, i32 5, i32 8, i32 11>
+; AVX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %shuffle = shufflevector <12 x i64> %src, <12 x i64> poison, <12 x i32> <i32 0, i32 3, i32 6, i32 9, i32 1, i32 4, i32 7, i32 10, i32 2, i32 5, i32 8, i32 11>
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <12 x i64> %shuffle
;
entry:
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-non-pow-2.ll b/llvm/test/Analysis/CostModel/X86/shuffle-non-pow-2.ll
index 365a678815f189..f27241dfd8cf9e 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-non-pow-2.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-non-pow-2.ll
@@ -22,7 +22,7 @@ define <12 x i64> @foo(<12 x i64> noundef %src) {
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <12 x i64> %shuffle
;
; AVX-LABEL: 'foo'
-; AVX-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %shuffle = shufflevector <12 x i64> %src, <12 x i64> poison, <12 x i32> <i32 0, i32 3, i32 6, i32 9, i32 1, i32 4, i32 7, i32 10, i32 2, i32 5, i32 8, i32 11>
+; AVX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %shuffle = shufflevector <12 x i64> %src, <12 x i64> poison, <12 x i32> <i32 0, i32 3, i32 6, i32 9, i32 1, i32 4, i32 7, i32 10, i32 2, i32 5, i32 8, i32 11>
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <12 x i64> %shuffle
;
entry:
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-transpose-codesize.ll b/llvm/test/Analysis/CostModel/X86/shuffle-transpose-codesize.ll
index 53da7454267777..7783161375916f 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-transpose-codesize.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-transpose-codesize.ll
@@ -25,8 +25,8 @@ define void @test_vXf64(<2 x double> %a128, <2 x double> %b128, <4 x double> %a2
;
; AVX-LABEL: 'test_vXf64'
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <2 x double> %a128, <2 x double> %b128, <2 x i32> <i32 0, i32 2>
-; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <4 x double> %a256, <4 x double> %b256, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512 = shufflevector <8 x double> %a512, <8 x double> %b512, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <4 x double> %a256, <4 x double> %b256, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <8 x double> %a512, <8 x double> %b512, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX512-LABEL: 'test_vXf64'
@@ -50,8 +50,8 @@ define void @test_vXi64(<2 x i64> %a128, <2 x i64> %b128, <4 x i64> %a256, <4 x
;
; AVX-LABEL: 'test_vXi64'
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <2 x i64> %a128, <2 x i64> %b128, <2 x i32> <i32 0, i32 2>
-; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <4 x i64> %a256, <4 x i64> %b256, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512 = shufflevector <8 x i64> %a512, <8 x i64> %b512, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <4 x i64> %a256, <4 x i64> %b256, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <8 x i64> %a512, <8 x i64> %b512, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX512-LABEL: 'test_vXi64'
@@ -74,19 +74,12 @@ define void @test_vXf32(<2 x float> %a64, <2 x float> %b64, <4 x float> %a128, <
; SSE-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
-; AVX1-LABEL: 'test_vXf32'
-; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x float> %a64, <2 x float> %b64, <2 x i32> <i32 0, i32 2>
-; AVX1-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 4, i32 2, i32 6>
-; 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 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX1-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 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
-;
-; AVX2-LABEL: 'test_vXf32'
-; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x float> %a64, <2 x float> %b64, <2 x i32> <i32 0, i32 2>
-; AVX2-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 4, i32 2, i32 6>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <8 x float> %a256, <8 x float> %b256, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+; AVX-LABEL: 'test_vXf32'
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x float> %a64, <2 x float> %b64, <2 x i32> <i32 0, i32 2>
+; AVX-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 4, i32 2, i32 6>
+; AVX-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 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX512-LABEL: 'test_vXf32'
; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <2 x float> %a64, <2 x float> %b64, <2 x i32> <i32 0, i32 2>
@@ -110,19 +103,12 @@ define void @test_vXi32(<2 x i32> %a64, <2 x i32> %b64, <4 x i32> %a128, <4 x i3
; SSE-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V512 = shufflevector <16 x i32> %a512, <16 x i32> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
-; AVX1-LABEL: 'test_vXi32'
-; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x i32> %a64, <2 x i32> %b64, <2 x i32> <i32 0, i32 2>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <4 x i32> %a128, <4 x i32> %b128, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <8 x i32> %a256, <8 x i32> %b256, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512 = shufflevector <16 x i32> %a512, <16 x i32> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
-;
-; AVX2-LABEL: 'test_vXi32'
-; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x i32> %a64, <2 x i32> %b64, <2 x i32> <i32 0, i32 2>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <4 x i32> %a128, <4 x i32> %b128, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <8 x i32> %a256, <8 x i32> %b256, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512 = shufflevector <16 x i32> %a512, <16 x i32> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+; AVX-LABEL: 'test_vXi32'
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x i32> %a64, <2 x i32> %b64, <2 x i32> <i32 0, i32 2>
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <4 x i32> %a128, <4 x i32> %b128, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <8 x i32> %a256, <8 x i32> %b256, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <16 x i32> %a512, <16 x i32> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX512-LABEL: 'test_vXi32'
; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <2 x i32> %a64, <2 x i32> %b64, <2 x i32> <i32 0, i32 2>
@@ -167,23 +153,23 @@ define void @test_vXi16(<2 x i16> %a32, <2 x i16> %b32, <4 x i16> %a64, <4 x i16
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <2 x i16> %a32, <2 x i16> %b32, <2 x i32> <i32 0, i32 2>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <4 x i16> %a64, <4 x i16> %b64, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <8 x i16> %a128, <8 x i16> %b128, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX2-LABEL: 'test_vXi16'
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <2 x i16> %a32, <2 x i16> %b32, <2 x i32> <i32 0, i32 2>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <4 x i16> %a64, <4 x i16> %b64, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <8 x i16> %a128, <8 x i16> %b128, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX512F-LABEL: 'test_vXi16'
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <2 x i16> %a32, <2 x i16> %b32, <2 x i32> <i32 0, i32 2>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <4 x i16> %a64, <4 x i16> %b64, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <8 x i16> %a128, <8 x i16> %b128, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
@@ -244,8 +230,8 @@ define void @test_vXi8(<2 x i8> %a16, <2 x i8> %b16, <4 x i8> %a32, <4 x i8> %b3
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX2-LABEL: 'test_vXi8'
@@ -253,8 +239,8 @@ define void @test_vXi8(<2 x i8> %a16, <2 x i8> %b16, <4 x i8> %a32, <4 x i8> %b3
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX512F-LABEL: 'test_vXi8'
@@ -262,7 +248,7 @@ define void @test_vXi8(<2 x i8> %a16, <2 x i8> %b16, <4 x i8> %a32, <4 x i8> %b3
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
@@ -271,7 +257,7 @@ define void @test_vXi8(<2 x i8> %a16, <2 x i8> %b16, <4 x i8> %a32, <4 x i8> %b3
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-transpose-latency.ll b/llvm/test/Analysis/CostModel/X86/shuffle-transpose-latency.ll
index 93613634d8c6b3..f96bb0d8e6ed09 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-transpose-latency.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-transpose-latency.ll
@@ -25,8 +25,8 @@ define void @test_vXf64(<2 x double> %a128, <2 x double> %b128, <4 x double> %a2
;
; AVX-LABEL: 'test_vXf64'
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <2 x double> %a128, <2 x double> %b128, <2 x i32> <i32 0, i32 2>
-; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <4 x double> %a256, <4 x double> %b256, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512 = shufflevector <8 x double> %a512, <8 x double> %b512, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <4 x double> %a256, <4 x double> %b256, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <8 x double> %a512, <8 x double> %b512, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX512-LABEL: 'test_vXf64'
@@ -50,8 +50,8 @@ define void @test_vXi64(<2 x i64> %a128, <2 x i64> %b128, <4 x i64> %a256, <4 x
;
; AVX-LABEL: 'test_vXi64'
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <2 x i64> %a128, <2 x i64> %b128, <2 x i32> <i32 0, i32 2>
-; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <4 x i64> %a256, <4 x i64> %b256, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512 = shufflevector <8 x i64> %a512, <8 x i64> %b512, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <4 x i64> %a256, <4 x i64> %b256, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <8 x i64> %a512, <8 x i64> %b512, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX512-LABEL: 'test_vXi64'
@@ -74,19 +74,12 @@ define void @test_vXf32(<2 x float> %a64, <2 x float> %b64, <4 x float> %a128, <
; SSE-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
-; AVX1-LABEL: 'test_vXf32'
-; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x float> %a64, <2 x float> %b64, <2 x i32> <i32 0, i32 2>
-; AVX1-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 4, i32 2, i32 6>
-; 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 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX1-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 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
-;
-; AVX2-LABEL: 'test_vXf32'
-; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x float> %a64, <2 x float> %b64, <2 x i32> <i32 0, i32 2>
-; AVX2-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 4, i32 2, i32 6>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <8 x float> %a256, <8 x float> %b256, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+; AVX-LABEL: 'test_vXf32'
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x float> %a64, <2 x float> %b64, <2 x i32> <i32 0, i32 2>
+; AVX-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 4, i32 2, i32 6>
+; AVX-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 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX512-LABEL: 'test_vXf32'
; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <2 x float> %a64, <2 x float> %b64, <2 x i32> <i32 0, i32 2>
@@ -110,19 +103,12 @@ define void @test_vXi32(<2 x i32> %a64, <2 x i32> %b64, <4 x i32> %a128, <4 x i3
; SSE-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V512 = shufflevector <16 x i32> %a512, <16 x i32> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
-; AVX1-LABEL: 'test_vXi32'
-; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x i32> %a64, <2 x i32> %b64, <2 x i32> <i32 0, i32 2>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <4 x i32> %a128, <4 x i32> %b128, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <8 x i32> %a256, <8 x i32> %b256, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512 = shufflevector <16 x i32> %a512, <16 x i32> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
-;
-; AVX2-LABEL: 'test_vXi32'
-; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x i32> %a64, <2 x i32> %b64, <2 x i32> <i32 0, i32 2>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <4 x i32> %a128, <4 x i32> %b128, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <8 x i32> %a256, <8 x i32> %b256, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512 = shufflevector <16 x i32> %a512, <16 x i32> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+; AVX-LABEL: 'test_vXi32'
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x i32> %a64, <2 x i32> %b64, <2 x i32> <i32 0, i32 2>
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <4 x i32> %a128, <4 x i32> %b128, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <8 x i32> %a256, <8 x i32> %b256, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <16 x i32> %a512, <16 x i32> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX512-LABEL: 'test_vXi32'
; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <2 x i32> %a64, <2 x i32> %b64, <2 x i32> <i32 0, i32 2>
@@ -167,23 +153,23 @@ define void @test_vXi16(<2 x i16> %a32, <2 x i16> %b32, <4 x i16> %a64, <4 x i16
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <2 x i16> %a32, <2 x i16> %b32, <2 x i32> <i32 0, i32 2>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <4 x i16> %a64, <4 x i16> %b64, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <8 x i16> %a128, <8 x i16> %b128, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX2-LABEL: 'test_vXi16'
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <2 x i16> %a32, <2 x i16> %b32, <2 x i32> <i32 0, i32 2>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <4 x i16> %a64, <4 x i16> %b64, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <8 x i16> %a128, <8 x i16> %b128, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX512F-LABEL: 'test_vXi16'
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <2 x i16> %a32, <2 x i16> %b32, <2 x i32> <i32 0, i32 2>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <4 x i16> %a64, <4 x i16> %b64, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <8 x i16> %a128, <8 x i16> %b128, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
@@ -244,8 +230,8 @@ define void @test_vXi8(<2 x i8> %a16, <2 x i8> %b16, <4 x i8> %a32, <4 x i8> %b3
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX2-LABEL: 'test_vXi8'
@@ -253,8 +239,8 @@ define void @test_vXi8(<2 x i8> %a16, <2 x i8> %b16, <4 x i8> %a32, <4 x i8> %b3
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX512F-LABEL: 'test_vXi8'
@@ -262,7 +248,7 @@ define void @test_vXi8(<2 x i8> %a16, <2 x i8> %b16, <4 x i8> %a32, <4 x i8> %b3
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
@@ -271,7 +257,7 @@ define void @test_vXi8(<2 x i8> %a16, <2 x i8> %b16, <4 x i8> %a32, <4 x i8> %b3
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-transpose-sizelatency.ll b/llvm/test/Analysis/CostModel/X86/shuffle-transpose-sizelatency.ll
index 0073a294bbbb1c..e9927c61e77417 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-transpose-sizelatency.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-transpose-sizelatency.ll
@@ -25,8 +25,8 @@ define void @test_vXf64(<2 x double> %a128, <2 x double> %b128, <4 x double> %a2
;
; AVX-LABEL: 'test_vXf64'
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <2 x double> %a128, <2 x double> %b128, <2 x i32> <i32 0, i32 2>
-; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <4 x double> %a256, <4 x double> %b256, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512 = shufflevector <8 x double> %a512, <8 x double> %b512, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <4 x double> %a256, <4 x double> %b256, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <8 x double> %a512, <8 x double> %b512, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX512-LABEL: 'test_vXf64'
@@ -50,8 +50,8 @@ define void @test_vXi64(<2 x i64> %a128, <2 x i64> %b128, <4 x i64> %a256, <4 x
;
; AVX-LABEL: 'test_vXi64'
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <2 x i64> %a128, <2 x i64> %b128, <2 x i32> <i32 0, i32 2>
-; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <4 x i64> %a256, <4 x i64> %b256, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512 = shufflevector <8 x i64> %a512, <8 x i64> %b512, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <4 x i64> %a256, <4 x i64> %b256, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <8 x i64> %a512, <8 x i64> %b512, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX512-LABEL: 'test_vXi64'
@@ -74,19 +74,12 @@ define void @test_vXf32(<2 x float> %a64, <2 x float> %b64, <4 x float> %a128, <
; SSE-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
-; AVX1-LABEL: 'test_vXf32'
-; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x float> %a64, <2 x float> %b64, <2 x i32> <i32 0, i32 2>
-; AVX1-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 4, i32 2, i32 6>
-; 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 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX1-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 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
-;
-; AVX2-LABEL: 'test_vXf32'
-; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x float> %a64, <2 x float> %b64, <2 x i32> <i32 0, i32 2>
-; AVX2-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 4, i32 2, i32 6>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <8 x float> %a256, <8 x float> %b256, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+; AVX-LABEL: 'test_vXf32'
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x float> %a64, <2 x float> %b64, <2 x i32> <i32 0, i32 2>
+; AVX-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 4, i32 2, i32 6>
+; AVX-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 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX512-LABEL: 'test_vXf32'
; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <2 x float> %a64, <2 x float> %b64, <2 x i32> <i32 0, i32 2>
@@ -110,19 +103,12 @@ define void @test_vXi32(<2 x i32> %a64, <2 x i32> %b64, <4 x i32> %a128, <4 x i3
; SSE-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V512 = shufflevector <16 x i32> %a512, <16 x i32> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
-; AVX1-LABEL: 'test_vXi32'
-; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x i32> %a64, <2 x i32> %b64, <2 x i32> <i32 0, i32 2>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <4 x i32> %a128, <4 x i32> %b128, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <8 x i32> %a256, <8 x i32> %b256, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512 = shufflevector <16 x i32> %a512, <16 x i32> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
-;
-; AVX2-LABEL: 'test_vXi32'
-; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x i32> %a64, <2 x i32> %b64, <2 x i32> <i32 0, i32 2>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <4 x i32> %a128, <4 x i32> %b128, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <8 x i32> %a256, <8 x i32> %b256, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512 = shufflevector <16 x i32> %a512, <16 x i32> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+; AVX-LABEL: 'test_vXi32'
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x i32> %a64, <2 x i32> %b64, <2 x i32> <i32 0, i32 2>
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <4 x i32> %a128, <4 x i32> %b128, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <8 x i32> %a256, <8 x i32> %b256, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <16 x i32> %a512, <16 x i32> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX512-LABEL: 'test_vXi32'
; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <2 x i32> %a64, <2 x i32> %b64, <2 x i32> <i32 0, i32 2>
@@ -167,23 +153,23 @@ define void @test_vXi16(<2 x i16> %a32, <2 x i16> %b32, <4 x i16> %a64, <4 x i16
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <2 x i16> %a32, <2 x i16> %b32, <2 x i32> <i32 0, i32 2>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <4 x i16> %a64, <4 x i16> %b64, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <8 x i16> %a128, <8 x i16> %b128, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX2-LABEL: 'test_vXi16'
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <2 x i16> %a32, <2 x i16> %b32, <2 x i32> <i32 0, i32 2>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <4 x i16> %a64, <4 x i16> %b64, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <8 x i16> %a128, <8 x i16> %b128, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX512F-LABEL: 'test_vXi16'
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <2 x i16> %a32, <2 x i16> %b32, <2 x i32> <i32 0, i32 2>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <4 x i16> %a64, <4 x i16> %b64, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <8 x i16> %a128, <8 x i16> %b128, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
@@ -244,8 +230,8 @@ define void @test_vXi8(<2 x i8> %a16, <2 x i8> %b16, <4 x i8> %a32, <4 x i8> %b3
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX2-LABEL: 'test_vXi8'
@@ -253,8 +239,8 @@ define void @test_vXi8(<2 x i8> %a16, <2 x i8> %b16, <4 x i8> %a32, <4 x i8> %b3
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
; AVX512F-LABEL: 'test_vXi8'
@@ -262,7 +248,7 @@ define void @test_vXi8(<2 x i8> %a16, <2 x i8> %b16, <4 x i8> %a32, <4 x i8> %b3
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
@@ -271,7 +257,7 @@ define void @test_vXi8(<2 x i8> %a16, <2 x i8> %b16, <4 x i8> %a32, <4 x i8> %b3
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-transpose.ll b/llvm/test/Analysis/CostModel/X86/shuffle-transpose.ll
index db27364684429f..4e32b45f4e4140 100644
--- a/llvm/test/Analysis/CostModel/X86/shuffle-transpose.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-transpose.ll
@@ -25,8 +25,8 @@ define void @test_vXf64(<2 x double> %a128, <2 x double> %b128, <4 x double> %a2
;
; AVX-LABEL: 'test_vXf64'
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <2 x double> %a128, <2 x double> %b128, <2 x i32> <i32 0, i32 2>
-; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <4 x double> %a256, <4 x double> %b256, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512 = shufflevector <8 x double> %a512, <8 x double> %b512, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <4 x double> %a256, <4 x double> %b256, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <8 x double> %a512, <8 x double> %b512, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512-LABEL: 'test_vXf64'
@@ -50,8 +50,8 @@ define void @test_vXi64(<2 x i64> %a128, <2 x i64> %b128, <4 x i64> %a256, <4 x
;
; AVX-LABEL: 'test_vXi64'
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <2 x i64> %a128, <2 x i64> %b128, <2 x i32> <i32 0, i32 2>
-; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <4 x i64> %a256, <4 x i64> %b256, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512 = shufflevector <8 x i64> %a512, <8 x i64> %b512, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <4 x i64> %a256, <4 x i64> %b256, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <8 x i64> %a512, <8 x i64> %b512, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512-LABEL: 'test_vXi64'
@@ -74,19 +74,12 @@ define void @test_vXf32(<2 x float> %a64, <2 x float> %b64, <4 x float> %a128, <
; SSE-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
-; AVX1-LABEL: 'test_vXf32'
-; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x float> %a64, <2 x float> %b64, <2 x i32> <i32 0, i32 2>
-; AVX1-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 4, i32 2, i32 6>
-; 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 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX1-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 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
-;
-; AVX2-LABEL: 'test_vXf32'
-; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x float> %a64, <2 x float> %b64, <2 x i32> <i32 0, i32 2>
-; AVX2-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 4, i32 2, i32 6>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <8 x float> %a256, <8 x float> %b256, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; AVX-LABEL: 'test_vXf32'
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x float> %a64, <2 x float> %b64, <2 x i32> <i32 0, i32 2>
+; AVX-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 4, i32 2, i32 6>
+; AVX-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 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <16 x float> %a512, <16 x float> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512-LABEL: 'test_vXf32'
; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <2 x float> %a64, <2 x float> %b64, <2 x i32> <i32 0, i32 2>
@@ -110,19 +103,12 @@ define void @test_vXi32(<2 x i32> %a64, <2 x i32> %b64, <4 x i32> %a128, <4 x i3
; SSE-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V512 = shufflevector <16 x i32> %a512, <16 x i32> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
-; AVX1-LABEL: 'test_vXi32'
-; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x i32> %a64, <2 x i32> %b64, <2 x i32> <i32 0, i32 2>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <4 x i32> %a128, <4 x i32> %b128, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <8 x i32> %a256, <8 x i32> %b256, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512 = shufflevector <16 x i32> %a512, <16 x i32> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
-;
-; AVX2-LABEL: 'test_vXi32'
-; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x i32> %a64, <2 x i32> %b64, <2 x i32> <i32 0, i32 2>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <4 x i32> %a128, <4 x i32> %b128, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <8 x i32> %a256, <8 x i32> %b256, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512 = shufflevector <16 x i32> %a512, <16 x i32> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; AVX-LABEL: 'test_vXi32'
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <2 x i32> %a64, <2 x i32> %b64, <2 x i32> <i32 0, i32 2>
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <4 x i32> %a128, <4 x i32> %b128, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <8 x i32> %a256, <8 x i32> %b256, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <16 x i32> %a512, <16 x i32> %b512, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512-LABEL: 'test_vXi32'
; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <2 x i32> %a64, <2 x i32> %b64, <2 x i32> <i32 0, i32 2>
@@ -167,23 +153,23 @@ define void @test_vXi16(<2 x i16> %a32, <2 x i16> %b32, <4 x i16> %a64, <4 x i16
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <2 x i16> %a32, <2 x i16> %b32, <2 x i32> <i32 0, i32 2>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <4 x i16> %a64, <4 x i16> %b64, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <8 x i16> %a128, <8 x i16> %b128, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX2-LABEL: 'test_vXi16'
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <2 x i16> %a32, <2 x i16> %b32, <2 x i32> <i32 0, i32 2>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <4 x i16> %a64, <4 x i16> %b64, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <8 x i16> %a128, <8 x i16> %b128, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512F-LABEL: 'test_vXi16'
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <2 x i16> %a32, <2 x i16> %b32, <2 x i32> <i32 0, i32 2>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <4 x i16> %a64, <4 x i16> %b64, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <8 x i16> %a128, <8 x i16> %b128, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
@@ -244,8 +230,8 @@ define void @test_vXi8(<2 x i8> %a16, <2 x i8> %b16, <4 x i8> %a32, <4 x i8> %b3
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
-; AVX1-NEXT: Cost Model: Found an estimated cost of 90 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX2-LABEL: 'test_vXi8'
@@ -253,8 +239,8 @@ define void @test_vXi8(<2 x i8> %a16, <2 x i8> %b16, <4 x i8> %a32, <4 x i8> %b3
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
-; AVX2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512F-LABEL: 'test_vXi8'
@@ -262,7 +248,7 @@ define void @test_vXi8(<2 x i8> %a16, <2 x i8> %b16, <4 x i8> %a32, <4 x i8> %b3
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
@@ -271,7 +257,7 @@ define void @test_vXi8(<2 x i8> %a16, <2 x i8> %b16, <4 x i8> %a32, <4 x i8> %b3
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
diff --git a/llvm/test/Transforms/PhaseOrdering/X86/horiz-math-inseltpoison.ll b/llvm/test/Transforms/PhaseOrdering/X86/horiz-math-inseltpoison.ll
index 324503a30783d1..1d1c9d1f1d18c3 100644
--- a/llvm/test/Transforms/PhaseOrdering/X86/horiz-math-inseltpoison.ll
+++ b/llvm/test/Transforms/PhaseOrdering/X86/horiz-math-inseltpoison.ll
@@ -108,10 +108,11 @@ define <8 x float> @hadd_reverse_v8f32(<8 x float> %a, <8 x float> %b) #0 {
define <8 x float> @reverse_hadd_v8f32(<8 x float> %a, <8 x float> %b) #0 {
; CHECK-LABEL: @reverse_hadd_v8f32(
-; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A:%.*]], <8 x float> [[B:%.*]], <8 x i32> <i32 14, i32 12, i32 6, i32 4, i32 10, i32 8, i32 2, i32 0>
-; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x float> [[A]], <8 x float> [[B]], <8 x i32> <i32 15, i32 13, i32 7, i32 5, i32 11, i32 9, i32 3, i32 1>
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A:%.*]], <8 x float> [[B:%.*]], <8 x i32> <i32 0, i32 2, i32 8, i32 10, i32 4, i32 6, i32 12, i32 14>
+; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x float> [[A]], <8 x float> [[B]], <8 x i32> <i32 1, i32 3, i32 9, i32 11, i32 5, i32 7, i32 13, i32 15>
; CHECK-NEXT: [[TMP3:%.*]] = fadd <8 x float> [[TMP1]], [[TMP2]]
-; CHECK-NEXT: ret <8 x float> [[TMP3]]
+; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <8 x float> [[TMP3]], <8 x float> poison, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; CHECK-NEXT: ret <8 x float> [[SHUFFLE]]
;
%vecext = extractelement <8 x float> %a, i32 0
%vecext1 = extractelement <8 x float> %a, i32 1
diff --git a/llvm/test/Transforms/PhaseOrdering/X86/horiz-math.ll b/llvm/test/Transforms/PhaseOrdering/X86/horiz-math.ll
index 9d3b69218313e8..4f8f04ec42497b 100644
--- a/llvm/test/Transforms/PhaseOrdering/X86/horiz-math.ll
+++ b/llvm/test/Transforms/PhaseOrdering/X86/horiz-math.ll
@@ -108,10 +108,11 @@ define <8 x float> @hadd_reverse_v8f32(<8 x float> %a, <8 x float> %b) #0 {
define <8 x float> @reverse_hadd_v8f32(<8 x float> %a, <8 x float> %b) #0 {
; CHECK-LABEL: @reverse_hadd_v8f32(
-; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A:%.*]], <8 x float> [[B:%.*]], <8 x i32> <i32 14, i32 12, i32 6, i32 4, i32 10, i32 8, i32 2, i32 0>
-; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x float> [[A]], <8 x float> [[B]], <8 x i32> <i32 15, i32 13, i32 7, i32 5, i32 11, i32 9, i32 3, i32 1>
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A:%.*]], <8 x float> [[B:%.*]], <8 x i32> <i32 0, i32 2, i32 8, i32 10, i32 4, i32 6, i32 12, i32 14>
+; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x float> [[A]], <8 x float> [[B]], <8 x i32> <i32 1, i32 3, i32 9, i32 11, i32 5, i32 7, i32 13, i32 15>
; CHECK-NEXT: [[TMP3:%.*]] = fadd <8 x float> [[TMP1]], [[TMP2]]
-; CHECK-NEXT: ret <8 x float> [[TMP3]]
+; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <8 x float> [[TMP3]], <8 x float> poison, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; CHECK-NEXT: ret <8 x float> [[SHUFFLE]]
;
%vecext = extractelement <8 x float> %a, i32 0
%vecext1 = extractelement <8 x float> %a, i32 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/alternate-calls-inseltpoison.ll b/llvm/test/Transforms/SLPVectorizer/X86/alternate-calls-inseltpoison.ll
index 6c21cc1cfc5be8..78dd39be777cda 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/alternate-calls-inseltpoison.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/alternate-calls-inseltpoison.ll
@@ -51,20 +51,18 @@ define <8 x float> @ceil_floor(<8 x float> %a) {
;
; AVX-LABEL: @ceil_floor(
; AVX-NEXT: [[A0:%.*]] = extractelement <8 x float> [[A:%.*]], i64 0
-; AVX-NEXT: [[A1:%.*]] = extractelement <8 x float> [[A]], i64 1
-; AVX-NEXT: [[A2:%.*]] = extractelement <8 x float> [[A]], i64 2
; AVX-NEXT: [[A3:%.*]] = extractelement <8 x float> [[A]], i64 3
; AVX-NEXT: [[AB0:%.*]] = call float @llvm.ceil.f32(float [[A0]])
-; AVX-NEXT: [[AB1:%.*]] = call float @llvm.floor.f32(float [[A1]])
-; AVX-NEXT: [[AB2:%.*]] = call float @llvm.floor.f32(float [[A2]])
+; AVX-NEXT: [[TMP8:%.*]] = shufflevector <8 x float> [[A]], <8 x float> poison, <2 x i32> <i32 1, i32 2>
+; AVX-NEXT: [[TMP9:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP8]])
; AVX-NEXT: [[AB3:%.*]] = call float @llvm.ceil.f32(float [[A3]])
; AVX-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A]], <8 x float> poison, <2 x i32> <i32 4, i32 5>
; AVX-NEXT: [[TMP2:%.*]] = call <2 x float> @llvm.ceil.v2f32(<2 x float> [[TMP1]])
; AVX-NEXT: [[TMP3:%.*]] = shufflevector <8 x float> [[A]], <8 x float> poison, <2 x i32> <i32 6, i32 7>
; AVX-NEXT: [[TMP4:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP3]])
; AVX-NEXT: [[R0:%.*]] = insertelement <8 x float> poison, float [[AB0]], i64 0
-; AVX-NEXT: [[R1:%.*]] = insertelement <8 x float> [[R0]], float [[AB1]], i64 1
-; AVX-NEXT: [[R2:%.*]] = insertelement <8 x float> [[R1]], float [[AB2]], i64 2
+; AVX-NEXT: [[TMP7:%.*]] = shufflevector <2 x float> [[TMP9]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; AVX-NEXT: [[R2:%.*]] = shufflevector <8 x float> [[R0]], <8 x float> [[TMP7]], <8 x i32> <i32 0, i32 8, i32 9, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; AVX-NEXT: [[R3:%.*]] = insertelement <8 x float> [[R2]], float [[AB3]], i64 3
; AVX-NEXT: [[TMP5:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; AVX-NEXT: [[R52:%.*]] = shufflevector <8 x float> [[R3]], <8 x float> [[TMP5]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 poison, i32 poison>
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/alternate-calls.ll b/llvm/test/Transforms/SLPVectorizer/X86/alternate-calls.ll
index bc5bcee361168a..bfa5c56e935adc 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/alternate-calls.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/alternate-calls.ll
@@ -51,20 +51,18 @@ define <8 x float> @ceil_floor(<8 x float> %a) {
;
; AVX-LABEL: @ceil_floor(
; AVX-NEXT: [[A0:%.*]] = extractelement <8 x float> [[A:%.*]], i64 0
-; AVX-NEXT: [[A1:%.*]] = extractelement <8 x float> [[A]], i64 1
-; AVX-NEXT: [[A2:%.*]] = extractelement <8 x float> [[A]], i64 2
; AVX-NEXT: [[A3:%.*]] = extractelement <8 x float> [[A]], i64 3
; AVX-NEXT: [[AB0:%.*]] = call float @llvm.ceil.f32(float [[A0]])
-; AVX-NEXT: [[AB1:%.*]] = call float @llvm.floor.f32(float [[A1]])
-; AVX-NEXT: [[AB2:%.*]] = call float @llvm.floor.f32(float [[A2]])
+; AVX-NEXT: [[TMP8:%.*]] = shufflevector <8 x float> [[A]], <8 x float> poison, <2 x i32> <i32 1, i32 2>
+; AVX-NEXT: [[TMP9:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP8]])
; AVX-NEXT: [[AB3:%.*]] = call float @llvm.ceil.f32(float [[A3]])
; AVX-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A]], <8 x float> poison, <2 x i32> <i32 4, i32 5>
; AVX-NEXT: [[TMP2:%.*]] = call <2 x float> @llvm.ceil.v2f32(<2 x float> [[TMP1]])
; AVX-NEXT: [[TMP3:%.*]] = shufflevector <8 x float> [[A]], <8 x float> poison, <2 x i32> <i32 6, i32 7>
; AVX-NEXT: [[TMP4:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP3]])
; AVX-NEXT: [[R0:%.*]] = insertelement <8 x float> poison, float [[AB0]], i64 0
-; AVX-NEXT: [[R1:%.*]] = insertelement <8 x float> [[R0]], float [[AB1]], i64 1
-; AVX-NEXT: [[R2:%.*]] = insertelement <8 x float> [[R1]], float [[AB2]], i64 2
+; AVX-NEXT: [[TMP7:%.*]] = shufflevector <2 x float> [[TMP9]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; AVX-NEXT: [[R2:%.*]] = shufflevector <8 x float> [[R0]], <8 x float> [[TMP7]], <8 x i32> <i32 0, i32 8, i32 9, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; AVX-NEXT: [[R3:%.*]] = insertelement <8 x float> [[R2]], float [[AB3]], i64 3
; AVX-NEXT: [[TMP5:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; AVX-NEXT: [[R52:%.*]] = shufflevector <8 x float> [[R3]], <8 x float> [[TMP5]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 poison, i32 poison>
More information about the llvm-commits
mailing list