[llvm] 3036547 - Precommit analysis/etc tests for inselt poison placeholder
Juneyoung Lee via llvm-commits
llvm-commits at lists.llvm.org
Wed Dec 23 19:15:56 PST 2020
Author: Juneyoung Lee
Date: 2020-12-24T12:14:24+09:00
New Revision: 3036547248966a7cfc376eed41a0d2d1e9014348
URL: https://github.com/llvm/llvm-project/commit/3036547248966a7cfc376eed41a0d2d1e9014348
DIFF: https://github.com/llvm/llvm-project/commit/3036547248966a7cfc376eed41a0d2d1e9014348.diff
LOG: Precommit analysis/etc tests for inselt poison placeholder
This adds tests in directories missing from https://reviews.llvm.org/rGdb7a2f347f132b3920415013d62d1adfb18d8d58
Added:
llvm/test/Analysis/CostModel/AArch64/kryo-inseltpoison.ll
llvm/test/Analysis/CostModel/PowerPC/insert_extract-inseltpoison.ll
llvm/test/Analysis/CostModel/SystemZ/vectorinstrs-inseltpoison.ll
llvm/test/Analysis/CostModel/X86/insert-extract-at-zero-inseltpoison.ll
llvm/test/Analysis/CostModel/X86/loop_v2-inseltpoison.ll
llvm/test/Analysis/CostModel/X86/masked-intrinsic-cost-inseltpoison.ll
llvm/test/Analysis/CostModel/X86/uniformshift-inseltpoison.ll
llvm/test/Analysis/CostModel/X86/vector-insert-inseltpoison.ll
llvm/test/Analysis/CostModel/X86/vector_gep-inseltpoison.ll
llvm/test/Analysis/CostModel/X86/vshift-ashr-cost-inseltpoison.ll
llvm/test/Analysis/CostModel/X86/vshift-lshr-cost-inseltpoison.ll
llvm/test/Analysis/CostModel/X86/vshift-shl-cost-inseltpoison.ll
llvm/test/Analysis/DemandedBits/vectors-inseltpoison.ll
llvm/test/DebugInfo/X86/stack-value-piece-inseltpoison.ll
Modified:
llvm/test/Other/scalable-vectors-core-ir.ll
Removed:
################################################################################
diff --git a/llvm/test/Analysis/CostModel/AArch64/kryo-inseltpoison.ll b/llvm/test/Analysis/CostModel/AArch64/kryo-inseltpoison.ll
new file mode 100644
index 000000000000..cb9f992f6c88
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AArch64/kryo-inseltpoison.ll
@@ -0,0 +1,26 @@
+; RUN: opt < %s -cost-model -analyze -mcpu=kryo | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
+target triple = "aarch64--linux-gnu"
+
+; CHECK-LABEL: vectorInstrCost
+define void @vectorInstrCost() {
+
+ ; Vector extracts - extracting the first element should have a zero cost;
+ ; all other elements should have a cost of two.
+ ;
+ ; CHECK: cost of 0 {{.*}} extractelement <2 x i64> undef, i32 0
+ ; CHECK: cost of 2 {{.*}} extractelement <2 x i64> undef, i32 1
+ %t1 = extractelement <2 x i64> undef, i32 0
+ %t2 = extractelement <2 x i64> undef, i32 1
+
+ ; Vector inserts - inserting the first element should have a zero cost; all
+ ; other elements should have a cost of two.
+ ;
+ ; CHECK: cost of 0 {{.*}} insertelement <2 x i64> poison, i64 undef, i32 0
+ ; CHECK: cost of 2 {{.*}} insertelement <2 x i64> poison, i64 undef, i32 1
+ %t3 = insertelement <2 x i64> poison, i64 undef, i32 0
+ %t4 = insertelement <2 x i64> poison, i64 undef, i32 1
+
+ ret void
+}
diff --git a/llvm/test/Analysis/CostModel/PowerPC/insert_extract-inseltpoison.ll b/llvm/test/Analysis/CostModel/PowerPC/insert_extract-inseltpoison.ll
new file mode 100644
index 000000000000..c2fc2cd0a90b
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/PowerPC/insert_extract-inseltpoison.ll
@@ -0,0 +1,187 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -cost-model -analyze -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr7 -mattr=+vsx | FileCheck --check-prefix=CHECK-P7 %s
+; RUN: opt < %s -cost-model -analyze -mtriple=powerpc64le-unknown-linux-gnu -mcpu=pwr8 -mattr=+vsx | FileCheck --check-prefix=CHECK-P8LE %s
+; RUN: opt < %s -cost-model -analyze -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr9 -mattr=+vsx | FileCheck --check-prefix=CHECK-P9BE %s
+; RUN: opt < %s -cost-model -analyze -mtriple=powerpc64le-unknown-linux-gnu -mcpu=pwr9 -mattr=+vsx | FileCheck --check-prefix=CHECK-P9LE %s
+
+target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-f128:128:128-v128:128:128-n32:64"
+target triple = "powerpc64-unknown-linux-gnu"
+
+define i32 @insert(i32 %arg) {
+ ; CHECK: cost of 10 {{.*}} insertelement
+; CHECK-P7-LABEL: 'insert'
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %x = insertelement <4 x i32> poison, i32 %arg, i32 0
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; CHECK-P8LE-LABEL: 'insert'
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %x = insertelement <4 x i32> poison, i32 %arg, i32 0
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; CHECK-P9BE-LABEL: 'insert'
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %x = insertelement <4 x i32> poison, i32 %arg, i32 0
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; CHECK-P9LE-LABEL: 'insert'
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %x = insertelement <4 x i32> poison, i32 %arg, i32 0
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+ %x = insertelement <4 x i32> poison, i32 %arg, i32 0
+ ret i32 undef
+}
+
+define i32 @extract(<4 x i32> %arg) {
+ ; CHECK: cost of 3 {{.*}} extractelement
+; CHECK-P7-LABEL: 'extract'
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %x = extractelement <4 x i32> %arg, i32 0
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x
+;
+; CHECK-P8LE-LABEL: 'extract'
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %x = extractelement <4 x i32> %arg, i32 0
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x
+;
+; CHECK-P9BE-LABEL: 'extract'
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <4 x i32> %arg, i32 0
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x
+;
+; CHECK-P9LE-LABEL: 'extract'
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <4 x i32> %arg, i32 0
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x
+;
+ %x = extractelement <4 x i32> %arg, i32 0
+ ret i32 %x
+}
+
+define void @test2xdouble(<2 x double> %arg1) {
+; CHECK-P7-LABEL: 'test2xdouble'
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v1 = extractelement <2 x double> %arg1, i32 0
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2 = extractelement <2 x double> %arg1, i32 1
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; CHECK-P8LE-LABEL: 'test2xdouble'
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v1 = extractelement <2 x double> %arg1, i32 0
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2 = extractelement <2 x double> %arg1, i32 1
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; CHECK-P9BE-LABEL: 'test2xdouble'
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v1 = extractelement <2 x double> %arg1, i32 0
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2 = extractelement <2 x double> %arg1, i32 1
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; CHECK-P9LE-LABEL: 'test2xdouble'
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v1 = extractelement <2 x double> %arg1, i32 0
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2 = extractelement <2 x double> %arg1, i32 1
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+ %v1 = extractelement <2 x double> %arg1, i32 0
+ %v2 = extractelement <2 x double> %arg1, i32 1
+ ret void
+}
+
+define void @test4xi32(<4 x i32> %v1, i32 %x1) {
+; CHECK-P7-LABEL: 'test4xi32'
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; CHECK-P8LE-LABEL: 'test4xi32'
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; CHECK-P9BE-LABEL: 'test4xi32'
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; CHECK-P9LE-LABEL: 'test4xi32'
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+ %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
+ ret void
+}
+
+define void @vexti32(<4 x i32> %p1) {
+; CHECK-P7-LABEL: 'vexti32'
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i1 = extractelement <4 x i32> %p1, i32 0
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i2 = extractelement <4 x i32> %p1, i32 1
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i3 = extractelement <4 x i32> %p1, i32 2
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i4 = extractelement <4 x i32> %p1, i32 3
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; CHECK-P8LE-LABEL: 'vexti32'
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i1 = extractelement <4 x i32> %p1, i32 0
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i2 = extractelement <4 x i32> %p1, i32 1
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i3 = extractelement <4 x i32> %p1, i32 2
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i4 = extractelement <4 x i32> %p1, i32 3
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; CHECK-P9BE-LABEL: 'vexti32'
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i1 = extractelement <4 x i32> %p1, i32 0
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i2 = extractelement <4 x i32> %p1, i32 1
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i3 = extractelement <4 x i32> %p1, i32 2
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i4 = extractelement <4 x i32> %p1, i32 3
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; CHECK-P9LE-LABEL: 'vexti32'
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i1 = extractelement <4 x i32> %p1, i32 0
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i2 = extractelement <4 x i32> %p1, i32 1
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i3 = extractelement <4 x i32> %p1, i32 2
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i4 = extractelement <4 x i32> %p1, i32 3
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+ %i1 = extractelement <4 x i32> %p1, i32 0
+ %i2 = extractelement <4 x i32> %p1, i32 1
+ %i3 = extractelement <4 x i32> %p1, i32 2
+ %i4 = extractelement <4 x i32> %p1, i32 3
+ ret void
+}
+
+define void @vexti64(<2 x i64> %p1) {
+; CHECK-P7-LABEL: 'vexti64'
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i1 = extractelement <2 x i64> %p1, i32 0
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i2 = extractelement <2 x i64> %p1, i32 1
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; CHECK-P8LE-LABEL: 'vexti64'
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i1 = extractelement <2 x i64> %p1, i32 0
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i2 = extractelement <2 x i64> %p1, i32 1
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; CHECK-P9BE-LABEL: 'vexti64'
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i1 = extractelement <2 x i64> %p1, i32 0
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i2 = extractelement <2 x i64> %p1, i32 1
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; CHECK-P9LE-LABEL: 'vexti64'
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i1 = extractelement <2 x i64> %p1, i32 0
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i2 = extractelement <2 x i64> %p1, i32 1
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+ %i1 = extractelement <2 x i64> %p1, i32 0
+ %i2 = extractelement <2 x i64> %p1, i32 1
+ ret void
+}
+
+define void @vext(<8 x i16> %p1, <16 x i8> %p2) {
+; CHECK-P7-LABEL: 'vext'
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i1 = extractelement <8 x i16> %p1, i32 0
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i2 = extractelement <16 x i8> %p2, i32 0
+; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; CHECK-P8LE-LABEL: 'vext'
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i1 = extractelement <8 x i16> %p1, i32 0
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i2 = extractelement <16 x i8> %p2, i32 0
+; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; CHECK-P9BE-LABEL: 'vext'
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i1 = extractelement <8 x i16> %p1, i32 0
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i2 = extractelement <16 x i8> %p2, i32 0
+; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; CHECK-P9LE-LABEL: 'vext'
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i1 = extractelement <8 x i16> %p1, i32 0
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i2 = extractelement <16 x i8> %p2, i32 0
+; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+ %i1 = extractelement <8 x i16> %p1, i32 0
+ %i2 = extractelement <16 x i8> %p2, i32 0
+ ret void
+}
diff --git a/llvm/test/Analysis/CostModel/SystemZ/vectorinstrs-inseltpoison.ll b/llvm/test/Analysis/CostModel/SystemZ/vectorinstrs-inseltpoison.ll
new file mode 100644
index 000000000000..696550a861a5
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/SystemZ/vectorinstrs-inseltpoison.ll
@@ -0,0 +1,56 @@
+; RUN: opt < %s -cost-model -analyze -mtriple=systemz-unknown -mcpu=z13 | FileCheck %s
+
+; CHECK: vecinstrs
+define void @vecinstrs() {
+
+ ;; Extract element is penalized somewhat with a cost of 2 for index 0.
+ extractelement <16 x i8> undef, i32 0
+ extractelement <16 x i8> undef, i32 1
+
+ extractelement <8 x i16> undef, i32 0
+ extractelement <8 x i16> undef, i32 1
+
+ extractelement <4 x i32> undef, i32 0
+ extractelement <4 x i32> undef, i32 1
+
+ extractelement <2 x i64> undef, i32 0
+ extractelement <2 x i64> undef, i32 1
+
+ extractelement <2 x double> undef, i32 0
+ extractelement <2 x double> undef, i32 1
+
+ ; Extraction of i1 means extract + test under mask before branch.
+ extractelement <2 x i1> undef, i32 0
+ extractelement <4 x i1> undef, i32 1
+ extractelement <8 x i1> undef, i32 2
+
+ ;; Insert element
+ insertelement <16 x i8> poison, i8 undef, i32 0
+ insertelement <8 x i16> poison, i16 undef, i32 0
+ insertelement <4 x i32> poison, i32 undef, i32 0
+
+ ; vlvgp will do two grs into a vector register: only add cost half of the time.
+ insertelement <2 x i64> poison, i64 undef, i32 0
+ insertelement <2 x i64> poison, i64 undef, i32 1
+
+ ret void
+
+; CHECK: Cost Model: Found an estimated cost of 2 for instruction: %1 = extractelement <16 x i8> undef, i32 0
+; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %2 = extractelement <16 x i8> undef, i32 1
+; CHECK: Cost Model: Found an estimated cost of 2 for instruction: %3 = extractelement <8 x i16> undef, i32 0
+; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %4 = extractelement <8 x i16> undef, i32 1
+; CHECK: Cost Model: Found an estimated cost of 2 for instruction: %5 = extractelement <4 x i32> undef, i32 0
+; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %6 = extractelement <4 x i32> undef, i32 1
+; CHECK: Cost Model: Found an estimated cost of 2 for instruction: %7 = extractelement <2 x i64> undef, i32 0
+; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %8 = extractelement <2 x i64> undef, i32 1
+; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %9 = extractelement <2 x double> undef, i32 0
+; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %10 = extractelement <2 x double> undef, i32 1
+; CHECK: Cost Model: Found an estimated cost of 3 for instruction: %11 = extractelement <2 x i1> undef, i32 0
+; CHECK: Cost Model: Found an estimated cost of 2 for instruction: %12 = extractelement <4 x i1> undef, i32 1
+; CHECK: Cost Model: Found an estimated cost of 2 for instruction: %13 = extractelement <8 x i1> undef, i32 2
+; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %14 = insertelement <16 x i8> poison, i8 undef, i32 0
+; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %15 = insertelement <8 x i16> poison, i16 undef, i32 0
+; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %16 = insertelement <4 x i32> poison, i32 undef, i32 0
+; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %17 = insertelement <2 x i64> poison, i64 undef, i32 0
+; CHECK: Cost Model: Found an estimated cost of 0 for instruction: %18 = insertelement <2 x i64> poison, i64 undef, i32 1
+}
diff --git a/llvm/test/Analysis/CostModel/X86/insert-extract-at-zero-inseltpoison.ll b/llvm/test/Analysis/CostModel/X86/insert-extract-at-zero-inseltpoison.ll
new file mode 100644
index 000000000000..0d5b07c4c0f8
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/X86/insert-extract-at-zero-inseltpoison.ll
@@ -0,0 +1,40 @@
+; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.8.0"
+
+define i32 @insert-extract-at-zero-idx(i32 %arg, float %fl) {
+ ;CHECK: cost of 0 {{.*}} extract
+ %A = extractelement <4 x float> undef, i32 0
+ ;CHECK: cost of 1 {{.*}} extract
+ %B = extractelement <4 x i32> undef, i32 0
+ ;CHECK: cost of 1 {{.*}} extract
+ %C = extractelement <4 x float> undef, i32 1
+
+ ;CHECK: cost of 0 {{.*}} extract
+ %D = extractelement <8 x float> undef, i32 0
+ ;CHECK: cost of 1 {{.*}} extract
+ %E = extractelement <8 x float> undef, i32 1
+
+ ;CHECK: cost of 1 {{.*}} extract
+ %F = extractelement <8 x float> undef, i32 %arg
+
+ ;CHECK: cost of 0 {{.*}} insert
+ %G = insertelement <4 x float> poison, float %fl, i32 0
+ ;CHECK: cost of 1 {{.*}} insert
+ %H = insertelement <4 x float> poison, float %fl, i32 1
+ ;CHECK: cost of 1 {{.*}} insert
+ %I = insertelement <4 x i32> poison, i32 %arg, i32 0
+
+ ;CHECK: cost of 0 {{.*}} insert
+ %J = insertelement <4 x double> poison, double undef, i32 0
+
+ ;CHECK: cost of 0 {{.*}} insert
+ %K = insertelement <8 x double> poison, double undef, i32 4
+ ;CHECK: cost of 0 {{.*}} insert
+ %L = insertelement <16 x double> poison, double undef, i32 8
+ ;CHECK: cost of 1 {{.*}} insert
+ %M = insertelement <16 x double> poison, double undef, i32 9
+ ret i32 0
+}
+
diff --git a/llvm/test/Analysis/CostModel/X86/loop_v2-inseltpoison.ll b/llvm/test/Analysis/CostModel/X86/loop_v2-inseltpoison.ll
new file mode 100644
index 000000000000..ef411b5235fe
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/X86/loop_v2-inseltpoison.ll
@@ -0,0 +1,39 @@
+; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.9.0"
+
+define i32 @foo(i32* nocapture %A) nounwind uwtable readonly ssp {
+vector.ph:
+ br label %vector.body
+
+vector.body: ; preds = %vector.body, %vector.ph
+ %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
+ %vec.phi = phi <2 x i32> [ zeroinitializer, %vector.ph ], [ %12, %vector.body ]
+ %0 = getelementptr inbounds i32, i32* %A, i64 %index
+ %1 = bitcast i32* %0 to <2 x i32>*
+ %2 = load <2 x i32>, <2 x i32>* %1, align 4
+ %3 = sext <2 x i32> %2 to <2 x i64>
+ ;CHECK: cost of 1 {{.*}} extract
+ %4 = extractelement <2 x i64> %3, i32 0
+ %5 = getelementptr inbounds i32, i32* %A, i64 %4
+ ;CHECK: cost of 1 {{.*}} extract
+ %6 = extractelement <2 x i64> %3, i32 1
+ %7 = getelementptr inbounds i32, i32* %A, i64 %6
+ %8 = load i32, i32* %5, align 4
+ ;CHECK: cost of 1 {{.*}} insert
+ %9 = insertelement <2 x i32> poison, i32 %8, i32 0
+ %10 = load i32, i32* %7, align 4
+ ;CHECK: cost of 1 {{.*}} insert
+ %11 = insertelement <2 x i32> %9, i32 %10, i32 1
+ %12 = add nsw <2 x i32> %11, %vec.phi
+ %index.next = add i64 %index, 2
+ %13 = icmp eq i64 %index.next, 192
+ br i1 %13, label %for.end, label %vector.body
+
+for.end: ; preds = %vector.body
+ %14 = extractelement <2 x i32> %12, i32 0
+ %15 = extractelement <2 x i32> %12, i32 1
+ %16 = add i32 %14, %15
+ ret i32 %16
+}
diff --git a/llvm/test/Analysis/CostModel/X86/masked-intrinsic-cost-inseltpoison.ll b/llvm/test/Analysis/CostModel/X86/masked-intrinsic-cost-inseltpoison.ll
new file mode 100644
index 000000000000..0f6f6e2177da
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/X86/masked-intrinsic-cost-inseltpoison.ll
@@ -0,0 +1,1911 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mattr=+sse2 -cost-model -analyze | FileCheck %s --check-prefixes=SSE2
+; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mattr=+sse4.2 -cost-model -analyze | FileCheck %s --check-prefixes=SSE42
+; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mattr=+avx -cost-model -analyze | FileCheck %s --check-prefixes=AVX,AVX1
+; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mattr=+avx2 -cost-model -analyze | FileCheck %s --check-prefixes=AVX,AVX2
+;
+; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mcpu=skylake -cost-model -analyze | FileCheck %s --check-prefixes=AVX,SKL
+; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mcpu=knl -cost-model -analyze | FileCheck %s --check-prefixes=AVX512,KNL
+; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mcpu=skx -cost-model -analyze | FileCheck %s --check-prefixes=AVX512,SKX
+
+define i32 @masked_load() {
+; SSE2-LABEL: 'masked_load'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %V8F64 = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V4F64 = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2F64 = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F64 = call <1 x double> @llvm.masked.load.v1f64.p0v1f64(<1 x double>* undef, i32 1, <1 x i1> undef, <1 x double> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 75 for instruction: %V16F32 = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V8F32 = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V4F32 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2F32 = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 43 for instruction: %V8I64 = call <8 x i64> @llvm.masked.load.v8i64.p0v8i64(<8 x i64>* undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V4I64 = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I64 = call <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64>* undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1I64 = call <1 x i64> @llvm.masked.load.v1i64.p0v1i64(<1 x i64>* undef, i32 1, <1 x i1> undef, <1 x i64> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 91 for instruction: %V16I32 = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %V8I32 = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V4I32 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V2I32 = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 158 for instruction: %V32I16 = call <32 x i16> @llvm.masked.load.v32i16.p0v32i16(<32 x i16>* undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %V16I16 = call <16 x i16> @llvm.masked.load.v16i16.p0v16i16(<16 x i16>* undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 39 for instruction: %V8I16 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V4I16 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 376 for instruction: %V64I8 = call <64 x i8> @llvm.masked.load.v64i8.p0v64i8(<64 x i8>* undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 188 for instruction: %V32I8 = call <32 x i8> @llvm.masked.load.v32i8.p0v32i8(<32 x i8>* undef, i32 1, <32 x i1> undef, <32 x i8> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 94 for instruction: %V16I8 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* undef, i32 1, <16 x i1> undef, <16 x i8> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V8I8 = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* undef, i32 1, <8 x i1> undef, <8 x i8> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; SSE42-LABEL: 'masked_load'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V8F64 = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V4F64 = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2F64 = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F64 = call <1 x double> @llvm.masked.load.v1f64.p0v1f64(<1 x double>* undef, i32 1, <1 x i1> undef, <1 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %V16F32 = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V8F32 = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V4F32 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2F32 = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I64 = call <8 x i64> @llvm.masked.load.v8i64.p0v8i64(<8 x i64>* undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64>* undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1I64 = call <1 x i64> @llvm.masked.load.v1i64.p0v1i64(<1 x i64>* undef, i32 1, <1 x i1> undef, <1 x i64> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16I32 = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I32 = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I32 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I32 = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V32I16 = call <32 x i16> @llvm.masked.load.v32i16.p0v32i16(<32 x i16>* undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16I16 = call <16 x i16> @llvm.masked.load.v16i16.p0v16i16(<16 x i16>* undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I16 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I16 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V64I8 = call <64 x i8> @llvm.masked.load.v64i8.p0v64i8(<64 x i8>* undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V32I8 = call <32 x i8> @llvm.masked.load.v32i8.p0v32i8(<32 x i8>* undef, i32 1, <32 x i1> undef, <32 x i8> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16I8 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* undef, i32 1, <16 x i1> undef, <16 x i8> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I8 = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* undef, i32 1, <8 x i1> undef, <8 x i8> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; AVX-LABEL: 'masked_load'
+; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F64 = call <1 x double> @llvm.masked.load.v1f64.p0v1f64(<1 x double>* undef, i32 1, <1 x i1> undef, <1 x double> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2F32 = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call <8 x i64> @llvm.masked.load.v8i64.p0v8i64(<8 x i64>* undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64>* undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1I64 = call <1 x i64> @llvm.masked.load.v1i64.p0v1i64(<1 x i64>* undef, i32 1, <1 x i1> undef, <1 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I32 = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 148 for instruction: %V32I16 = call <32 x i16> @llvm.masked.load.v32i16.p0v32i16(<32 x i16>* undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V16I16 = call <16 x i16> @llvm.masked.load.v16i16.p0v16i16(<16 x i16>* undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I16 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I16 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 292 for instruction: %V64I8 = call <64 x i8> @llvm.masked.load.v64i8.p0v64i8(<64 x i8>* undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 146 for instruction: %V32I8 = call <32 x i8> @llvm.masked.load.v32i8.p0v32i8(<32 x i8>* undef, i32 1, <32 x i1> undef, <32 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16I8 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* undef, i32 1, <16 x i1> undef, <16 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I8 = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* undef, i32 1, <8 x i1> undef, <8 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; KNL-LABEL: 'masked_load'
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F64 = call <1 x double> @llvm.masked.load.v1f64.p0v1f64(<1 x double>* undef, i32 1, <1 x i1> undef, <1 x double> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2F32 = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.masked.load.v8i64.p0v8i64(<8 x i64>* undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64>* undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1I64 = call <1 x i64> @llvm.masked.load.v1i64.p0v1i64(<1 x i64>* undef, i32 1, <1 x i1> undef, <1 x i64> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2I32 = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 148 for instruction: %V32I16 = call <32 x i16> @llvm.masked.load.v32i16.p0v32i16(<32 x i16>* undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V16I16 = call <16 x i16> @llvm.masked.load.v16i16.p0v16i16(<16 x i16>* undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I16 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I16 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 308 for instruction: %V64I8 = call <64 x i8> @llvm.masked.load.v64i8.p0v64i8(<64 x i8>* undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 146 for instruction: %V32I8 = call <32 x i8> @llvm.masked.load.v32i8.p0v32i8(<32 x i8>* undef, i32 1, <32 x i1> undef, <32 x i8> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16I8 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* undef, i32 1, <16 x i1> undef, <16 x i8> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I8 = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* undef, i32 1, <8 x i1> undef, <8 x i8> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; SKX-LABEL: 'masked_load'
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F64 = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F64 = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F64 = call <1 x double> @llvm.masked.load.v1f64.p0v1f64(<1 x double>* undef, i32 1, <1 x i1> undef, <1 x double> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16F32 = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8F32 = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2F32 = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.masked.load.v8i64.p0v8i64(<8 x i64>* undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64>* undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1I64 = call <1 x i64> @llvm.masked.load.v1i64.p0v1i64(<1 x i64>* undef, i32 1, <1 x i1> undef, <1 x i64> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2I32 = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = call <32 x i16> @llvm.masked.load.v32i16.p0v32i16(<32 x i16>* undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.masked.load.v16i16.p0v16i16(<16 x i16>* undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V4I16 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = call <64 x i8> @llvm.masked.load.v64i8.p0v64i8(<64 x i8>* undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.masked.load.v32i8.p0v32i8(<32 x i8>* undef, i32 1, <32 x i1> undef, <32 x i8> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* undef, i32 1, <16 x i1> undef, <16 x i8> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V8I8 = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* undef, i32 1, <8 x i1> undef, <8 x i8> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+ %V8F64 = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* undef, i32 1, <8 x i1> undef, <8 x double> undef)
+ %V4F64 = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* undef, i32 1, <4 x i1> undef, <4 x double> undef)
+ %V2F64 = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* undef, i32 1, <2 x i1> undef, <2 x double> undef)
+ %V1F64 = call <1 x double> @llvm.masked.load.v1f64.p0v1f64(<1 x double>* undef, i32 1, <1 x i1> undef, <1 x double> undef)
+
+ %V16F32 = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* undef, i32 1, <16 x i1> undef, <16 x float> undef)
+ %V8F32 = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* undef, i32 1, <8 x i1> undef, <8 x float> undef)
+ %V4F32 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* undef, i32 1, <4 x i1> undef, <4 x float> undef)
+ %V2F32 = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* undef, i32 1, <2 x i1> undef, <2 x float> undef)
+
+ %V8I64 = call <8 x i64> @llvm.masked.load.v8i64.p0v8i64(<8 x i64>* undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+ %V4I64 = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+ %V2I64 = call <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64>* undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+ %V1I64 = call <1 x i64> @llvm.masked.load.v1i64.p0v1i64(<1 x i64>* undef, i32 1, <1 x i1> undef, <1 x i64> undef)
+
+ %V16I32 = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+ %V8I32 = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+ %V4I32 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+ %V2I32 = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+
+ %V32I16 = call <32 x i16> @llvm.masked.load.v32i16.p0v32i16(<32 x i16>* undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+ %V16I16 = call <16 x i16> @llvm.masked.load.v16i16.p0v16i16(<16 x i16>* undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+ %V8I16 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+ %V4I16 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+
+ %V64I8 = call <64 x i8> @llvm.masked.load.v64i8.p0v64i8(<64 x i8>* undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+ %V32I8 = call <32 x i8> @llvm.masked.load.v32i8.p0v32i8(<32 x i8>* undef, i32 1, <32 x i1> undef, <32 x i8> undef)
+ %V16I8 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* undef, i32 1, <16 x i1> undef, <16 x i8> undef)
+ %V8I8 = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* undef, i32 1, <8 x i1> undef, <8 x i8> undef)
+
+ ret i32 0
+}
+
+define i32 @masked_store() {
+; SSE2-LABEL: 'masked_store'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 35 for instruction: call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> undef, <8 x double>* undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> undef, <4 x double>* undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2f64.p0v2f64(<2 x double> undef, <2 x double>* undef, i32 1, <2 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1f64.p0v1f64(<1 x double> undef, <1 x double>* undef, i32 1, <1 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 75 for instruction: call void @llvm.masked.store.v16f32.p0v16f32(<16 x float> undef, <16 x float>* undef, i32 1, <16 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 37 for instruction: call void @llvm.masked.store.v8f32.p0v8f32(<8 x float> undef, <8 x float>* undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> undef, <4 x float>* undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> undef, <2 x float>* undef, i32 1, <2 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 43 for instruction: call void @llvm.masked.store.v8i64.p0v8i64(<8 x i64> undef, <8 x i64>* undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: call void @llvm.masked.store.v4i64.p0v4i64(<4 x i64> undef, <4 x i64>* undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.store.v2i64.p0v2i64(<2 x i64> undef, <2 x i64>* undef, i32 1, <2 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1i64.p0v1i64(<1 x i64> undef, <1 x i64>* undef, i32 1, <1 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 91 for instruction: call void @llvm.masked.store.v16i32.p0v16i32(<16 x i32> undef, <16 x i32>* undef, i32 1, <16 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 45 for instruction: call void @llvm.masked.store.v8i32.p0v8i32(<8 x i32> undef, <8 x i32>* undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> undef, <4 x i32>* undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> undef, <2 x i32>* undef, i32 1, <2 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 158 for instruction: call void @llvm.masked.store.v32i16.p0v32i16(<32 x i16> undef, <32 x i16>* undef, i32 1, <32 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 79 for instruction: call void @llvm.masked.store.v16i16.p0v16i16(<16 x i16> undef, <16 x i16>* undef, i32 1, <16 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 39 for instruction: call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> undef, <8 x i16>* undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: call void @llvm.masked.store.v4i16.p0v4i16(<4 x i16> undef, <4 x i16>* undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 376 for instruction: call void @llvm.masked.store.v64i8.p0v64i8(<64 x i8> undef, <64 x i8>* undef, i32 1, <64 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 188 for instruction: call void @llvm.masked.store.v32i8.p0v32i8(<32 x i8> undef, <32 x i8>* undef, i32 1, <32 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 94 for instruction: call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> undef, <16 x i8>* undef, i32 1, <16 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 46 for instruction: call void @llvm.masked.store.v8i8.p0v8i8(<8 x i8> undef, <8 x i8>* undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; SSE42-LABEL: 'masked_store'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> undef, <8 x double>* undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> undef, <4 x double>* undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.store.v2f64.p0v2f64(<2 x double> undef, <2 x double>* undef, i32 1, <2 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1f64.p0v1f64(<1 x double> undef, <1 x double>* undef, i32 1, <1 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 60 for instruction: call void @llvm.masked.store.v16f32.p0v16f32(<16 x float> undef, <16 x float>* undef, i32 1, <16 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.store.v8f32.p0v8f32(<8 x float> undef, <8 x float>* undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 15 for instruction: call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> undef, <4 x float>* undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> undef, <2 x float>* undef, i32 1, <2 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.store.v8i64.p0v8i64(<8 x i64> undef, <8 x i64>* undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v4i64.p0v4i64(<4 x i64> undef, <4 x i64>* undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2i64.p0v2i64(<2 x i64> undef, <2 x i64>* undef, i32 1, <2 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1i64.p0v1i64(<1 x i64> undef, <1 x i64>* undef, i32 1, <1 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.store.v16i32.p0v16i32(<16 x i32> undef, <16 x i32>* undef, i32 1, <16 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.store.v8i32.p0v8i32(<8 x i32> undef, <8 x i32>* undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> undef, <4 x i32>* undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> undef, <2 x i32>* undef, i32 1, <2 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.store.v32i16.p0v32i16(<32 x i16> undef, <32 x i16>* undef, i32 1, <32 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.store.v16i16.p0v16i16(<16 x i16> undef, <16 x i16>* undef, i32 1, <16 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> undef, <8 x i16>* undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v4i16.p0v4i16(<4 x i16> undef, <4 x i16>* undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 256 for instruction: call void @llvm.masked.store.v64i8.p0v64i8(<64 x i8> undef, <64 x i8>* undef, i32 1, <64 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.store.v32i8.p0v32i8(<32 x i8> undef, <32 x i8>* undef, i32 1, <32 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> undef, <16 x i8>* undef, i32 1, <16 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.store.v8i8.p0v8i8(<8 x i8> undef, <8 x i8>* undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; AVX-LABEL: 'masked_store'
+; AVX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> undef, <8 x double>* undef, i32 1, <8 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> undef, <4 x double>* undef, i32 1, <4 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2f64.p0v2f64(<2 x double> undef, <2 x double>* undef, i32 1, <2 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1f64.p0v1f64(<1 x double> undef, <1 x double>* undef, i32 1, <1 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v16f32.p0v16f32(<16 x float> undef, <16 x float>* undef, i32 1, <16 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v8f32.p0v8f32(<8 x float> undef, <8 x float>* undef, i32 1, <8 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> undef, <4 x float>* undef, i32 1, <4 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> undef, <2 x float>* undef, i32 1, <2 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v8i64.p0v8i64(<8 x i64> undef, <8 x i64>* undef, i32 1, <8 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v4i64.p0v4i64(<4 x i64> undef, <4 x i64>* undef, i32 1, <4 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2i64.p0v2i64(<2 x i64> undef, <2 x i64>* undef, i32 1, <2 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1i64.p0v1i64(<1 x i64> undef, <1 x i64>* undef, i32 1, <1 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v16i32.p0v16i32(<16 x i32> undef, <16 x i32>* undef, i32 1, <16 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v8i32.p0v8i32(<8 x i32> undef, <8 x i32>* undef, i32 1, <8 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> undef, <4 x i32>* undef, i32 1, <4 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> undef, <2 x i32>* undef, i32 1, <2 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.store.v32i16.p0v32i16(<32 x i16> undef, <32 x i16>* undef, i32 1, <32 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.store.v16i16.p0v16i16(<16 x i16> undef, <16 x i16>* undef, i32 1, <16 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> undef, <8 x i16>* undef, i32 1, <8 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v4i16.p0v4i16(<4 x i16> undef, <4 x i16>* undef, i32 1, <4 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 320 for instruction: call void @llvm.masked.store.v64i8.p0v64i8(<64 x i8> undef, <64 x i8>* undef, i32 1, <64 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.store.v32i8.p0v32i8(<32 x i8> undef, <32 x i8>* undef, i32 1, <32 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> undef, <16 x i8>* undef, i32 1, <16 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.store.v8i8.p0v8i8(<8 x i8> undef, <8 x i8>* undef, i32 1, <8 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; KNL-LABEL: 'masked_store'
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> undef, <8 x double>* undef, i32 1, <8 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> undef, <4 x double>* undef, i32 1, <4 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v2f64.p0v2f64(<2 x double> undef, <2 x double>* undef, i32 1, <2 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1f64.p0v1f64(<1 x double> undef, <1 x double>* undef, i32 1, <1 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v16f32.p0v16f32(<16 x float> undef, <16 x float>* undef, i32 1, <16 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v8f32.p0v8f32(<8 x float> undef, <8 x float>* undef, i32 1, <8 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> undef, <4 x float>* undef, i32 1, <4 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> undef, <2 x float>* undef, i32 1, <2 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v8i64.p0v8i64(<8 x i64> undef, <8 x i64>* undef, i32 1, <8 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4i64.p0v4i64(<4 x i64> undef, <4 x i64>* undef, i32 1, <4 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v2i64.p0v2i64(<2 x i64> undef, <2 x i64>* undef, i32 1, <2 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1i64.p0v1i64(<1 x i64> undef, <1 x i64>* undef, i32 1, <1 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v16i32.p0v16i32(<16 x i32> undef, <16 x i32>* undef, i32 1, <16 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v8i32.p0v8i32(<8 x i32> undef, <8 x i32>* undef, i32 1, <8 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> undef, <4 x i32>* undef, i32 1, <4 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> undef, <2 x i32>* undef, i32 1, <2 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 168 for instruction: call void @llvm.masked.store.v32i16.p0v32i16(<32 x i16> undef, <32 x i16>* undef, i32 1, <32 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.store.v16i16.p0v16i16(<16 x i16> undef, <16 x i16>* undef, i32 1, <16 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> undef, <8 x i16>* undef, i32 1, <8 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v4i16.p0v4i16(<4 x i16> undef, <4 x i16>* undef, i32 1, <4 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 352 for instruction: call void @llvm.masked.store.v64i8.p0v64i8(<64 x i8> undef, <64 x i8>* undef, i32 1, <64 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.store.v32i8.p0v32i8(<32 x i8> undef, <32 x i8>* undef, i32 1, <32 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> undef, <16 x i8>* undef, i32 1, <16 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.store.v8i8.p0v8i8(<8 x i8> undef, <8 x i8>* undef, i32 1, <8 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; SKX-LABEL: 'masked_store'
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> undef, <8 x double>* undef, i32 1, <8 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> undef, <4 x double>* undef, i32 1, <4 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v2f64.p0v2f64(<2 x double> undef, <2 x double>* undef, i32 1, <2 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1f64.p0v1f64(<1 x double> undef, <1 x double>* undef, i32 1, <1 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v16f32.p0v16f32(<16 x float> undef, <16 x float>* undef, i32 1, <16 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v8f32.p0v8f32(<8 x float> undef, <8 x float>* undef, i32 1, <8 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> undef, <4 x float>* undef, i32 1, <4 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> undef, <2 x float>* undef, i32 1, <2 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v8i64.p0v8i64(<8 x i64> undef, <8 x i64>* undef, i32 1, <8 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4i64.p0v4i64(<4 x i64> undef, <4 x i64>* undef, i32 1, <4 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v2i64.p0v2i64(<2 x i64> undef, <2 x i64>* undef, i32 1, <2 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.masked.store.v1i64.p0v1i64(<1 x i64> undef, <1 x i64>* undef, i32 1, <1 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v16i32.p0v16i32(<16 x i32> undef, <16 x i32>* undef, i32 1, <16 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v8i32.p0v8i32(<8 x i32> undef, <8 x i32>* undef, i32 1, <8 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> undef, <4 x i32>* undef, i32 1, <4 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> undef, <2 x i32>* undef, i32 1, <2 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v32i16.p0v32i16(<32 x i16> undef, <32 x i16>* undef, i32 1, <32 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v16i16.p0v16i16(<16 x i16> undef, <16 x i16>* undef, i32 1, <16 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> undef, <8 x i16>* undef, i32 1, <8 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.store.v4i16.p0v4i16(<4 x i16> undef, <4 x i16>* undef, i32 1, <4 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v64i8.p0v64i8(<64 x i8> undef, <64 x i8>* undef, i32 1, <64 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v32i8.p0v32i8(<32 x i8> undef, <32 x i8>* undef, i32 1, <32 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> undef, <16 x i8>* undef, i32 1, <16 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.store.v8i8.p0v8i8(<8 x i8> undef, <8 x i8>* undef, i32 1, <8 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+ call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> undef, <8 x double>* undef, i32 1, <8 x i1> undef)
+ call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> undef, <4 x double>* undef, i32 1, <4 x i1> undef)
+ call void @llvm.masked.store.v2f64.p0v2f64(<2 x double> undef, <2 x double>* undef, i32 1, <2 x i1> undef)
+ call void @llvm.masked.store.v1f64.p0v1f64(<1 x double> undef, <1 x double>* undef, i32 1, <1 x i1> undef)
+
+ call void @llvm.masked.store.v16f32.p0v16f32(<16 x float> undef, <16 x float>* undef, i32 1, <16 x i1> undef)
+ call void @llvm.masked.store.v8f32.p0v8f32(<8 x float> undef, <8 x float>* undef, i32 1, <8 x i1> undef)
+ call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> undef, <4 x float>* undef, i32 1, <4 x i1> undef)
+ call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> undef, <2 x float>* undef, i32 1, <2 x i1> undef)
+
+ call void @llvm.masked.store.v8i64.p0v8i64(<8 x i64> undef, <8 x i64>* undef, i32 1, <8 x i1> undef)
+ call void @llvm.masked.store.v4i64.p0v4i64(<4 x i64> undef, <4 x i64>* undef, i32 1, <4 x i1> undef)
+ call void @llvm.masked.store.v2i64.p0v2i64(<2 x i64> undef, <2 x i64>* undef, i32 1, <2 x i1> undef)
+ call void @llvm.masked.store.v1i64.p0v1i64(<1 x i64> undef, <1 x i64>* undef, i32 1, <1 x i1> undef)
+
+ call void @llvm.masked.store.v16i32.p0v16i32(<16 x i32> undef, <16 x i32>* undef, i32 1, <16 x i1> undef)
+ call void @llvm.masked.store.v8i32.p0v8i32(<8 x i32> undef, <8 x i32>* undef, i32 1, <8 x i1> undef)
+ call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> undef, <4 x i32>* undef, i32 1, <4 x i1> undef)
+ call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> undef, <2 x i32>* undef, i32 1, <2 x i1> undef)
+
+ call void @llvm.masked.store.v32i16.p0v32i16(<32 x i16> undef, <32 x i16>* undef, i32 1, <32 x i1> undef)
+ call void @llvm.masked.store.v16i16.p0v16i16(<16 x i16> undef, <16 x i16>* undef, i32 1, <16 x i1> undef)
+ call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> undef, <8 x i16>* undef, i32 1, <8 x i1> undef)
+ call void @llvm.masked.store.v4i16.p0v4i16(<4 x i16> undef, <4 x i16>* undef, i32 1, <4 x i1> undef)
+
+ call void @llvm.masked.store.v64i8.p0v64i8(<64 x i8> undef, <64 x i8>* undef, i32 1, <64 x i1> undef)
+ call void @llvm.masked.store.v32i8.p0v32i8(<32 x i8> undef, <32 x i8>* undef, i32 1, <32 x i1> undef)
+ call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> undef, <16 x i8>* undef, i32 1, <16 x i1> undef)
+ call void @llvm.masked.store.v8i8.p0v8i8(<8 x i8> undef, <8 x i8>* undef, i32 1, <8 x i1> undef)
+
+ ret i32 0
+}
+
+define i32 @masked_gather() {
+; SSE2-LABEL: 'masked_gather'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 960 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 480 for instruction: %V32I8 = call <32 x i8> @llvm.masked.gather.v32i8.v32p0i8(<32 x i8*> undef, i32 1, <32 x i1> undef, <32 x i8> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 240 for instruction: %V16I8 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> undef, i32 1, <16 x i1> undef, <16 x i8> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %V8I8 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> undef, i32 1, <8 x i1> undef, <8 x i8> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; SSE42-LABEL: 'masked_gather'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I8 = call <32 x i8> @llvm.masked.gather.v32i8.v32p0i8(<32 x i8*> undef, i32 1, <32 x i1> undef, <32 x i8> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> undef, i32 1, <16 x i1> undef, <16 x i8> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> undef, i32 1, <8 x i1> undef, <8 x i8> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; AVX1-LABEL: 'masked_gather'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V32I8 = call <32 x i8> @llvm.masked.gather.v32i8.v32p0i8(<32 x i8*> undef, i32 1, <32 x i1> undef, <32 x i8> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> undef, i32 1, <16 x i1> undef, <16 x i8> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> undef, i32 1, <8 x i1> undef, <8 x i8> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; AVX2-LABEL: 'masked_gather'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V32I8 = call <32 x i8> @llvm.masked.gather.v32i8.v32p0i8(<32 x i8*> undef, i32 1, <32 x i1> undef, <32 x i8> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> undef, i32 1, <16 x i1> undef, <16 x i8> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> undef, i32 1, <8 x i1> undef, <8 x i8> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; SKL-LABEL: 'masked_gather'
+; SKL-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V32I8 = call <32 x i8> @llvm.masked.gather.v32i8.v32p0i8(<32 x i8*> undef, i32 1, <32 x i1> undef, <32 x i8> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> undef, i32 1, <16 x i1> undef, <16 x i8> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> undef, i32 1, <8 x i1> undef, <8 x i8> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; KNL-LABEL: 'masked_gather'
+; KNL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 224 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V32I8 = call <32 x i8> @llvm.masked.gather.v32i8.v32p0i8(<32 x i8*> undef, i32 1, <32 x i1> undef, <32 x i8> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> undef, i32 1, <16 x i1> undef, <16 x i8> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> undef, i32 1, <8 x i1> undef, <8 x i8> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; SKX-LABEL: 'masked_gather'
+; SKX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 224 for instruction: %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V32I8 = call <32 x i8> @llvm.masked.gather.v32i8.v32p0i8(<32 x i8*> undef, i32 1, <32 x i1> undef, <32 x i8> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> undef, i32 1, <16 x i1> undef, <16 x i8> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> undef, i32 1, <8 x i1> undef, <8 x i8> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+ %V8F64 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> undef, i32 1, <8 x i1> undef, <8 x double> undef)
+ %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 1, <4 x i1> undef, <4 x double> undef)
+ %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 1, <2 x i1> undef, <2 x double> undef)
+ %V1F64 = call <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*> undef, i32 1, <1 x i1> undef, <1 x double> undef)
+
+ %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 1, <16 x i1> undef, <16 x float> undef)
+ %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 1, <8 x i1> undef, <8 x float> undef)
+ %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 1, <4 x i1> undef, <4 x float> undef)
+ %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 1, <2 x i1> undef, <2 x float> undef)
+
+ %V8I64 = call <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*> undef, i32 1, <8 x i1> undef, <8 x i64> undef)
+ %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 1, <4 x i1> undef, <4 x i64> undef)
+ %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 1, <2 x i1> undef, <2 x i64> undef)
+ %V1I64 = call <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*> undef, i32 1, <1 x i1> undef, <1 x i64> undef)
+
+ %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 1, <16 x i1> undef, <16 x i32> undef)
+ %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 1, <8 x i1> undef, <8 x i32> undef)
+ %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 1, <4 x i1> undef, <4 x i32> undef)
+ %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 1, <2 x i1> undef, <2 x i32> undef)
+
+ %V32I16 = call <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*> undef, i32 1, <32 x i1> undef, <32 x i16> undef)
+ %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 1, <16 x i1> undef, <16 x i16> undef)
+ %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 1, <8 x i1> undef, <8 x i16> undef)
+ %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 1, <4 x i1> undef, <4 x i16> undef)
+
+ %V64I8 = call <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*> undef, i32 1, <64 x i1> undef, <64 x i8> undef)
+ %V32I8 = call <32 x i8> @llvm.masked.gather.v32i8.v32p0i8(<32 x i8*> undef, i32 1, <32 x i1> undef, <32 x i8> undef)
+ %V16I8 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> undef, i32 1, <16 x i1> undef, <16 x i8> undef)
+ %V8I8 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> undef, i32 1, <8 x i1> undef, <8 x i8> undef)
+
+ ret i32 0
+}
+
+define i32 @masked_scatter() {
+; SSE2-LABEL: 'masked_scatter'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double> undef, <1 x double*> undef, i32 1, <1 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64> undef, <1 x i64*> undef, i32 1, <1 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 44 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 188 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 94 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 47 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; SSE42-LABEL: 'masked_scatter'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double> undef, <1 x double*> undef, i32 1, <1 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64> undef, <1 x i64*> undef, i32 1, <1 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 128 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; AVX-LABEL: 'masked_scatter'
+; AVX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double> undef, <1 x double*> undef, i32 1, <1 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64> undef, <1 x i64*> undef, i32 1, <1 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; KNL-LABEL: 'masked_scatter'
+; KNL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double> undef, <1 x double*> undef, i32 1, <1 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64> undef, <1 x i64*> undef, i32 1, <1 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 88 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 176 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; SKX-LABEL: 'masked_scatter'
+; SKX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double> undef, <1 x double*> undef, i32 1, <1 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64> undef, <1 x i64*> undef, i32 1, <1 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 88 for instruction: call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 176 for instruction: call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+ call void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double> undef, <8 x double*> undef, i32 1, <8 x i1> undef)
+ call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 1, <4 x i1> undef)
+ call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 1, <2 x i1> undef)
+ call void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double> undef, <1 x double*> undef, i32 1, <1 x i1> undef)
+
+ call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 1, <16 x i1> undef)
+ call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 1, <8 x i1> undef)
+ call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 1, <4 x i1> undef)
+ call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 1, <2 x i1> undef)
+
+ call void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64> undef, <8 x i64*> undef, i32 1, <8 x i1> undef)
+ call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 1, <4 x i1> undef)
+ call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 1, <2 x i1> undef)
+ call void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64> undef, <1 x i64*> undef, i32 1, <1 x i1> undef)
+
+ call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 1, <16 x i1> undef)
+ call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 1, <8 x i1> undef)
+ call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 1, <4 x i1> undef)
+ call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 1, <2 x i1> undef)
+
+ call void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16> undef, <32 x i16*> undef, i32 1, <32 x i1> undef)
+ call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 1, <16 x i1> undef)
+ call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 1, <8 x i1> undef)
+ call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 1, <4 x i1> undef)
+
+ call void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8> undef, <64 x i8*> undef, i32 1, <64 x i1> undef)
+ call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
+ call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
+ call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
+
+ ret i32 0
+}
+
+define i32 @masked_expandload() {
+; SSE2-LABEL: 'masked_expandload'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8F64 = call <8 x double> @llvm.masked.expandload.v8f64(double* undef, <8 x i1> undef, <8 x double> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4F64 = call <4 x double> @llvm.masked.expandload.v4f64(double* undef, <4 x i1> undef, <4 x double> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.expandload.v2f64(double* undef, <2 x i1> undef, <2 x double> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.expandload.v1f64(double* undef, <1 x i1> undef, <1 x double> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V16F32 = call <16 x float> @llvm.masked.expandload.v16f32(float* undef, <16 x i1> undef, <16 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8F32 = call <8 x float> @llvm.masked.expandload.v8f32(float* undef, <8 x i1> undef, <8 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.expandload.v4f32(float* undef, <4 x i1> undef, <4 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.expandload.v2f32(float* undef, <2 x i1> undef, <2 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8I64 = call <8 x i64> @llvm.masked.expandload.v8i64(i64* undef, <8 x i1> undef, <8 x i64> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.masked.expandload.v4i64(i64* undef, <4 x i1> undef, <4 x i64> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2I64 = call <2 x i64> @llvm.masked.expandload.v2i64(i64* undef, <2 x i1> undef, <2 x i64> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.expandload.v1i64(i64* undef, <1 x i1> undef, <1 x i64> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V16I32 = call <16 x i32> @llvm.masked.expandload.v16i32(i32* undef, <16 x i1> undef, <16 x i32> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V8I32 = call <8 x i32> @llvm.masked.expandload.v8i32(i32* undef, <8 x i1> undef, <8 x i32> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V4I32 = call <4 x i32> @llvm.masked.expandload.v4i32(i32* undef, <4 x i1> undef, <4 x i32> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2I32 = call <2 x i32> @llvm.masked.expandload.v2i32(i32* undef, <2 x i1> undef, <2 x i32> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call <32 x i16> @llvm.masked.expandload.v32i16(i16* undef, <32 x i1> undef, <32 x i16> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call <16 x i16> @llvm.masked.expandload.v16i16(i16* undef, <16 x i1> undef, <16 x i16> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.expandload.v8i16(i16* undef, <8 x i1> undef, <8 x i16> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.expandload.v4i16(i16* undef, <4 x i1> undef, <4 x i16> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 188 for instruction: %V64I8 = call <64 x i8> @llvm.masked.expandload.v64i8(i8* undef, <64 x i1> undef, <64 x i8> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 94 for instruction: %V32I8 = call <32 x i8> @llvm.masked.expandload.v32i8(i8* undef, <32 x i1> undef, <32 x i8> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V16I8 = call <16 x i8> @llvm.masked.expandload.v16i8(i8* undef, <16 x i1> undef, <16 x i8> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V8I8 = call <8 x i8> @llvm.masked.expandload.v8i8(i8* undef, <8 x i1> undef, <8 x i8> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; SSE42-LABEL: 'masked_expandload'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8F64 = call <8 x double> @llvm.masked.expandload.v8f64(double* undef, <8 x i1> undef, <8 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4F64 = call <4 x double> @llvm.masked.expandload.v4f64(double* undef, <4 x i1> undef, <4 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.expandload.v2f64(double* undef, <2 x i1> undef, <2 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.expandload.v1f64(double* undef, <1 x i1> undef, <1 x double> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V16F32 = call <16 x float> @llvm.masked.expandload.v16f32(float* undef, <16 x i1> undef, <16 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8F32 = call <8 x float> @llvm.masked.expandload.v8f32(float* undef, <8 x i1> undef, <8 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.expandload.v4f32(float* undef, <4 x i1> undef, <4 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.expandload.v2f32(float* undef, <2 x i1> undef, <2 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call <8 x i64> @llvm.masked.expandload.v8i64(i64* undef, <8 x i1> undef, <8 x i64> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call <4 x i64> @llvm.masked.expandload.v4i64(i64* undef, <4 x i1> undef, <4 x i64> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.expandload.v2i64(i64* undef, <2 x i1> undef, <2 x i64> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.expandload.v1i64(i64* undef, <1 x i1> undef, <1 x i64> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.masked.expandload.v16i32(i32* undef, <16 x i1> undef, <16 x i32> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.masked.expandload.v8i32(i32* undef, <8 x i1> undef, <8 x i32> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.expandload.v4i32(i32* undef, <4 x i1> undef, <4 x i32> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.expandload.v2i32(i32* undef, <2 x i1> undef, <2 x i32> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call <32 x i16> @llvm.masked.expandload.v32i16(i16* undef, <32 x i1> undef, <32 x i16> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call <16 x i16> @llvm.masked.expandload.v16i16(i16* undef, <16 x i1> undef, <16 x i16> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.expandload.v8i16(i16* undef, <8 x i1> undef, <8 x i16> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.expandload.v4i16(i16* undef, <4 x i1> undef, <4 x i16> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64I8 = call <64 x i8> @llvm.masked.expandload.v64i8(i8* undef, <64 x i1> undef, <64 x i8> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I8 = call <32 x i8> @llvm.masked.expandload.v32i8(i8* undef, <32 x i1> undef, <32 x i8> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.masked.expandload.v16i8(i8* undef, <16 x i1> undef, <16 x i8> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.masked.expandload.v8i8(i8* undef, <8 x i1> undef, <8 x i8> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; AVX-LABEL: 'masked_expandload'
+; AVX-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8F64 = call <8 x double> @llvm.masked.expandload.v8f64(double* undef, <8 x i1> undef, <8 x double> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4F64 = call <4 x double> @llvm.masked.expandload.v4f64(double* undef, <4 x i1> undef, <4 x double> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.expandload.v2f64(double* undef, <2 x i1> undef, <2 x double> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.expandload.v1f64(double* undef, <1 x i1> undef, <1 x double> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x float> @llvm.masked.expandload.v16f32(float* undef, <16 x i1> undef, <16 x float> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x float> @llvm.masked.expandload.v8f32(float* undef, <8 x i1> undef, <8 x float> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.expandload.v4f32(float* undef, <4 x i1> undef, <4 x float> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.expandload.v2f32(float* undef, <2 x i1> undef, <2 x float> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8I64 = call <8 x i64> @llvm.masked.expandload.v8i64(i64* undef, <8 x i1> undef, <8 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.masked.expandload.v4i64(i64* undef, <4 x i1> undef, <4 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.expandload.v2i64(i64* undef, <2 x i1> undef, <2 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.expandload.v1i64(i64* undef, <1 x i1> undef, <1 x i64> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V16I32 = call <16 x i32> @llvm.masked.expandload.v16i32(i32* undef, <16 x i1> undef, <16 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V8I32 = call <8 x i32> @llvm.masked.expandload.v8i32(i32* undef, <8 x i1> undef, <8 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.expandload.v4i32(i32* undef, <4 x i1> undef, <4 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.expandload.v2i32(i32* undef, <2 x i1> undef, <2 x i32> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V32I16 = call <32 x i16> @llvm.masked.expandload.v32i16(i16* undef, <32 x i1> undef, <32 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V16I16 = call <16 x i16> @llvm.masked.expandload.v16i16(i16* undef, <16 x i1> undef, <16 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.expandload.v8i16(i16* undef, <8 x i1> undef, <8 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.expandload.v4i16(i16* undef, <4 x i1> undef, <4 x i16> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 132 for instruction: %V64I8 = call <64 x i8> @llvm.masked.expandload.v64i8(i8* undef, <64 x i1> undef, <64 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32I8 = call <32 x i8> @llvm.masked.expandload.v32i8(i8* undef, <32 x i1> undef, <32 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.masked.expandload.v16i8(i8* undef, <16 x i1> undef, <16 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.masked.expandload.v8i8(i8* undef, <8 x i1> undef, <8 x i8> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; AVX512-LABEL: 'masked_expandload'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8F64 = call <8 x double> @llvm.masked.expandload.v8f64(double* undef, <8 x i1> undef, <8 x double> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4F64 = call <4 x double> @llvm.masked.expandload.v4f64(double* undef, <4 x i1> undef, <4 x double> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F64 = call <2 x double> @llvm.masked.expandload.v2f64(double* undef, <2 x i1> undef, <2 x double> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = call <1 x double> @llvm.masked.expandload.v1f64(double* undef, <1 x i1> undef, <1 x double> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x float> @llvm.masked.expandload.v16f32(float* undef, <16 x i1> undef, <16 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x float> @llvm.masked.expandload.v8f32(float* undef, <8 x i1> undef, <8 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4F32 = call <4 x float> @llvm.masked.expandload.v4f32(float* undef, <4 x i1> undef, <4 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2F32 = call <2 x float> @llvm.masked.expandload.v2f32(float* undef, <2 x i1> undef, <2 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8I64 = call <8 x i64> @llvm.masked.expandload.v8i64(i64* undef, <8 x i1> undef, <8 x i64> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.masked.expandload.v4i64(i64* undef, <4 x i1> undef, <4 x i64> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.masked.expandload.v2i64(i64* undef, <2 x i1> undef, <2 x i64> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1I64 = call <1 x i64> @llvm.masked.expandload.v1i64(i64* undef, <1 x i1> undef, <1 x i64> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V16I32 = call <16 x i32> @llvm.masked.expandload.v16i32(i32* undef, <16 x i1> undef, <16 x i32> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V8I32 = call <8 x i32> @llvm.masked.expandload.v8i32(i32* undef, <8 x i1> undef, <8 x i32> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.expandload.v4i32(i32* undef, <4 x i1> undef, <4 x i32> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.masked.expandload.v2i32(i32* undef, <2 x i1> undef, <2 x i32> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V32I16 = call <32 x i16> @llvm.masked.expandload.v32i16(i16* undef, <32 x i1> undef, <32 x i16> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V16I16 = call <16 x i16> @llvm.masked.expandload.v16i16(i16* undef, <16 x i1> undef, <16 x i16> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call <8 x i16> @llvm.masked.expandload.v8i16(i16* undef, <8 x i1> undef, <8 x i16> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I16 = call <4 x i16> @llvm.masked.expandload.v4i16(i16* undef, <4 x i1> undef, <4 x i16> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 132 for instruction: %V64I8 = call <64 x i8> @llvm.masked.expandload.v64i8(i8* undef, <64 x i1> undef, <64 x i8> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V32I8 = call <32 x i8> @llvm.masked.expandload.v32i8(i8* undef, <32 x i1> undef, <32 x i8> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call <16 x i8> @llvm.masked.expandload.v16i8(i8* undef, <16 x i1> undef, <16 x i8> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I8 = call <8 x i8> @llvm.masked.expandload.v8i8(i8* undef, <8 x i1> undef, <8 x i8> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+ %V8F64 = call <8 x double> @llvm.masked.expandload.v8f64(double* undef, <8 x i1> undef, <8 x double> undef)
+ %V4F64 = call <4 x double> @llvm.masked.expandload.v4f64(double* undef, <4 x i1> undef, <4 x double> undef)
+ %V2F64 = call <2 x double> @llvm.masked.expandload.v2f64(double* undef, <2 x i1> undef, <2 x double> undef)
+ %V1F64 = call <1 x double> @llvm.masked.expandload.v1f64(double* undef, <1 x i1> undef, <1 x double> undef)
+
+ %V16F32 = call <16 x float> @llvm.masked.expandload.v16f32(float* undef, <16 x i1> undef, <16 x float> undef)
+ %V8F32 = call <8 x float> @llvm.masked.expandload.v8f32(float* undef, <8 x i1> undef, <8 x float> undef)
+ %V4F32 = call <4 x float> @llvm.masked.expandload.v4f32(float* undef, <4 x i1> undef, <4 x float> undef)
+ %V2F32 = call <2 x float> @llvm.masked.expandload.v2f32(float* undef, <2 x i1> undef, <2 x float> undef)
+
+ %V8I64 = call <8 x i64> @llvm.masked.expandload.v8i64(i64* undef, <8 x i1> undef, <8 x i64> undef)
+ %V4I64 = call <4 x i64> @llvm.masked.expandload.v4i64(i64* undef, <4 x i1> undef, <4 x i64> undef)
+ %V2I64 = call <2 x i64> @llvm.masked.expandload.v2i64(i64* undef, <2 x i1> undef, <2 x i64> undef)
+ %V1I64 = call <1 x i64> @llvm.masked.expandload.v1i64(i64* undef, <1 x i1> undef, <1 x i64> undef)
+
+ %V16I32 = call <16 x i32> @llvm.masked.expandload.v16i32(i32* undef, <16 x i1> undef, <16 x i32> undef)
+ %V8I32 = call <8 x i32> @llvm.masked.expandload.v8i32(i32* undef, <8 x i1> undef, <8 x i32> undef)
+ %V4I32 = call <4 x i32> @llvm.masked.expandload.v4i32(i32* undef, <4 x i1> undef, <4 x i32> undef)
+ %V2I32 = call <2 x i32> @llvm.masked.expandload.v2i32(i32* undef, <2 x i1> undef, <2 x i32> undef)
+
+ %V32I16 = call <32 x i16> @llvm.masked.expandload.v32i16(i16* undef, <32 x i1> undef, <32 x i16> undef)
+ %V16I16 = call <16 x i16> @llvm.masked.expandload.v16i16(i16* undef, <16 x i1> undef, <16 x i16> undef)
+ %V8I16 = call <8 x i16> @llvm.masked.expandload.v8i16(i16* undef, <8 x i1> undef, <8 x i16> undef)
+ %V4I16 = call <4 x i16> @llvm.masked.expandload.v4i16(i16* undef, <4 x i1> undef, <4 x i16> undef)
+
+ %V64I8 = call <64 x i8> @llvm.masked.expandload.v64i8(i8* undef, <64 x i1> undef, <64 x i8> undef)
+ %V32I8 = call <32 x i8> @llvm.masked.expandload.v32i8(i8* undef, <32 x i1> undef, <32 x i8> undef)
+ %V16I8 = call <16 x i8> @llvm.masked.expandload.v16i8(i8* undef, <16 x i1> undef, <16 x i8> undef)
+ %V8I8 = call <8 x i8> @llvm.masked.expandload.v8i8(i8* undef, <8 x i1> undef, <8 x i8> undef)
+
+ ret i32 0
+}
+
+define i32 @masked_compressstore() {
+; SSE2-LABEL: 'masked_compressstore'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: call void @llvm.masked.compressstore.v8f64(<8 x double> undef, double* undef, <8 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.compressstore.v4f64(<4 x double> undef, double* undef, <4 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.compressstore.v2f64(<2 x double> undef, double* undef, <2 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.compressstore.v1f64(<1 x double> undef, double* undef, <1 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 58 for instruction: call void @llvm.masked.compressstore.v16f32(<16 x float> undef, float* undef, <16 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: call void @llvm.masked.compressstore.v8f32(<8 x float> undef, float* undef, <8 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 13 for instruction: call void @llvm.masked.compressstore.v4f32(<4 x float> undef, float* undef, <4 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.compressstore.v2f32(<2 x float> undef, float* undef, <2 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: call void @llvm.masked.compressstore.v8i64(<8 x i64> undef, i64* undef, <8 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.compressstore.v4i64(<4 x i64> undef, i64* undef, <4 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.compressstore.v2i64(<2 x i64> undef, i64* undef, <2 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.compressstore.v1i64(<1 x i64> undef, i64* undef, <1 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 74 for instruction: call void @llvm.masked.compressstore.v16i32(<16 x i32> undef, i32* undef, <16 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 29 for instruction: call void @llvm.masked.compressstore.v8i32(<8 x i32> undef, i32* undef, <8 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 17 for instruction: call void @llvm.masked.compressstore.v4i32(<4 x i32> undef, i32* undef, <4 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.compressstore.v2i32(<2 x i32> undef, i32* undef, <2 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 125 for instruction: call void @llvm.masked.compressstore.v32i16(<32 x i16> undef, i16* undef, <32 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 62 for instruction: call void @llvm.masked.compressstore.v16i16(<16 x i16> undef, i16* undef, <16 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 23 for instruction: call void @llvm.masked.compressstore.v8i16(<8 x i16> undef, i16* undef, <8 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: call void @llvm.masked.compressstore.v4i16(<4 x i16> undef, i16* undef, <4 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 311 for instruction: call void @llvm.masked.compressstore.v64i8(<64 x i8> undef, i8* undef, <64 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 155 for instruction: call void @llvm.masked.compressstore.v32i8(<32 x i8> undef, i8* undef, <32 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 77 for instruction: call void @llvm.masked.compressstore.v16i8(<16 x i8> undef, i8* undef, <16 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 30 for instruction: call void @llvm.masked.compressstore.v8i8(<8 x i8> undef, i8* undef, <8 x i1> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; SSE42-LABEL: 'masked_compressstore'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 19 for instruction: call void @llvm.masked.compressstore.v8f64(<8 x double> undef, double* undef, <8 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 9 for instruction: call void @llvm.masked.compressstore.v4f64(<4 x double> undef, double* undef, <4 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.compressstore.v2f64(<2 x double> undef, double* undef, <2 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.compressstore.v1f64(<1 x double> undef, double* undef, <1 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 43 for instruction: call void @llvm.masked.compressstore.v16f32(<16 x float> undef, float* undef, <16 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 21 for instruction: call void @llvm.masked.compressstore.v8f32(<8 x float> undef, float* undef, <8 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.compressstore.v4f32(<4 x float> undef, float* undef, <4 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.compressstore.v2f32(<2 x float> undef, float* undef, <2 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 23 for instruction: call void @llvm.masked.compressstore.v8i64(<8 x i64> undef, i64* undef, <8 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: call void @llvm.masked.compressstore.v4i64(<4 x i64> undef, i64* undef, <4 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.compressstore.v2i64(<2 x i64> undef, i64* undef, <2 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.compressstore.v1i64(<1 x i64> undef, i64* undef, <1 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 47 for instruction: call void @llvm.masked.compressstore.v16i32(<16 x i32> undef, i32* undef, <16 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 23 for instruction: call void @llvm.masked.compressstore.v8i32(<8 x i32> undef, i32* undef, <8 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: call void @llvm.masked.compressstore.v4i32(<4 x i32> undef, i32* undef, <4 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.compressstore.v2i32(<2 x i32> undef, i32* undef, <2 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 95 for instruction: call void @llvm.masked.compressstore.v32i16(<32 x i16> undef, i16* undef, <32 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 47 for instruction: call void @llvm.masked.compressstore.v16i16(<16 x i16> undef, i16* undef, <16 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 23 for instruction: call void @llvm.masked.compressstore.v8i16(<8 x i16> undef, i16* undef, <8 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: call void @llvm.masked.compressstore.v4i16(<4 x i16> undef, i16* undef, <4 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 191 for instruction: call void @llvm.masked.compressstore.v64i8(<64 x i8> undef, i8* undef, <64 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 95 for instruction: call void @llvm.masked.compressstore.v32i8(<32 x i8> undef, i8* undef, <32 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 47 for instruction: call void @llvm.masked.compressstore.v16i8(<16 x i8> undef, i8* undef, <16 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 23 for instruction: call void @llvm.masked.compressstore.v8i8(<8 x i8> undef, i8* undef, <8 x i1> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; AVX-LABEL: 'masked_compressstore'
+; AVX-NEXT: Cost Model: Found an estimated cost of 23 for instruction: call void @llvm.masked.compressstore.v8f64(<8 x double> undef, double* undef, <8 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 11 for instruction: call void @llvm.masked.compressstore.v4f64(<4 x double> undef, double* undef, <4 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.compressstore.v2f64(<2 x double> undef, double* undef, <2 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.compressstore.v1f64(<1 x double> undef, double* undef, <1 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 51 for instruction: call void @llvm.masked.compressstore.v16f32(<16 x float> undef, float* undef, <16 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 25 for instruction: call void @llvm.masked.compressstore.v8f32(<8 x float> undef, float* undef, <8 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.compressstore.v4f32(<4 x float> undef, float* undef, <4 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.compressstore.v2f32(<2 x float> undef, float* undef, <2 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 27 for instruction: call void @llvm.masked.compressstore.v8i64(<8 x i64> undef, i64* undef, <8 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 13 for instruction: call void @llvm.masked.compressstore.v4i64(<4 x i64> undef, i64* undef, <4 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.compressstore.v2i64(<2 x i64> undef, i64* undef, <2 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.compressstore.v1i64(<1 x i64> undef, i64* undef, <1 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 55 for instruction: call void @llvm.masked.compressstore.v16i32(<16 x i32> undef, i32* undef, <16 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 27 for instruction: call void @llvm.masked.compressstore.v8i32(<8 x i32> undef, i32* undef, <8 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 11 for instruction: call void @llvm.masked.compressstore.v4i32(<4 x i32> undef, i32* undef, <4 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.compressstore.v2i32(<2 x i32> undef, i32* undef, <2 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 127 for instruction: call void @llvm.masked.compressstore.v32i16(<32 x i16> undef, i16* undef, <32 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 55 for instruction: call void @llvm.masked.compressstore.v16i16(<16 x i16> undef, i16* undef, <16 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 23 for instruction: call void @llvm.masked.compressstore.v8i16(<8 x i16> undef, i16* undef, <8 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 11 for instruction: call void @llvm.masked.compressstore.v4i16(<4 x i16> undef, i16* undef, <4 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 255 for instruction: call void @llvm.masked.compressstore.v64i8(<64 x i8> undef, i8* undef, <64 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 127 for instruction: call void @llvm.masked.compressstore.v32i8(<32 x i8> undef, i8* undef, <32 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 47 for instruction: call void @llvm.masked.compressstore.v16i8(<16 x i8> undef, i8* undef, <16 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 23 for instruction: call void @llvm.masked.compressstore.v8i8(<8 x i8> undef, i8* undef, <8 x i1> undef)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+; AVX512-LABEL: 'masked_compressstore'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 25 for instruction: call void @llvm.masked.compressstore.v8f64(<8 x double> undef, double* undef, <8 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: call void @llvm.masked.compressstore.v4f64(<4 x double> undef, double* undef, <4 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.compressstore.v2f64(<2 x double> undef, double* undef, <2 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.compressstore.v1f64(<1 x double> undef, double* undef, <1 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 55 for instruction: call void @llvm.masked.compressstore.v16f32(<16 x float> undef, float* undef, <16 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 25 for instruction: call void @llvm.masked.compressstore.v8f32(<8 x float> undef, float* undef, <8 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.compressstore.v4f32(<4 x float> undef, float* undef, <4 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.compressstore.v2f32(<2 x float> undef, float* undef, <2 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 29 for instruction: call void @llvm.masked.compressstore.v8i64(<8 x i64> undef, i64* undef, <8 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 13 for instruction: call void @llvm.masked.compressstore.v4i64(<4 x i64> undef, i64* undef, <4 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.compressstore.v2i64(<2 x i64> undef, i64* undef, <2 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.compressstore.v1i64(<1 x i64> undef, i64* undef, <1 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 59 for instruction: call void @llvm.masked.compressstore.v16i32(<16 x i32> undef, i32* undef, <16 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 27 for instruction: call void @llvm.masked.compressstore.v8i32(<8 x i32> undef, i32* undef, <8 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: call void @llvm.masked.compressstore.v4i32(<4 x i32> undef, i32* undef, <4 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.compressstore.v2i32(<2 x i32> undef, i32* undef, <2 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 119 for instruction: call void @llvm.masked.compressstore.v32i16(<32 x i16> undef, i16* undef, <32 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 55 for instruction: call void @llvm.masked.compressstore.v16i16(<16 x i16> undef, i16* undef, <16 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 23 for instruction: call void @llvm.masked.compressstore.v8i16(<8 x i16> undef, i16* undef, <8 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: call void @llvm.masked.compressstore.v4i16(<4 x i16> undef, i16* undef, <4 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 239 for instruction: call void @llvm.masked.compressstore.v64i8(<64 x i8> undef, i8* undef, <64 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 111 for instruction: call void @llvm.masked.compressstore.v32i8(<32 x i8> undef, i8* undef, <32 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 47 for instruction: call void @llvm.masked.compressstore.v16i8(<16 x i8> undef, i8* undef, <16 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 23 for instruction: call void @llvm.masked.compressstore.v8i8(<8 x i8> undef, i8* undef, <8 x i1> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
+;
+ call void @llvm.masked.compressstore.v8f64(<8 x double> undef, double* undef, <8 x i1> undef)
+ call void @llvm.masked.compressstore.v4f64(<4 x double> undef, double* undef, <4 x i1> undef)
+ call void @llvm.masked.compressstore.v2f64(<2 x double> undef, double* undef, <2 x i1> undef)
+ call void @llvm.masked.compressstore.v1f64(<1 x double> undef, double* undef, <1 x i1> undef)
+
+ call void @llvm.masked.compressstore.v16f32(<16 x float> undef, float* undef, <16 x i1> undef)
+ call void @llvm.masked.compressstore.v8f32(<8 x float> undef, float* undef, <8 x i1> undef)
+ call void @llvm.masked.compressstore.v4f32(<4 x float> undef, float* undef, <4 x i1> undef)
+ call void @llvm.masked.compressstore.v2f32(<2 x float> undef, float* undef, <2 x i1> undef)
+
+ call void @llvm.masked.compressstore.v8i64(<8 x i64> undef, i64* undef, <8 x i1> undef)
+ call void @llvm.masked.compressstore.v4i64(<4 x i64> undef, i64* undef, <4 x i1> undef)
+ call void @llvm.masked.compressstore.v2i64(<2 x i64> undef, i64* undef, <2 x i1> undef)
+ call void @llvm.masked.compressstore.v1i64(<1 x i64> undef, i64* undef, <1 x i1> undef)
+
+ call void @llvm.masked.compressstore.v16i32(<16 x i32> undef, i32* undef, <16 x i1> undef)
+ call void @llvm.masked.compressstore.v8i32(<8 x i32> undef, i32* undef, <8 x i1> undef)
+ call void @llvm.masked.compressstore.v4i32(<4 x i32> undef, i32* undef, <4 x i1> undef)
+ call void @llvm.masked.compressstore.v2i32(<2 x i32> undef, i32* undef, <2 x i1> undef)
+
+ call void @llvm.masked.compressstore.v32i16(<32 x i16> undef, i16* undef, <32 x i1> undef)
+ call void @llvm.masked.compressstore.v16i16(<16 x i16> undef, i16* undef, <16 x i1> undef)
+ call void @llvm.masked.compressstore.v8i16(<8 x i16> undef, i16* undef, <8 x i1> undef)
+ call void @llvm.masked.compressstore.v4i16(<4 x i16> undef, i16* undef, <4 x i1> undef)
+
+ call void @llvm.masked.compressstore.v64i8(<64 x i8> undef, i8* undef, <64 x i1> undef)
+ call void @llvm.masked.compressstore.v32i8(<32 x i8> undef, i8* undef, <32 x i1> undef)
+ call void @llvm.masked.compressstore.v16i8(<16 x i8> undef, i8* undef, <16 x i1> undef)
+ call void @llvm.masked.compressstore.v8i8(<8 x i8> undef, i8* undef, <8 x i1> undef)
+
+ ret i32 0
+}
+
+define <2 x double> @test1(<2 x i64> %trigger, <2 x double>* %addr, <2 x double> %dst) {
+; SSE2-LABEL: 'test1'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %mask = icmp eq <2 x i64> %trigger, zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %addr, i32 4, <2 x i1> %mask, <2 x double> %dst)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
+;
+; SSE42-LABEL: 'test1'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i64> %trigger, zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %addr, i32 4, <2 x i1> %mask, <2 x double> %dst)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
+;
+; AVX-LABEL: 'test1'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i64> %trigger, zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %addr, i32 4, <2 x i1> %mask, <2 x double> %dst)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
+;
+; AVX512-LABEL: 'test1'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i64> %trigger, zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %addr, i32 4, <2 x i1> %mask, <2 x double> %dst)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
+;
+ %mask = icmp eq <2 x i64> %trigger, zeroinitializer
+ %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %addr, i32 4, <2 x i1>%mask, <2 x double>%dst)
+ ret <2 x double> %res
+}
+
+define <4 x i32> @test2(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %dst) {
+; SSE2-LABEL: 'test2'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1> %mask, <4 x i32> %dst)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+; SSE42-LABEL: 'test2'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1> %mask, <4 x i32> %dst)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+; AVX-LABEL: 'test2'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1> %mask, <4 x i32> %dst)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+; AVX512-LABEL: 'test2'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1> %mask, <4 x i32> %dst)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+ %mask = icmp eq <4 x i32> %trigger, zeroinitializer
+ %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1>%mask, <4 x i32>%dst)
+ ret <4 x i32> %res
+}
+
+define void @test3(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %val) {
+; SSE2-LABEL: 'test3'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %val, <4 x i32>* %addr, i32 4, <4 x i1> %mask)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; SSE42-LABEL: 'test3'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %val, <4 x i32>* %addr, i32 4, <4 x i1> %mask)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; AVX-LABEL: 'test3'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %val, <4 x i32>* %addr, i32 4, <4 x i1> %mask)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; AVX512-LABEL: 'test3'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %val, <4 x i32>* %addr, i32 4, <4 x i1> %mask)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+ %mask = icmp eq <4 x i32> %trigger, zeroinitializer
+ call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>%val, <4 x i32>* %addr, i32 4, <4 x i1>%mask)
+ ret void
+}
+
+define <8 x float> @test4(<8 x i32> %trigger, <8 x float>* %addr, <8 x float> %dst) {
+; SSE2-LABEL: 'test4'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %mask = icmp eq <8 x i32> %trigger, zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> %mask, <8 x float> %dst)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x float> %res
+;
+; SSE42-LABEL: 'test4'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %mask = icmp eq <8 x i32> %trigger, zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> %mask, <8 x float> %dst)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x float> %res
+;
+; AVX1-LABEL: 'test4'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %mask = icmp eq <8 x i32> %trigger, zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> %mask, <8 x float> %dst)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x float> %res
+;
+; AVX2-LABEL: 'test4'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <8 x i32> %trigger, zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> %mask, <8 x float> %dst)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x float> %res
+;
+; SKL-LABEL: 'test4'
+; SKL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <8 x i32> %trigger, zeroinitializer
+; SKL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> %mask, <8 x float> %dst)
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x float> %res
+;
+; AVX512-LABEL: 'test4'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <8 x i32> %trigger, zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> %mask, <8 x float> %dst)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x float> %res
+;
+ %mask = icmp eq <8 x i32> %trigger, zeroinitializer
+ %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1>%mask, <8 x float>%dst)
+ ret <8 x float> %res
+}
+
+define void @test5(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %val) {
+; SSE2-LABEL: 'test5'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> %val, <2 x float>* %addr, i32 4, <2 x i1> %mask)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; SSE42-LABEL: 'test5'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> %val, <2 x float>* %addr, i32 4, <2 x i1> %mask)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; AVX-LABEL: 'test5'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> %val, <2 x float>* %addr, i32 4, <2 x i1> %mask)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; AVX512-LABEL: 'test5'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> %val, <2 x float>* %addr, i32 4, <2 x i1> %mask)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+ %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+ call void @llvm.masked.store.v2f32.p0v2f32(<2 x float>%val, <2 x float>* %addr, i32 4, <2 x i1>%mask)
+ ret void
+}
+
+define void @test6(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %val) {
+; SSE2-LABEL: 'test6'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> %val, <2 x i32>* %addr, i32 4, <2 x i1> %mask)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; SSE42-LABEL: 'test6'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> %val, <2 x i32>* %addr, i32 4, <2 x i1> %mask)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; AVX-LABEL: 'test6'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> %val, <2 x i32>* %addr, i32 4, <2 x i1> %mask)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; AVX512-LABEL: 'test6'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> %val, <2 x i32>* %addr, i32 4, <2 x i1> %mask)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+ %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+ call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32>%val, <2 x i32>* %addr, i32 4, <2 x i1>%mask)
+ ret void
+}
+
+define <2 x float> @test7(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %dst) {
+; SSE2-LABEL: 'test7'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1> %mask, <2 x float> %dst)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x float> %res
+;
+; SSE42-LABEL: 'test7'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1> %mask, <2 x float> %dst)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x float> %res
+;
+; AVX-LABEL: 'test7'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1> %mask, <2 x float> %dst)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x float> %res
+;
+; AVX512-LABEL: 'test7'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1> %mask, <2 x float> %dst)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x float> %res
+;
+ %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+ %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1>%mask, <2 x float>%dst)
+ ret <2 x float> %res
+}
+
+define <2 x i32> @test8(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %dst) {
+; SSE2-LABEL: 'test8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1> %mask, <2 x i32> %dst)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i32> %res
+;
+; SSE42-LABEL: 'test8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1> %mask, <2 x i32> %dst)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i32> %res
+;
+; AVX-LABEL: 'test8'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1> %mask, <2 x i32> %dst)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i32> %res
+;
+; AVX512-LABEL: 'test8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1> %mask, <2 x i32> %dst)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i32> %res
+;
+ %mask = icmp eq <2 x i32> %trigger, zeroinitializer
+ %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1>%mask, <2 x i32>%dst)
+ ret <2 x i32> %res
+}
+
+define <2 x double> @test_gather_2f64(<2 x double*> %ptrs, <2 x i1> %mask, <2 x double> %src0) {
+; SSE2-LABEL: 'test_gather_2f64'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
+;
+; SSE42-LABEL: 'test_gather_2f64'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
+;
+; AVX1-LABEL: 'test_gather_2f64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
+;
+; AVX2-LABEL: 'test_gather_2f64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
+;
+; SKL-LABEL: 'test_gather_2f64'
+; SKL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
+;
+; AVX512-LABEL: 'test_gather_2f64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
+;
+ %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
+ ret <2 x double> %res
+}
+
+define <4 x i32> @test_gather_4i32(<4 x i32*> %ptrs, <4 x i1> %mask, <4 x i32> %src0) {
+; SSE2-LABEL: 'test_gather_4i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+; SSE42-LABEL: 'test_gather_4i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+; AVX1-LABEL: 'test_gather_4i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+; AVX2-LABEL: 'test_gather_4i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+; SKL-LABEL: 'test_gather_4i32'
+; SKL-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+; KNL-LABEL: 'test_gather_4i32'
+; KNL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
+; KNL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+; SKX-LABEL: 'test_gather_4i32'
+; SKX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
+; SKX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+ %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
+ ret <4 x i32> %res
+}
+
+define <4 x i32> @test_gather_4i32_const_mask(<4 x i32*> %ptrs, <4 x i32> %src0) {
+; SSE2-LABEL: 'test_gather_4i32_const_mask'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+; SSE42-LABEL: 'test_gather_4i32_const_mask'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+; AVX1-LABEL: 'test_gather_4i32_const_mask'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+; AVX2-LABEL: 'test_gather_4i32_const_mask'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+; SKL-LABEL: 'test_gather_4i32_const_mask'
+; SKL-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+; KNL-LABEL: 'test_gather_4i32_const_mask'
+; KNL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
+; KNL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+; SKX-LABEL: 'test_gather_4i32_const_mask'
+; SKX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
+; SKX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
+;
+ %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
+ ret <4 x i32> %res
+}
+
+define <16 x float> @test_gather_16f32_const_mask(float* %base, <16 x i32> %ind) {
+; SSE2-LABEL: 'test_gather_16f32_const_mask'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
+; SSE2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; SSE42-LABEL: 'test_gather_16f32_const_mask'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
+; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; AVX1-LABEL: 'test_gather_16f32_const_mask'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
+; AVX1-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; AVX2-LABEL: 'test_gather_16f32_const_mask'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
+; AVX2-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; SKL-LABEL: 'test_gather_16f32_const_mask'
+; SKL-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
+; SKL-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; AVX512-LABEL: 'test_gather_16f32_const_mask'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
+; AVX512-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+ %sext_ind = sext <16 x i32> %ind to <16 x i64>
+ %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
+
+ %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+ ret <16 x float>%res
+}
+
+define <16 x float> @test_gather_16f32_var_mask(float* %base, <16 x i32> %ind, <16 x i1>%mask) {
+; SSE2-LABEL: 'test_gather_16f32_var_mask'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
+; SSE2-NEXT: Cost Model: Found an estimated cost of 87 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; SSE42-LABEL: 'test_gather_16f32_var_mask'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
+; SSE42-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; AVX1-LABEL: 'test_gather_16f32_var_mask'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
+; AVX1-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; AVX2-LABEL: 'test_gather_16f32_var_mask'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
+; AVX2-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; SKL-LABEL: 'test_gather_16f32_var_mask'
+; SKL-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
+; SKL-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; AVX512-LABEL: 'test_gather_16f32_var_mask'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
+; AVX512-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+ %sext_ind = sext <16 x i32> %ind to <16 x i64>
+ %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
+
+ %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+ ret <16 x float>%res
+}
+
+define <16 x float> @test_gather_16f32_ra_var_mask(<16 x float*> %ptrs, <16 x i32> %ind, <16 x i1>%mask) {
+; SSE2-LABEL: 'test_gather_16f32_ra_var_mask'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
+; SSE2-NEXT: Cost Model: Found an estimated cost of 87 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; SSE42-LABEL: 'test_gather_16f32_ra_var_mask'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
+; SSE42-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; AVX1-LABEL: 'test_gather_16f32_ra_var_mask'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
+; AVX1-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; AVX2-LABEL: 'test_gather_16f32_ra_var_mask'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
+; AVX2-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; SKL-LABEL: 'test_gather_16f32_ra_var_mask'
+; SKL-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
+; SKL-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; AVX512-LABEL: 'test_gather_16f32_ra_var_mask'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
+; AVX512-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+ %sext_ind = sext <16 x i32> %ind to <16 x i64>
+ %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
+
+ %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
+ ret <16 x float>%res
+}
+
+define <16 x float> @test_gather_16f32_const_mask2(float* %base, <16 x i32> %ind) {
+; SSE2-LABEL: 'test_gather_16f32_const_mask2'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %broadcast.splatinsert = insertelement <16 x float*> poison, float* %base, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
+; SSE2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; SSE42-LABEL: 'test_gather_16f32_const_mask2'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> poison, float* %base, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
+; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; AVX1-LABEL: 'test_gather_16f32_const_mask2'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> poison, float* %base, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
+; AVX1-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; AVX2-LABEL: 'test_gather_16f32_const_mask2'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> poison, float* %base, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
+; AVX2-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; SKL-LABEL: 'test_gather_16f32_const_mask2'
+; SKL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> poison, float* %base, i32 0
+; SKL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer
+; SKL-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
+; SKL-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+; AVX512-LABEL: 'test_gather_16f32_const_mask2'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> poison, float* %base, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
+; AVX512-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
+;
+ %broadcast.splatinsert = insertelement <16 x float*> poison, float* %base, i32 0
+ %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer
+
+ %sext_ind = sext <16 x i32> %ind to <16 x i64>
+ %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
+
+ %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
+ ret <16 x float>%res
+}
+
+define void @test_scatter_16i32(i32* %base, <16 x i32> %ind, i16 %mask, <16 x i32>%val) {
+; SSE2-LABEL: 'test_scatter_16i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> poison, i32* %base, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 91 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; SSE42-LABEL: 'test_scatter_16i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> poison, i32* %base, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; AVX1-LABEL: 'test_scatter_16i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> poison, i32* %base, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; AVX2-LABEL: 'test_scatter_16i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> poison, i32* %base, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; SKL-LABEL: 'test_scatter_16i32'
+; SKL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> poison, i32* %base, i32 0
+; SKL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
+; SKL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
+; SKL-NEXT: Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; AVX512-LABEL: 'test_scatter_16i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> poison, i32* %base, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+ %broadcast.splatinsert = insertelement <16 x i32*> poison, i32* %base, i32 0
+ %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
+
+ %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
+ %imask = bitcast i16 %mask to <16 x i1>
+ call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32>%val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
+ ret void
+}
+
+define void @test_scatter_8i32(<8 x i32>%a1, <8 x i32*> %ptr, <8 x i1>%mask) {
+; SSE2-LABEL: 'test_scatter_8i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 38 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; SSE42-LABEL: 'test_scatter_8i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; AVX-LABEL: 'test_scatter_8i32'
+; AVX-NEXT: Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; AVX512-LABEL: 'test_scatter_8i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+ call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
+ ret void
+}
+
+define void @test_scatter_4i32(<4 x i32>%a1, <4 x i32*> %ptr, <4 x i1>%mask) {
+; SSE2-LABEL: 'test_scatter_4i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; SSE42-LABEL: 'test_scatter_4i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; AVX-LABEL: 'test_scatter_4i32'
+; AVX-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; KNL-LABEL: 'test_scatter_4i32'
+; KNL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
+; KNL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; SKX-LABEL: 'test_scatter_4i32'
+; SKX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
+; SKX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+ call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
+ ret void
+}
+
+define <4 x float> @test_gather_4f32(float* %ptr, <4 x i32> %ind, <4 x i1>%mask) {
+; SSE2-LABEL: 'test_gather_4f32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
+; SSE2-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
+;
+; SSE42-LABEL: 'test_gather_4f32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
+; SSE42-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
+;
+; AVX1-LABEL: 'test_gather_4f32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
+; AVX1-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
+;
+; AVX2-LABEL: 'test_gather_4f32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
+; AVX2-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
+;
+; SKL-LABEL: 'test_gather_4f32'
+; SKL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
+; SKL-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
+;
+; KNL-LABEL: 'test_gather_4f32'
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
+; KNL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
+; KNL-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
+;
+; SKX-LABEL: 'test_gather_4f32'
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
+; SKX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
+; SKX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
+;
+ %sext_ind = sext <4 x i32> %ind to <4 x i64>
+ %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
+
+ %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
+ ret <4 x float>%res
+}
+
+define <4 x float> @test_gather_4f32_const_mask(float* %ptr, <4 x i32> %ind) {
+; SSE2-LABEL: 'test_gather_4f32_const_mask'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
+; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
+;
+; SSE42-LABEL: 'test_gather_4f32_const_mask'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
+; SSE42-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
+;
+; AVX1-LABEL: 'test_gather_4f32_const_mask'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
+; AVX1-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
+;
+; AVX2-LABEL: 'test_gather_4f32_const_mask'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
+; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
+;
+; SKL-LABEL: 'test_gather_4f32_const_mask'
+; SKL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
+; SKL-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
+; SKL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
+;
+; KNL-LABEL: 'test_gather_4f32_const_mask'
+; KNL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
+; KNL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
+; KNL-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
+; KNL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
+;
+; SKX-LABEL: 'test_gather_4f32_const_mask'
+; SKX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
+; SKX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
+; SKX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
+; SKX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
+;
+ %sext_ind = sext <4 x i32> %ind to <4 x i64>
+ %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
+
+ %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
+ ret <4 x float>%res
+}
+
+declare <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>*, i32, <8 x i1>, <8 x double>)
+declare <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>*, i32, <4 x i1>, <4 x double>)
+declare <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>*, i32, <2 x i1>, <2 x double>)
+declare <1 x double> @llvm.masked.load.v1f64.p0v1f64(<1 x double>*, i32, <1 x i1>, <1 x double>)
+
+declare <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>*, i32, <16 x i1>, <16 x float>)
+declare <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>*, i32, <8 x i1>, <8 x float>)
+declare <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>*, i32, <4 x i1>, <4 x float>)
+declare <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>*, i32, <2 x i1>, <2 x float>)
+
+declare <8 x i64> @llvm.masked.load.v8i64.p0v8i64(<8 x i64>*, i32, <8 x i1>, <8 x i64>)
+declare <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>*, i32, <4 x i1>, <4 x i64>)
+declare <2 x i64> @llvm.masked.load.v2i64.p0v2i64(<2 x i64>*, i32, <2 x i1>, <2 x i64>)
+declare <1 x i64> @llvm.masked.load.v1i64.p0v1i64(<1 x i64>*, i32, <1 x i1>, <1 x i64>)
+
+declare <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>*, i32, <16 x i1>, <16 x i32>)
+declare <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>*, i32, <8 x i1>, <8 x i32>)
+declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32, <4 x i1>, <4 x i32>)
+declare <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>*, i32, <2 x i1>, <2 x i32>)
+
+declare <32 x i16> @llvm.masked.load.v32i16.p0v32i16(<32 x i16>*, i32, <32 x i1>, <32 x i16>)
+declare <16 x i16> @llvm.masked.load.v16i16.p0v16i16(<16 x i16>*, i32, <16 x i1>, <16 x i16>)
+declare <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>*, i32, <8 x i1>, <8 x i16>)
+declare <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>*, i32, <4 x i1>, <4 x i16>)
+
+declare <64 x i8> @llvm.masked.load.v64i8.p0v64i8(<64 x i8>*, i32, <64 x i1>, <64 x i8>)
+declare <32 x i8> @llvm.masked.load.v32i8.p0v32i8(<32 x i8>*, i32, <32 x i1>, <32 x i8>)
+declare <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>*, i32, <16 x i1>, <16 x i8>)
+declare <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>*, i32, <8 x i1>, <8 x i8>)
+
+declare void @llvm.masked.store.v8f64.p0v8f64(<8 x double>, <8 x double>*, i32, <8 x i1>)
+declare void @llvm.masked.store.v4f64.p0v4f64(<4 x double>, <4 x double>*, i32, <4 x i1>)
+declare void @llvm.masked.store.v2f64.p0v2f64(<2 x double>, <2 x double>*, i32, <2 x i1>)
+declare void @llvm.masked.store.v1f64.p0v1f64(<1 x double>, <1 x double>*, i32, <1 x i1>)
+
+declare void @llvm.masked.store.v16f32.p0v16f32(<16 x float>, <16 x float>*, i32, <16 x i1>)
+declare void @llvm.masked.store.v8f32.p0v8f32(<8 x float>, <8 x float>*, i32, <8 x i1>)
+declare void @llvm.masked.store.v4f32.p0v4f32(<4 x float>, <4 x float>*, i32, <4 x i1>)
+declare void @llvm.masked.store.v2f32.p0v2f32(<2 x float>, <2 x float>*, i32, <2 x i1>)
+
+declare void @llvm.masked.store.v8i64.p0v8i64(<8 x i64>, <8 x i64>*, i32, <8 x i1>)
+declare void @llvm.masked.store.v4i64.p0v4i64(<4 x i64>, <4 x i64>*, i32, <4 x i1>)
+declare void @llvm.masked.store.v2i64.p0v2i64(<2 x i64>, <2 x i64>*, i32, <2 x i1>)
+declare void @llvm.masked.store.v1i64.p0v1i64(<1 x i64>, <1 x i64>*, i32, <1 x i1>)
+
+declare void @llvm.masked.store.v16i32.p0v16i32(<16 x i32>, <16 x i32>*, i32, <16 x i1>)
+declare void @llvm.masked.store.v8i32.p0v8i32(<8 x i32>, <8 x i32>*, i32, <8 x i1>)
+declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32, <4 x i1>)
+declare void @llvm.masked.store.v2i32.p0v2i32(<2 x i32>, <2 x i32>*, i32, <2 x i1>)
+
+declare void @llvm.masked.store.v32i16.p0v32i16(<32 x i16>, <32 x i16>*, i32, <32 x i1>)
+declare void @llvm.masked.store.v16i16.p0v16i16(<16 x i16>, <16 x i16>*, i32, <16 x i1>)
+declare void @llvm.masked.store.v8i16.p0v8i16(<8 x i16>, <8 x i16>*, i32, <8 x i1>)
+declare void @llvm.masked.store.v4i16.p0v4i16(<4 x i16>, <4 x i16>*, i32, <4 x i1>)
+
+declare void @llvm.masked.store.v64i8.p0v64i8(<64 x i8>, <64 x i8>*, i32, <64 x i1>)
+declare void @llvm.masked.store.v32i8.p0v32i8(<32 x i8>, <32 x i8>*, i32, <32 x i1>)
+declare void @llvm.masked.store.v16i8.p0v16i8(<16 x i8>, <16 x i8>*, i32, <16 x i1>)
+declare void @llvm.masked.store.v8i8.p0v8i8(<8 x i8>, <8 x i8>*, i32, <8 x i1>)
+
+declare <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*>, i32, <8 x i1>, <8 x double>)
+declare <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*>, i32, <4 x i1>, <4 x double>)
+declare <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*>, i32, <2 x i1>, <2 x double>)
+declare <1 x double> @llvm.masked.gather.v1f64.v1p0f64(<1 x double*>, i32, <1 x i1>, <1 x double>)
+
+declare <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*>, i32, <16 x i1>, <16 x float>)
+declare <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*>, i32, <8 x i1>, <8 x float>)
+declare <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*>, i32, <4 x i1>, <4 x float>)
+declare <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*>, i32, <2 x i1>, <2 x float>)
+
+declare <8 x i64> @llvm.masked.gather.v8i64.v8p0i64(<8 x i64*>, i32, <8 x i1>, <8 x i64>)
+declare <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*>, i32, <4 x i1>, <4 x i64>)
+declare <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*>, i32, <2 x i1>, <2 x i64>)
+declare <1 x i64> @llvm.masked.gather.v1i64.v1p0i64(<1 x i64*>, i32, <1 x i1>, <1 x i64>)
+
+declare <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*>, i32, <16 x i1>, <16 x i32>)
+declare <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*>, i32, <8 x i1>, <8 x i32>)
+declare <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*>, i32, <4 x i1>, <4 x i32>)
+declare <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*>, i32, <2 x i1>, <2 x i32>)
+
+declare <32 x i16> @llvm.masked.gather.v32i16.v32p0i16(<32 x i16*>, i32, <32 x i1>, <32 x i16>)
+declare <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*>, i32, <16 x i1>, <16 x i16>)
+declare <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*>, i32, <8 x i1>, <8 x i16>)
+declare <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*>, i32, <4 x i1>, <4 x i16>)
+
+declare <64 x i8> @llvm.masked.gather.v64i8.v64p0i8(<64 x i8*>, i32, <64 x i1>, <64 x i8>)
+declare <32 x i8> @llvm.masked.gather.v32i8.v32p0i8(<32 x i8*>, i32, <32 x i1>, <32 x i8>)
+declare <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*>, i32, <16 x i1>, <16 x i8>)
+declare <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*>, i32, <8 x i1>, <8 x i8>)
+
+declare void @llvm.masked.scatter.v8f64.v8p0f64(<8 x double>, <8 x double*>, i32, <8 x i1>)
+declare void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double>, <4 x double*>, i32, <4 x i1>)
+declare void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double>, <2 x double*>, i32, <2 x i1>)
+declare void @llvm.masked.scatter.v1f64.v1p0f64(<1 x double>, <1 x double*>, i32, <1 x i1>)
+
+declare void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float>, <16 x float*>, i32, <16 x i1>)
+declare void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float>, <8 x float*>, i32, <8 x i1>)
+declare void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float>, <4 x float*>, i32, <4 x i1>)
+declare void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float>, <2 x float*>, i32, <2 x i1>)
+
+declare void @llvm.masked.scatter.v8i64.v8p0i64(<8 x i64>, <8 x i64*>, i32, <8 x i1>)
+declare void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64>, <4 x i64*>, i32, <4 x i1>)
+declare void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64>, <2 x i64*>, i32, <2 x i1>)
+declare void @llvm.masked.scatter.v1i64.v1p0i64(<1 x i64>, <1 x i64*>, i32, <1 x i1>)
+
+declare void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32>, <16 x i32*>, i32, <16 x i1>)
+declare void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32>, <8 x i32*>, i32, <8 x i1>)
+declare void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32>, <4 x i32*>, i32, <4 x i1>)
+declare void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32>, <2 x i32*>, i32, <2 x i1>)
+
+declare void @llvm.masked.scatter.v32i16.v32p0i16(<32 x i16>, <32 x i16*>, i32, <32 x i1>)
+declare void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16>, <16 x i16*>, i32, <16 x i1>)
+declare void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16>, <8 x i16*>, i32, <8 x i1>)
+declare void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16>, <4 x i16*>, i32, <4 x i1>)
+
+declare void @llvm.masked.scatter.v64i8.v64p0i8(<64 x i8>, <64 x i8*>, i32, <64 x i1>)
+declare void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8>, <32 x i8*>, i32, <32 x i1>)
+declare void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8>, <16 x i8*>, i32, <16 x i1>)
+declare void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8>, <8 x i8*>, i32, <8 x i1>)
+
+declare <8 x double> @llvm.masked.expandload.v8f64(double*, <8 x i1>, <8 x double>)
+declare <4 x double> @llvm.masked.expandload.v4f64(double*, <4 x i1>, <4 x double>)
+declare <2 x double> @llvm.masked.expandload.v2f64(double*, <2 x i1>, <2 x double>)
+declare <1 x double> @llvm.masked.expandload.v1f64(double*, <1 x i1>, <1 x double>)
+
+declare <16 x float> @llvm.masked.expandload.v16f32(float*, <16 x i1>, <16 x float>)
+declare <8 x float> @llvm.masked.expandload.v8f32(float*, <8 x i1>, <8 x float>)
+declare <4 x float> @llvm.masked.expandload.v4f32(float*, <4 x i1>, <4 x float>)
+declare <2 x float> @llvm.masked.expandload.v2f32(float*, <2 x i1>, <2 x float>)
+
+declare <8 x i64> @llvm.masked.expandload.v8i64(i64*, <8 x i1>, <8 x i64>)
+declare <4 x i64> @llvm.masked.expandload.v4i64(i64*, <4 x i1>, <4 x i64>)
+declare <2 x i64> @llvm.masked.expandload.v2i64(i64*, <2 x i1>, <2 x i64>)
+declare <1 x i64> @llvm.masked.expandload.v1i64(i64*, <1 x i1>, <1 x i64>)
+
+declare <16 x i32> @llvm.masked.expandload.v16i32(i32*, <16 x i1>, <16 x i32>)
+declare <8 x i32> @llvm.masked.expandload.v8i32(i32*, <8 x i1>, <8 x i32>)
+declare <4 x i32> @llvm.masked.expandload.v4i32(i32*, <4 x i1>, <4 x i32>)
+declare <2 x i32> @llvm.masked.expandload.v2i32(i32*, <2 x i1>, <2 x i32>)
+
+declare <32 x i16> @llvm.masked.expandload.v32i16(i16*, <32 x i1>, <32 x i16>)
+declare <16 x i16> @llvm.masked.expandload.v16i16(i16*, <16 x i1>, <16 x i16>)
+declare <8 x i16> @llvm.masked.expandload.v8i16(i16*, <8 x i1>, <8 x i16>)
+declare <4 x i16> @llvm.masked.expandload.v4i16(i16*, <4 x i1>, <4 x i16>)
+
+declare <64 x i8> @llvm.masked.expandload.v64i8(i8*, <64 x i1>, <64 x i8>)
+declare <32 x i8> @llvm.masked.expandload.v32i8(i8*, <32 x i1>, <32 x i8>)
+declare <16 x i8> @llvm.masked.expandload.v16i8(i8*, <16 x i1>, <16 x i8>)
+declare <8 x i8> @llvm.masked.expandload.v8i8(i8*, <8 x i1>, <8 x i8>)
+
+declare void @llvm.masked.compressstore.v8f64(<8 x double>, double*, <8 x i1>)
+declare void @llvm.masked.compressstore.v4f64(<4 x double>, double*, <4 x i1>)
+declare void @llvm.masked.compressstore.v2f64(<2 x double>, double*, <2 x i1>)
+declare void @llvm.masked.compressstore.v1f64(<1 x double>, double*, <1 x i1>)
+
+declare void @llvm.masked.compressstore.v16f32(<16 x float>, float*, <16 x i1>)
+declare void @llvm.masked.compressstore.v8f32(<8 x float>, float*, <8 x i1>)
+declare void @llvm.masked.compressstore.v4f32(<4 x float>, float*, <4 x i1>)
+declare void @llvm.masked.compressstore.v2f32(<2 x float>, float*, <2 x i1>)
+
+declare void @llvm.masked.compressstore.v8i64(<8 x i64>, i64*, <8 x i1>)
+declare void @llvm.masked.compressstore.v4i64(<4 x i64>, i64*, <4 x i1>)
+declare void @llvm.masked.compressstore.v2i64(<2 x i64>, i64*, <2 x i1>)
+declare void @llvm.masked.compressstore.v1i64(<1 x i64>, i64*, <1 x i1>)
+
+declare void @llvm.masked.compressstore.v16i32(<16 x i32>, i32*, <16 x i1>)
+declare void @llvm.masked.compressstore.v8i32(<8 x i32>, i32*, <8 x i1>)
+declare void @llvm.masked.compressstore.v4i32(<4 x i32>, i32*, <4 x i1>)
+declare void @llvm.masked.compressstore.v2i32(<2 x i32>, i32*, <2 x i1>)
+
+declare void @llvm.masked.compressstore.v32i16(<32 x i16>, i16*, <32 x i1>)
+declare void @llvm.masked.compressstore.v16i16(<16 x i16>, i16*, <16 x i1>)
+declare void @llvm.masked.compressstore.v8i16(<8 x i16>, i16*, <8 x i1>)
+declare void @llvm.masked.compressstore.v4i16(<4 x i16>, i16*, <4 x i1>)
+
+declare void @llvm.masked.compressstore.v64i8(<64 x i8>, i8*, <64 x i1>)
+declare void @llvm.masked.compressstore.v32i8(<32 x i8>, i8*, <32 x i1>)
+declare void @llvm.masked.compressstore.v16i8(<16 x i8>, i8*, <16 x i1>)
+declare void @llvm.masked.compressstore.v8i8(<8 x i8>, i8*, <8 x i1>)
diff --git a/llvm/test/Analysis/CostModel/X86/uniformshift-inseltpoison.ll b/llvm/test/Analysis/CostModel/X86/uniformshift-inseltpoison.ll
new file mode 100644
index 000000000000..bfbfcdbcd5e3
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/X86/uniformshift-inseltpoison.ll
@@ -0,0 +1,39 @@
+; RUN: llc -mtriple=x86_64-apple-darwin -mattr=+sse2 < %s | FileCheck --check-prefix=SSE2-CODEGEN %s
+; RUN: opt -mtriple=x86_64-apple-darwin -mattr=+sse2 -cost-model -analyze < %s | FileCheck --check-prefix=SSE2 %s
+
+define <4 x i32> @shl(<4 x i32> %vector, i32 %scalar) {
+entry:
+ ; SSE2: 'shl'
+ ; SSE2: cost of 1 {{.*}} shl
+ ; SSE2-CODEGEN: movd %edi, %xmm1
+ ; SSE2-CODEGEN: pslld %xmm1, %xmm0
+ %insert = insertelement <4 x i32> poison, i32 %scalar, i32 0
+ %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+ %ret = shl <4 x i32> %vector , %splat
+ ret <4 x i32> %ret
+}
+
+define <4 x i32> @ashr(<4 x i32> %vector, i32 %scalar) {
+entry:
+ ; SSE2: 'ashr'
+ ; SSE2: cost of 1 {{.*}} ashr
+ ; SSE2-CODEGEN: movd %edi, %xmm1
+ ; SSE2-CODEGEN: psrad %xmm1, %xmm0
+ %insert = insertelement <4 x i32> poison, i32 %scalar, i32 0
+ %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+ %ret = ashr <4 x i32> %vector , %splat
+ ret <4 x i32> %ret
+}
+
+define <4 x i32> @lshr(<4 x i32> %vector, i32 %scalar) {
+entry:
+ ; SSE2: 'lshr'
+ ; SSE2: cost of 1 {{.*}} lshr
+ ; SSE2-CODEGEN: movd %edi, %xmm1
+ ; SSE2-CODEGEN: psrld %xmm1, %xmm0
+ %insert = insertelement <4 x i32> poison, i32 %scalar, i32 0
+ %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+ %ret = lshr <4 x i32> %vector , %splat
+ ret <4 x i32> %ret
+}
+
diff --git a/llvm/test/Analysis/CostModel/X86/vector-insert-inseltpoison.ll b/llvm/test/Analysis/CostModel/X86/vector-insert-inseltpoison.ll
new file mode 100644
index 000000000000..f6f5ed8029b1
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/X86/vector-insert-inseltpoison.ll
@@ -0,0 +1,1270 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -mtriple=x86_64-apple-macosx10.8.0 -cost-model -analyze -mattr=+sse2 | FileCheck %s --check-prefixes=SSE,SSE2
+; RUN: opt < %s -mtriple=x86_64-apple-macosx10.8.0 -cost-model -analyze -mattr=+sse3 | FileCheck %s --check-prefixes=SSE,SSE3
+; RUN: opt < %s -mtriple=x86_64-apple-macosx10.8.0 -cost-model -analyze -mattr=+ssse3 | FileCheck %s --check-prefixes=SSE,SSSE3
+; RUN: opt < %s -mtriple=x86_64-apple-macosx10.8.0 -cost-model -analyze -mattr=+sse4.1 | FileCheck %s --check-prefixes=SSE,SSE4
+; RUN: opt < %s -mtriple=x86_64-apple-macosx10.8.0 -cost-model -analyze -mattr=+sse4.2 | FileCheck %s --check-prefixes=SSE,SSE4
+; RUN: opt < %s -mtriple=x86_64-apple-macosx10.8.0 -cost-model -analyze -mattr=+avx | FileCheck %s --check-prefixes=AVX
+; RUN: opt < %s -mtriple=x86_64-apple-macosx10.8.0 -cost-model -analyze -mattr=+avx2 | FileCheck %s --check-prefixes=AVX
+; RUN: opt < %s -mtriple=x86_64-apple-macosx10.8.0 -cost-model -analyze -mattr=+avx512f | FileCheck %s --check-prefixes=AVX512
+; RUN: opt < %s -mtriple=x86_64-apple-macosx10.8.0 -cost-model -analyze -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=AVX512
+;
+; RUN: opt < %s -mtriple=x86_64-apple-macosx10.8.0 -cost-model -analyze -mcpu=slm | FileCheck %s --check-prefixes=SSE,SLM
+; RUN: opt < %s -mtriple=x86_64-apple-macosx10.8.0 -cost-model -analyze -mcpu=goldmont | FileCheck %s --check-prefixes=SSE,GLM
+; RUN: opt < %s -mtriple=x86_64-apple-macosx10.8.0 -cost-model -analyze -mcpu=btver2 | FileCheck %s --check-prefixes=AVX
+
+define i32 @insert_double(i32 %arg) {
+; SSE-LABEL: 'insert_double'
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f64_a = insertelement <2 x double> poison, double undef, i32 %arg
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2f64_0 = insertelement <2 x double> poison, double undef, i32 0
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f64_1 = insertelement <2 x double> poison, double undef, i32 1
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f64_a = insertelement <4 x double> poison, double undef, i32 %arg
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v4f64_0 = insertelement <4 x double> poison, double undef, i32 0
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f64_3 = insertelement <4 x double> poison, double undef, i32 3
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f64_a = insertelement <8 x double> poison, double undef, i32 %arg
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f64_0 = insertelement <8 x double> poison, double undef, i32 0
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f64_3 = insertelement <8 x double> poison, double undef, i32 3
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f64_4 = insertelement <8 x double> poison, double undef, i32 4
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f64_7 = insertelement <8 x double> poison, double undef, i32 7
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'insert_double'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f64_a = insertelement <2 x double> poison, double undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2f64_0 = insertelement <2 x double> poison, double undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f64_1 = insertelement <2 x double> poison, double undef, i32 1
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f64_a = insertelement <4 x double> poison, double undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v4f64_0 = insertelement <4 x double> poison, double undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4f64_3 = insertelement <4 x double> poison, double undef, i32 3
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f64_a = insertelement <8 x double> poison, double undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f64_0 = insertelement <8 x double> poison, double undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8f64_3 = insertelement <8 x double> poison, double undef, i32 3
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f64_4 = insertelement <8 x double> poison, double undef, i32 4
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8f64_7 = insertelement <8 x double> poison, double undef, i32 7
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'insert_double'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f64_a = insertelement <2 x double> poison, double undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2f64_0 = insertelement <2 x double> poison, double undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f64_1 = insertelement <2 x double> poison, double undef, i32 1
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f64_a = insertelement <4 x double> poison, double undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v4f64_0 = insertelement <4 x double> poison, double undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4f64_3 = insertelement <4 x double> poison, double undef, i32 3
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f64_a = insertelement <8 x double> poison, double undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f64_0 = insertelement <8 x double> poison, double undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8f64_3 = insertelement <8 x double> poison, double undef, i32 3
+; AVX512-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f64_4 = insertelement <8 x double> poison, double undef, i32 4
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8f64_7 = insertelement <8 x double> poison, double undef, i32 7
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+ %v2f64_a = insertelement <2 x double> poison, double undef, i32 %arg
+ %v2f64_0 = insertelement <2 x double> poison, double undef, i32 0
+ %v2f64_1 = insertelement <2 x double> poison, double undef, i32 1
+
+ %v4f64_a = insertelement <4 x double> poison, double undef, i32 %arg
+ %v4f64_0 = insertelement <4 x double> poison, double undef, i32 0
+ %v4f64_3 = insertelement <4 x double> poison, double undef, i32 3
+
+ %v8f64_a = insertelement <8 x double> poison, double undef, i32 %arg
+ %v8f64_0 = insertelement <8 x double> poison, double undef, i32 0
+ %v8f64_3 = insertelement <8 x double> poison, double undef, i32 3
+ %v8f64_4 = insertelement <8 x double> poison, double undef, i32 4
+ %v8f64_7 = insertelement <8 x double> poison, double undef, i32 7
+
+ ret i32 undef
+}
+
+define i32 @insert_float(i32 %arg) {
+; SSE2-LABEL: 'insert_float'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32_a = insertelement <2 x float> poison, float undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2f32_0 = insertelement <2 x float> poison, float undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2f32_1 = insertelement <2 x float> poison, float undef, i32 1
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32_a = insertelement <4 x float> poison, float undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v4f32_0 = insertelement <4 x float> poison, float undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4f32_3 = insertelement <4 x float> poison, float undef, i32 3
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_a = insertelement <8 x float> poison, float undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f32_0 = insertelement <8 x float> poison, float undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f32_3 = insertelement <8 x float> poison, float undef, i32 3
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f32_4 = insertelement <8 x float> poison, float undef, i32 4
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f32_7 = insertelement <8 x float> poison, float undef, i32 7
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32_a = insertelement <16 x float> poison, float undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f32_0 = insertelement <16 x float> poison, float undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16f32_3 = insertelement <16 x float> poison, float undef, i32 3
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f32_8 = insertelement <16 x float> poison, float undef, i32 8
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16f32_15 = insertelement <16 x float> poison, float undef, i32 15
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE3-LABEL: 'insert_float'
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32_a = insertelement <2 x float> poison, float undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2f32_0 = insertelement <2 x float> poison, float undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2f32_1 = insertelement <2 x float> poison, float undef, i32 1
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32_a = insertelement <4 x float> poison, float undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v4f32_0 = insertelement <4 x float> poison, float undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4f32_3 = insertelement <4 x float> poison, float undef, i32 3
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_a = insertelement <8 x float> poison, float undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f32_0 = insertelement <8 x float> poison, float undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f32_3 = insertelement <8 x float> poison, float undef, i32 3
+; SSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f32_4 = insertelement <8 x float> poison, float undef, i32 4
+; SSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f32_7 = insertelement <8 x float> poison, float undef, i32 7
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32_a = insertelement <16 x float> poison, float undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f32_0 = insertelement <16 x float> poison, float undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16f32_3 = insertelement <16 x float> poison, float undef, i32 3
+; SSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f32_8 = insertelement <16 x float> poison, float undef, i32 8
+; SSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16f32_15 = insertelement <16 x float> poison, float undef, i32 15
+; SSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSSE3-LABEL: 'insert_float'
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32_a = insertelement <2 x float> poison, float undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2f32_0 = insertelement <2 x float> poison, float undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2f32_1 = insertelement <2 x float> poison, float undef, i32 1
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32_a = insertelement <4 x float> poison, float undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v4f32_0 = insertelement <4 x float> poison, float undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4f32_3 = insertelement <4 x float> poison, float undef, i32 3
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_a = insertelement <8 x float> poison, float undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f32_0 = insertelement <8 x float> poison, float undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f32_3 = insertelement <8 x float> poison, float undef, i32 3
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f32_4 = insertelement <8 x float> poison, float undef, i32 4
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f32_7 = insertelement <8 x float> poison, float undef, i32 7
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32_a = insertelement <16 x float> poison, float undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f32_0 = insertelement <16 x float> poison, float undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16f32_3 = insertelement <16 x float> poison, float undef, i32 3
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f32_8 = insertelement <16 x float> poison, float undef, i32 8
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16f32_15 = insertelement <16 x float> poison, float undef, i32 15
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE4-LABEL: 'insert_float'
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32_a = insertelement <2 x float> poison, float undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2f32_0 = insertelement <2 x float> poison, float undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32_1 = insertelement <2 x float> poison, float undef, i32 1
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32_a = insertelement <4 x float> poison, float undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v4f32_0 = insertelement <4 x float> poison, float undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32_3 = insertelement <4 x float> poison, float undef, i32 3
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_a = insertelement <8 x float> poison, float undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f32_0 = insertelement <8 x float> poison, float undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_3 = insertelement <8 x float> poison, float undef, i32 3
+; SSE4-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f32_4 = insertelement <8 x float> poison, float undef, i32 4
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_7 = insertelement <8 x float> poison, float undef, i32 7
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32_a = insertelement <16 x float> poison, float undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f32_0 = insertelement <16 x float> poison, float undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32_3 = insertelement <16 x float> poison, float undef, i32 3
+; SSE4-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f32_8 = insertelement <16 x float> poison, float undef, i32 8
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32_15 = insertelement <16 x float> poison, float undef, i32 15
+; SSE4-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'insert_float'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32_a = insertelement <2 x float> poison, float undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2f32_0 = insertelement <2 x float> poison, float undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32_1 = insertelement <2 x float> poison, float undef, i32 1
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32_a = insertelement <4 x float> poison, float undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v4f32_0 = insertelement <4 x float> poison, float undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32_3 = insertelement <4 x float> poison, float undef, i32 3
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_a = insertelement <8 x float> poison, float undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f32_0 = insertelement <8 x float> poison, float undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_3 = insertelement <8 x float> poison, float undef, i32 3
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f32_4 = insertelement <8 x float> poison, float undef, i32 4
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8f32_7 = insertelement <8 x float> poison, float undef, i32 7
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32_a = insertelement <16 x float> poison, float undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f32_0 = insertelement <16 x float> poison, float undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32_3 = insertelement <16 x float> poison, float undef, i32 3
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f32_8 = insertelement <16 x float> poison, float undef, i32 8
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16f32_15 = insertelement <16 x float> poison, float undef, i32 15
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'insert_float'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32_a = insertelement <2 x float> poison, float undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2f32_0 = insertelement <2 x float> poison, float undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32_1 = insertelement <2 x float> poison, float undef, i32 1
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32_a = insertelement <4 x float> poison, float undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v4f32_0 = insertelement <4 x float> poison, float undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32_3 = insertelement <4 x float> poison, float undef, i32 3
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_a = insertelement <8 x float> poison, float undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f32_0 = insertelement <8 x float> poison, float undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_3 = insertelement <8 x float> poison, float undef, i32 3
+; AVX512-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f32_4 = insertelement <8 x float> poison, float undef, i32 4
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8f32_7 = insertelement <8 x float> poison, float undef, i32 7
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32_a = insertelement <16 x float> poison, float undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f32_0 = insertelement <16 x float> poison, float undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32_3 = insertelement <16 x float> poison, float undef, i32 3
+; AVX512-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16f32_8 = insertelement <16 x float> poison, float undef, i32 8
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16f32_15 = insertelement <16 x float> poison, float undef, i32 15
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'insert_float'
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32_a = insertelement <2 x float> poison, float undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2f32_0 = insertelement <2 x float> poison, float undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32_1 = insertelement <2 x float> poison, float undef, i32 1
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32_a = insertelement <4 x float> poison, float undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v4f32_0 = insertelement <4 x float> poison, float undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32_3 = insertelement <4 x float> poison, float undef, i32 3
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_a = insertelement <8 x float> poison, float undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f32_0 = insertelement <8 x float> poison, float undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_3 = insertelement <8 x float> poison, float undef, i32 3
+; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f32_4 = insertelement <8 x float> poison, float undef, i32 4
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_7 = insertelement <8 x float> poison, float undef, i32 7
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32_a = insertelement <16 x float> poison, float undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f32_0 = insertelement <16 x float> poison, float undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32_3 = insertelement <16 x float> poison, float undef, i32 3
+; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f32_8 = insertelement <16 x float> poison, float undef, i32 8
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32_15 = insertelement <16 x float> poison, float undef, i32 15
+; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'insert_float'
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32_a = insertelement <2 x float> poison, float undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2f32_0 = insertelement <2 x float> poison, float undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32_1 = insertelement <2 x float> poison, float undef, i32 1
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32_a = insertelement <4 x float> poison, float undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v4f32_0 = insertelement <4 x float> poison, float undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32_3 = insertelement <4 x float> poison, float undef, i32 3
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_a = insertelement <8 x float> poison, float undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f32_0 = insertelement <8 x float> poison, float undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_3 = insertelement <8 x float> poison, float undef, i32 3
+; GLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v8f32_4 = insertelement <8 x float> poison, float undef, i32 4
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32_7 = insertelement <8 x float> poison, float undef, i32 7
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32_a = insertelement <16 x float> poison, float undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f32_0 = insertelement <16 x float> poison, float undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32_3 = insertelement <16 x float> poison, float undef, i32 3
+; GLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v16f32_8 = insertelement <16 x float> poison, float undef, i32 8
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32_15 = insertelement <16 x float> poison, float undef, i32 15
+; GLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+ %v2f32_a = insertelement <2 x float> poison, float undef, i32 %arg
+ %v2f32_0 = insertelement <2 x float> poison, float undef, i32 0
+ %v2f32_1 = insertelement <2 x float> poison, float undef, i32 1
+
+ %v4f32_a = insertelement <4 x float> poison, float undef, i32 %arg
+ %v4f32_0 = insertelement <4 x float> poison, float undef, i32 0
+ %v4f32_3 = insertelement <4 x float> poison, float undef, i32 3
+
+ %v8f32_a = insertelement <8 x float> poison, float undef, i32 %arg
+ %v8f32_0 = insertelement <8 x float> poison, float undef, i32 0
+ %v8f32_3 = insertelement <8 x float> poison, float undef, i32 3
+ %v8f32_4 = insertelement <8 x float> poison, float undef, i32 4
+ %v8f32_7 = insertelement <8 x float> poison, float undef, i32 7
+
+ %v16f32_a = insertelement <16 x float> poison, float undef, i32 %arg
+ %v16f32_0 = insertelement <16 x float> poison, float undef, i32 0
+ %v16f32_3 = insertelement <16 x float> poison, float undef, i32 3
+ %v16f32_8 = insertelement <16 x float> poison, float undef, i32 8
+ %v16f32_15 = insertelement <16 x float> poison, float undef, i32 15
+
+ ret i32 undef
+}
+
+define i32 @insert_i64(i32 %arg) {
+; SSE2-LABEL: 'insert_i64'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_a = insertelement <2 x i64> poison, i64 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i64_0 = insertelement <2 x i64> poison, i64 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i64_1 = insertelement <2 x i64> poison, i64 undef, i32 1
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64_a = insertelement <4 x i64> poison, i64 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i64_0 = insertelement <4 x i64> poison, i64 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i64_3 = insertelement <4 x i64> poison, i64 undef, i32 3
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_a = insertelement <8 x i64> poison, i64 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i64_0 = insertelement <8 x i64> poison, i64 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i64_3 = insertelement <8 x i64> poison, i64 undef, i32 3
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i64_4 = insertelement <8 x i64> poison, i64 undef, i32 4
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i64_7 = insertelement <8 x i64> poison, i64 undef, i32 7
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE3-LABEL: 'insert_i64'
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_a = insertelement <2 x i64> poison, i64 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i64_0 = insertelement <2 x i64> poison, i64 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i64_1 = insertelement <2 x i64> poison, i64 undef, i32 1
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64_a = insertelement <4 x i64> poison, i64 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i64_0 = insertelement <4 x i64> poison, i64 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i64_3 = insertelement <4 x i64> poison, i64 undef, i32 3
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_a = insertelement <8 x i64> poison, i64 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i64_0 = insertelement <8 x i64> poison, i64 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i64_3 = insertelement <8 x i64> poison, i64 undef, i32 3
+; SSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i64_4 = insertelement <8 x i64> poison, i64 undef, i32 4
+; SSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i64_7 = insertelement <8 x i64> poison, i64 undef, i32 7
+; SSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSSE3-LABEL: 'insert_i64'
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_a = insertelement <2 x i64> poison, i64 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i64_0 = insertelement <2 x i64> poison, i64 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i64_1 = insertelement <2 x i64> poison, i64 undef, i32 1
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64_a = insertelement <4 x i64> poison, i64 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i64_0 = insertelement <4 x i64> poison, i64 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i64_3 = insertelement <4 x i64> poison, i64 undef, i32 3
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_a = insertelement <8 x i64> poison, i64 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i64_0 = insertelement <8 x i64> poison, i64 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i64_3 = insertelement <8 x i64> poison, i64 undef, i32 3
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i64_4 = insertelement <8 x i64> poison, i64 undef, i32 4
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i64_7 = insertelement <8 x i64> poison, i64 undef, i32 7
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE4-LABEL: 'insert_i64'
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_a = insertelement <2 x i64> poison, i64 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_0 = insertelement <2 x i64> poison, i64 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_1 = insertelement <2 x i64> poison, i64 undef, i32 1
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64_a = insertelement <4 x i64> poison, i64 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64_0 = insertelement <4 x i64> poison, i64 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64_3 = insertelement <4 x i64> poison, i64 undef, i32 3
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_a = insertelement <8 x i64> poison, i64 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_0 = insertelement <8 x i64> poison, i64 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_3 = insertelement <8 x i64> poison, i64 undef, i32 3
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_4 = insertelement <8 x i64> poison, i64 undef, i32 4
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_7 = insertelement <8 x i64> poison, i64 undef, i32 7
+; SSE4-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'insert_i64'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_a = insertelement <2 x i64> poison, i64 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_0 = insertelement <2 x i64> poison, i64 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_1 = insertelement <2 x i64> poison, i64 undef, i32 1
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64_a = insertelement <4 x i64> poison, i64 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64_0 = insertelement <4 x i64> poison, i64 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i64_3 = insertelement <4 x i64> poison, i64 undef, i32 3
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_a = insertelement <8 x i64> poison, i64 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_0 = insertelement <8 x i64> poison, i64 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i64_3 = insertelement <8 x i64> poison, i64 undef, i32 3
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_4 = insertelement <8 x i64> poison, i64 undef, i32 4
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i64_7 = insertelement <8 x i64> poison, i64 undef, i32 7
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'insert_i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_a = insertelement <2 x i64> poison, i64 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_0 = insertelement <2 x i64> poison, i64 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_1 = insertelement <2 x i64> poison, i64 undef, i32 1
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64_a = insertelement <4 x i64> poison, i64 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64_0 = insertelement <4 x i64> poison, i64 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i64_3 = insertelement <4 x i64> poison, i64 undef, i32 3
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_a = insertelement <8 x i64> poison, i64 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_0 = insertelement <8 x i64> poison, i64 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i64_3 = insertelement <8 x i64> poison, i64 undef, i32 3
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i64_4 = insertelement <8 x i64> poison, i64 undef, i32 4
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i64_7 = insertelement <8 x i64> poison, i64 undef, i32 7
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'insert_i64'
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_a = insertelement <2 x i64> poison, i64 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_0 = insertelement <2 x i64> poison, i64 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_1 = insertelement <2 x i64> poison, i64 undef, i32 1
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64_a = insertelement <4 x i64> poison, i64 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64_0 = insertelement <4 x i64> poison, i64 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64_3 = insertelement <4 x i64> poison, i64 undef, i32 3
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_a = insertelement <8 x i64> poison, i64 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_0 = insertelement <8 x i64> poison, i64 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_3 = insertelement <8 x i64> poison, i64 undef, i32 3
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_4 = insertelement <8 x i64> poison, i64 undef, i32 4
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_7 = insertelement <8 x i64> poison, i64 undef, i32 7
+; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'insert_i64'
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_a = insertelement <2 x i64> poison, i64 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_0 = insertelement <2 x i64> poison, i64 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64_1 = insertelement <2 x i64> poison, i64 undef, i32 1
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64_a = insertelement <4 x i64> poison, i64 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64_0 = insertelement <4 x i64> poison, i64 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64_3 = insertelement <4 x i64> poison, i64 undef, i32 3
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_a = insertelement <8 x i64> poison, i64 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_0 = insertelement <8 x i64> poison, i64 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_3 = insertelement <8 x i64> poison, i64 undef, i32 3
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_4 = insertelement <8 x i64> poison, i64 undef, i32 4
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64_7 = insertelement <8 x i64> poison, i64 undef, i32 7
+; GLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+ %v2i64_a = insertelement <2 x i64> poison, i64 undef, i32 %arg
+ %v2i64_0 = insertelement <2 x i64> poison, i64 undef, i32 0
+ %v2i64_1 = insertelement <2 x i64> poison, i64 undef, i32 1
+
+ %v4i64_a = insertelement <4 x i64> poison, i64 undef, i32 %arg
+ %v4i64_0 = insertelement <4 x i64> poison, i64 undef, i32 0
+ %v4i64_3 = insertelement <4 x i64> poison, i64 undef, i32 3
+
+ %v8i64_a = insertelement <8 x i64> poison, i64 undef, i32 %arg
+ %v8i64_0 = insertelement <8 x i64> poison, i64 undef, i32 0
+ %v8i64_3 = insertelement <8 x i64> poison, i64 undef, i32 3
+ %v8i64_4 = insertelement <8 x i64> poison, i64 undef, i32 4
+ %v8i64_7 = insertelement <8 x i64> poison, i64 undef, i32 7
+
+ ret i32 undef
+}
+
+define i32 @insert_i32(i32 %arg) {
+; SSE2-LABEL: 'insert_i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32_a = insertelement <2 x i32> poison, i32 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i32_0 = insertelement <2 x i32> poison, i32 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i32_1 = insertelement <2 x i32> poison, i32 undef, i32 1
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32_a = insertelement <4 x i32> poison, i32 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i32_0 = insertelement <4 x i32> poison, i32 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i32_3 = insertelement <4 x i32> poison, i32 undef, i32 3
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_a = insertelement <8 x i32> poison, i32 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i32_0 = insertelement <8 x i32> poison, i32 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i32_3 = insertelement <8 x i32> poison, i32 undef, i32 3
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i32_4 = insertelement <8 x i32> poison, i32 undef, i32 4
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i32_7 = insertelement <8 x i32> poison, i32 undef, i32 7
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_a = insertelement <16 x i32> poison, i32 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i32_0 = insertelement <16 x i32> poison, i32 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i32_3 = insertelement <16 x i32> poison, i32 undef, i32 3
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i32_8 = insertelement <16 x i32> poison, i32 undef, i32 8
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i32_15 = insertelement <16 x i32> poison, i32 undef, i32 15
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE3-LABEL: 'insert_i32'
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32_a = insertelement <2 x i32> poison, i32 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i32_0 = insertelement <2 x i32> poison, i32 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i32_1 = insertelement <2 x i32> poison, i32 undef, i32 1
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32_a = insertelement <4 x i32> poison, i32 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i32_0 = insertelement <4 x i32> poison, i32 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i32_3 = insertelement <4 x i32> poison, i32 undef, i32 3
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_a = insertelement <8 x i32> poison, i32 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i32_0 = insertelement <8 x i32> poison, i32 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i32_3 = insertelement <8 x i32> poison, i32 undef, i32 3
+; SSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i32_4 = insertelement <8 x i32> poison, i32 undef, i32 4
+; SSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i32_7 = insertelement <8 x i32> poison, i32 undef, i32 7
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_a = insertelement <16 x i32> poison, i32 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i32_0 = insertelement <16 x i32> poison, i32 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i32_3 = insertelement <16 x i32> poison, i32 undef, i32 3
+; SSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i32_8 = insertelement <16 x i32> poison, i32 undef, i32 8
+; SSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i32_15 = insertelement <16 x i32> poison, i32 undef, i32 15
+; SSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSSE3-LABEL: 'insert_i32'
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32_a = insertelement <2 x i32> poison, i32 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i32_0 = insertelement <2 x i32> poison, i32 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i32_1 = insertelement <2 x i32> poison, i32 undef, i32 1
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32_a = insertelement <4 x i32> poison, i32 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i32_0 = insertelement <4 x i32> poison, i32 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i32_3 = insertelement <4 x i32> poison, i32 undef, i32 3
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_a = insertelement <8 x i32> poison, i32 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i32_0 = insertelement <8 x i32> poison, i32 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i32_3 = insertelement <8 x i32> poison, i32 undef, i32 3
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i32_4 = insertelement <8 x i32> poison, i32 undef, i32 4
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i32_7 = insertelement <8 x i32> poison, i32 undef, i32 7
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_a = insertelement <16 x i32> poison, i32 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i32_0 = insertelement <16 x i32> poison, i32 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i32_3 = insertelement <16 x i32> poison, i32 undef, i32 3
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i32_8 = insertelement <16 x i32> poison, i32 undef, i32 8
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i32_15 = insertelement <16 x i32> poison, i32 undef, i32 15
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE4-LABEL: 'insert_i32'
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32_a = insertelement <2 x i32> poison, i32 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32_0 = insertelement <2 x i32> poison, i32 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32_1 = insertelement <2 x i32> poison, i32 undef, i32 1
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32_a = insertelement <4 x i32> poison, i32 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32_0 = insertelement <4 x i32> poison, i32 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32_3 = insertelement <4 x i32> poison, i32 undef, i32 3
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_a = insertelement <8 x i32> poison, i32 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_0 = insertelement <8 x i32> poison, i32 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_3 = insertelement <8 x i32> poison, i32 undef, i32 3
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_4 = insertelement <8 x i32> poison, i32 undef, i32 4
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_7 = insertelement <8 x i32> poison, i32 undef, i32 7
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_a = insertelement <16 x i32> poison, i32 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_0 = insertelement <16 x i32> poison, i32 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_3 = insertelement <16 x i32> poison, i32 undef, i32 3
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_8 = insertelement <16 x i32> poison, i32 undef, i32 8
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_15 = insertelement <16 x i32> poison, i32 undef, i32 15
+; SSE4-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'insert_i32'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32_a = insertelement <2 x i32> poison, i32 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32_0 = insertelement <2 x i32> poison, i32 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32_1 = insertelement <2 x i32> poison, i32 undef, i32 1
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32_a = insertelement <4 x i32> poison, i32 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32_0 = insertelement <4 x i32> poison, i32 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32_3 = insertelement <4 x i32> poison, i32 undef, i32 3
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_a = insertelement <8 x i32> poison, i32 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_0 = insertelement <8 x i32> poison, i32 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_3 = insertelement <8 x i32> poison, i32 undef, i32 3
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i32_4 = insertelement <8 x i32> poison, i32 undef, i32 4
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i32_7 = insertelement <8 x i32> poison, i32 undef, i32 7
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_a = insertelement <16 x i32> poison, i32 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_0 = insertelement <16 x i32> poison, i32 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_3 = insertelement <16 x i32> poison, i32 undef, i32 3
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_8 = insertelement <16 x i32> poison, i32 undef, i32 8
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i32_15 = insertelement <16 x i32> poison, i32 undef, i32 15
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'insert_i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32_a = insertelement <2 x i32> poison, i32 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32_0 = insertelement <2 x i32> poison, i32 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32_1 = insertelement <2 x i32> poison, i32 undef, i32 1
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32_a = insertelement <4 x i32> poison, i32 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32_0 = insertelement <4 x i32> poison, i32 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32_3 = insertelement <4 x i32> poison, i32 undef, i32 3
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_a = insertelement <8 x i32> poison, i32 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_0 = insertelement <8 x i32> poison, i32 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_3 = insertelement <8 x i32> poison, i32 undef, i32 3
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i32_4 = insertelement <8 x i32> poison, i32 undef, i32 4
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v8i32_7 = insertelement <8 x i32> poison, i32 undef, i32 7
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_a = insertelement <16 x i32> poison, i32 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_0 = insertelement <16 x i32> poison, i32 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_3 = insertelement <16 x i32> poison, i32 undef, i32 3
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i32_8 = insertelement <16 x i32> poison, i32 undef, i32 8
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i32_15 = insertelement <16 x i32> poison, i32 undef, i32 15
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'insert_i32'
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32_a = insertelement <2 x i32> poison, i32 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32_0 = insertelement <2 x i32> poison, i32 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32_1 = insertelement <2 x i32> poison, i32 undef, i32 1
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32_a = insertelement <4 x i32> poison, i32 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32_0 = insertelement <4 x i32> poison, i32 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32_3 = insertelement <4 x i32> poison, i32 undef, i32 3
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_a = insertelement <8 x i32> poison, i32 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_0 = insertelement <8 x i32> poison, i32 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_3 = insertelement <8 x i32> poison, i32 undef, i32 3
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_4 = insertelement <8 x i32> poison, i32 undef, i32 4
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_7 = insertelement <8 x i32> poison, i32 undef, i32 7
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_a = insertelement <16 x i32> poison, i32 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_0 = insertelement <16 x i32> poison, i32 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_3 = insertelement <16 x i32> poison, i32 undef, i32 3
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_8 = insertelement <16 x i32> poison, i32 undef, i32 8
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_15 = insertelement <16 x i32> poison, i32 undef, i32 15
+; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'insert_i32'
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32_a = insertelement <2 x i32> poison, i32 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32_0 = insertelement <2 x i32> poison, i32 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32_1 = insertelement <2 x i32> poison, i32 undef, i32 1
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32_a = insertelement <4 x i32> poison, i32 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32_0 = insertelement <4 x i32> poison, i32 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32_3 = insertelement <4 x i32> poison, i32 undef, i32 3
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_a = insertelement <8 x i32> poison, i32 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_0 = insertelement <8 x i32> poison, i32 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_3 = insertelement <8 x i32> poison, i32 undef, i32 3
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_4 = insertelement <8 x i32> poison, i32 undef, i32 4
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32_7 = insertelement <8 x i32> poison, i32 undef, i32 7
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_a = insertelement <16 x i32> poison, i32 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_0 = insertelement <16 x i32> poison, i32 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_3 = insertelement <16 x i32> poison, i32 undef, i32 3
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_8 = insertelement <16 x i32> poison, i32 undef, i32 8
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32_15 = insertelement <16 x i32> poison, i32 undef, i32 15
+; GLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+ %v2i32_a = insertelement <2 x i32> poison, i32 undef, i32 %arg
+ %v2i32_0 = insertelement <2 x i32> poison, i32 undef, i32 0
+ %v2i32_1 = insertelement <2 x i32> poison, i32 undef, i32 1
+
+ %v4i32_a = insertelement <4 x i32> poison, i32 undef, i32 %arg
+ %v4i32_0 = insertelement <4 x i32> poison, i32 undef, i32 0
+ %v4i32_3 = insertelement <4 x i32> poison, i32 undef, i32 3
+
+ %v8i32_a = insertelement <8 x i32> poison, i32 undef, i32 %arg
+ %v8i32_0 = insertelement <8 x i32> poison, i32 undef, i32 0
+ %v8i32_3 = insertelement <8 x i32> poison, i32 undef, i32 3
+ %v8i32_4 = insertelement <8 x i32> poison, i32 undef, i32 4
+ %v8i32_7 = insertelement <8 x i32> poison, i32 undef, i32 7
+
+ %v16i32_a = insertelement <16 x i32> poison, i32 undef, i32 %arg
+ %v16i32_0 = insertelement <16 x i32> poison, i32 undef, i32 0
+ %v16i32_3 = insertelement <16 x i32> poison, i32 undef, i32 3
+ %v16i32_8 = insertelement <16 x i32> poison, i32 undef, i32 8
+ %v16i32_15 = insertelement <16 x i32> poison, i32 undef, i32 15
+
+ ret i32 undef
+}
+
+define i32 @insert_i16(i32 %arg) {
+; SSE-LABEL: 'insert_i16'
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16_a = insertelement <2 x i16> poison, i16 undef, i32 %arg
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16_0 = insertelement <2 x i16> poison, i16 undef, i32 0
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16_1 = insertelement <2 x i16> poison, i16 undef, i32 1
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16_a = insertelement <4 x i16> poison, i16 undef, i32 %arg
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16_0 = insertelement <4 x i16> poison, i16 undef, i32 0
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16_3 = insertelement <4 x i16> poison, i16 undef, i32 3
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16_a = insertelement <8 x i16> poison, i16 undef, i32 %arg
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16_0 = insertelement <8 x i16> poison, i16 undef, i32 0
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16_7 = insertelement <8 x i16> poison, i16 undef, i32 7
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16_a = insertelement <16 x i16> poison, i16 undef, i32 %arg
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16_0 = insertelement <16 x i16> poison, i16 undef, i32 0
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16_7 = insertelement <16 x i16> poison, i16 undef, i32 7
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16_8 = insertelement <16 x i16> poison, i16 undef, i32 8
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16_15 = insertelement <16 x i16> poison, i16 undef, i32 15
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i16_a = insertelement <32 x i16> poison, i16 undef, i32 %arg
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i16_0 = insertelement <32 x i16> poison, i16 undef, i32 0
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i16_7 = insertelement <32 x i16> poison, i16 undef, i32 7
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i16_8 = insertelement <32 x i16> poison, i16 undef, i32 8
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i16_15 = insertelement <32 x i16> poison, i16 undef, i32 15
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i16_16 = insertelement <32 x i16> poison, i16 undef, i32 16
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i16_24 = insertelement <32 x i16> poison, i16 undef, i32 24
+; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i16_31 = insertelement <32 x i16> poison, i16 undef, i32 31
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'insert_i16'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16_a = insertelement <2 x i16> poison, i16 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16_0 = insertelement <2 x i16> poison, i16 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16_1 = insertelement <2 x i16> poison, i16 undef, i32 1
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16_a = insertelement <4 x i16> poison, i16 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16_0 = insertelement <4 x i16> poison, i16 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16_3 = insertelement <4 x i16> poison, i16 undef, i32 3
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16_a = insertelement <8 x i16> poison, i16 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16_0 = insertelement <8 x i16> poison, i16 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16_7 = insertelement <8 x i16> poison, i16 undef, i32 7
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16_a = insertelement <16 x i16> poison, i16 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16_0 = insertelement <16 x i16> poison, i16 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16_7 = insertelement <16 x i16> poison, i16 undef, i32 7
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i16_8 = insertelement <16 x i16> poison, i16 undef, i32 8
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i16_15 = insertelement <16 x i16> poison, i16 undef, i32 15
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i16_a = insertelement <32 x i16> poison, i16 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i16_0 = insertelement <32 x i16> poison, i16 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i16_7 = insertelement <32 x i16> poison, i16 undef, i32 7
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v32i16_8 = insertelement <32 x i16> poison, i16 undef, i32 8
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v32i16_15 = insertelement <32 x i16> poison, i16 undef, i32 15
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i16_16 = insertelement <32 x i16> poison, i16 undef, i32 16
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v32i16_24 = insertelement <32 x i16> poison, i16 undef, i32 24
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v32i16_31 = insertelement <32 x i16> poison, i16 undef, i32 31
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'insert_i16'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16_a = insertelement <2 x i16> poison, i16 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16_0 = insertelement <2 x i16> poison, i16 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16_1 = insertelement <2 x i16> poison, i16 undef, i32 1
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16_a = insertelement <4 x i16> poison, i16 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16_0 = insertelement <4 x i16> poison, i16 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16_3 = insertelement <4 x i16> poison, i16 undef, i32 3
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16_a = insertelement <8 x i16> poison, i16 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16_0 = insertelement <8 x i16> poison, i16 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16_7 = insertelement <8 x i16> poison, i16 undef, i32 7
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16_a = insertelement <16 x i16> poison, i16 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16_0 = insertelement <16 x i16> poison, i16 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16_7 = insertelement <16 x i16> poison, i16 undef, i32 7
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i16_8 = insertelement <16 x i16> poison, i16 undef, i32 8
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v16i16_15 = insertelement <16 x i16> poison, i16 undef, i32 15
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i16_a = insertelement <32 x i16> poison, i16 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i16_0 = insertelement <32 x i16> poison, i16 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i16_7 = insertelement <32 x i16> poison, i16 undef, i32 7
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v32i16_8 = insertelement <32 x i16> poison, i16 undef, i32 8
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v32i16_15 = insertelement <32 x i16> poison, i16 undef, i32 15
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v32i16_16 = insertelement <32 x i16> poison, i16 undef, i32 16
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v32i16_24 = insertelement <32 x i16> poison, i16 undef, i32 24
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v32i16_31 = insertelement <32 x i16> poison, i16 undef, i32 31
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+ %v2i16_a = insertelement <2 x i16> poison, i16 undef, i32 %arg
+ %v2i16_0 = insertelement <2 x i16> poison, i16 undef, i32 0
+ %v2i16_1 = insertelement <2 x i16> poison, i16 undef, i32 1
+
+ %v4i16_a = insertelement <4 x i16> poison, i16 undef, i32 %arg
+ %v4i16_0 = insertelement <4 x i16> poison, i16 undef, i32 0
+ %v4i16_3 = insertelement <4 x i16> poison, i16 undef, i32 3
+
+ %v8i16_a = insertelement <8 x i16> poison, i16 undef, i32 %arg
+ %v8i16_0 = insertelement <8 x i16> poison, i16 undef, i32 0
+ %v8i16_7 = insertelement <8 x i16> poison, i16 undef, i32 7
+
+ %v16i16_a = insertelement <16 x i16> poison, i16 undef, i32 %arg
+ %v16i16_0 = insertelement <16 x i16> poison, i16 undef, i32 0
+ %v16i16_7 = insertelement <16 x i16> poison, i16 undef, i32 7
+ %v16i16_8 = insertelement <16 x i16> poison, i16 undef, i32 8
+ %v16i16_15 = insertelement <16 x i16> poison, i16 undef, i32 15
+
+ %v32i16_a = insertelement <32 x i16> poison, i16 undef, i32 %arg
+ %v32i16_0 = insertelement <32 x i16> poison, i16 undef, i32 0
+ %v32i16_7 = insertelement <32 x i16> poison, i16 undef, i32 7
+ %v32i16_8 = insertelement <32 x i16> poison, i16 undef, i32 8
+ %v32i16_15 = insertelement <32 x i16> poison, i16 undef, i32 15
+ %v32i16_16 = insertelement <32 x i16> poison, i16 undef, i32 16
+ %v32i16_24 = insertelement <32 x i16> poison, i16 undef, i32 24
+ %v32i16_31 = insertelement <32 x i16> poison, i16 undef, i32 31
+
+ ret i32 undef
+}
+
+define i32 @insert_i8(i32 %arg) {
+; SSE2-LABEL: 'insert_i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i8_a = insertelement <2 x i8> poison, i8 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i8_0 = insertelement <2 x i8> poison, i8 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i8_3 = insertelement <2 x i8> poison, i8 undef, i32 1
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_a = insertelement <4 x i8> poison, i8 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %v4i8_0 = insertelement <4 x i8> poison, i8 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %v4i8_3 = insertelement <4 x i8> poison, i8 undef, i32 3
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_a = insertelement <8 x i8> poison, i8 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8i8_0 = insertelement <8 x i8> poison, i8 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8i8_7 = insertelement <8 x i8> poison, i8 undef, i32 7
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_a = insertelement <16 x i8> poison, i8 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v16i8_0 = insertelement <16 x i8> poison, i8 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v16i8_8 = insertelement <16 x i8> poison, i8 undef, i32 8
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v16i8_15 = insertelement <16 x i8> poison, i8 undef, i32 15
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_a = insertelement <32 x i8> poison, i8 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i8_0 = insertelement <32 x i8> poison, i8 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i8_7 = insertelement <32 x i8> poison, i8 undef, i32 7
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i8_8 = insertelement <32 x i8> poison, i8 undef, i32 8
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i8_15 = insertelement <32 x i8> poison, i8 undef, i32 15
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i8_24 = insertelement <32 x i8> poison, i8 undef, i32 24
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i8_31 = insertelement <32 x i8> poison, i8 undef, i32 31
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_a = insertelement <64 x i8> poison, i8 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i8_0 = insertelement <64 x i8> poison, i8 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i8_7 = insertelement <64 x i8> poison, i8 undef, i32 7
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i8_8 = insertelement <64 x i8> poison, i8 undef, i32 8
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i8_15 = insertelement <64 x i8> poison, i8 undef, i32 15
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i8_24 = insertelement <64 x i8> poison, i8 undef, i32 24
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i8_31 = insertelement <64 x i8> poison, i8 undef, i32 31
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i8_32 = insertelement <64 x i8> poison, i8 undef, i32 32
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i8_48 = insertelement <64 x i8> poison, i8 undef, i32 48
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i8_63 = insertelement <64 x i8> poison, i8 undef, i32 63
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE3-LABEL: 'insert_i8'
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i8_a = insertelement <2 x i8> poison, i8 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i8_0 = insertelement <2 x i8> poison, i8 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2i8_3 = insertelement <2 x i8> poison, i8 undef, i32 1
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_a = insertelement <4 x i8> poison, i8 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %v4i8_0 = insertelement <4 x i8> poison, i8 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %v4i8_3 = insertelement <4 x i8> poison, i8 undef, i32 3
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_a = insertelement <8 x i8> poison, i8 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8i8_0 = insertelement <8 x i8> poison, i8 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %v8i8_7 = insertelement <8 x i8> poison, i8 undef, i32 7
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_a = insertelement <16 x i8> poison, i8 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v16i8_0 = insertelement <16 x i8> poison, i8 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v16i8_8 = insertelement <16 x i8> poison, i8 undef, i32 8
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v16i8_15 = insertelement <16 x i8> poison, i8 undef, i32 15
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_a = insertelement <32 x i8> poison, i8 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i8_0 = insertelement <32 x i8> poison, i8 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i8_7 = insertelement <32 x i8> poison, i8 undef, i32 7
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i8_8 = insertelement <32 x i8> poison, i8 undef, i32 8
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i8_15 = insertelement <32 x i8> poison, i8 undef, i32 15
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i8_24 = insertelement <32 x i8> poison, i8 undef, i32 24
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i8_31 = insertelement <32 x i8> poison, i8 undef, i32 31
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_a = insertelement <64 x i8> poison, i8 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i8_0 = insertelement <64 x i8> poison, i8 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i8_7 = insertelement <64 x i8> poison, i8 undef, i32 7
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i8_8 = insertelement <64 x i8> poison, i8 undef, i32 8
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i8_15 = insertelement <64 x i8> poison, i8 undef, i32 15
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i8_24 = insertelement <64 x i8> poison, i8 undef, i32 24
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i8_31 = insertelement <64 x i8> poison, i8 undef, i32 31
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i8_32 = insertelement <64 x i8> poison, i8 undef, i32 32
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i8_48 = insertelement <64 x i8> poison, i8 undef, i32 48
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i8_63 = insertelement <64 x i8> poison, i8 undef, i32 63
+; SSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSSE3-LABEL: 'insert_i8'
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i8_a = insertelement <2 x i8> poison, i8 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2i8_0 = insertelement <2 x i8> poison, i8 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2i8_3 = insertelement <2 x i8> poison, i8 undef, i32 1
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_a = insertelement <4 x i8> poison, i8 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v4i8_0 = insertelement <4 x i8> poison, i8 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v4i8_3 = insertelement <4 x i8> poison, i8 undef, i32 3
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_a = insertelement <8 x i8> poison, i8 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i8_0 = insertelement <8 x i8> poison, i8 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i8_7 = insertelement <8 x i8> poison, i8 undef, i32 7
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_a = insertelement <16 x i8> poison, i8 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i8_0 = insertelement <16 x i8> poison, i8 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i8_8 = insertelement <16 x i8> poison, i8 undef, i32 8
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i8_15 = insertelement <16 x i8> poison, i8 undef, i32 15
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_a = insertelement <32 x i8> poison, i8 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v32i8_0 = insertelement <32 x i8> poison, i8 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v32i8_7 = insertelement <32 x i8> poison, i8 undef, i32 7
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v32i8_8 = insertelement <32 x i8> poison, i8 undef, i32 8
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v32i8_15 = insertelement <32 x i8> poison, i8 undef, i32 15
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v32i8_24 = insertelement <32 x i8> poison, i8 undef, i32 24
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v32i8_31 = insertelement <32 x i8> poison, i8 undef, i32 31
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_a = insertelement <64 x i8> poison, i8 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i8_0 = insertelement <64 x i8> poison, i8 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i8_7 = insertelement <64 x i8> poison, i8 undef, i32 7
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i8_8 = insertelement <64 x i8> poison, i8 undef, i32 8
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i8_15 = insertelement <64 x i8> poison, i8 undef, i32 15
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i8_24 = insertelement <64 x i8> poison, i8 undef, i32 24
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i8_31 = insertelement <64 x i8> poison, i8 undef, i32 31
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i8_32 = insertelement <64 x i8> poison, i8 undef, i32 32
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i8_48 = insertelement <64 x i8> poison, i8 undef, i32 48
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i8_63 = insertelement <64 x i8> poison, i8 undef, i32 63
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE4-LABEL: 'insert_i8'
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i8_a = insertelement <2 x i8> poison, i8 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i8_0 = insertelement <2 x i8> poison, i8 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i8_3 = insertelement <2 x i8> poison, i8 undef, i32 1
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_a = insertelement <4 x i8> poison, i8 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_0 = insertelement <4 x i8> poison, i8 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_3 = insertelement <4 x i8> poison, i8 undef, i32 3
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_a = insertelement <8 x i8> poison, i8 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_0 = insertelement <8 x i8> poison, i8 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_7 = insertelement <8 x i8> poison, i8 undef, i32 7
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_a = insertelement <16 x i8> poison, i8 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_0 = insertelement <16 x i8> poison, i8 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_8 = insertelement <16 x i8> poison, i8 undef, i32 8
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_15 = insertelement <16 x i8> poison, i8 undef, i32 15
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_a = insertelement <32 x i8> poison, i8 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_0 = insertelement <32 x i8> poison, i8 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_7 = insertelement <32 x i8> poison, i8 undef, i32 7
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_8 = insertelement <32 x i8> poison, i8 undef, i32 8
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_15 = insertelement <32 x i8> poison, i8 undef, i32 15
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_24 = insertelement <32 x i8> poison, i8 undef, i32 24
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_31 = insertelement <32 x i8> poison, i8 undef, i32 31
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_a = insertelement <64 x i8> poison, i8 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_0 = insertelement <64 x i8> poison, i8 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_7 = insertelement <64 x i8> poison, i8 undef, i32 7
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_8 = insertelement <64 x i8> poison, i8 undef, i32 8
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_15 = insertelement <64 x i8> poison, i8 undef, i32 15
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_24 = insertelement <64 x i8> poison, i8 undef, i32 24
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_31 = insertelement <64 x i8> poison, i8 undef, i32 31
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_32 = insertelement <64 x i8> poison, i8 undef, i32 32
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_48 = insertelement <64 x i8> poison, i8 undef, i32 48
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_63 = insertelement <64 x i8> poison, i8 undef, i32 63
+; SSE4-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'insert_i8'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i8_a = insertelement <2 x i8> poison, i8 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i8_0 = insertelement <2 x i8> poison, i8 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i8_3 = insertelement <2 x i8> poison, i8 undef, i32 1
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_a = insertelement <4 x i8> poison, i8 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_0 = insertelement <4 x i8> poison, i8 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_3 = insertelement <4 x i8> poison, i8 undef, i32 3
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_a = insertelement <8 x i8> poison, i8 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_0 = insertelement <8 x i8> poison, i8 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_7 = insertelement <8 x i8> poison, i8 undef, i32 7
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_a = insertelement <16 x i8> poison, i8 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_0 = insertelement <16 x i8> poison, i8 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_8 = insertelement <16 x i8> poison, i8 undef, i32 8
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_15 = insertelement <16 x i8> poison, i8 undef, i32 15
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_a = insertelement <32 x i8> poison, i8 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_0 = insertelement <32 x i8> poison, i8 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_7 = insertelement <32 x i8> poison, i8 undef, i32 7
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_8 = insertelement <32 x i8> poison, i8 undef, i32 8
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_15 = insertelement <32 x i8> poison, i8 undef, i32 15
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v32i8_24 = insertelement <32 x i8> poison, i8 undef, i32 24
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v32i8_31 = insertelement <32 x i8> poison, i8 undef, i32 31
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_a = insertelement <64 x i8> poison, i8 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_0 = insertelement <64 x i8> poison, i8 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_7 = insertelement <64 x i8> poison, i8 undef, i32 7
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_8 = insertelement <64 x i8> poison, i8 undef, i32 8
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_15 = insertelement <64 x i8> poison, i8 undef, i32 15
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v64i8_24 = insertelement <64 x i8> poison, i8 undef, i32 24
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v64i8_31 = insertelement <64 x i8> poison, i8 undef, i32 31
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_32 = insertelement <64 x i8> poison, i8 undef, i32 32
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v64i8_48 = insertelement <64 x i8> poison, i8 undef, i32 48
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v64i8_63 = insertelement <64 x i8> poison, i8 undef, i32 63
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'insert_i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i8_a = insertelement <2 x i8> poison, i8 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i8_0 = insertelement <2 x i8> poison, i8 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i8_3 = insertelement <2 x i8> poison, i8 undef, i32 1
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_a = insertelement <4 x i8> poison, i8 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_0 = insertelement <4 x i8> poison, i8 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_3 = insertelement <4 x i8> poison, i8 undef, i32 3
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_a = insertelement <8 x i8> poison, i8 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_0 = insertelement <8 x i8> poison, i8 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_7 = insertelement <8 x i8> poison, i8 undef, i32 7
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_a = insertelement <16 x i8> poison, i8 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_0 = insertelement <16 x i8> poison, i8 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_8 = insertelement <16 x i8> poison, i8 undef, i32 8
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_15 = insertelement <16 x i8> poison, i8 undef, i32 15
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_a = insertelement <32 x i8> poison, i8 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_0 = insertelement <32 x i8> poison, i8 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_7 = insertelement <32 x i8> poison, i8 undef, i32 7
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_8 = insertelement <32 x i8> poison, i8 undef, i32 8
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_15 = insertelement <32 x i8> poison, i8 undef, i32 15
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v32i8_24 = insertelement <32 x i8> poison, i8 undef, i32 24
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v32i8_31 = insertelement <32 x i8> poison, i8 undef, i32 31
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_a = insertelement <64 x i8> poison, i8 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_0 = insertelement <64 x i8> poison, i8 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_7 = insertelement <64 x i8> poison, i8 undef, i32 7
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_8 = insertelement <64 x i8> poison, i8 undef, i32 8
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_15 = insertelement <64 x i8> poison, i8 undef, i32 15
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v64i8_24 = insertelement <64 x i8> poison, i8 undef, i32 24
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v64i8_31 = insertelement <64 x i8> poison, i8 undef, i32 31
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v64i8_32 = insertelement <64 x i8> poison, i8 undef, i32 32
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v64i8_48 = insertelement <64 x i8> poison, i8 undef, i32 48
+; AVX512-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v64i8_63 = insertelement <64 x i8> poison, i8 undef, i32 63
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'insert_i8'
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i8_a = insertelement <2 x i8> poison, i8 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i8_0 = insertelement <2 x i8> poison, i8 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i8_3 = insertelement <2 x i8> poison, i8 undef, i32 1
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_a = insertelement <4 x i8> poison, i8 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_0 = insertelement <4 x i8> poison, i8 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_3 = insertelement <4 x i8> poison, i8 undef, i32 3
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_a = insertelement <8 x i8> poison, i8 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_0 = insertelement <8 x i8> poison, i8 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_7 = insertelement <8 x i8> poison, i8 undef, i32 7
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_a = insertelement <16 x i8> poison, i8 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_0 = insertelement <16 x i8> poison, i8 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_8 = insertelement <16 x i8> poison, i8 undef, i32 8
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_15 = insertelement <16 x i8> poison, i8 undef, i32 15
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_a = insertelement <32 x i8> poison, i8 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_0 = insertelement <32 x i8> poison, i8 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_7 = insertelement <32 x i8> poison, i8 undef, i32 7
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_8 = insertelement <32 x i8> poison, i8 undef, i32 8
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_15 = insertelement <32 x i8> poison, i8 undef, i32 15
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_24 = insertelement <32 x i8> poison, i8 undef, i32 24
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_31 = insertelement <32 x i8> poison, i8 undef, i32 31
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_a = insertelement <64 x i8> poison, i8 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_0 = insertelement <64 x i8> poison, i8 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_7 = insertelement <64 x i8> poison, i8 undef, i32 7
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_8 = insertelement <64 x i8> poison, i8 undef, i32 8
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_15 = insertelement <64 x i8> poison, i8 undef, i32 15
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_24 = insertelement <64 x i8> poison, i8 undef, i32 24
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_31 = insertelement <64 x i8> poison, i8 undef, i32 31
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_32 = insertelement <64 x i8> poison, i8 undef, i32 32
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_48 = insertelement <64 x i8> poison, i8 undef, i32 48
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_63 = insertelement <64 x i8> poison, i8 undef, i32 63
+; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'insert_i8'
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i8_a = insertelement <2 x i8> poison, i8 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i8_0 = insertelement <2 x i8> poison, i8 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i8_3 = insertelement <2 x i8> poison, i8 undef, i32 1
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_a = insertelement <4 x i8> poison, i8 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_0 = insertelement <4 x i8> poison, i8 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8_3 = insertelement <4 x i8> poison, i8 undef, i32 3
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_a = insertelement <8 x i8> poison, i8 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_0 = insertelement <8 x i8> poison, i8 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8_7 = insertelement <8 x i8> poison, i8 undef, i32 7
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_a = insertelement <16 x i8> poison, i8 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_0 = insertelement <16 x i8> poison, i8 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_8 = insertelement <16 x i8> poison, i8 undef, i32 8
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8_15 = insertelement <16 x i8> poison, i8 undef, i32 15
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_a = insertelement <32 x i8> poison, i8 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_0 = insertelement <32 x i8> poison, i8 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_7 = insertelement <32 x i8> poison, i8 undef, i32 7
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_8 = insertelement <32 x i8> poison, i8 undef, i32 8
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_15 = insertelement <32 x i8> poison, i8 undef, i32 15
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_24 = insertelement <32 x i8> poison, i8 undef, i32 24
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8_31 = insertelement <32 x i8> poison, i8 undef, i32 31
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_a = insertelement <64 x i8> poison, i8 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_0 = insertelement <64 x i8> poison, i8 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_7 = insertelement <64 x i8> poison, i8 undef, i32 7
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_8 = insertelement <64 x i8> poison, i8 undef, i32 8
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_15 = insertelement <64 x i8> poison, i8 undef, i32 15
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_24 = insertelement <64 x i8> poison, i8 undef, i32 24
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_31 = insertelement <64 x i8> poison, i8 undef, i32 31
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_32 = insertelement <64 x i8> poison, i8 undef, i32 32
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_48 = insertelement <64 x i8> poison, i8 undef, i32 48
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i8_63 = insertelement <64 x i8> poison, i8 undef, i32 63
+; GLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+ %v2i8_a = insertelement <2 x i8> poison, i8 undef, i32 %arg
+ %v2i8_0 = insertelement <2 x i8> poison, i8 undef, i32 0
+ %v2i8_3 = insertelement <2 x i8> poison, i8 undef, i32 1
+
+ %v4i8_a = insertelement <4 x i8> poison, i8 undef, i32 %arg
+ %v4i8_0 = insertelement <4 x i8> poison, i8 undef, i32 0
+ %v4i8_3 = insertelement <4 x i8> poison, i8 undef, i32 3
+
+ %v8i8_a = insertelement <8 x i8> poison, i8 undef, i32 %arg
+ %v8i8_0 = insertelement <8 x i8> poison, i8 undef, i32 0
+ %v8i8_7 = insertelement <8 x i8> poison, i8 undef, i32 7
+
+ %v16i8_a = insertelement <16 x i8> poison, i8 undef, i32 %arg
+ %v16i8_0 = insertelement <16 x i8> poison, i8 undef, i32 0
+ %v16i8_8 = insertelement <16 x i8> poison, i8 undef, i32 8
+ %v16i8_15 = insertelement <16 x i8> poison, i8 undef, i32 15
+
+ %v32i8_a = insertelement <32 x i8> poison, i8 undef, i32 %arg
+ %v32i8_0 = insertelement <32 x i8> poison, i8 undef, i32 0
+ %v32i8_7 = insertelement <32 x i8> poison, i8 undef, i32 7
+ %v32i8_8 = insertelement <32 x i8> poison, i8 undef, i32 8
+ %v32i8_15 = insertelement <32 x i8> poison, i8 undef, i32 15
+ %v32i8_24 = insertelement <32 x i8> poison, i8 undef, i32 24
+ %v32i8_31 = insertelement <32 x i8> poison, i8 undef, i32 31
+
+ %v64i8_a = insertelement <64 x i8> poison, i8 undef, i32 %arg
+ %v64i8_0 = insertelement <64 x i8> poison, i8 undef, i32 0
+ %v64i8_7 = insertelement <64 x i8> poison, i8 undef, i32 7
+ %v64i8_8 = insertelement <64 x i8> poison, i8 undef, i32 8
+ %v64i8_15 = insertelement <64 x i8> poison, i8 undef, i32 15
+ %v64i8_24 = insertelement <64 x i8> poison, i8 undef, i32 24
+ %v64i8_31 = insertelement <64 x i8> poison, i8 undef, i32 31
+ %v64i8_32 = insertelement <64 x i8> poison, i8 undef, i32 32
+ %v64i8_48 = insertelement <64 x i8> poison, i8 undef, i32 48
+ %v64i8_63 = insertelement <64 x i8> poison, i8 undef, i32 63
+
+ ret i32 undef
+}
+
+define i32 @insert_i1(i32 %arg) {
+; SSE2-LABEL: 'insert_i1'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i1_a = insertelement <2 x i1> poison, i1 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i1_0 = insertelement <2 x i1> poison, i1 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i1_1 = insertelement <2 x i1> poison, i1 undef, i32 1
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i1_a = insertelement <4 x i1> poison, i1 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i1_0 = insertelement <4 x i1> poison, i1 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i1_2 = insertelement <4 x i1> poison, i1 undef, i32 2
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_a = insertelement <8 x i1> poison, i1 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_0 = insertelement <8 x i1> poison, i1 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_4 = insertelement <8 x i1> poison, i1 undef, i32 4
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_a = insertelement <16 x i1> poison, i1 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v16i1_0 = insertelement <16 x i1> poison, i1 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v16i1_8 = insertelement <16 x i1> poison, i1 undef, i32 8
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v16i1_15 = insertelement <16 x i1> poison, i1 undef, i32 15
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_a = insertelement <32 x i1> poison, i1 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i1_0 = insertelement <32 x i1> poison, i1 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i1_7 = insertelement <32 x i1> poison, i1 undef, i32 7
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i1_8 = insertelement <32 x i1> poison, i1 undef, i32 8
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i1_15 = insertelement <32 x i1> poison, i1 undef, i32 15
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i1_24 = insertelement <32 x i1> poison, i1 undef, i32 24
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i1_31 = insertelement <32 x i1> poison, i1 undef, i32 31
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_a = insertelement <64 x i1> poison, i1 undef, i32 %arg
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i1_0 = insertelement <64 x i1> poison, i1 undef, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i1_7 = insertelement <64 x i1> poison, i1 undef, i32 7
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i1_8 = insertelement <64 x i1> poison, i1 undef, i32 8
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i1_15 = insertelement <64 x i1> poison, i1 undef, i32 15
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i1_24 = insertelement <64 x i1> poison, i1 undef, i32 24
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i1_31 = insertelement <64 x i1> poison, i1 undef, i32 31
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i1_32 = insertelement <64 x i1> poison, i1 undef, i32 32
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i1_48 = insertelement <64 x i1> poison, i1 undef, i32 48
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i1_63 = insertelement <64 x i1> poison, i1 undef, i32 63
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE3-LABEL: 'insert_i1'
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i1_a = insertelement <2 x i1> poison, i1 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i1_0 = insertelement <2 x i1> poison, i1 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i1_1 = insertelement <2 x i1> poison, i1 undef, i32 1
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i1_a = insertelement <4 x i1> poison, i1 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i1_0 = insertelement <4 x i1> poison, i1 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i1_2 = insertelement <4 x i1> poison, i1 undef, i32 2
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_a = insertelement <8 x i1> poison, i1 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_0 = insertelement <8 x i1> poison, i1 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_4 = insertelement <8 x i1> poison, i1 undef, i32 4
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_a = insertelement <16 x i1> poison, i1 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v16i1_0 = insertelement <16 x i1> poison, i1 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v16i1_8 = insertelement <16 x i1> poison, i1 undef, i32 8
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v16i1_15 = insertelement <16 x i1> poison, i1 undef, i32 15
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_a = insertelement <32 x i1> poison, i1 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i1_0 = insertelement <32 x i1> poison, i1 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i1_7 = insertelement <32 x i1> poison, i1 undef, i32 7
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i1_8 = insertelement <32 x i1> poison, i1 undef, i32 8
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i1_15 = insertelement <32 x i1> poison, i1 undef, i32 15
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i1_24 = insertelement <32 x i1> poison, i1 undef, i32 24
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v32i1_31 = insertelement <32 x i1> poison, i1 undef, i32 31
+; SSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_a = insertelement <64 x i1> poison, i1 undef, i32 %arg
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i1_0 = insertelement <64 x i1> poison, i1 undef, i32 0
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i1_7 = insertelement <64 x i1> poison, i1 undef, i32 7
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i1_8 = insertelement <64 x i1> poison, i1 undef, i32 8
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i1_15 = insertelement <64 x i1> poison, i1 undef, i32 15
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i1_24 = insertelement <64 x i1> poison, i1 undef, i32 24
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i1_31 = insertelement <64 x i1> poison, i1 undef, i32 31
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i1_32 = insertelement <64 x i1> poison, i1 undef, i32 32
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i1_48 = insertelement <64 x i1> poison, i1 undef, i32 48
+; SSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %v64i1_63 = insertelement <64 x i1> poison, i1 undef, i32 63
+; SSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSSE3-LABEL: 'insert_i1'
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i1_a = insertelement <2 x i1> poison, i1 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i1_0 = insertelement <2 x i1> poison, i1 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2i1_1 = insertelement <2 x i1> poison, i1 undef, i32 1
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i1_a = insertelement <4 x i1> poison, i1 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i1_0 = insertelement <4 x i1> poison, i1 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v4i1_2 = insertelement <4 x i1> poison, i1 undef, i32 2
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_a = insertelement <8 x i1> poison, i1 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_0 = insertelement <8 x i1> poison, i1 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_4 = insertelement <8 x i1> poison, i1 undef, i32 4
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_a = insertelement <16 x i1> poison, i1 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i1_0 = insertelement <16 x i1> poison, i1 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i1_8 = insertelement <16 x i1> poison, i1 undef, i32 8
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i1_15 = insertelement <16 x i1> poison, i1 undef, i32 15
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_a = insertelement <32 x i1> poison, i1 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v32i1_0 = insertelement <32 x i1> poison, i1 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v32i1_7 = insertelement <32 x i1> poison, i1 undef, i32 7
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v32i1_8 = insertelement <32 x i1> poison, i1 undef, i32 8
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v32i1_15 = insertelement <32 x i1> poison, i1 undef, i32 15
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v32i1_24 = insertelement <32 x i1> poison, i1 undef, i32 24
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v32i1_31 = insertelement <32 x i1> poison, i1 undef, i32 31
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_a = insertelement <64 x i1> poison, i1 undef, i32 %arg
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i1_0 = insertelement <64 x i1> poison, i1 undef, i32 0
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i1_7 = insertelement <64 x i1> poison, i1 undef, i32 7
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i1_8 = insertelement <64 x i1> poison, i1 undef, i32 8
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i1_15 = insertelement <64 x i1> poison, i1 undef, i32 15
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i1_24 = insertelement <64 x i1> poison, i1 undef, i32 24
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i1_31 = insertelement <64 x i1> poison, i1 undef, i32 31
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i1_32 = insertelement <64 x i1> poison, i1 undef, i32 32
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i1_48 = insertelement <64 x i1> poison, i1 undef, i32 48
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v64i1_63 = insertelement <64 x i1> poison, i1 undef, i32 63
+; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SSE4-LABEL: 'insert_i1'
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i1_a = insertelement <2 x i1> poison, i1 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i1_0 = insertelement <2 x i1> poison, i1 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i1_1 = insertelement <2 x i1> poison, i1 undef, i32 1
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i1_a = insertelement <4 x i1> poison, i1 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i1_0 = insertelement <4 x i1> poison, i1 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i1_2 = insertelement <4 x i1> poison, i1 undef, i32 2
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_a = insertelement <8 x i1> poison, i1 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_0 = insertelement <8 x i1> poison, i1 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_4 = insertelement <8 x i1> poison, i1 undef, i32 4
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_a = insertelement <16 x i1> poison, i1 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_0 = insertelement <16 x i1> poison, i1 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_8 = insertelement <16 x i1> poison, i1 undef, i32 8
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_15 = insertelement <16 x i1> poison, i1 undef, i32 15
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_a = insertelement <32 x i1> poison, i1 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_0 = insertelement <32 x i1> poison, i1 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_7 = insertelement <32 x i1> poison, i1 undef, i32 7
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_8 = insertelement <32 x i1> poison, i1 undef, i32 8
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_15 = insertelement <32 x i1> poison, i1 undef, i32 15
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_24 = insertelement <32 x i1> poison, i1 undef, i32 24
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_31 = insertelement <32 x i1> poison, i1 undef, i32 31
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_a = insertelement <64 x i1> poison, i1 undef, i32 %arg
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_0 = insertelement <64 x i1> poison, i1 undef, i32 0
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_7 = insertelement <64 x i1> poison, i1 undef, i32 7
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_8 = insertelement <64 x i1> poison, i1 undef, i32 8
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_15 = insertelement <64 x i1> poison, i1 undef, i32 15
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_24 = insertelement <64 x i1> poison, i1 undef, i32 24
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_31 = insertelement <64 x i1> poison, i1 undef, i32 31
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_32 = insertelement <64 x i1> poison, i1 undef, i32 32
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_48 = insertelement <64 x i1> poison, i1 undef, i32 48
+; SSE4-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_63 = insertelement <64 x i1> poison, i1 undef, i32 63
+; SSE4-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'insert_i1'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i1_a = insertelement <2 x i1> poison, i1 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i1_0 = insertelement <2 x i1> poison, i1 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i1_1 = insertelement <2 x i1> poison, i1 undef, i32 1
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i1_a = insertelement <4 x i1> poison, i1 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i1_0 = insertelement <4 x i1> poison, i1 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i1_2 = insertelement <4 x i1> poison, i1 undef, i32 2
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_a = insertelement <8 x i1> poison, i1 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_0 = insertelement <8 x i1> poison, i1 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_4 = insertelement <8 x i1> poison, i1 undef, i32 4
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_a = insertelement <16 x i1> poison, i1 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_0 = insertelement <16 x i1> poison, i1 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_8 = insertelement <16 x i1> poison, i1 undef, i32 8
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_15 = insertelement <16 x i1> poison, i1 undef, i32 15
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_a = insertelement <32 x i1> poison, i1 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_0 = insertelement <32 x i1> poison, i1 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_7 = insertelement <32 x i1> poison, i1 undef, i32 7
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_8 = insertelement <32 x i1> poison, i1 undef, i32 8
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_15 = insertelement <32 x i1> poison, i1 undef, i32 15
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v32i1_24 = insertelement <32 x i1> poison, i1 undef, i32 24
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v32i1_31 = insertelement <32 x i1> poison, i1 undef, i32 31
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_a = insertelement <64 x i1> poison, i1 undef, i32 %arg
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_0 = insertelement <64 x i1> poison, i1 undef, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_7 = insertelement <64 x i1> poison, i1 undef, i32 7
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_8 = insertelement <64 x i1> poison, i1 undef, i32 8
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_15 = insertelement <64 x i1> poison, i1 undef, i32 15
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v64i1_24 = insertelement <64 x i1> poison, i1 undef, i32 24
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v64i1_31 = insertelement <64 x i1> poison, i1 undef, i32 31
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_32 = insertelement <64 x i1> poison, i1 undef, i32 32
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v64i1_48 = insertelement <64 x i1> poison, i1 undef, i32 48
+; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v64i1_63 = insertelement <64 x i1> poison, i1 undef, i32 63
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'insert_i1'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i1_a = insertelement <2 x i1> poison, i1 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i1_0 = insertelement <2 x i1> poison, i1 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i1_1 = insertelement <2 x i1> poison, i1 undef, i32 1
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i1_a = insertelement <4 x i1> poison, i1 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i1_0 = insertelement <4 x i1> poison, i1 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i1_2 = insertelement <4 x i1> poison, i1 undef, i32 2
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_a = insertelement <8 x i1> poison, i1 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_0 = insertelement <8 x i1> poison, i1 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_4 = insertelement <8 x i1> poison, i1 undef, i32 4
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_a = insertelement <16 x i1> poison, i1 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_0 = insertelement <16 x i1> poison, i1 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_8 = insertelement <16 x i1> poison, i1 undef, i32 8
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_15 = insertelement <16 x i1> poison, i1 undef, i32 15
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_a = insertelement <32 x i1> poison, i1 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_0 = insertelement <32 x i1> poison, i1 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_7 = insertelement <32 x i1> poison, i1 undef, i32 7
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_8 = insertelement <32 x i1> poison, i1 undef, i32 8
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_15 = insertelement <32 x i1> poison, i1 undef, i32 15
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_24 = insertelement <32 x i1> poison, i1 undef, i32 24
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_31 = insertelement <32 x i1> poison, i1 undef, i32 31
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_a = insertelement <64 x i1> poison, i1 undef, i32 %arg
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_0 = insertelement <64 x i1> poison, i1 undef, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_7 = insertelement <64 x i1> poison, i1 undef, i32 7
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_8 = insertelement <64 x i1> poison, i1 undef, i32 8
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_15 = insertelement <64 x i1> poison, i1 undef, i32 15
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_24 = insertelement <64 x i1> poison, i1 undef, i32 24
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_31 = insertelement <64 x i1> poison, i1 undef, i32 31
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_32 = insertelement <64 x i1> poison, i1 undef, i32 32
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_48 = insertelement <64 x i1> poison, i1 undef, i32 48
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_63 = insertelement <64 x i1> poison, i1 undef, i32 63
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; SLM-LABEL: 'insert_i1'
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i1_a = insertelement <2 x i1> poison, i1 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i1_0 = insertelement <2 x i1> poison, i1 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i1_1 = insertelement <2 x i1> poison, i1 undef, i32 1
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i1_a = insertelement <4 x i1> poison, i1 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i1_0 = insertelement <4 x i1> poison, i1 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i1_2 = insertelement <4 x i1> poison, i1 undef, i32 2
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_a = insertelement <8 x i1> poison, i1 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_0 = insertelement <8 x i1> poison, i1 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_4 = insertelement <8 x i1> poison, i1 undef, i32 4
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_a = insertelement <16 x i1> poison, i1 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_0 = insertelement <16 x i1> poison, i1 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_8 = insertelement <16 x i1> poison, i1 undef, i32 8
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_15 = insertelement <16 x i1> poison, i1 undef, i32 15
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_a = insertelement <32 x i1> poison, i1 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_0 = insertelement <32 x i1> poison, i1 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_7 = insertelement <32 x i1> poison, i1 undef, i32 7
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_8 = insertelement <32 x i1> poison, i1 undef, i32 8
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_15 = insertelement <32 x i1> poison, i1 undef, i32 15
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_24 = insertelement <32 x i1> poison, i1 undef, i32 24
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_31 = insertelement <32 x i1> poison, i1 undef, i32 31
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_a = insertelement <64 x i1> poison, i1 undef, i32 %arg
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_0 = insertelement <64 x i1> poison, i1 undef, i32 0
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_7 = insertelement <64 x i1> poison, i1 undef, i32 7
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_8 = insertelement <64 x i1> poison, i1 undef, i32 8
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_15 = insertelement <64 x i1> poison, i1 undef, i32 15
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_24 = insertelement <64 x i1> poison, i1 undef, i32 24
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_31 = insertelement <64 x i1> poison, i1 undef, i32 31
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_32 = insertelement <64 x i1> poison, i1 undef, i32 32
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_48 = insertelement <64 x i1> poison, i1 undef, i32 48
+; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_63 = insertelement <64 x i1> poison, i1 undef, i32 63
+; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; GLM-LABEL: 'insert_i1'
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i1_a = insertelement <2 x i1> poison, i1 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i1_0 = insertelement <2 x i1> poison, i1 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i1_1 = insertelement <2 x i1> poison, i1 undef, i32 1
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i1_a = insertelement <4 x i1> poison, i1 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i1_0 = insertelement <4 x i1> poison, i1 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i1_2 = insertelement <4 x i1> poison, i1 undef, i32 2
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_a = insertelement <8 x i1> poison, i1 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_0 = insertelement <8 x i1> poison, i1 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i1_4 = insertelement <8 x i1> poison, i1 undef, i32 4
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_a = insertelement <16 x i1> poison, i1 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_0 = insertelement <16 x i1> poison, i1 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_8 = insertelement <16 x i1> poison, i1 undef, i32 8
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i1_15 = insertelement <16 x i1> poison, i1 undef, i32 15
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_a = insertelement <32 x i1> poison, i1 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_0 = insertelement <32 x i1> poison, i1 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_7 = insertelement <32 x i1> poison, i1 undef, i32 7
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_8 = insertelement <32 x i1> poison, i1 undef, i32 8
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_15 = insertelement <32 x i1> poison, i1 undef, i32 15
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_24 = insertelement <32 x i1> poison, i1 undef, i32 24
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i1_31 = insertelement <32 x i1> poison, i1 undef, i32 31
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_a = insertelement <64 x i1> poison, i1 undef, i32 %arg
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_0 = insertelement <64 x i1> poison, i1 undef, i32 0
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_7 = insertelement <64 x i1> poison, i1 undef, i32 7
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_8 = insertelement <64 x i1> poison, i1 undef, i32 8
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_15 = insertelement <64 x i1> poison, i1 undef, i32 15
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_24 = insertelement <64 x i1> poison, i1 undef, i32 24
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_31 = insertelement <64 x i1> poison, i1 undef, i32 31
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_32 = insertelement <64 x i1> poison, i1 undef, i32 32
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_48 = insertelement <64 x i1> poison, i1 undef, i32 48
+; GLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v64i1_63 = insertelement <64 x i1> poison, i1 undef, i32 63
+; GLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+ %v2i1_a = insertelement <2 x i1> poison, i1 undef, i32 %arg
+ %v2i1_0 = insertelement <2 x i1> poison, i1 undef, i32 0
+ %v2i1_1 = insertelement <2 x i1> poison, i1 undef, i32 1
+
+ %v4i1_a = insertelement <4 x i1> poison, i1 undef, i32 %arg
+ %v4i1_0 = insertelement <4 x i1> poison, i1 undef, i32 0
+ %v4i1_2 = insertelement <4 x i1> poison, i1 undef, i32 2
+
+ %v8i1_a = insertelement <8 x i1> poison, i1 undef, i32 %arg
+ %v8i1_0 = insertelement <8 x i1> poison, i1 undef, i32 0
+ %v8i1_4 = insertelement <8 x i1> poison, i1 undef, i32 4
+
+ %v16i1_a = insertelement <16 x i1> poison, i1 undef, i32 %arg
+ %v16i1_0 = insertelement <16 x i1> poison, i1 undef, i32 0
+ %v16i1_8 = insertelement <16 x i1> poison, i1 undef, i32 8
+ %v16i1_15 = insertelement <16 x i1> poison, i1 undef, i32 15
+
+ %v32i1_a = insertelement <32 x i1> poison, i1 undef, i32 %arg
+ %v32i1_0 = insertelement <32 x i1> poison, i1 undef, i32 0
+ %v32i1_7 = insertelement <32 x i1> poison, i1 undef, i32 7
+ %v32i1_8 = insertelement <32 x i1> poison, i1 undef, i32 8
+ %v32i1_15 = insertelement <32 x i1> poison, i1 undef, i32 15
+ %v32i1_24 = insertelement <32 x i1> poison, i1 undef, i32 24
+ %v32i1_31 = insertelement <32 x i1> poison, i1 undef, i32 31
+
+ %v64i1_a = insertelement <64 x i1> poison, i1 undef, i32 %arg
+ %v64i1_0 = insertelement <64 x i1> poison, i1 undef, i32 0
+ %v64i1_7 = insertelement <64 x i1> poison, i1 undef, i32 7
+ %v64i1_8 = insertelement <64 x i1> poison, i1 undef, i32 8
+ %v64i1_15 = insertelement <64 x i1> poison, i1 undef, i32 15
+ %v64i1_24 = insertelement <64 x i1> poison, i1 undef, i32 24
+ %v64i1_31 = insertelement <64 x i1> poison, i1 undef, i32 31
+ %v64i1_32 = insertelement <64 x i1> poison, i1 undef, i32 32
+ %v64i1_48 = insertelement <64 x i1> poison, i1 undef, i32 48
+ %v64i1_63 = insertelement <64 x i1> poison, i1 undef, i32 63
+
+ ret i32 undef
+}
diff --git a/llvm/test/Analysis/CostModel/X86/vector_gep-inseltpoison.ll b/llvm/test/Analysis/CostModel/X86/vector_gep-inseltpoison.ll
new file mode 100644
index 000000000000..8e8d6cb9c25a
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/X86/vector_gep-inseltpoison.ll
@@ -0,0 +1,17 @@
+; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-linux-unknown-unknown -mattr=+avx512f | FileCheck %s
+
+%struct.S = type { [1000 x i32] }
+
+
+declare <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*>, i32, <4 x i1>, <4 x i32>)
+
+define <4 x i32> @foov(<4 x %struct.S*> %s, i64 %base){
+ %temp = insertelement <4 x i64> poison, i64 %base, i32 0
+ %vector = shufflevector <4 x i64> %temp, <4 x i64> undef, <4 x i32> zeroinitializer
+;CHECK: cost of 0 for instruction: {{.*}} getelementptr inbounds %struct.S
+ %B = getelementptr inbounds %struct.S, <4 x %struct.S*> %s, <4 x i32> zeroinitializer, <4 x i32> zeroinitializer
+;CHECK: cost of 0 for instruction: {{.*}} getelementptr inbounds [1000 x i32]
+ %arrayidx = getelementptr inbounds [1000 x i32], <4 x [1000 x i32]*> %B, <4 x i64> zeroinitializer, <4 x i64> %vector
+ %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %arrayidx, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> undef)
+ ret <4 x i32> %res
+}
diff --git a/llvm/test/Analysis/CostModel/X86/vshift-ashr-cost-inseltpoison.ll b/llvm/test/Analysis/CostModel/X86/vshift-ashr-cost-inseltpoison.ll
new file mode 100644
index 000000000000..47a36874965d
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/X86/vshift-ashr-cost-inseltpoison.ll
@@ -0,0 +1,1843 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+xop,+avx | FileCheck %s --check-prefixes=CHECK,XOP,XOPAVX1
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+xop,+avx2 | FileCheck %s --check-prefixes=CHECK,XOP,XOPAVX2
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx512f,+avx512dq | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BW
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx512f,+avx512vl | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx512f,+avx512dq,+avx512vl | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512VL
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx512f,+avx512bw,+avx512vl | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BWVL
+;
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mcpu=slm | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mcpu=goldmont | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mcpu=btver2 | FileCheck %s --check-prefixes=CHECK,AVX,BTVER2
+
+; Verify the cost of vector arithmetic shift right instructions.
+
+;
+; Variable Shifts
+;
+
+define <2 x i64> @var_shift_v2i64(<2 x i64> %a, <2 x i64> %b) {
+; SSE-LABEL: 'var_shift_v2i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <2 x i64> %a, %b
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX1-LABEL: 'var_shift_v2i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <2 x i64> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX2-LABEL: 'var_shift_v2i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <2 x i64> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; XOP-LABEL: 'var_shift_v2i64'
+; XOP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <2 x i64> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX512-LABEL: 'var_shift_v2i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <2 x i64> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; BTVER2-LABEL: 'var_shift_v2i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <2 x i64> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+ %shift = ashr <2 x i64> %a, %b
+ ret <2 x i64> %shift
+}
+
+define <4 x i64> @var_shift_v4i64(<4 x i64> %a, <4 x i64> %b) {
+; SSE-LABEL: 'var_shift_v4i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <4 x i64> %a, %b
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX1-LABEL: 'var_shift_v4i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = ashr <4 x i64> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX2-LABEL: 'var_shift_v4i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <4 x i64> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOP-LABEL: 'var_shift_v4i64'
+; XOP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = ashr <4 x i64> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX512-LABEL: 'var_shift_v4i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <4 x i64> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; BTVER2-LABEL: 'var_shift_v4i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = ashr <4 x i64> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+ %shift = ashr <4 x i64> %a, %b
+ ret <4 x i64> %shift
+}
+
+define <8 x i64> @var_shift_v8i64(<8 x i64> %a, <8 x i64> %b) {
+; SSE-LABEL: 'var_shift_v8i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = ashr <8 x i64> %a, %b
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX1-LABEL: 'var_shift_v8i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = ashr <8 x i64> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX2-LABEL: 'var_shift_v8i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <8 x i64> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOP-LABEL: 'var_shift_v8i64'
+; XOP-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <8 x i64> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX512-LABEL: 'var_shift_v8i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i64> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; BTVER2-LABEL: 'var_shift_v8i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = ashr <8 x i64> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+ %shift = ashr <8 x i64> %a, %b
+ ret <8 x i64> %shift
+}
+
+define <4 x i32> @var_shift_v4i32(<4 x i32> %a, <4 x i32> %b) {
+; SSE2-LABEL: 'var_shift_v4i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %shift = ashr <4 x i32> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; SSE42-LABEL: 'var_shift_v4i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <4 x i32> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX1-LABEL: 'var_shift_v4i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <4 x i32> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX2-LABEL: 'var_shift_v4i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <4 x i32> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; XOPAVX1-LABEL: 'var_shift_v4i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <4 x i32> %a, %b
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; XOPAVX2-LABEL: 'var_shift_v4i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <4 x i32> %a, %b
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX512-LABEL: 'var_shift_v4i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <4 x i32> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; BTVER2-LABEL: 'var_shift_v4i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <4 x i32> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+ %shift = ashr <4 x i32> %a, %b
+ ret <4 x i32> %shift
+}
+
+define <8 x i32> @var_shift_v8i32(<8 x i32> %a, <8 x i32> %b) {
+; SSE2-LABEL: 'var_shift_v8i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %shift = ashr <8 x i32> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; SSE42-LABEL: 'var_shift_v8i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <8 x i32> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX1-LABEL: 'var_shift_v8i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = ashr <8 x i32> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX2-LABEL: 'var_shift_v8i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i32> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX1-LABEL: 'var_shift_v8i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = ashr <8 x i32> %a, %b
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX2-LABEL: 'var_shift_v8i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i32> %a, %b
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX512-LABEL: 'var_shift_v8i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i32> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; BTVER2-LABEL: 'var_shift_v8i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = ashr <8 x i32> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+ %shift = ashr <8 x i32> %a, %b
+ ret <8 x i32> %shift
+}
+
+define <16 x i32> @var_shift_v16i32(<16 x i32> %a, <16 x i32> %b) {
+; SSE2-LABEL: 'var_shift_v16i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %shift = ashr <16 x i32> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; SSE42-LABEL: 'var_shift_v16i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = ashr <16 x i32> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX1-LABEL: 'var_shift_v16i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = ashr <16 x i32> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX2-LABEL: 'var_shift_v16i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <16 x i32> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX1-LABEL: 'var_shift_v16i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <16 x i32> %a, %b
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX2-LABEL: 'var_shift_v16i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <16 x i32> %a, %b
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX512-LABEL: 'var_shift_v16i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <16 x i32> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; BTVER2-LABEL: 'var_shift_v16i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = ashr <16 x i32> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+ %shift = ashr <16 x i32> %a, %b
+ ret <16 x i32> %shift
+}
+
+define <8 x i16> @var_shift_v8i16(<8 x i16> %a, <8 x i16> %b) {
+; SSE2-LABEL: 'var_shift_v8i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %shift = ashr <8 x i16> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; SSE42-LABEL: 'var_shift_v8i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = ashr <8 x i16> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX-LABEL: 'var_shift_v8i16'
+; AVX-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = ashr <8 x i16> %a, %b
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; XOP-LABEL: 'var_shift_v8i16'
+; XOP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <8 x i16> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512F-LABEL: 'var_shift_v8i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = ashr <8 x i16> %a, %b
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512BW-LABEL: 'var_shift_v8i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i16> %a, %b
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512VL-LABEL: 'var_shift_v8i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = ashr <8 x i16> %a, %b
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'var_shift_v8i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i16> %a, %b
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+ %shift = ashr <8 x i16> %a, %b
+ ret <8 x i16> %shift
+}
+
+define <16 x i16> @var_shift_v16i16(<16 x i16> %a, <16 x i16> %b) {
+; SSE2-LABEL: 'var_shift_v16i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %shift = ashr <16 x i16> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; SSE42-LABEL: 'var_shift_v16i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %shift = ashr <16 x i16> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX1-LABEL: 'var_shift_v16i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %shift = ashr <16 x i16> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX2-LABEL: 'var_shift_v16i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = ashr <16 x i16> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOP-LABEL: 'var_shift_v16i16'
+; XOP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = ashr <16 x i16> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512F-LABEL: 'var_shift_v16i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = ashr <16 x i16> %a, %b
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512BW-LABEL: 'var_shift_v16i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <16 x i16> %a, %b
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512VL-LABEL: 'var_shift_v16i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = ashr <16 x i16> %a, %b
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'var_shift_v16i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <16 x i16> %a, %b
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; BTVER2-LABEL: 'var_shift_v16i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %shift = ashr <16 x i16> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+ %shift = ashr <16 x i16> %a, %b
+ ret <16 x i16> %shift
+}
+
+define <32 x i16> @var_shift_v32i16(<32 x i16> %a, <32 x i16> %b) {
+; SSE2-LABEL: 'var_shift_v32i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %shift = ashr <32 x i16> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; SSE42-LABEL: 'var_shift_v32i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %shift = ashr <32 x i16> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX1-LABEL: 'var_shift_v32i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %shift = ashr <32 x i16> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX2-LABEL: 'var_shift_v32i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = ashr <32 x i16> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOP-LABEL: 'var_shift_v32i16'
+; XOP-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <32 x i16> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512F-LABEL: 'var_shift_v32i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = ashr <32 x i16> %a, %b
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BW-LABEL: 'var_shift_v32i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <32 x i16> %a, %b
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512VL-LABEL: 'var_shift_v32i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = ashr <32 x i16> %a, %b
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'var_shift_v32i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <32 x i16> %a, %b
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; BTVER2-LABEL: 'var_shift_v32i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %shift = ashr <32 x i16> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+ %shift = ashr <32 x i16> %a, %b
+ ret <32 x i16> %shift
+}
+
+define <16 x i8> @var_shift_v16i8(<16 x i8> %a, <16 x i8> %b) {
+; SSE2-LABEL: 'var_shift_v16i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %shift = ashr <16 x i8> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; SSE42-LABEL: 'var_shift_v16i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <16 x i8> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX-LABEL: 'var_shift_v16i8'
+; AVX-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <16 x i8> %a, %b
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; XOP-LABEL: 'var_shift_v16i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <16 x i8> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX512-LABEL: 'var_shift_v16i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <16 x i8> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+ %shift = ashr <16 x i8> %a, %b
+ ret <16 x i8> %shift
+}
+
+define <32 x i8> @var_shift_v32i8(<32 x i8> %a, <32 x i8> %b) {
+; SSE2-LABEL: 'var_shift_v32i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 108 for instruction: %shift = ashr <32 x i8> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; SSE42-LABEL: 'var_shift_v32i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = ashr <32 x i8> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX1-LABEL: 'var_shift_v32i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %shift = ashr <32 x i8> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX2-LABEL: 'var_shift_v32i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <32 x i8> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; XOP-LABEL: 'var_shift_v32i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = ashr <32 x i8> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX512-LABEL: 'var_shift_v32i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <32 x i8> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; BTVER2-LABEL: 'var_shift_v32i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %shift = ashr <32 x i8> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+ %shift = ashr <32 x i8> %a, %b
+ ret <32 x i8> %shift
+}
+
+define <64 x i8> @var_shift_v64i8(<64 x i8> %a, <64 x i8> %b) {
+; SSE2-LABEL: 'var_shift_v64i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 216 for instruction: %shift = ashr <64 x i8> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; SSE42-LABEL: 'var_shift_v64i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %shift = ashr <64 x i8> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX1-LABEL: 'var_shift_v64i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %shift = ashr <64 x i8> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX2-LABEL: 'var_shift_v64i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = ashr <64 x i8> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; XOP-LABEL: 'var_shift_v64i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <64 x i8> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512F-LABEL: 'var_shift_v64i8'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = ashr <64 x i8> %a, %b
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BW-LABEL: 'var_shift_v64i8'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <64 x i8> %a, %b
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512VL-LABEL: 'var_shift_v64i8'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = ashr <64 x i8> %a, %b
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BWVL-LABEL: 'var_shift_v64i8'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <64 x i8> %a, %b
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; BTVER2-LABEL: 'var_shift_v64i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %shift = ashr <64 x i8> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+ %shift = ashr <64 x i8> %a, %b
+ ret <64 x i8> %shift
+}
+
+;
+; Uniform Variable Shifts
+;
+
+define <2 x i64> @splatvar_shift_v2i64(<2 x i64> %a, i64 %b) {
+; SSE2-LABEL: 'splatvar_shift_v2i64'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %insert = insertelement <2 x i64> poison, i64 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <2 x i64> %insert, <2 x i64> undef, <2 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <2 x i64> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v2i64'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <2 x i64> poison, i64 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <2 x i64> %insert, <2 x i64> undef, <2 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <2 x i64> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX-LABEL: 'splatvar_shift_v2i64'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <2 x i64> poison, i64 %b, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <2 x i64> %insert, <2 x i64> undef, <2 x i32> zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <2 x i64> %a, %splat
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; XOP-LABEL: 'splatvar_shift_v2i64'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <2 x i64> poison, i64 %b, i32 0
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <2 x i64> %insert, <2 x i64> undef, <2 x i32> zeroinitializer
+; XOP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <2 x i64> %a, %splat
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v2i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <2 x i64> poison, i64 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <2 x i64> %insert, <2 x i64> undef, <2 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <2 x i64> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+ %insert = insertelement <2 x i64> poison, i64 %b, i32 0
+ %splat = shufflevector <2 x i64> %insert, <2 x i64> undef, <2 x i32> zeroinitializer
+ %shift = ashr <2 x i64> %a, %splat
+ ret <2 x i64> %shift
+}
+
+define <4 x i64> @splatvar_shift_v4i64(<4 x i64> %a, i64 %b) {
+; SSE2-LABEL: 'splatvar_shift_v4i64'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <4 x i64> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v4i64'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <4 x i64> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v4i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = ashr <4 x i64> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v4i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <4 x i64> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v4i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = ashr <4 x i64> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v4i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = ashr <4 x i64> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v4i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <4 x i64> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v4i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = ashr <4 x i64> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+ %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+ %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+ %shift = ashr <4 x i64> %a, %splat
+ ret <4 x i64> %shift
+}
+
+define <8 x i64> @splatvar_shift_v8i64(<8 x i64> %a, i64 %b) {
+; SSE2-LABEL: 'splatvar_shift_v8i64'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %shift = ashr <8 x i64> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v8i64'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %shift = ashr <8 x i64> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v8i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = ashr <8 x i64> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v8i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <8 x i64> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v8i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <8 x i64> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v8i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <8 x i64> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v8i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i64> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v8i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = ashr <8 x i64> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+ %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+ %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+ %shift = ashr <8 x i64> %a, %splat
+ ret <8 x i64> %shift
+}
+
+define <4 x i32> @splatvar_shift_v4i32(<4 x i32> %a, i32 %b) {
+; SSE2-LABEL: 'splatvar_shift_v4i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %insert = insertelement <4 x i32> poison, i32 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <4 x i32> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v4i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i32> poison, i32 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <4 x i32> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX-LABEL: 'splatvar_shift_v4i32'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i32> poison, i32 %b, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <4 x i32> %a, %splat
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; XOP-LABEL: 'splatvar_shift_v4i32'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i32> poison, i32 %b, i32 0
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <4 x i32> %a, %splat
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v4i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i32> poison, i32 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <4 x i32> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+ %insert = insertelement <4 x i32> poison, i32 %b, i32 0
+ %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+ %shift = ashr <4 x i32> %a, %splat
+ ret <4 x i32> %shift
+}
+
+define <8 x i32> @splatvar_shift_v8i32(<8 x i32> %a, i32 %b) {
+; SSE2-LABEL: 'splatvar_shift_v8i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <8 x i32> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v8i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <8 x i32> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v8i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <8 x i32> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v8i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i32> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v8i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = ashr <8 x i32> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v8i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i32> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v8i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i32> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v8i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <8 x i32> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+ %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+ %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+ %shift = ashr <8 x i32> %a, %splat
+ ret <8 x i32> %shift
+}
+
+define <16 x i32> @splatvar_shift_v16i32(<16 x i32> %a, i32 %b) {
+; SSE2-LABEL: 'splatvar_shift_v16i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <16 x i32> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v16i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <16 x i32> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v16i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <16 x i32> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v16i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <16 x i32> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v16i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <16 x i32> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v16i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <16 x i32> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v16i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <16 x i32> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v16i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <16 x i32> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+ %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+ %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+ %shift = ashr <16 x i32> %a, %splat
+ ret <16 x i32> %shift
+}
+
+define <8 x i16> @splatvar_shift_v8i16(<8 x i16> %a, i16 %b) {
+; SSE2-LABEL: 'splatvar_shift_v8i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i16> poison, i16 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i16> %insert, <8 x i16> undef, <8 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i16> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v8i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i16> poison, i16 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i16> %insert, <8 x i16> undef, <8 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i16> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX-LABEL: 'splatvar_shift_v8i16'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i16> poison, i16 %b, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i16> %insert, <8 x i16> undef, <8 x i32> zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i16> %a, %splat
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; XOP-LABEL: 'splatvar_shift_v8i16'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i16> poison, i16 %b, i32 0
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i16> %insert, <8 x i16> undef, <8 x i32> zeroinitializer
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i16> %a, %splat
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v8i16'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i16> poison, i16 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i16> %insert, <8 x i16> undef, <8 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i16> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+ %insert = insertelement <8 x i16> poison, i16 %b, i32 0
+ %splat = shufflevector <8 x i16> %insert, <8 x i16> undef, <8 x i32> zeroinitializer
+ %shift = ashr <8 x i16> %a, %splat
+ ret <8 x i16> %shift
+}
+
+define <16 x i16> @splatvar_shift_v16i16(<16 x i16> %a, i16 %b) {
+; SSE2-LABEL: 'splatvar_shift_v16i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <16 x i16> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v16i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <16 x i16> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v16i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <16 x i16> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v16i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <16 x i16> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v16i16'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = ashr <16 x i16> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v16i16'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <16 x i16> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v16i16'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <16 x i16> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v16i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <16 x i16> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+ %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+ %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+ %shift = ashr <16 x i16> %a, %splat
+ ret <16 x i16> %shift
+}
+
+define <32 x i16> @splatvar_shift_v32i16(<32 x i16> %a, i16 %b) {
+; SSE2-LABEL: 'splatvar_shift_v32i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <32 x i16> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v32i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <32 x i16> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v32i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <32 x i16> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v32i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <32 x i16> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v32i16'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <32 x i16> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v32i16'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <32 x i16> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512F-LABEL: 'splatvar_shift_v32i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <32 x i16> %a, %splat
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BW-LABEL: 'splatvar_shift_v32i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <32 x i16> %a, %splat
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512VL-LABEL: 'splatvar_shift_v32i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <32 x i16> %a, %splat
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'splatvar_shift_v32i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <32 x i16> %a, %splat
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v32i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <32 x i16> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+ %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+ %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+ %shift = ashr <32 x i16> %a, %splat
+ ret <32 x i16> %shift
+}
+
+define <16 x i8> @splatvar_shift_v16i8(<16 x i8> %a, i8 %b) {
+; SSE2-LABEL: 'splatvar_shift_v16i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %insert = insertelement <16 x i8> poison, i8 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <16 x i8> %insert, <16 x i8> undef, <16 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %shift = ashr <16 x i8> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v16i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i8> poison, i8 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i8> %insert, <16 x i8> undef, <16 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <16 x i8> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX-LABEL: 'splatvar_shift_v16i8'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i8> poison, i8 %b, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i8> %insert, <16 x i8> undef, <16 x i32> zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <16 x i8> %a, %splat
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; XOP-LABEL: 'splatvar_shift_v16i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i8> poison, i8 %b, i32 0
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i8> %insert, <16 x i8> undef, <16 x i32> zeroinitializer
+; XOP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <16 x i8> %a, %splat
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v16i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i8> poison, i8 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i8> %insert, <16 x i8> undef, <16 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <16 x i8> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+ %insert = insertelement <16 x i8> poison, i8 %b, i32 0
+ %splat = shufflevector <16 x i8> %insert, <16 x i8> undef, <16 x i32> zeroinitializer
+ %shift = ashr <16 x i8> %a, %splat
+ ret <16 x i8> %shift
+}
+
+define <32 x i8> @splatvar_shift_v32i8(<32 x i8> %a, i8 %b) {
+; SSE2-LABEL: 'splatvar_shift_v32i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 108 for instruction: %shift = ashr <32 x i8> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v32i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = ashr <32 x i8> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v32i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %shift = ashr <32 x i8> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v32i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <32 x i8> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v32i8'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = ashr <32 x i8> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v32i8'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = ashr <32 x i8> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v32i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <32 x i8> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v32i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %shift = ashr <32 x i8> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+ %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+ %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+ %shift = ashr <32 x i8> %a, %splat
+ ret <32 x i8> %shift
+}
+
+define <64 x i8> @splatvar_shift_v64i8(<64 x i8> %a, i8 %b) {
+; SSE2-LABEL: 'splatvar_shift_v64i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 216 for instruction: %shift = ashr <64 x i8> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v64i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %shift = ashr <64 x i8> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v64i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %shift = ashr <64 x i8> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v64i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = ashr <64 x i8> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v64i8'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <64 x i8> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v64i8'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <64 x i8> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512F-LABEL: 'splatvar_shift_v64i8'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = ashr <64 x i8> %a, %splat
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BW-LABEL: 'splatvar_shift_v64i8'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <64 x i8> %a, %splat
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512VL-LABEL: 'splatvar_shift_v64i8'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = ashr <64 x i8> %a, %splat
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BWVL-LABEL: 'splatvar_shift_v64i8'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <64 x i8> %a, %splat
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v64i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %shift = ashr <64 x i8> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+ %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+ %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+ %shift = ashr <64 x i8> %a, %splat
+ ret <64 x i8> %shift
+}
+
+;
+; Constant Shifts
+;
+
+define <2 x i64> @constant_shift_v2i64(<2 x i64> %a) {
+; SSE-LABEL: 'constant_shift_v2i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <2 x i64> %a, <i64 1, i64 7>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX1-LABEL: 'constant_shift_v2i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <2 x i64> %a, <i64 1, i64 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX2-LABEL: 'constant_shift_v2i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <2 x i64> %a, <i64 1, i64 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; XOP-LABEL: 'constant_shift_v2i64'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <2 x i64> %a, <i64 1, i64 7>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX512-LABEL: 'constant_shift_v2i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <2 x i64> %a, <i64 1, i64 7>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v2i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <2 x i64> %a, <i64 1, i64 7>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+ %shift = ashr <2 x i64> %a, <i64 1, i64 7>
+ ret <2 x i64> %shift
+}
+
+define <4 x i64> @constant_shift_v4i64(<4 x i64> %a) {
+; SSE-LABEL: 'constant_shift_v4i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX1-LABEL: 'constant_shift_v4i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = ashr <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX2-LABEL: 'constant_shift_v4i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOP-LABEL: 'constant_shift_v4i64'
+; XOP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX512-LABEL: 'constant_shift_v4i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v4i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = ashr <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+ %shift = ashr <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+ ret <4 x i64> %shift
+}
+
+define <8 x i64> @constant_shift_v8i64(<8 x i64> %a) {
+; SSE-LABEL: 'constant_shift_v8i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = ashr <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX1-LABEL: 'constant_shift_v8i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = ashr <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX2-LABEL: 'constant_shift_v8i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOP-LABEL: 'constant_shift_v8i64'
+; XOP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX512-LABEL: 'constant_shift_v8i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v8i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = ashr <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+ %shift = ashr <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+ ret <8 x i64> %shift
+}
+
+define <4 x i32> @constant_shift_v4i32(<4 x i32> %a) {
+; SSE2-LABEL: 'constant_shift_v4i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %shift = ashr <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; SSE42-LABEL: 'constant_shift_v4i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX1-LABEL: 'constant_shift_v4i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX2-LABEL: 'constant_shift_v4i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; XOP-LABEL: 'constant_shift_v4i32'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX512-LABEL: 'constant_shift_v4i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v4i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = ashr <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+ %shift = ashr <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+ ret <4 x i32> %shift
+}
+
+define <8 x i32> @constant_shift_v8i32(<8 x i32> %a) {
+; SSE2-LABEL: 'constant_shift_v8i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %shift = ashr <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; SSE42-LABEL: 'constant_shift_v8i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX1-LABEL: 'constant_shift_v8i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = ashr <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX2-LABEL: 'constant_shift_v8i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX1-LABEL: 'constant_shift_v8i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX2-LABEL: 'constant_shift_v8i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX512-LABEL: 'constant_shift_v8i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v8i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = ashr <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+ %shift = ashr <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+ ret <8 x i32> %shift
+}
+
+define <16 x i32> @constant_shift_v16i32(<16 x i32> %a) {
+; SSE2-LABEL: 'constant_shift_v16i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %shift = ashr <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; SSE42-LABEL: 'constant_shift_v16i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = ashr <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX1-LABEL: 'constant_shift_v16i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = ashr <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX2-LABEL: 'constant_shift_v16i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX1-LABEL: 'constant_shift_v16i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX2-LABEL: 'constant_shift_v16i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX512-LABEL: 'constant_shift_v16i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v16i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = ashr <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+ %shift = ashr <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+ ret <16 x i32> %shift
+}
+
+define <8 x i16> @constant_shift_v8i16(<8 x i16> %a) {
+; SSE2-LABEL: 'constant_shift_v8i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %shift = ashr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; SSE42-LABEL: 'constant_shift_v8i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = ashr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX-LABEL: 'constant_shift_v8i16'
+; AVX-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = ashr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; XOP-LABEL: 'constant_shift_v8i16'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512F-LABEL: 'constant_shift_v8i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = ashr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512BW-LABEL: 'constant_shift_v8i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512VL-LABEL: 'constant_shift_v8i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = ashr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'constant_shift_v8i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+ %shift = ashr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+ ret <8 x i16> %shift
+}
+
+define <16 x i16> @constant_shift_v16i16(<16 x i16> %a) {
+; SSE2-LABEL: 'constant_shift_v16i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %shift = ashr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; SSE42-LABEL: 'constant_shift_v16i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %shift = ashr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX1-LABEL: 'constant_shift_v16i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %shift = ashr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX2-LABEL: 'constant_shift_v16i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = ashr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOP-LABEL: 'constant_shift_v16i16'
+; XOP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512F-LABEL: 'constant_shift_v16i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = ashr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512BW-LABEL: 'constant_shift_v16i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512VL-LABEL: 'constant_shift_v16i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = ashr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'constant_shift_v16i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v16i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %shift = ashr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+ %shift = ashr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+ ret <16 x i16> %shift
+}
+
+define <32 x i16> @constant_shift_v32i16(<32 x i16> %a) {
+; SSE2-LABEL: 'constant_shift_v32i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %shift = ashr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; SSE42-LABEL: 'constant_shift_v32i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %shift = ashr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX1-LABEL: 'constant_shift_v32i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %shift = ashr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX2-LABEL: 'constant_shift_v32i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = ashr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOP-LABEL: 'constant_shift_v32i16'
+; XOP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512F-LABEL: 'constant_shift_v32i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = ashr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BW-LABEL: 'constant_shift_v32i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512VL-LABEL: 'constant_shift_v32i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = ashr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'constant_shift_v32i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v32i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %shift = ashr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+ %shift = ashr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+ ret <32 x i16> %shift
+}
+
+define <16 x i8> @constant_shift_v16i8(<16 x i8> %a) {
+; SSE2-LABEL: 'constant_shift_v16i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %shift = ashr <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; SSE42-LABEL: 'constant_shift_v16i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX-LABEL: 'constant_shift_v16i8'
+; AVX-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; XOP-LABEL: 'constant_shift_v16i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX512-LABEL: 'constant_shift_v16i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+ %shift = ashr <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+ ret <16 x i8> %shift
+}
+
+define <32 x i8> @constant_shift_v32i8(<32 x i8> %a) {
+; SSE2-LABEL: 'constant_shift_v32i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 108 for instruction: %shift = ashr <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; SSE42-LABEL: 'constant_shift_v32i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = ashr <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX1-LABEL: 'constant_shift_v32i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %shift = ashr <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX2-LABEL: 'constant_shift_v32i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; XOP-LABEL: 'constant_shift_v32i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX512-LABEL: 'constant_shift_v32i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v32i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %shift = ashr <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+ %shift = ashr <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+ ret <32 x i8> %shift
+}
+
+define <64 x i8> @constant_shift_v64i8(<64 x i8> %a) {
+; SSE2-LABEL: 'constant_shift_v64i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 216 for instruction: %shift = ashr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; SSE42-LABEL: 'constant_shift_v64i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %shift = ashr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX1-LABEL: 'constant_shift_v64i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %shift = ashr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX2-LABEL: 'constant_shift_v64i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = ashr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; XOP-LABEL: 'constant_shift_v64i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512F-LABEL: 'constant_shift_v64i8'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = ashr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BW-LABEL: 'constant_shift_v64i8'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512VL-LABEL: 'constant_shift_v64i8'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = ashr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BWVL-LABEL: 'constant_shift_v64i8'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = ashr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v64i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %shift = ashr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+ %shift = ashr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+ ret <64 x i8> %shift
+}
+
+;
+; Uniform Constant Shifts
+;
+
+define <2 x i64> @splatconstant_shift_v2i64(<2 x i64> %a) {
+; SSE-LABEL: 'splatconstant_shift_v2i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <2 x i64> %a, <i64 7, i64 7>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX-LABEL: 'splatconstant_shift_v2i64'
+; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <2 x i64> %a, <i64 7, i64 7>
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; XOP-LABEL: 'splatconstant_shift_v2i64'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <2 x i64> %a, <i64 7, i64 7>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v2i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <2 x i64> %a, <i64 7, i64 7>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+ %shift = ashr <2 x i64> %a, <i64 7, i64 7>
+ ret <2 x i64> %shift
+}
+
+define <4 x i64> @splatconstant_shift_v4i64(<4 x i64> %a) {
+; SSE-LABEL: 'splatconstant_shift_v4i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v4i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = ashr <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v4i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOP-LABEL: 'splatconstant_shift_v4i64'
+; XOP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v4i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v4i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = ashr <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+ %shift = ashr <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+ ret <4 x i64> %shift
+}
+
+define <8 x i64> @splatconstant_shift_v8i64(<8 x i64> %a) {
+; SSE-LABEL: 'splatconstant_shift_v8i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %shift = ashr <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v8i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = ashr <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v8i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOP-LABEL: 'splatconstant_shift_v8i64'
+; XOP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v8i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v8i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = ashr <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+ %shift = ashr <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+ ret <8 x i64> %shift
+}
+
+define <4 x i32> @splatconstant_shift_v4i32(<4 x i32> %a) {
+; CHECK-LABEL: 'splatconstant_shift_v4i32'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <4 x i32> %a, <i32 5, i32 5, i32 5, i32 5>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+ %shift = ashr <4 x i32> %a, <i32 5, i32 5, i32 5, i32 5>
+ ret <4 x i32> %shift
+}
+
+define <8 x i32> @splatconstant_shift_v8i32(<8 x i32> %a) {
+; SSE-LABEL: 'splatconstant_shift_v8i32'
+; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v8i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v8i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v8i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v8i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v8i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v8i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+ %shift = ashr <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+ ret <8 x i32> %shift
+}
+
+define <16 x i32> @splatconstant_shift_v16i32(<16 x i32> %a) {
+; SSE-LABEL: 'splatconstant_shift_v16i32'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v16i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v16i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v16i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v16i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v16i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v16i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+ %shift = ashr <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+ ret <16 x i32> %shift
+}
+
+define <8 x i16> @splatconstant_shift_v8i16(<8 x i16> %a) {
+; CHECK-LABEL: 'splatconstant_shift_v8i16'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <8 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+ %shift = ashr <8 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+ ret <8 x i16> %shift
+}
+
+define <16 x i16> @splatconstant_shift_v16i16(<16 x i16> %a) {
+; SSE-LABEL: 'splatconstant_shift_v16i16'
+; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v16i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v16i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v16i16'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v16i16'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v16i16'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v16i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+ %shift = ashr <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+ ret <16 x i16> %shift
+}
+
+define <32 x i16> @splatconstant_shift_v32i16(<32 x i16> %a) {
+; SSE-LABEL: 'splatconstant_shift_v32i16'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v32i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v32i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v32i16'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v32i16'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512F-LABEL: 'splatconstant_shift_v32i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BW-LABEL: 'splatconstant_shift_v32i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512VL-LABEL: 'splatconstant_shift_v32i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = ashr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'splatconstant_shift_v32i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v32i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+ %shift = ashr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+ ret <32 x i16> %shift
+}
+
+define <16 x i8> @splatconstant_shift_v16i8(<16 x i8> %a) {
+; SSE-LABEL: 'splatconstant_shift_v16i8'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <16 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX-LABEL: 'splatconstant_shift_v16i8'
+; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <16 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; XOP-LABEL: 'splatconstant_shift_v16i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = ashr <16 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v16i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <16 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+ %shift = ashr <16 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+ ret <16 x i8> %shift
+}
+
+define <32 x i8> @splatconstant_shift_v32i8(<32 x i8> %a) {
+; SSE-LABEL: 'splatconstant_shift_v32i8'
+; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v32i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = ashr <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v32i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; XOP-LABEL: 'splatconstant_shift_v32i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v32i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v32i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = ashr <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+ %shift = ashr <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+ ret <32 x i8> %shift
+}
+
+define <64 x i8> @splatconstant_shift_v64i8(<64 x i8> %a) {
+; SSE-LABEL: 'splatconstant_shift_v64i8'
+; SSE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %shift = ashr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v64i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = ashr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v64i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; XOP-LABEL: 'splatconstant_shift_v64i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512F-LABEL: 'splatconstant_shift_v64i8'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BW-LABEL: 'splatconstant_shift_v64i8'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512VL-LABEL: 'splatconstant_shift_v64i8'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = ashr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BWVL-LABEL: 'splatconstant_shift_v64i8'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = ashr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v64i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = ashr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+ %shift = ashr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+ ret <64 x i8> %shift
+}
diff --git a/llvm/test/Analysis/CostModel/X86/vshift-lshr-cost-inseltpoison.ll b/llvm/test/Analysis/CostModel/X86/vshift-lshr-cost-inseltpoison.ll
new file mode 100644
index 000000000000..2af629bb7518
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/X86/vshift-lshr-cost-inseltpoison.ll
@@ -0,0 +1,1867 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+xop,+avx | FileCheck %s --check-prefixes=CHECK,XOP,XOPAVX1
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+xop,+avx2 | FileCheck %s --check-prefixes=CHECK,XOP,XOPAVX2
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx512f,+avx512dq | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BW
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx512f,+avx512vl | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx512f,+avx512dq,+avx512vl | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512VL
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx512f,+avx512bw,+avx512vl | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BWVL
+;
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mcpu=slm | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mcpu=goldmont | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mcpu=btver2 | FileCheck %s --check-prefixes=CHECK,AVX,BTVER2
+
+; Verify the cost of vector logical shift right instructions.
+
+;
+; Variable Shifts
+;
+
+define <2 x i64> @var_shift_v2i64(<2 x i64> %a, <2 x i64> %b) {
+; SSE-LABEL: 'var_shift_v2i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <2 x i64> %a, %b
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX1-LABEL: 'var_shift_v2i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <2 x i64> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX2-LABEL: 'var_shift_v2i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <2 x i64> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; XOPAVX1-LABEL: 'var_shift_v2i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <2 x i64> %a, %b
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; XOPAVX2-LABEL: 'var_shift_v2i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <2 x i64> %a, %b
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX512-LABEL: 'var_shift_v2i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <2 x i64> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; BTVER2-LABEL: 'var_shift_v2i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <2 x i64> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+ %shift = lshr <2 x i64> %a, %b
+ ret <2 x i64> %shift
+}
+
+define <4 x i64> @var_shift_v4i64(<4 x i64> %a, <4 x i64> %b) {
+; SSE-LABEL: 'var_shift_v4i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <4 x i64> %a, %b
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX1-LABEL: 'var_shift_v4i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = lshr <4 x i64> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX2-LABEL: 'var_shift_v4i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i64> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOPAVX1-LABEL: 'var_shift_v4i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = lshr <4 x i64> %a, %b
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOPAVX2-LABEL: 'var_shift_v4i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i64> %a, %b
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX512-LABEL: 'var_shift_v4i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i64> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; BTVER2-LABEL: 'var_shift_v4i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = lshr <4 x i64> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+ %shift = lshr <4 x i64> %a, %b
+ ret <4 x i64> %shift
+}
+
+define <8 x i64> @var_shift_v8i64(<8 x i64> %a, <8 x i64> %b) {
+; SSE-LABEL: 'var_shift_v8i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %shift = lshr <8 x i64> %a, %b
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX1-LABEL: 'var_shift_v8i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = lshr <8 x i64> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX2-LABEL: 'var_shift_v8i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <8 x i64> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOPAVX1-LABEL: 'var_shift_v8i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <8 x i64> %a, %b
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOPAVX2-LABEL: 'var_shift_v8i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <8 x i64> %a, %b
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX512-LABEL: 'var_shift_v8i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i64> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; BTVER2-LABEL: 'var_shift_v8i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = lshr <8 x i64> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+ %shift = lshr <8 x i64> %a, %b
+ ret <8 x i64> %shift
+}
+
+define <4 x i32> @var_shift_v4i32(<4 x i32> %a, <4 x i32> %b) {
+; SSE2-LABEL: 'var_shift_v4i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %shift = lshr <4 x i32> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; SSE42-LABEL: 'var_shift_v4i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = lshr <4 x i32> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX1-LABEL: 'var_shift_v4i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = lshr <4 x i32> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX2-LABEL: 'var_shift_v4i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i32> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; XOPAVX1-LABEL: 'var_shift_v4i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <4 x i32> %a, %b
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; XOPAVX2-LABEL: 'var_shift_v4i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i32> %a, %b
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX512-LABEL: 'var_shift_v4i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i32> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; BTVER2-LABEL: 'var_shift_v4i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = lshr <4 x i32> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+ %shift = lshr <4 x i32> %a, %b
+ ret <4 x i32> %shift
+}
+
+define <8 x i32> @var_shift_v8i32(<8 x i32> %a, <8 x i32> %b) {
+; SSE2-LABEL: 'var_shift_v8i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %shift = lshr <8 x i32> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; SSE42-LABEL: 'var_shift_v8i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = lshr <8 x i32> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX1-LABEL: 'var_shift_v8i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = lshr <8 x i32> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX2-LABEL: 'var_shift_v8i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i32> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX1-LABEL: 'var_shift_v8i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = lshr <8 x i32> %a, %b
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX2-LABEL: 'var_shift_v8i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i32> %a, %b
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX512-LABEL: 'var_shift_v8i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i32> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; BTVER2-LABEL: 'var_shift_v8i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = lshr <8 x i32> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+ %shift = lshr <8 x i32> %a, %b
+ ret <8 x i32> %shift
+}
+
+define <16 x i32> @var_shift_v16i32(<16 x i32> %a, <16 x i32> %b) {
+; SSE2-LABEL: 'var_shift_v16i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %shift = lshr <16 x i32> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; SSE42-LABEL: 'var_shift_v16i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %shift = lshr <16 x i32> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX1-LABEL: 'var_shift_v16i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = lshr <16 x i32> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX2-LABEL: 'var_shift_v16i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <16 x i32> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX1-LABEL: 'var_shift_v16i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <16 x i32> %a, %b
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX2-LABEL: 'var_shift_v16i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <16 x i32> %a, %b
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX512-LABEL: 'var_shift_v16i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <16 x i32> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; BTVER2-LABEL: 'var_shift_v16i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = lshr <16 x i32> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+ %shift = lshr <16 x i32> %a, %b
+ ret <16 x i32> %shift
+}
+
+define <8 x i16> @var_shift_v8i16(<8 x i16> %a, <8 x i16> %b) {
+; SSE2-LABEL: 'var_shift_v8i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %shift = lshr <8 x i16> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; SSE42-LABEL: 'var_shift_v8i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = lshr <8 x i16> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX-LABEL: 'var_shift_v8i16'
+; AVX-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = lshr <8 x i16> %a, %b
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; XOP-LABEL: 'var_shift_v8i16'
+; XOP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <8 x i16> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512F-LABEL: 'var_shift_v8i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = lshr <8 x i16> %a, %b
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512BW-LABEL: 'var_shift_v8i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i16> %a, %b
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512VL-LABEL: 'var_shift_v8i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = lshr <8 x i16> %a, %b
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'var_shift_v8i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i16> %a, %b
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+ %shift = lshr <8 x i16> %a, %b
+ ret <8 x i16> %shift
+}
+
+define <16 x i16> @var_shift_v16i16(<16 x i16> %a, <16 x i16> %b) {
+; SSE2-LABEL: 'var_shift_v16i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %shift = lshr <16 x i16> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; SSE42-LABEL: 'var_shift_v16i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %shift = lshr <16 x i16> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX1-LABEL: 'var_shift_v16i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %shift = lshr <16 x i16> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX2-LABEL: 'var_shift_v16i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = lshr <16 x i16> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOP-LABEL: 'var_shift_v16i16'
+; XOP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = lshr <16 x i16> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512F-LABEL: 'var_shift_v16i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = lshr <16 x i16> %a, %b
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512BW-LABEL: 'var_shift_v16i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <16 x i16> %a, %b
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512VL-LABEL: 'var_shift_v16i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = lshr <16 x i16> %a, %b
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'var_shift_v16i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <16 x i16> %a, %b
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; BTVER2-LABEL: 'var_shift_v16i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %shift = lshr <16 x i16> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+ %shift = lshr <16 x i16> %a, %b
+ ret <16 x i16> %shift
+}
+
+define <32 x i16> @var_shift_v32i16(<32 x i16> %a, <32 x i16> %b) {
+; SSE2-LABEL: 'var_shift_v32i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %shift = lshr <32 x i16> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; SSE42-LABEL: 'var_shift_v32i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %shift = lshr <32 x i16> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX1-LABEL: 'var_shift_v32i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %shift = lshr <32 x i16> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX2-LABEL: 'var_shift_v32i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = lshr <32 x i16> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOP-LABEL: 'var_shift_v32i16'
+; XOP-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <32 x i16> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512F-LABEL: 'var_shift_v32i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = lshr <32 x i16> %a, %b
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BW-LABEL: 'var_shift_v32i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <32 x i16> %a, %b
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512VL-LABEL: 'var_shift_v32i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = lshr <32 x i16> %a, %b
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'var_shift_v32i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <32 x i16> %a, %b
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; BTVER2-LABEL: 'var_shift_v32i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %shift = lshr <32 x i16> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+ %shift = lshr <32 x i16> %a, %b
+ ret <32 x i16> %shift
+}
+
+define <16 x i8> @var_shift_v16i8(<16 x i8> %a, <16 x i8> %b) {
+; SSE2-LABEL: 'var_shift_v16i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = lshr <16 x i8> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; SSE42-LABEL: 'var_shift_v16i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <16 x i8> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX-LABEL: 'var_shift_v16i8'
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <16 x i8> %a, %b
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; XOP-LABEL: 'var_shift_v16i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <16 x i8> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX512-LABEL: 'var_shift_v16i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <16 x i8> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+ %shift = lshr <16 x i8> %a, %b
+ ret <16 x i8> %shift
+}
+
+define <32 x i8> @var_shift_v32i8(<32 x i8> %a, <32 x i8> %b) {
+; SSE2-LABEL: 'var_shift_v32i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = lshr <32 x i8> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; SSE42-LABEL: 'var_shift_v32i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = lshr <32 x i8> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX1-LABEL: 'var_shift_v32i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = lshr <32 x i8> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX2-LABEL: 'var_shift_v32i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = lshr <32 x i8> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; XOP-LABEL: 'var_shift_v32i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = lshr <32 x i8> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX512-LABEL: 'var_shift_v32i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = lshr <32 x i8> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; BTVER2-LABEL: 'var_shift_v32i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = lshr <32 x i8> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+ %shift = lshr <32 x i8> %a, %b
+ ret <32 x i8> %shift
+}
+
+define <64 x i8> @var_shift_v64i8(<64 x i8> %a, <64 x i8> %b) {
+; SSE2-LABEL: 'var_shift_v64i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %shift = lshr <64 x i8> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; SSE42-LABEL: 'var_shift_v64i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = lshr <64 x i8> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX1-LABEL: 'var_shift_v64i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = lshr <64 x i8> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX2-LABEL: 'var_shift_v64i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = lshr <64 x i8> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; XOP-LABEL: 'var_shift_v64i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <64 x i8> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512F-LABEL: 'var_shift_v64i8'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = lshr <64 x i8> %a, %b
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BW-LABEL: 'var_shift_v64i8'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = lshr <64 x i8> %a, %b
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512VL-LABEL: 'var_shift_v64i8'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = lshr <64 x i8> %a, %b
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BWVL-LABEL: 'var_shift_v64i8'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = lshr <64 x i8> %a, %b
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; BTVER2-LABEL: 'var_shift_v64i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = lshr <64 x i8> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+ %shift = lshr <64 x i8> %a, %b
+ ret <64 x i8> %shift
+}
+
+;
+; Uniform Variable Shifts
+;
+
+define <2 x i64> @splatvar_shift_v2i64(<2 x i64> %a, i64 %b) {
+; SSE2-LABEL: 'splatvar_shift_v2i64'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %insert = insertelement <2 x i64> poison, i64 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <2 x i64> %insert, <2 x i64> undef, <2 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <2 x i64> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v2i64'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <2 x i64> poison, i64 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <2 x i64> %insert, <2 x i64> undef, <2 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <2 x i64> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX-LABEL: 'splatvar_shift_v2i64'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <2 x i64> poison, i64 %b, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <2 x i64> %insert, <2 x i64> undef, <2 x i32> zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <2 x i64> %a, %splat
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; XOP-LABEL: 'splatvar_shift_v2i64'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <2 x i64> poison, i64 %b, i32 0
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <2 x i64> %insert, <2 x i64> undef, <2 x i32> zeroinitializer
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <2 x i64> %a, %splat
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v2i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <2 x i64> poison, i64 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <2 x i64> %insert, <2 x i64> undef, <2 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <2 x i64> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+ %insert = insertelement <2 x i64> poison, i64 %b, i32 0
+ %splat = shufflevector <2 x i64> %insert, <2 x i64> undef, <2 x i32> zeroinitializer
+ %shift = lshr <2 x i64> %a, %splat
+ ret <2 x i64> %shift
+}
+
+define <4 x i64> @splatvar_shift_v4i64(<4 x i64> %a, i64 %b) {
+; SSE2-LABEL: 'splatvar_shift_v4i64'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <4 x i64> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v4i64'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <4 x i64> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v4i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <4 x i64> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v4i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i64> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v4i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = lshr <4 x i64> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v4i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i64> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v4i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i64> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v4i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <4 x i64> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+ %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+ %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+ %shift = lshr <4 x i64> %a, %splat
+ ret <4 x i64> %shift
+}
+
+define <8 x i64> @splatvar_shift_v8i64(<8 x i64> %a, i64 %b) {
+; SSE2-LABEL: 'splatvar_shift_v8i64'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <8 x i64> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v8i64'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <8 x i64> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v8i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <8 x i64> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v8i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <8 x i64> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v8i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <8 x i64> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v8i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <8 x i64> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v8i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i64> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v8i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <8 x i64> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+ %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+ %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+ %shift = lshr <8 x i64> %a, %splat
+ ret <8 x i64> %shift
+}
+
+define <4 x i32> @splatvar_shift_v4i32(<4 x i32> %a, i32 %b) {
+; SSE2-LABEL: 'splatvar_shift_v4i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %insert = insertelement <4 x i32> poison, i32 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i32> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v4i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i32> poison, i32 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i32> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX-LABEL: 'splatvar_shift_v4i32'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i32> poison, i32 %b, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i32> %a, %splat
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; XOP-LABEL: 'splatvar_shift_v4i32'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i32> poison, i32 %b, i32 0
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i32> %a, %splat
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v4i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i32> poison, i32 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i32> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+ %insert = insertelement <4 x i32> poison, i32 %b, i32 0
+ %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+ %shift = lshr <4 x i32> %a, %splat
+ ret <4 x i32> %shift
+}
+
+define <8 x i32> @splatvar_shift_v8i32(<8 x i32> %a, i32 %b) {
+; SSE2-LABEL: 'splatvar_shift_v8i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <8 x i32> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v8i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <8 x i32> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v8i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <8 x i32> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v8i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i32> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v8i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = lshr <8 x i32> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v8i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i32> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v8i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i32> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v8i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <8 x i32> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+ %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+ %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+ %shift = lshr <8 x i32> %a, %splat
+ ret <8 x i32> %shift
+}
+
+define <16 x i32> @splatvar_shift_v16i32(<16 x i32> %a, i32 %b) {
+; SSE2-LABEL: 'splatvar_shift_v16i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <16 x i32> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v16i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <16 x i32> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v16i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <16 x i32> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v16i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <16 x i32> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v16i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <16 x i32> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v16i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <16 x i32> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v16i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <16 x i32> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v16i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <16 x i32> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+ %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+ %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+ %shift = lshr <16 x i32> %a, %splat
+ ret <16 x i32> %shift
+}
+
+define <8 x i16> @splatvar_shift_v8i16(<8 x i16> %a, i16 %b) {
+; SSE2-LABEL: 'splatvar_shift_v8i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i16> poison, i16 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i16> %insert, <8 x i16> undef, <8 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i16> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v8i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i16> poison, i16 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i16> %insert, <8 x i16> undef, <8 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i16> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX-LABEL: 'splatvar_shift_v8i16'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i16> poison, i16 %b, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i16> %insert, <8 x i16> undef, <8 x i32> zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i16> %a, %splat
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; XOP-LABEL: 'splatvar_shift_v8i16'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i16> poison, i16 %b, i32 0
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i16> %insert, <8 x i16> undef, <8 x i32> zeroinitializer
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i16> %a, %splat
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v8i16'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i16> poison, i16 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i16> %insert, <8 x i16> undef, <8 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i16> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+ %insert = insertelement <8 x i16> poison, i16 %b, i32 0
+ %splat = shufflevector <8 x i16> %insert, <8 x i16> undef, <8 x i32> zeroinitializer
+ %shift = lshr <8 x i16> %a, %splat
+ ret <8 x i16> %shift
+}
+
+define <16 x i16> @splatvar_shift_v16i16(<16 x i16> %a, i16 %b) {
+; SSE2-LABEL: 'splatvar_shift_v16i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <16 x i16> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v16i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <16 x i16> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v16i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <16 x i16> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v16i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <16 x i16> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v16i16'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = lshr <16 x i16> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v16i16'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <16 x i16> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v16i16'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <16 x i16> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v16i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <16 x i16> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+ %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+ %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+ %shift = lshr <16 x i16> %a, %splat
+ ret <16 x i16> %shift
+}
+
+define <32 x i16> @splatvar_shift_v32i16(<32 x i16> %a, i16 %b) {
+; SSE2-LABEL: 'splatvar_shift_v32i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <32 x i16> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v32i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <32 x i16> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v32i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <32 x i16> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v32i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <32 x i16> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v32i16'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <32 x i16> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v32i16'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <32 x i16> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512F-LABEL: 'splatvar_shift_v32i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <32 x i16> %a, %splat
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BW-LABEL: 'splatvar_shift_v32i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <32 x i16> %a, %splat
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512VL-LABEL: 'splatvar_shift_v32i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <32 x i16> %a, %splat
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'splatvar_shift_v32i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <32 x i16> %a, %splat
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v32i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <32 x i16> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+ %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+ %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+ %shift = lshr <32 x i16> %a, %splat
+ ret <32 x i16> %shift
+}
+
+define <16 x i8> @splatvar_shift_v16i8(<16 x i8> %a, i8 %b) {
+; SSE2-LABEL: 'splatvar_shift_v16i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %insert = insertelement <16 x i8> poison, i8 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <16 x i8> %insert, <16 x i8> undef, <16 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = lshr <16 x i8> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v16i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i8> poison, i8 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i8> %insert, <16 x i8> undef, <16 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <16 x i8> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX-LABEL: 'splatvar_shift_v16i8'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i8> poison, i8 %b, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i8> %insert, <16 x i8> undef, <16 x i32> zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <16 x i8> %a, %splat
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; XOP-LABEL: 'splatvar_shift_v16i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i8> poison, i8 %b, i32 0
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i8> %insert, <16 x i8> undef, <16 x i32> zeroinitializer
+; XOP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <16 x i8> %a, %splat
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v16i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i8> poison, i8 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i8> %insert, <16 x i8> undef, <16 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <16 x i8> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+ %insert = insertelement <16 x i8> poison, i8 %b, i32 0
+ %splat = shufflevector <16 x i8> %insert, <16 x i8> undef, <16 x i32> zeroinitializer
+ %shift = lshr <16 x i8> %a, %splat
+ ret <16 x i8> %shift
+}
+
+define <32 x i8> @splatvar_shift_v32i8(<32 x i8> %a, i8 %b) {
+; SSE2-LABEL: 'splatvar_shift_v32i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = lshr <32 x i8> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v32i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = lshr <32 x i8> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v32i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = lshr <32 x i8> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v32i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = lshr <32 x i8> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v32i8'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = lshr <32 x i8> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v32i8'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = lshr <32 x i8> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v32i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = lshr <32 x i8> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v32i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = lshr <32 x i8> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+ %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+ %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+ %shift = lshr <32 x i8> %a, %splat
+ ret <32 x i8> %shift
+}
+
+define <64 x i8> @splatvar_shift_v64i8(<64 x i8> %a, i8 %b) {
+; SSE2-LABEL: 'splatvar_shift_v64i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %shift = lshr <64 x i8> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v64i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = lshr <64 x i8> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v64i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = lshr <64 x i8> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v64i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = lshr <64 x i8> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v64i8'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <64 x i8> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v64i8'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <64 x i8> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512F-LABEL: 'splatvar_shift_v64i8'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = lshr <64 x i8> %a, %splat
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BW-LABEL: 'splatvar_shift_v64i8'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = lshr <64 x i8> %a, %splat
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512VL-LABEL: 'splatvar_shift_v64i8'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = lshr <64 x i8> %a, %splat
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BWVL-LABEL: 'splatvar_shift_v64i8'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = lshr <64 x i8> %a, %splat
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v64i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = lshr <64 x i8> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+ %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+ %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+ %shift = lshr <64 x i8> %a, %splat
+ ret <64 x i8> %shift
+}
+
+;
+; Constant Shifts
+;
+
+define <2 x i64> @constant_shift_v2i64(<2 x i64> %a) {
+; SSE-LABEL: 'constant_shift_v2i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <2 x i64> %a, <i64 1, i64 7>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX1-LABEL: 'constant_shift_v2i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <2 x i64> %a, <i64 1, i64 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX2-LABEL: 'constant_shift_v2i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <2 x i64> %a, <i64 1, i64 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; XOP-LABEL: 'constant_shift_v2i64'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <2 x i64> %a, <i64 1, i64 7>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX512-LABEL: 'constant_shift_v2i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <2 x i64> %a, <i64 1, i64 7>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v2i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <2 x i64> %a, <i64 1, i64 7>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+ %shift = lshr <2 x i64> %a, <i64 1, i64 7>
+ ret <2 x i64> %shift
+}
+
+define <4 x i64> @constant_shift_v4i64(<4 x i64> %a) {
+; SSE-LABEL: 'constant_shift_v4i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX1-LABEL: 'constant_shift_v4i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = lshr <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX2-LABEL: 'constant_shift_v4i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOPAVX1-LABEL: 'constant_shift_v4i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOPAVX2-LABEL: 'constant_shift_v4i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX512-LABEL: 'constant_shift_v4i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v4i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = lshr <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+ %shift = lshr <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+ ret <4 x i64> %shift
+}
+
+define <8 x i64> @constant_shift_v8i64(<8 x i64> %a) {
+; SSE-LABEL: 'constant_shift_v8i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %shift = lshr <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX1-LABEL: 'constant_shift_v8i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = lshr <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX2-LABEL: 'constant_shift_v8i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOPAVX1-LABEL: 'constant_shift_v8i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOPAVX2-LABEL: 'constant_shift_v8i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX512-LABEL: 'constant_shift_v8i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v8i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = lshr <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+ %shift = lshr <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+ ret <8 x i64> %shift
+}
+
+define <4 x i32> @constant_shift_v4i32(<4 x i32> %a) {
+; SSE2-LABEL: 'constant_shift_v4i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %shift = lshr <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; SSE42-LABEL: 'constant_shift_v4i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = lshr <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX1-LABEL: 'constant_shift_v4i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = lshr <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX2-LABEL: 'constant_shift_v4i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; XOP-LABEL: 'constant_shift_v4i32'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX512-LABEL: 'constant_shift_v4i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v4i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = lshr <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+ %shift = lshr <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+ ret <4 x i32> %shift
+}
+
+define <8 x i32> @constant_shift_v8i32(<8 x i32> %a) {
+; SSE2-LABEL: 'constant_shift_v8i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %shift = lshr <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; SSE42-LABEL: 'constant_shift_v8i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = lshr <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX1-LABEL: 'constant_shift_v8i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = lshr <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX2-LABEL: 'constant_shift_v8i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX1-LABEL: 'constant_shift_v8i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX2-LABEL: 'constant_shift_v8i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX512-LABEL: 'constant_shift_v8i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v8i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = lshr <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+ %shift = lshr <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+ ret <8 x i32> %shift
+}
+
+define <16 x i32> @constant_shift_v16i32(<16 x i32> %a) {
+; SSE2-LABEL: 'constant_shift_v16i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %shift = lshr <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; SSE42-LABEL: 'constant_shift_v16i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %shift = lshr <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX1-LABEL: 'constant_shift_v16i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = lshr <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX2-LABEL: 'constant_shift_v16i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX1-LABEL: 'constant_shift_v16i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX2-LABEL: 'constant_shift_v16i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX512-LABEL: 'constant_shift_v16i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v16i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = lshr <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+ %shift = lshr <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+ ret <16 x i32> %shift
+}
+
+define <8 x i16> @constant_shift_v8i16(<8 x i16> %a) {
+; SSE2-LABEL: 'constant_shift_v8i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %shift = lshr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; SSE42-LABEL: 'constant_shift_v8i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = lshr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX-LABEL: 'constant_shift_v8i16'
+; AVX-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = lshr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; XOP-LABEL: 'constant_shift_v8i16'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512F-LABEL: 'constant_shift_v8i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = lshr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512BW-LABEL: 'constant_shift_v8i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512VL-LABEL: 'constant_shift_v8i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = lshr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'constant_shift_v8i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+ %shift = lshr <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+ ret <8 x i16> %shift
+}
+
+define <16 x i16> @constant_shift_v16i16(<16 x i16> %a) {
+; SSE2-LABEL: 'constant_shift_v16i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %shift = lshr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; SSE42-LABEL: 'constant_shift_v16i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %shift = lshr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX1-LABEL: 'constant_shift_v16i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %shift = lshr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX2-LABEL: 'constant_shift_v16i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = lshr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOP-LABEL: 'constant_shift_v16i16'
+; XOP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512F-LABEL: 'constant_shift_v16i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = lshr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512BW-LABEL: 'constant_shift_v16i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512VL-LABEL: 'constant_shift_v16i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = lshr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'constant_shift_v16i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v16i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %shift = lshr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+ %shift = lshr <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+ ret <16 x i16> %shift
+}
+
+define <32 x i16> @constant_shift_v32i16(<32 x i16> %a) {
+; SSE2-LABEL: 'constant_shift_v32i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %shift = lshr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; SSE42-LABEL: 'constant_shift_v32i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %shift = lshr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX1-LABEL: 'constant_shift_v32i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %shift = lshr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX2-LABEL: 'constant_shift_v32i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = lshr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOP-LABEL: 'constant_shift_v32i16'
+; XOP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512F-LABEL: 'constant_shift_v32i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = lshr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BW-LABEL: 'constant_shift_v32i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512VL-LABEL: 'constant_shift_v32i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = lshr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'constant_shift_v32i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v32i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %shift = lshr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+ %shift = lshr <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+ ret <32 x i16> %shift
+}
+
+define <16 x i8> @constant_shift_v16i8(<16 x i8> %a) {
+; SSE2-LABEL: 'constant_shift_v16i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = lshr <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; SSE42-LABEL: 'constant_shift_v16i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX-LABEL: 'constant_shift_v16i8'
+; AVX-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; XOP-LABEL: 'constant_shift_v16i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX512-LABEL: 'constant_shift_v16i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+ %shift = lshr <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+ ret <16 x i8> %shift
+}
+
+define <32 x i8> @constant_shift_v32i8(<32 x i8> %a) {
+; SSE2-LABEL: 'constant_shift_v32i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = lshr <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; SSE42-LABEL: 'constant_shift_v32i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = lshr <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX1-LABEL: 'constant_shift_v32i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = lshr <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX2-LABEL: 'constant_shift_v32i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = lshr <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; XOP-LABEL: 'constant_shift_v32i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX512-LABEL: 'constant_shift_v32i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = lshr <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v32i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = lshr <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+ %shift = lshr <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+ ret <32 x i8> %shift
+}
+
+define <64 x i8> @constant_shift_v64i8(<64 x i8> %a) {
+; SSE2-LABEL: 'constant_shift_v64i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %shift = lshr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; SSE42-LABEL: 'constant_shift_v64i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = lshr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX1-LABEL: 'constant_shift_v64i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = lshr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX2-LABEL: 'constant_shift_v64i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = lshr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; XOP-LABEL: 'constant_shift_v64i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512F-LABEL: 'constant_shift_v64i8'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = lshr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BW-LABEL: 'constant_shift_v64i8'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = lshr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512VL-LABEL: 'constant_shift_v64i8'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = lshr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BWVL-LABEL: 'constant_shift_v64i8'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = lshr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v64i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = lshr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+ %shift = lshr <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+ ret <64 x i8> %shift
+}
+
+;
+; Uniform Constant Shifts
+;
+
+define <2 x i64> @splatconstant_shift_v2i64(<2 x i64> %a) {
+; CHECK-LABEL: 'splatconstant_shift_v2i64'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <2 x i64> %a, <i64 7, i64 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+ %shift = lshr <2 x i64> %a, <i64 7, i64 7>
+ ret <2 x i64> %shift
+}
+
+define <4 x i64> @splatconstant_shift_v4i64(<4 x i64> %a) {
+; SSE-LABEL: 'splatconstant_shift_v4i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v4i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v4i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v4i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v4i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v4i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v4i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+ %shift = lshr <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+ ret <4 x i64> %shift
+}
+
+define <8 x i64> @splatconstant_shift_v8i64(<8 x i64> %a) {
+; SSE-LABEL: 'splatconstant_shift_v8i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v8i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v8i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v8i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v8i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v8i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v8i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+ %shift = lshr <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+ ret <8 x i64> %shift
+}
+
+define <4 x i32> @splatconstant_shift_v4i32(<4 x i32> %a) {
+; CHECK-LABEL: 'splatconstant_shift_v4i32'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <4 x i32> %a, <i32 5, i32 5, i32 5, i32 5>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+ %shift = lshr <4 x i32> %a, <i32 5, i32 5, i32 5, i32 5>
+ ret <4 x i32> %shift
+}
+
+define <8 x i32> @splatconstant_shift_v8i32(<8 x i32> %a) {
+; SSE-LABEL: 'splatconstant_shift_v8i32'
+; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v8i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v8i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v8i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v8i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v8i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v8i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+ %shift = lshr <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+ ret <8 x i32> %shift
+}
+
+define <16 x i32> @splatconstant_shift_v16i32(<16 x i32> %a) {
+; SSE-LABEL: 'splatconstant_shift_v16i32'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v16i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v16i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v16i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v16i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v16i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v16i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+ %shift = lshr <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+ ret <16 x i32> %shift
+}
+
+define <8 x i16> @splatconstant_shift_v8i16(<8 x i16> %a) {
+; CHECK-LABEL: 'splatconstant_shift_v8i16'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <8 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+ %shift = lshr <8 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+ ret <8 x i16> %shift
+}
+
+define <16 x i16> @splatconstant_shift_v16i16(<16 x i16> %a) {
+; SSE-LABEL: 'splatconstant_shift_v16i16'
+; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v16i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v16i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v16i16'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v16i16'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v16i16'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v16i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+ %shift = lshr <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+ ret <16 x i16> %shift
+}
+
+define <32 x i16> @splatconstant_shift_v32i16(<32 x i16> %a) {
+; SSE-LABEL: 'splatconstant_shift_v32i16'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v32i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v32i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v32i16'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v32i16'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512F-LABEL: 'splatconstant_shift_v32i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BW-LABEL: 'splatconstant_shift_v32i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512VL-LABEL: 'splatconstant_shift_v32i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'splatconstant_shift_v32i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v32i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+ %shift = lshr <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+ ret <32 x i16> %shift
+}
+
+define <16 x i8> @splatconstant_shift_v16i8(<16 x i8> %a) {
+; SSE-LABEL: 'splatconstant_shift_v16i8'
+; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <16 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX-LABEL: 'splatconstant_shift_v16i8'
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <16 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; XOP-LABEL: 'splatconstant_shift_v16i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = lshr <16 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v16i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <16 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+ %shift = lshr <16 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+ ret <16 x i8> %shift
+}
+
+define <32 x i8> @splatconstant_shift_v32i8(<32 x i8> %a) {
+; SSE-LABEL: 'splatconstant_shift_v32i8'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v32i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = lshr <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v32i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v32i8'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v32i8'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v32i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v32i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = lshr <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+ %shift = lshr <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+ ret <32 x i8> %shift
+}
+
+define <64 x i8> @splatconstant_shift_v64i8(<64 x i8> %a) {
+; SSE-LABEL: 'splatconstant_shift_v64i8'
+; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v64i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v64i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v64i8'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = lshr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v64i8'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512F-LABEL: 'splatconstant_shift_v64i8'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BW-LABEL: 'splatconstant_shift_v64i8'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512VL-LABEL: 'splatconstant_shift_v64i8'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = lshr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BWVL-LABEL: 'splatconstant_shift_v64i8'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = lshr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v64i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = lshr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+ %shift = lshr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+ ret <64 x i8> %shift
+}
diff --git a/llvm/test/Analysis/CostModel/X86/vshift-shl-cost-inseltpoison.ll b/llvm/test/Analysis/CostModel/X86/vshift-shl-cost-inseltpoison.ll
new file mode 100644
index 000000000000..cf6144e9f014
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/X86/vshift-shl-cost-inseltpoison.ll
@@ -0,0 +1,2197 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+xop,+avx | FileCheck %s --check-prefixes=CHECK,XOP,XOPAVX1
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+xop,+avx2 | FileCheck %s --check-prefixes=CHECK,XOP,XOPAVX2
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx512f,+avx512dq | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BW
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx512f,+avx512vl | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx512f,+avx512dq,+avx512vl | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512VL
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+avx512f,+avx512bw,+avx512vl | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BWVL
+;
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mcpu=slm | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mcpu=goldmont | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mcpu=btver2 | FileCheck %s --check-prefixes=CHECK,AVX,BTVER2
+
+; Verify the cost of vector shift left instructions.
+
+;
+; Variable Shifts
+;
+
+define <2 x i64> @var_shift_v2i64(<2 x i64> %a, <2 x i64> %b) {
+; SSE-LABEL: 'var_shift_v2i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <2 x i64> %a, %b
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX1-LABEL: 'var_shift_v2i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <2 x i64> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX2-LABEL: 'var_shift_v2i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <2 x i64> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; XOP-LABEL: 'var_shift_v2i64'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <2 x i64> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX512-LABEL: 'var_shift_v2i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <2 x i64> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; BTVER2-LABEL: 'var_shift_v2i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <2 x i64> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+ %shift = shl <2 x i64> %a, %b
+ ret <2 x i64> %shift
+}
+
+define <4 x i64> @var_shift_v4i64(<4 x i64> %a, <4 x i64> %b) {
+; SSE-LABEL: 'var_shift_v4i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <4 x i64> %a, %b
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX1-LABEL: 'var_shift_v4i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = shl <4 x i64> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX2-LABEL: 'var_shift_v4i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i64> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOPAVX1-LABEL: 'var_shift_v4i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <4 x i64> %a, %b
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOPAVX2-LABEL: 'var_shift_v4i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i64> %a, %b
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX512-LABEL: 'var_shift_v4i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i64> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; BTVER2-LABEL: 'var_shift_v4i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = shl <4 x i64> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+ %shift = shl <4 x i64> %a, %b
+ ret <4 x i64> %shift
+}
+
+define <8 x i64> @var_shift_v8i64(<8 x i64> %a, <8 x i64> %b) {
+; SSE-LABEL: 'var_shift_v8i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %shift = shl <8 x i64> %a, %b
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX1-LABEL: 'var_shift_v8i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = shl <8 x i64> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX2-LABEL: 'var_shift_v8i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <8 x i64> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOPAVX1-LABEL: 'var_shift_v8i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <8 x i64> %a, %b
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOPAVX2-LABEL: 'var_shift_v8i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <8 x i64> %a, %b
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX512-LABEL: 'var_shift_v8i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i64> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; BTVER2-LABEL: 'var_shift_v8i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = shl <8 x i64> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+ %shift = shl <8 x i64> %a, %b
+ ret <8 x i64> %shift
+}
+
+define <4 x i32> @var_shift_v4i32(<4 x i32> %a, <4 x i32> %b) {
+; SSE2-LABEL: 'var_shift_v4i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = shl <4 x i32> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; SSE42-LABEL: 'var_shift_v4i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <4 x i32> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX1-LABEL: 'var_shift_v4i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <4 x i32> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX2-LABEL: 'var_shift_v4i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i32> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; XOP-LABEL: 'var_shift_v4i32'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i32> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX512-LABEL: 'var_shift_v4i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i32> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; BTVER2-LABEL: 'var_shift_v4i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <4 x i32> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+ %shift = shl <4 x i32> %a, %b
+ ret <4 x i32> %shift
+}
+
+define <8 x i32> @var_shift_v8i32(<8 x i32> %a, <8 x i32> %b) {
+; SSE2-LABEL: 'var_shift_v8i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = shl <8 x i32> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; SSE42-LABEL: 'var_shift_v8i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <8 x i32> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX1-LABEL: 'var_shift_v8i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = shl <8 x i32> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX2-LABEL: 'var_shift_v8i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i32> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX1-LABEL: 'var_shift_v8i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <8 x i32> %a, %b
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX2-LABEL: 'var_shift_v8i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i32> %a, %b
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX512-LABEL: 'var_shift_v8i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i32> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; BTVER2-LABEL: 'var_shift_v8i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = shl <8 x i32> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+ %shift = shl <8 x i32> %a, %b
+ ret <8 x i32> %shift
+}
+
+define <16 x i32> @var_shift_v16i32(<16 x i32> %a, <16 x i32> %b) {
+; SSE2-LABEL: 'var_shift_v16i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %shift = shl <16 x i32> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; SSE42-LABEL: 'var_shift_v16i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %shift = shl <16 x i32> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX1-LABEL: 'var_shift_v16i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = shl <16 x i32> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX2-LABEL: 'var_shift_v16i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <16 x i32> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX1-LABEL: 'var_shift_v16i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <16 x i32> %a, %b
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX2-LABEL: 'var_shift_v16i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <16 x i32> %a, %b
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX512-LABEL: 'var_shift_v16i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i32> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; BTVER2-LABEL: 'var_shift_v16i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = shl <16 x i32> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+ %shift = shl <16 x i32> %a, %b
+ ret <16 x i32> %shift
+}
+
+define <8 x i16> @var_shift_v8i16(<8 x i16> %a, <8 x i16> %b) {
+; SSE2-LABEL: 'var_shift_v8i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %shift = shl <8 x i16> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; SSE42-LABEL: 'var_shift_v8i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = shl <8 x i16> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX-LABEL: 'var_shift_v8i16'
+; AVX-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = shl <8 x i16> %a, %b
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; XOP-LABEL: 'var_shift_v8i16'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i16> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512F-LABEL: 'var_shift_v8i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = shl <8 x i16> %a, %b
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512BW-LABEL: 'var_shift_v8i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i16> %a, %b
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512VL-LABEL: 'var_shift_v8i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %shift = shl <8 x i16> %a, %b
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'var_shift_v8i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i16> %a, %b
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+ %shift = shl <8 x i16> %a, %b
+ ret <8 x i16> %shift
+}
+
+define <16 x i16> @var_shift_v16i16(<16 x i16> %a, <16 x i16> %b) {
+; SSE2-LABEL: 'var_shift_v16i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %shift = shl <16 x i16> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; SSE42-LABEL: 'var_shift_v16i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %shift = shl <16 x i16> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX1-LABEL: 'var_shift_v16i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %shift = shl <16 x i16> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX2-LABEL: 'var_shift_v16i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = shl <16 x i16> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOP-LABEL: 'var_shift_v16i16'
+; XOP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <16 x i16> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512F-LABEL: 'var_shift_v16i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = shl <16 x i16> %a, %b
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512BW-LABEL: 'var_shift_v16i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i16> %a, %b
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512VL-LABEL: 'var_shift_v16i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = shl <16 x i16> %a, %b
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'var_shift_v16i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i16> %a, %b
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; BTVER2-LABEL: 'var_shift_v16i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %shift = shl <16 x i16> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+ %shift = shl <16 x i16> %a, %b
+ ret <16 x i16> %shift
+}
+
+define <32 x i16> @var_shift_v32i16(<32 x i16> %a, <32 x i16> %b) {
+; SSE2-LABEL: 'var_shift_v32i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %shift = shl <32 x i16> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; SSE42-LABEL: 'var_shift_v32i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %shift = shl <32 x i16> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX1-LABEL: 'var_shift_v32i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %shift = shl <32 x i16> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX2-LABEL: 'var_shift_v32i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = shl <32 x i16> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOP-LABEL: 'var_shift_v32i16'
+; XOP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <32 x i16> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512F-LABEL: 'var_shift_v32i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = shl <32 x i16> %a, %b
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BW-LABEL: 'var_shift_v32i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <32 x i16> %a, %b
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512VL-LABEL: 'var_shift_v32i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = shl <32 x i16> %a, %b
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'var_shift_v32i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <32 x i16> %a, %b
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; BTVER2-LABEL: 'var_shift_v32i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %shift = shl <32 x i16> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+ %shift = shl <32 x i16> %a, %b
+ ret <32 x i16> %shift
+}
+
+define <16 x i8> @var_shift_v16i8(<16 x i8> %a, <16 x i8> %b) {
+; SSE2-LABEL: 'var_shift_v16i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = shl <16 x i8> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; SSE42-LABEL: 'var_shift_v16i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <16 x i8> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX-LABEL: 'var_shift_v16i8'
+; AVX-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <16 x i8> %a, %b
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; XOP-LABEL: 'var_shift_v16i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i8> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX512-LABEL: 'var_shift_v16i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <16 x i8> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+ %shift = shl <16 x i8> %a, %b
+ ret <16 x i8> %shift
+}
+
+define <32 x i8> @var_shift_v32i8(<32 x i8> %a, <32 x i8> %b) {
+; SSE2-LABEL: 'var_shift_v32i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = shl <32 x i8> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; SSE42-LABEL: 'var_shift_v32i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = shl <32 x i8> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX1-LABEL: 'var_shift_v32i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = shl <32 x i8> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX2-LABEL: 'var_shift_v32i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <32 x i8> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; XOP-LABEL: 'var_shift_v32i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <32 x i8> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX512-LABEL: 'var_shift_v32i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <32 x i8> %a, %b
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; BTVER2-LABEL: 'var_shift_v32i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = shl <32 x i8> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+ %shift = shl <32 x i8> %a, %b
+ ret <32 x i8> %shift
+}
+
+define <64 x i8> @var_shift_v64i8(<64 x i8> %a, <64 x i8> %b) {
+; SSE2-LABEL: 'var_shift_v64i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %shift = shl <64 x i8> %a, %b
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; SSE42-LABEL: 'var_shift_v64i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %shift = shl <64 x i8> %a, %b
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX1-LABEL: 'var_shift_v64i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = shl <64 x i8> %a, %b
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX2-LABEL: 'var_shift_v64i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = shl <64 x i8> %a, %b
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; XOP-LABEL: 'var_shift_v64i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <64 x i8> %a, %b
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512F-LABEL: 'var_shift_v64i8'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = shl <64 x i8> %a, %b
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BW-LABEL: 'var_shift_v64i8'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <64 x i8> %a, %b
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512VL-LABEL: 'var_shift_v64i8'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = shl <64 x i8> %a, %b
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BWVL-LABEL: 'var_shift_v64i8'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <64 x i8> %a, %b
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; BTVER2-LABEL: 'var_shift_v64i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = shl <64 x i8> %a, %b
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+ %shift = shl <64 x i8> %a, %b
+ ret <64 x i8> %shift
+}
+
+;
+; Uniform Variable Shifts
+;
+
+define <2 x i64> @splatvar_shift_v2i64(<2 x i64> %a, i64 %b) {
+; SSE2-LABEL: 'splatvar_shift_v2i64'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %insert = insertelement <2 x i64> poison, i64 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <2 x i64> %insert, <2 x i64> undef, <2 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <2 x i64> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v2i64'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <2 x i64> poison, i64 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <2 x i64> %insert, <2 x i64> undef, <2 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <2 x i64> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX-LABEL: 'splatvar_shift_v2i64'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <2 x i64> poison, i64 %b, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <2 x i64> %insert, <2 x i64> undef, <2 x i32> zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <2 x i64> %a, %splat
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; XOP-LABEL: 'splatvar_shift_v2i64'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <2 x i64> poison, i64 %b, i32 0
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <2 x i64> %insert, <2 x i64> undef, <2 x i32> zeroinitializer
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <2 x i64> %a, %splat
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v2i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <2 x i64> poison, i64 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <2 x i64> %insert, <2 x i64> undef, <2 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <2 x i64> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+ %insert = insertelement <2 x i64> poison, i64 %b, i32 0
+ %splat = shufflevector <2 x i64> %insert, <2 x i64> undef, <2 x i32> zeroinitializer
+ %shift = shl <2 x i64> %a, %splat
+ ret <2 x i64> %shift
+}
+
+define <4 x i64> @splatvar_shift_v4i64(<4 x i64> %a, i64 %b) {
+; SSE2-LABEL: 'splatvar_shift_v4i64'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <4 x i64> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v4i64'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <4 x i64> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v4i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <4 x i64> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v4i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i64> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v4i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <4 x i64> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v4i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i64> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v4i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i64> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v4i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <4 x i64> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+ %insert = insertelement <4 x i64> poison, i64 %b, i32 0
+ %splat = shufflevector <4 x i64> %insert, <4 x i64> undef, <4 x i32> zeroinitializer
+ %shift = shl <4 x i64> %a, %splat
+ ret <4 x i64> %shift
+}
+
+define <8 x i64> @splatvar_shift_v8i64(<8 x i64> %a, i64 %b) {
+; SSE2-LABEL: 'splatvar_shift_v8i64'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <8 x i64> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v8i64'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <8 x i64> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v8i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <8 x i64> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v8i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <8 x i64> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v8i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <8 x i64> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v8i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <8 x i64> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v8i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i64> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v8i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <8 x i64> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+ %insert = insertelement <8 x i64> poison, i64 %b, i32 0
+ %splat = shufflevector <8 x i64> %insert, <8 x i64> undef, <8 x i32> zeroinitializer
+ %shift = shl <8 x i64> %a, %splat
+ ret <8 x i64> %shift
+}
+
+define <4 x i32> @splatvar_shift_v4i32(<4 x i32> %a, i32 %b) {
+; SSE2-LABEL: 'splatvar_shift_v4i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %insert = insertelement <4 x i32> poison, i32 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i32> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v4i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i32> poison, i32 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i32> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX-LABEL: 'splatvar_shift_v4i32'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i32> poison, i32 %b, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i32> %a, %splat
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; XOP-LABEL: 'splatvar_shift_v4i32'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i32> poison, i32 %b, i32 0
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i32> %a, %splat
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v4i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <4 x i32> poison, i32 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i32> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+ %insert = insertelement <4 x i32> poison, i32 %b, i32 0
+ %splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
+ %shift = shl <4 x i32> %a, %splat
+ ret <4 x i32> %shift
+}
+
+define <8 x i32> @splatvar_shift_v8i32(<8 x i32> %a, i32 %b) {
+; SSE2-LABEL: 'splatvar_shift_v8i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <8 x i32> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v8i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <8 x i32> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v8i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <8 x i32> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v8i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i32> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v8i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <8 x i32> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v8i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i32> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v8i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i32> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v8i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <8 x i32> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+ %insert = insertelement <8 x i32> poison, i32 %b, i32 0
+ %splat = shufflevector <8 x i32> %insert, <8 x i32> undef, <8 x i32> zeroinitializer
+ %shift = shl <8 x i32> %a, %splat
+ ret <8 x i32> %shift
+}
+
+define <16 x i32> @splatvar_shift_v16i32(<16 x i32> %a, i32 %b) {
+; SSE2-LABEL: 'splatvar_shift_v16i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <16 x i32> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v16i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <16 x i32> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v16i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <16 x i32> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v16i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <16 x i32> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v16i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <16 x i32> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v16i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <16 x i32> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v16i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i32> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v16i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <16 x i32> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+ %insert = insertelement <16 x i32> poison, i32 %b, i32 0
+ %splat = shufflevector <16 x i32> %insert, <16 x i32> undef, <16 x i32> zeroinitializer
+ %shift = shl <16 x i32> %a, %splat
+ ret <16 x i32> %shift
+}
+
+define <8 x i16> @splatvar_shift_v8i16(<8 x i16> %a, i16 %b) {
+; SSE2-LABEL: 'splatvar_shift_v8i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i16> poison, i16 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <8 x i16> %insert, <8 x i16> undef, <8 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i16> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v8i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i16> poison, i16 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i16> %insert, <8 x i16> undef, <8 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i16> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX-LABEL: 'splatvar_shift_v8i16'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i16> poison, i16 %b, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i16> %insert, <8 x i16> undef, <8 x i32> zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i16> %a, %splat
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; XOP-LABEL: 'splatvar_shift_v8i16'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i16> poison, i16 %b, i32 0
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i16> %insert, <8 x i16> undef, <8 x i32> zeroinitializer
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i16> %a, %splat
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v8i16'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <8 x i16> poison, i16 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <8 x i16> %insert, <8 x i16> undef, <8 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i16> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+ %insert = insertelement <8 x i16> poison, i16 %b, i32 0
+ %splat = shufflevector <8 x i16> %insert, <8 x i16> undef, <8 x i32> zeroinitializer
+ %shift = shl <8 x i16> %a, %splat
+ ret <8 x i16> %shift
+}
+
+define <16 x i16> @splatvar_shift_v16i16(<16 x i16> %a, i16 %b) {
+; SSE2-LABEL: 'splatvar_shift_v16i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <16 x i16> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v16i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <16 x i16> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v16i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <16 x i16> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v16i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i16> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v16i16'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <16 x i16> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v16i16'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i16> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v16i16'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i16> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v16i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <16 x i16> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+ %insert = insertelement <16 x i16> poison, i16 %b, i32 0
+ %splat = shufflevector <16 x i16> %insert, <16 x i16> undef, <16 x i32> zeroinitializer
+ %shift = shl <16 x i16> %a, %splat
+ ret <16 x i16> %shift
+}
+
+define <32 x i16> @splatvar_shift_v32i16(<32 x i16> %a, i16 %b) {
+; SSE2-LABEL: 'splatvar_shift_v32i16'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <32 x i16> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v32i16'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <32 x i16> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v32i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <32 x i16> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v32i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <32 x i16> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v32i16'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <32 x i16> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v32i16'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <32 x i16> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512F-LABEL: 'splatvar_shift_v32i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <32 x i16> %a, %splat
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BW-LABEL: 'splatvar_shift_v32i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <32 x i16> %a, %splat
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512VL-LABEL: 'splatvar_shift_v32i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <32 x i16> %a, %splat
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'splatvar_shift_v32i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <32 x i16> %a, %splat
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v32i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <32 x i16> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+ %insert = insertelement <32 x i16> poison, i16 %b, i32 0
+ %splat = shufflevector <32 x i16> %insert, <32 x i16> undef, <32 x i32> zeroinitializer
+ %shift = shl <32 x i16> %a, %splat
+ ret <32 x i16> %shift
+}
+
+define <16 x i8> @splatvar_shift_v16i8(<16 x i8> %a, i8 %b) {
+; SSE2-LABEL: 'splatvar_shift_v16i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %insert = insertelement <16 x i8> poison, i8 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <16 x i8> %insert, <16 x i8> undef, <16 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = shl <16 x i8> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v16i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i8> poison, i8 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i8> %insert, <16 x i8> undef, <16 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <16 x i8> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX-LABEL: 'splatvar_shift_v16i8'
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i8> poison, i8 %b, i32 0
+; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i8> %insert, <16 x i8> undef, <16 x i32> zeroinitializer
+; AVX-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <16 x i8> %a, %splat
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; XOP-LABEL: 'splatvar_shift_v16i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i8> poison, i8 %b, i32 0
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i8> %insert, <16 x i8> undef, <16 x i32> zeroinitializer
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i8> %a, %splat
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v16i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <16 x i8> poison, i8 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <16 x i8> %insert, <16 x i8> undef, <16 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <16 x i8> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+ %insert = insertelement <16 x i8> poison, i8 %b, i32 0
+ %splat = shufflevector <16 x i8> %insert, <16 x i8> undef, <16 x i32> zeroinitializer
+ %shift = shl <16 x i8> %a, %splat
+ ret <16 x i8> %shift
+}
+
+define <32 x i8> @splatvar_shift_v32i8(<32 x i8> %a, i8 %b) {
+; SSE2-LABEL: 'splatvar_shift_v32i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = shl <32 x i8> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v32i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = shl <32 x i8> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v32i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = shl <32 x i8> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v32i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <32 x i8> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v32i8'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <32 x i8> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v32i8'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <32 x i8> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX512-LABEL: 'splatvar_shift_v32i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <32 x i8> %a, %splat
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v32i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = shl <32 x i8> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+ %insert = insertelement <32 x i8> poison, i8 %b, i32 0
+ %splat = shufflevector <32 x i8> %insert, <32 x i8> undef, <32 x i32> zeroinitializer
+ %shift = shl <32 x i8> %a, %splat
+ ret <32 x i8> %shift
+}
+
+define <64 x i8> @splatvar_shift_v64i8(<64 x i8> %a, i8 %b) {
+; SSE2-LABEL: 'splatvar_shift_v64i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; SSE2-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %shift = shl <64 x i8> %a, %splat
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; SSE42-LABEL: 'splatvar_shift_v64i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; SSE42-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %shift = shl <64 x i8> %a, %splat
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX1-LABEL: 'splatvar_shift_v64i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = shl <64 x i8> %a, %splat
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX2-LABEL: 'splatvar_shift_v64i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = shl <64 x i8> %a, %splat
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; XOPAVX1-LABEL: 'splatvar_shift_v64i8'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <64 x i8> %a, %splat
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; XOPAVX2-LABEL: 'splatvar_shift_v64i8'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <64 x i8> %a, %splat
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512F-LABEL: 'splatvar_shift_v64i8'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = shl <64 x i8> %a, %splat
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BW-LABEL: 'splatvar_shift_v64i8'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <64 x i8> %a, %splat
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512VL-LABEL: 'splatvar_shift_v64i8'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = shl <64 x i8> %a, %splat
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BWVL-LABEL: 'splatvar_shift_v64i8'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <64 x i8> %a, %splat
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; BTVER2-LABEL: 'splatvar_shift_v64i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = shl <64 x i8> %a, %splat
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+ %insert = insertelement <64 x i8> poison, i8 %b, i32 0
+ %splat = shufflevector <64 x i8> %insert, <64 x i8> undef, <64 x i32> zeroinitializer
+ %shift = shl <64 x i8> %a, %splat
+ ret <64 x i8> %shift
+}
+
+;
+; Constant Shifts
+;
+
+define <2 x i64> @constant_shift_v2i64(<2 x i64> %a) {
+; SSE-LABEL: 'constant_shift_v2i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <2 x i64> %a, <i64 1, i64 7>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX1-LABEL: 'constant_shift_v2i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <2 x i64> %a, <i64 1, i64 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX2-LABEL: 'constant_shift_v2i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <2 x i64> %a, <i64 1, i64 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; XOP-LABEL: 'constant_shift_v2i64'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <2 x i64> %a, <i64 1, i64 7>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; AVX512-LABEL: 'constant_shift_v2i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <2 x i64> %a, <i64 1, i64 7>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v2i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <2 x i64> %a, <i64 1, i64 7>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+ %shift = shl <2 x i64> %a, <i64 1, i64 7>
+ ret <2 x i64> %shift
+}
+
+define <4 x i64> @constant_shift_v4i64(<4 x i64> %a) {
+; SSE-LABEL: 'constant_shift_v4i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX1-LABEL: 'constant_shift_v4i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = shl <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX2-LABEL: 'constant_shift_v4i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOPAVX1-LABEL: 'constant_shift_v4i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOPAVX2-LABEL: 'constant_shift_v4i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX512-LABEL: 'constant_shift_v4i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v4i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shift = shl <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+ %shift = shl <4 x i64> %a, <i64 1, i64 7, i64 15, i64 31>
+ ret <4 x i64> %shift
+}
+
+define <8 x i64> @constant_shift_v8i64(<8 x i64> %a) {
+; SSE-LABEL: 'constant_shift_v8i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %shift = shl <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX1-LABEL: 'constant_shift_v8i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = shl <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX2-LABEL: 'constant_shift_v8i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOPAVX1-LABEL: 'constant_shift_v8i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOPAVX2-LABEL: 'constant_shift_v8i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX512-LABEL: 'constant_shift_v8i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v8i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shift = shl <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+ %shift = shl <8 x i64> %a, <i64 1, i64 7, i64 15, i64 31, i64 1, i64 7, i64 15, i64 31>
+ ret <8 x i64> %shift
+}
+
+define <4 x i32> @constant_shift_v4i32(<4 x i32> %a) {
+; SSE2-LABEL: 'constant_shift_v4i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = shl <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; SSE42-LABEL: 'constant_shift_v4i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX1-LABEL: 'constant_shift_v4i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX2-LABEL: 'constant_shift_v4i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; XOP-LABEL: 'constant_shift_v4i32'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; AVX512-LABEL: 'constant_shift_v4i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v4i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+ %shift = shl <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
+ ret <4 x i32> %shift
+}
+
+define <8 x i32> @constant_shift_v8i32(<8 x i32> %a) {
+; SSE2-LABEL: 'constant_shift_v8i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = shl <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; SSE42-LABEL: 'constant_shift_v8i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX1-LABEL: 'constant_shift_v8i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX2-LABEL: 'constant_shift_v8i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX1-LABEL: 'constant_shift_v8i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX2-LABEL: 'constant_shift_v8i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX512-LABEL: 'constant_shift_v8i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v8i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+ %shift = shl <8 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+ ret <8 x i32> %shift
+}
+
+define <16 x i32> @constant_shift_v16i32(<16 x i32> %a) {
+; SSE2-LABEL: 'constant_shift_v16i32'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = shl <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; SSE42-LABEL: 'constant_shift_v16i32'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX1-LABEL: 'constant_shift_v16i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX2-LABEL: 'constant_shift_v16i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX1-LABEL: 'constant_shift_v16i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX2-LABEL: 'constant_shift_v16i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX512-LABEL: 'constant_shift_v16i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v16i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+ %shift = shl <16 x i32> %a, <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+ ret <16 x i32> %shift
+}
+
+define <8 x i16> @constant_shift_v8i16(<8 x i16> %a) {
+; CHECK-LABEL: 'constant_shift_v8i16'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+ %shift = shl <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+ ret <8 x i16> %shift
+}
+
+define <16 x i16> @constant_shift_v16i16(<16 x i16> %a) {
+; SSE-LABEL: 'constant_shift_v16i16'
+; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX1-LABEL: 'constant_shift_v16i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX2-LABEL: 'constant_shift_v16i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOPAVX1-LABEL: 'constant_shift_v16i16'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOPAVX2-LABEL: 'constant_shift_v16i16'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512-LABEL: 'constant_shift_v16i16'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v16i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+ %shift = shl <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+ ret <16 x i16> %shift
+}
+
+define <32 x i16> @constant_shift_v32i16(<32 x i16> %a) {
+; SSE-LABEL: 'constant_shift_v32i16'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX1-LABEL: 'constant_shift_v32i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX2-LABEL: 'constant_shift_v32i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOPAVX1-LABEL: 'constant_shift_v32i16'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOPAVX2-LABEL: 'constant_shift_v32i16'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512F-LABEL: 'constant_shift_v32i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BW-LABEL: 'constant_shift_v32i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512VL-LABEL: 'constant_shift_v32i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'constant_shift_v32i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v32i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+ %shift = shl <32 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
+ ret <32 x i16> %shift
+}
+
+define <16 x i8> @constant_shift_v16i8(<16 x i8> %a) {
+; SSE2-LABEL: 'constant_shift_v16i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %shift = shl <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; SSE42-LABEL: 'constant_shift_v16i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX-LABEL: 'constant_shift_v16i8'
+; AVX-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; XOP-LABEL: 'constant_shift_v16i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX512-LABEL: 'constant_shift_v16i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+ %shift = shl <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+ ret <16 x i8> %shift
+}
+
+define <32 x i8> @constant_shift_v32i8(<32 x i8> %a) {
+; SSE2-LABEL: 'constant_shift_v32i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %shift = shl <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; SSE42-LABEL: 'constant_shift_v32i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = shl <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX1-LABEL: 'constant_shift_v32i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = shl <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX2-LABEL: 'constant_shift_v32i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; XOP-LABEL: 'constant_shift_v32i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX512-LABEL: 'constant_shift_v32i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v32i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shift = shl <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+ %shift = shl <32 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+ ret <32 x i8> %shift
+}
+
+define <64 x i8> @constant_shift_v64i8(<64 x i8> %a) {
+; SSE2-LABEL: 'constant_shift_v64i8'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %shift = shl <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; SSE42-LABEL: 'constant_shift_v64i8'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %shift = shl <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX1-LABEL: 'constant_shift_v64i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = shl <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX2-LABEL: 'constant_shift_v64i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = shl <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; XOP-LABEL: 'constant_shift_v64i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512F-LABEL: 'constant_shift_v64i8'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = shl <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BW-LABEL: 'constant_shift_v64i8'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512VL-LABEL: 'constant_shift_v64i8'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %shift = shl <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BWVL-LABEL: 'constant_shift_v64i8'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %shift = shl <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; BTVER2-LABEL: 'constant_shift_v64i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %shift = shl <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+ %shift = shl <64 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>
+ ret <64 x i8> %shift
+}
+
+;
+; Uniform Constant Shifts
+;
+
+define <2 x i64> @splatconstant_shift_v2i64(<2 x i64> %a) {
+; CHECK-LABEL: 'splatconstant_shift_v2i64'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <2 x i64> %a, <i64 7, i64 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shift
+;
+ %shift = shl <2 x i64> %a, <i64 7, i64 7>
+ ret <2 x i64> %shift
+}
+
+define <4 x i64> @splatconstant_shift_v4i64(<4 x i64> %a) {
+; SSE-LABEL: 'splatconstant_shift_v4i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v4i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v4i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v4i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v4i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v4i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v4i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shift
+;
+ %shift = shl <4 x i64> %a, <i64 7, i64 7, i64 7, i64 7>
+ ret <4 x i64> %shift
+}
+
+define <8 x i64> @splatconstant_shift_v8i64(<8 x i64> %a) {
+; SSE-LABEL: 'splatconstant_shift_v8i64'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v8i64'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v8i64'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v8i64'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v8i64'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v8i64'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v8i64'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shift
+;
+ %shift = shl <8 x i64> %a, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+ ret <8 x i64> %shift
+}
+
+define <4 x i32> @splatconstant_shift_v4i32(<4 x i32> %a) {
+; CHECK-LABEL: 'splatconstant_shift_v4i32'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <4 x i32> %a, <i32 5, i32 5, i32 5, i32 5>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shift
+;
+ %shift = shl <4 x i32> %a, <i32 5, i32 5, i32 5, i32 5>
+ ret <4 x i32> %shift
+}
+
+define <8 x i32> @splatconstant_shift_v8i32(<8 x i32> %a) {
+; SSE-LABEL: 'splatconstant_shift_v8i32'
+; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v8i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v8i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v8i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v8i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v8i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v8i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shift
+;
+ %shift = shl <8 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+ ret <8 x i32> %shift
+}
+
+define <16 x i32> @splatconstant_shift_v16i32(<16 x i32> %a) {
+; SSE-LABEL: 'splatconstant_shift_v16i32'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v16i32'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v16i32'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v16i32'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v16i32'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v16i32'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v16i32'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shift
+;
+ %shift = shl <16 x i32> %a, <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
+ ret <16 x i32> %shift
+}
+
+define <8 x i16> @splatconstant_shift_v8i16(<8 x i16> %a) {
+; CHECK-LABEL: 'splatconstant_shift_v8i16'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <8 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shift
+;
+ %shift = shl <8 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+ ret <8 x i16> %shift
+}
+
+define <16 x i16> @splatconstant_shift_v16i16(<16 x i16> %a) {
+; SSE-LABEL: 'splatconstant_shift_v16i16'
+; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v16i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v16i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v16i16'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v16i16'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v16i16'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v16i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shift
+;
+ %shift = shl <16 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+ ret <16 x i16> %shift
+}
+
+define <32 x i16> @splatconstant_shift_v32i16(<32 x i16> %a) {
+; SSE-LABEL: 'splatconstant_shift_v32i16'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v32i16'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v32i16'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v32i16'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v32i16'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512F-LABEL: 'splatconstant_shift_v32i16'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BW-LABEL: 'splatconstant_shift_v32i16'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512VL-LABEL: 'splatconstant_shift_v32i16'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; AVX512BWVL-LABEL: 'splatconstant_shift_v32i16'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v32i16'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shift
+;
+ %shift = shl <32 x i16> %a, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
+ ret <32 x i16> %shift
+}
+
+define <16 x i8> @splatconstant_shift_v16i8(<16 x i8> %a) {
+; SSE-LABEL: 'splatconstant_shift_v16i8'
+; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <16 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX-LABEL: 'splatconstant_shift_v16i8'
+; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <16 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; XOP-LABEL: 'splatconstant_shift_v16i8'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shift = shl <16 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v16i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <16 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %shift
+;
+ %shift = shl <16 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+ ret <16 x i8> %shift
+}
+
+define <32 x i8> @splatconstant_shift_v32i8(<32 x i8> %a) {
+; SSE-LABEL: 'splatconstant_shift_v32i8'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v32i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = shl <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v32i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v32i8'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v32i8'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; AVX512-LABEL: 'splatconstant_shift_v32i8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v32i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shift = shl <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i8> %shift
+;
+ %shift = shl <32 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+ ret <32 x i8> %shift
+}
+
+define <64 x i8> @splatconstant_shift_v64i8(<64 x i8> %a) {
+; SSE-LABEL: 'splatconstant_shift_v64i8'
+; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX1-LABEL: 'splatconstant_shift_v64i8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = shl <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX2-LABEL: 'splatconstant_shift_v64i8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; XOPAVX1-LABEL: 'splatconstant_shift_v64i8'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shift = shl <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; XOPAVX2-LABEL: 'splatconstant_shift_v64i8'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512F-LABEL: 'splatconstant_shift_v64i8'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BW-LABEL: 'splatconstant_shift_v64i8'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512VL-LABEL: 'splatconstant_shift_v64i8'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shift = shl <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; AVX512BWVL-LABEL: 'splatconstant_shift_v64i8'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shift = shl <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+; BTVER2-LABEL: 'splatconstant_shift_v64i8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shift = shl <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <64 x i8> %shift
+;
+ %shift = shl <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
+ ret <64 x i8> %shift
+}
+
+;
+; Special Cases
+;
+
+; We always emit a single pmullw in the case of v8i16 vector shifts by
+; non-uniform constant.
+
+define <8 x i16> @test1(<8 x i16> %a) {
+; CHECK-LABEL: 'test1'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <8 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shl
+;
+ %shl = shl <8 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+ ret <8 x i16> %shl
+}
+
+define <8 x i16> @test2(<8 x i16> %a) {
+; CHECK-LABEL: 'test2'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <8 x i16> %a, <i16 0, i16 undef, i16 0, i16 0, i16 1, i16 undef, i16 -1, i16 1>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %shl
+;
+ %shl = shl <8 x i16> %a, <i16 0, i16 undef, i16 0, i16 0, i16 1, i16 undef, i16 -1, i16 1>
+ ret <8 x i16> %shl
+}
+
+; With SSE4.1, v4i32 shifts can be lowered into a single pmulld instruction.
+; Make sure that the estimated cost is always 2 except for the case where
+; we only have SSE2 support. With SSE2, we are forced to special lower the
+; v4i32 mul as a 2x shuffle, 2x pmuludq, 2x shuffle.
+
+define <4 x i32> @test3(<4 x i32> %a) {
+; SSE2-LABEL: 'test3'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shl = shl <4 x i32> %a, <i32 1, i32 -1, i32 2, i32 -3>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shl
+;
+; SSE42-LABEL: 'test3'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shl = shl <4 x i32> %a, <i32 1, i32 -1, i32 2, i32 -3>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shl
+;
+; AVX1-LABEL: 'test3'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shl = shl <4 x i32> %a, <i32 1, i32 -1, i32 2, i32 -3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shl
+;
+; AVX2-LABEL: 'test3'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <4 x i32> %a, <i32 1, i32 -1, i32 2, i32 -3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shl
+;
+; XOP-LABEL: 'test3'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <4 x i32> %a, <i32 1, i32 -1, i32 2, i32 -3>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shl
+;
+; AVX512-LABEL: 'test3'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <4 x i32> %a, <i32 1, i32 -1, i32 2, i32 -3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shl
+;
+; BTVER2-LABEL: 'test3'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shl = shl <4 x i32> %a, <i32 1, i32 -1, i32 2, i32 -3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shl
+;
+ %shl = shl <4 x i32> %a, <i32 1, i32 -1, i32 2, i32 -3>
+ ret <4 x i32> %shl
+}
+
+define <4 x i32> @test4(<4 x i32> %a) {
+; SSE2-LABEL: 'test4'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %shl = shl <4 x i32> %a, <i32 0, i32 0, i32 1, i32 1>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shl
+;
+; SSE42-LABEL: 'test4'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shl = shl <4 x i32> %a, <i32 0, i32 0, i32 1, i32 1>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shl
+;
+; AVX1-LABEL: 'test4'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shl = shl <4 x i32> %a, <i32 0, i32 0, i32 1, i32 1>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shl
+;
+; AVX2-LABEL: 'test4'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <4 x i32> %a, <i32 0, i32 0, i32 1, i32 1>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shl
+;
+; XOP-LABEL: 'test4'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <4 x i32> %a, <i32 0, i32 0, i32 1, i32 1>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shl
+;
+; AVX512-LABEL: 'test4'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <4 x i32> %a, <i32 0, i32 0, i32 1, i32 1>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shl
+;
+; BTVER2-LABEL: 'test4'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shl = shl <4 x i32> %a, <i32 0, i32 0, i32 1, i32 1>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %shl
+;
+ %shl = shl <4 x i32> %a, <i32 0, i32 0, i32 1, i32 1>
+ ret <4 x i32> %shl
+}
+
+; On AVX2 we are able to lower the following shift into a single
+; vpsllvq. Therefore, the expected cost is only 1.
+; In all other cases, this shift is scalarized as the target does not support
+; vpsllv instructions.
+
+define <2 x i64> @test5(<2 x i64> %a) {
+; SSE-LABEL: 'test5'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shl = shl <2 x i64> %a, <i64 2, i64 3>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shl
+;
+; AVX1-LABEL: 'test5'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shl = shl <2 x i64> %a, <i64 2, i64 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shl
+;
+; AVX2-LABEL: 'test5'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <2 x i64> %a, <i64 2, i64 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shl
+;
+; XOP-LABEL: 'test5'
+; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <2 x i64> %a, <i64 2, i64 3>
+; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shl
+;
+; AVX512-LABEL: 'test5'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <2 x i64> %a, <i64 2, i64 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shl
+;
+; BTVER2-LABEL: 'test5'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shl = shl <2 x i64> %a, <i64 2, i64 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %shl
+;
+ %shl = shl <2 x i64> %a, <i64 2, i64 3>
+ ret <2 x i64> %shl
+}
+
+; v16i16 and v8i32 shift left by non-uniform constant are lowered into
+; vector multiply instructions. With AVX (but not AVX2), the vector multiply
+; is lowered into a sequence of: 1 extract + 2 vpmullw + 1 insert.
+;
+; With AVX2, instruction vpmullw works with 256bit quantities and
+; therefore there is no need to split the resulting vector multiply into
+; a sequence of two multiply.
+;
+; With SSE2 and SSE4.1, the vector shift cost for 'test6' is twice
+; the cost computed in the case of 'test1'. That is because the backend
+; simply emits 2 pmullw with no extract/insert.
+
+define <16 x i16> @test6(<16 x i16> %a) {
+; SSE-LABEL: 'test6'
+; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shl = shl <16 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shl
+;
+; AVX1-LABEL: 'test6'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shl = shl <16 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shl
+;
+; AVX2-LABEL: 'test6'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <16 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shl
+;
+; XOPAVX1-LABEL: 'test6'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shl = shl <16 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shl
+;
+; XOPAVX2-LABEL: 'test6'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <16 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shl
+;
+; AVX512-LABEL: 'test6'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <16 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shl
+;
+; BTVER2-LABEL: 'test6'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shl = shl <16 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i16> %shl
+;
+ %shl = shl <16 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+ ret <16 x i16> %shl
+}
+
+; With SSE2 and SSE4.1, the vector shift cost for 'test7' is twice
+; the cost computed in the case of 'test3'. That is because the multiply
+; is type-legalized into two 4i32 vector multiply.
+
+define <8 x i32> @test7(<8 x i32> %a) {
+; SSE2-LABEL: 'test7'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %shl = shl <8 x i32> %a, <i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shl
+;
+; SSE42-LABEL: 'test7'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shl = shl <8 x i32> %a, <i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shl
+;
+; AVX1-LABEL: 'test7'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shl = shl <8 x i32> %a, <i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shl
+;
+; AVX2-LABEL: 'test7'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <8 x i32> %a, <i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shl
+;
+; XOPAVX1-LABEL: 'test7'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shl = shl <8 x i32> %a, <i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shl
+;
+; XOPAVX2-LABEL: 'test7'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <8 x i32> %a, <i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shl
+;
+; AVX512-LABEL: 'test7'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <8 x i32> %a, <i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shl
+;
+; BTVER2-LABEL: 'test7'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shl = shl <8 x i32> %a, <i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %shl
+;
+ %shl = shl <8 x i32> %a, <i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3>
+ ret <8 x i32> %shl
+}
+
+; On AVX2 we are able to lower the following shift into a single
+; vpsllvq. Therefore, the expected cost is only 1.
+; In all other cases, this shift is scalarized as the target does not support
+; vpsllv instructions.
+
+define <4 x i64> @test8(<4 x i64> %a) {
+; SSE-LABEL: 'test8'
+; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shl = shl <4 x i64> %a, <i64 1, i64 2, i64 3, i64 4>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shl
+;
+; AVX1-LABEL: 'test8'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shl = shl <4 x i64> %a, <i64 1, i64 2, i64 3, i64 4>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shl
+;
+; AVX2-LABEL: 'test8'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <4 x i64> %a, <i64 1, i64 2, i64 3, i64 4>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shl
+;
+; XOPAVX1-LABEL: 'test8'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shl = shl <4 x i64> %a, <i64 1, i64 2, i64 3, i64 4>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shl
+;
+; XOPAVX2-LABEL: 'test8'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <4 x i64> %a, <i64 1, i64 2, i64 3, i64 4>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shl
+;
+; AVX512-LABEL: 'test8'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <4 x i64> %a, <i64 1, i64 2, i64 3, i64 4>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shl
+;
+; BTVER2-LABEL: 'test8'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %shl = shl <4 x i64> %a, <i64 1, i64 2, i64 3, i64 4>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %shl
+;
+ %shl = shl <4 x i64> %a, <i64 1, i64 2, i64 3, i64 4>
+ ret <4 x i64> %shl
+}
+
+; Same as 'test6', with the
diff erence that the cost is double.
+
+define <32 x i16> @test9(<32 x i16> %a) {
+; SSE-LABEL: 'test9'
+; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %shl = shl <32 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shl
+;
+; AVX1-LABEL: 'test9'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shl = shl <32 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shl
+;
+; AVX2-LABEL: 'test9'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shl = shl <32 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shl
+;
+; XOPAVX1-LABEL: 'test9'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shl = shl <32 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shl
+;
+; XOPAVX2-LABEL: 'test9'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shl = shl <32 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shl
+;
+; AVX512F-LABEL: 'test9'
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shl = shl <32 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shl
+;
+; AVX512BW-LABEL: 'test9'
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <32 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shl
+;
+; AVX512VL-LABEL: 'test9'
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shl = shl <32 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+; AVX512VL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shl
+;
+; AVX512BWVL-LABEL: 'test9'
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <32 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+; AVX512BWVL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shl
+;
+; BTVER2-LABEL: 'test9'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shl = shl <32 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <32 x i16> %shl
+;
+ %shl = shl <32 x i16> %a, <i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11, i16 1, i16 1, i16 2, i16 3, i16 7, i16 0, i16 9, i16 11>
+ ret <32 x i16> %shl
+}
+
+; Same as 'test7', except that now the cost is double.
+
+define <16 x i32> @test10(<16 x i32> %a) {
+; SSE2-LABEL: 'test10'
+; SSE2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %shl = shl <16 x i32> %a, <i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3>
+; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shl
+;
+; SSE42-LABEL: 'test10'
+; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shl = shl <16 x i32> %a, <i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3>
+; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shl
+;
+; AVX1-LABEL: 'test10'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shl = shl <16 x i32> %a, <i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shl
+;
+; AVX2-LABEL: 'test10'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shl = shl <16 x i32> %a, <i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shl
+;
+; XOPAVX1-LABEL: 'test10'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shl = shl <16 x i32> %a, <i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shl
+;
+; XOPAVX2-LABEL: 'test10'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shl = shl <16 x i32> %a, <i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shl
+;
+; AVX512-LABEL: 'test10'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <16 x i32> %a, <i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shl
+;
+; BTVER2-LABEL: 'test10'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shl = shl <16 x i32> %a, <i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i32> %shl
+;
+ %shl = shl <16 x i32> %a, <i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 2, i32 3>
+ ret <16 x i32> %shl
+}
+
+; On AVX2 we are able to lower the following shift into a sequence of
+; two vpsllvq instructions. Therefore, the expected cost is only 2.
+; In all other cases, this shift is scalarized as we don't have vpsllv
+; instructions.
+
+define <8 x i64> @test11(<8 x i64> %a) {
+; SSE-LABEL: 'test11'
+; SSE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %shl = shl <8 x i64> %a, <i64 1, i64 1, i64 2, i64 3, i64 1, i64 1, i64 2, i64 3>
+; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shl
+;
+; AVX1-LABEL: 'test11'
+; AVX1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shl = shl <8 x i64> %a, <i64 1, i64 1, i64 2, i64 3, i64 1, i64 1, i64 2, i64 3>
+; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shl
+;
+; AVX2-LABEL: 'test11'
+; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shl = shl <8 x i64> %a, <i64 1, i64 1, i64 2, i64 3, i64 1, i64 1, i64 2, i64 3>
+; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shl
+;
+; XOPAVX1-LABEL: 'test11'
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %shl = shl <8 x i64> %a, <i64 1, i64 1, i64 2, i64 3, i64 1, i64 1, i64 2, i64 3>
+; XOPAVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shl
+;
+; XOPAVX2-LABEL: 'test11'
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %shl = shl <8 x i64> %a, <i64 1, i64 1, i64 2, i64 3, i64 1, i64 1, i64 2, i64 3>
+; XOPAVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shl
+;
+; AVX512-LABEL: 'test11'
+; AVX512-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %shl = shl <8 x i64> %a, <i64 1, i64 1, i64 2, i64 3, i64 1, i64 1, i64 2, i64 3>
+; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shl
+;
+; BTVER2-LABEL: 'test11'
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %shl = shl <8 x i64> %a, <i64 1, i64 1, i64 2, i64 3, i64 1, i64 1, i64 2, i64 3>
+; BTVER2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %shl
+;
+ %shl = shl <8 x i64> %a, <i64 1, i64 1, i64 2, i64 3, i64 1, i64 1, i64 2, i64 3>
+ ret <8 x i64> %shl
+}
diff --git a/llvm/test/Analysis/DemandedBits/vectors-inseltpoison.ll b/llvm/test/Analysis/DemandedBits/vectors-inseltpoison.ll
new file mode 100644
index 000000000000..ce735a289c6c
--- /dev/null
+++ b/llvm/test/Analysis/DemandedBits/vectors-inseltpoison.ll
@@ -0,0 +1,136 @@
+; RUN: opt -S -demanded-bits -analyze -enable-new-pm=0 < %s | FileCheck %s
+; RUN: opt -S -disable-output -passes="print<demanded-bits>" < %s 2>&1 | FileCheck %s
+
+; CHECK-DAG: DemandedBits: 0xff00 for %x = or <2 x i32> %a, zeroinitializer
+; CHECK-DAG: DemandedBits: 0xff00 for %y = or <2 x i32> %b, zeroinitializer
+; CHECK-DAG: DemandedBits: 0xff00 for %z = or <2 x i32> %x, %y
+; CHECK-DAG: DemandedBits: 0xff for %u = lshr <2 x i32> %z, <i32 8, i32 8>
+; CHECK-DAG: DemandedBits: 0xff for %r = trunc <2 x i32> %u to <2 x i8>
+define <2 x i8> @test_basic(<2 x i32> %a, <2 x i32> %b) {
+ %x = or <2 x i32> %a, zeroinitializer
+ %y = or <2 x i32> %b, zeroinitializer
+ %z = or <2 x i32> %x, %y
+ %u = lshr <2 x i32> %z, <i32 8, i32 8>
+ %r = trunc <2 x i32> %u to <2 x i8>
+ ret <2 x i8> %r
+}
+
+; Vector-specific instructions
+
+; CHECK-DAG: DemandedBits: 0xff for %x = or <2 x i32> %a, zeroinitializer
+; CHECK-DAG: DemandedBits: 0xf0 for %z = extractelement <2 x i32> %x, i32 1
+; CHECK-DAG: DemandedBits: 0xf for %y = extractelement <2 x i32> %x, i32 0
+; CHECK-DAG: DemandedBits: 0xffffffff for %u = and i32 %y, 15
+; CHECK-DAG: DemandedBits: 0xffffffff for %v = and i32 %z, 240
+; CHECK-DAG: DemandedBits: 0xffffffff for %r = or i32 %u, %v
+define i32 @test_extractelement(<2 x i32> %a) {
+ %x = or <2 x i32> %a, zeroinitializer
+ %y = extractelement <2 x i32> %x, i32 0
+ %z = extractelement <2 x i32> %x, i32 1
+ %u = and i32 %y, 15
+ %v = and i32 %z, 240
+ %r = or i32 %u, %v
+ ret i32 %r
+}
+
+; CHECK-DAG: DemandedBits: 0xff for %x = or i32 %a, 0
+; CHECK-DAG: DemandedBits: 0xff for %y = or i32 %b, 0
+; CHECK-DAG: DemandedBits: 0xff for %z = insertelement <2 x i32> poison, i32 %x, i32 0
+; CHECK-DAG: DemandedBits: 0xff for %u = insertelement <2 x i32> %z, i32 %y, i32 1
+; CHECK-DAG: DemandedBits: 0xffffffff for %r = and <2 x i32> %u, <i32 255, i32 127>
+define <2 x i32> @test_insertelement(i32 %a, i32 %b) {
+ %x = or i32 %a, 0
+ %y = or i32 %b, 0
+ %z = insertelement <2 x i32> poison, i32 %x, i32 0
+ %u = insertelement <2 x i32> %z, i32 %y, i32 1
+ %r = and <2 x i32> %u, <i32 255, i32 127>
+ ret <2 x i32> %r
+}
+
+; CHECK-DAG: DemandedBits: 0xff for %x = or <2 x i32> %a, zeroinitializer
+; CHECK-DAG: DemandedBits: 0xff for %y = or <2 x i32> %b, zeroinitializer
+; CHECK-DAG: DemandedBits: 0xff for %z = shufflevector <2 x i32> %x, <2 x i32> %y, <3 x i32> <i32 0, i32 3, i32 1>
+; CHECK-DAG: DemandedBits: 0xffffffff for %r = and <3 x i32> %z, <i32 255, i32 127, i32 0>
+define <3 x i32> @test_shufflevector(<2 x i32> %a, <2 x i32> %b) {
+ %x = or <2 x i32> %a, zeroinitializer
+ %y = or <2 x i32> %b, zeroinitializer
+ %z = shufflevector <2 x i32> %x, <2 x i32> %y, <3 x i32> <i32 0, i32 3, i32 1>
+ %r = and <3 x i32> %z, <i32 255, i32 127, i32 0>
+ ret <3 x i32> %r
+}
+
+; Shifts with splat shift amounts
+
+; CHECK-DAG: DemandedBits: 0xf for %x = or <2 x i32> %a, zeroinitializer
+; CHECK-DAG: DemandedBits: 0xf0 for %y = shl <2 x i32> %x, <i32 4, i32 4>
+; CHECK-DAG: DemandedBits: 0xffffffff for %r = and <2 x i32> %y, <i32 240, i32 240>
+define <2 x i32> @test_shl(<2 x i32> %a) {
+ %x = or <2 x i32> %a, zeroinitializer
+ %y = shl <2 x i32> %x, <i32 4, i32 4>
+ %r = and <2 x i32> %y, <i32 240, i32 240>
+ ret <2 x i32> %r
+}
+
+; CHECK-DAG: DemandedBits: 0xf00 for %x = or <2 x i32> %a, zeroinitializer
+; CHECK-DAG: DemandedBits: 0xf0 for %y = ashr <2 x i32> %x, <i32 4, i32 4>
+; CHECK-DAG: DemandedBits: 0xffffffff for %r = and <2 x i32> %y, <i32 240, i32 240>
+define <2 x i32> @test_ashr(<2 x i32> %a) {
+ %x = or <2 x i32> %a, zeroinitializer
+ %y = ashr <2 x i32> %x, <i32 4, i32 4>
+ %r = and <2 x i32> %y, <i32 240, i32 240>
+ ret <2 x i32> %r
+}
+
+; CHECK-DAG: DemandedBits: 0xf00 for %x = or <2 x i32> %a, zeroinitializer
+; CHECK-DAG: DemandedBits: 0xf0 for %y = lshr <2 x i32> %x, <i32 4, i32 4>
+; CHECK-DAG: DemandedBits: 0xffffffff for %r = and <2 x i32> %y, <i32 240, i32 240>
+define <2 x i32> @test_lshr(<2 x i32> %a) {
+ %x = or <2 x i32> %a, zeroinitializer
+ %y = lshr <2 x i32> %x, <i32 4, i32 4>
+ %r = and <2 x i32> %y, <i32 240, i32 240>
+ ret <2 x i32> %r
+}
+
+declare <2 x i32> @llvm.fshl.i32(<2 x i32>, <2 x i32>, <2 x i32>)
+declare <2 x i32> @llvm.fshr.i32(<2 x i32>, <2 x i32>, <2 x i32>)
+
+; CHECK-DAG: DemandedBits: 0xf for %x = or <2 x i32> %a, zeroinitializer
+; CHECK-DAG: DemandedBits: 0xf0000000 for %y = or <2 x i32> %b, zeroinitializer
+; CHECK-DAG: DemandedBits: 0xff for %z = call <2 x i32> @llvm.fshl.v2i32(<2 x i32> %x, <2 x i32> %y, <2 x i32> <i32 4, i32 4>)
+; CHECK-DAG: DemandedBits: 0xffffffff for %r = and <2 x i32> %z, <i32 255, i32 255>
+define <2 x i32> @test_fshl(<2 x i32> %a, <2 x i32> %b) {
+ %x = or <2 x i32> %a, zeroinitializer
+ %y = or <2 x i32> %b, zeroinitializer
+ %z = call <2 x i32> @llvm.fshl.i32(<2 x i32> %x, <2 x i32> %y, <2 x i32> <i32 4, i32 4>)
+ %r = and <2 x i32> %z, <i32 255, i32 255>
+ ret <2 x i32> %r
+}
+
+; CHECK-DAG: DemandedBits: 0xf for %x = or <2 x i32> %a, zeroinitializer
+; CHECK-DAG: DemandedBits: 0xf0000000 for %y = or <2 x i32> %b, zeroinitializer
+; CHECK-DAG: DemandedBits: 0xff for %z = call <2 x i32> @llvm.fshr.v2i32(<2 x i32> %x, <2 x i32> %y, <2 x i32> <i32 28, i32 28>)
+; CHECK-DAG: DemandedBits: 0xffffffff for %r = and <2 x i32> %z, <i32 255, i32 255>
+define <2 x i32> @test_fshr(<2 x i32> %a, <2 x i32> %b) {
+ %x = or <2 x i32> %a, zeroinitializer
+ %y = or <2 x i32> %b, zeroinitializer
+ %z = call <2 x i32> @llvm.fshr.i32(<2 x i32> %x, <2 x i32> %y, <2 x i32> <i32 28, i32 28>)
+ %r = and <2 x i32> %z, <i32 255, i32 255>
+ ret <2 x i32> %r
+}
+
+; FP / Int conversion. These have
diff erent input / output types.
+
+; CHECK-DAG: DemandedBits: 0xffffffff for %x = or <2 x i32> %a, zeroinitializer
+define <2 x float> @test_uitofp(<2 x i32> %a) {
+ %x = or <2 x i32> %a, zeroinitializer
+ %r = uitofp <2 x i32> %x to <2 x float>
+ ret <2 x float> %r
+}
+
+; CHECK-DAG: DemandedBits: 0xffffffff for %y = fptoui <2 x float> %x to <2 x i32>
+define <2 x i32> @test_fptoui(<2 x float> %a) {
+ %x = fadd <2 x float> %a, <float 1.0, float 1.0>
+ %y = fptoui <2 x float> %x to <2 x i32>
+ %r = and <2 x i32> %y, <i32 255, i32 255>
+ ret <2 x i32> %y
+}
diff --git a/llvm/test/DebugInfo/X86/stack-value-piece-inseltpoison.ll b/llvm/test/DebugInfo/X86/stack-value-piece-inseltpoison.ll
new file mode 100644
index 000000000000..69362f74b34c
--- /dev/null
+++ b/llvm/test/DebugInfo/X86/stack-value-piece-inseltpoison.ll
@@ -0,0 +1,114 @@
+; RUN: llc %s -filetype=obj -o - | llvm-dwarfdump -debug-info -debug-loc - | FileCheck %s
+; Test that DW_OP_piece is emitted for constants.
+;
+; // Generated from:
+; typedef struct { int a, b; } I;
+; I i(int i) {
+; I r = {i, 0};
+; return r;
+; }
+;
+; typedef struct { float a, b; } F;
+; F f(float f) {
+; F r = {f, 0};
+; return r;
+; }
+
+; CHECK: .debug_info contents:
+; CHECK: DW_TAG_subprogram
+; CHECK: DW_AT_name ("i")
+; CHECK: DW_TAG_variable
+; CHECK-NEXT: DW_AT_location ([[I:0x[0-9a-f]+]]
+; CHECK-NEXT: [{{.*}}, {{.*}}): DW_OP_reg5 RDI, DW_OP_piece 0x4, DW_OP_lit0, DW_OP_stack_value, DW_OP_piece 0x4)
+; CHECK-NEXT: DW_AT_name ("r")
+;
+; CHECK: DW_TAG_subprogram
+; CHECK: DW_AT_name ("f")
+; CHECK: DW_TAG_variable
+; CHECK-NEXT: DW_AT_location ([[F:0x[0-9a-f]+]]
+; CHECK-NEXT: [{{.*}}, {{.*}}): DW_OP_reg17 XMM0, DW_OP_piece 0x4, {{(DW_OP_lit0, DW_OP_stack_value, DW_OP_piece 0x4|DW_OP_implicit_value 0x4 0x00 0x00 0x00 0x00)}}
+; CHECK-NEXT: [{{.*}}, {{.*}}): DW_OP_piece 0x4, {{(DW_OP_lit0, DW_OP_stack_value, DW_OP_piece 0x4|DW_OP_implicit_value 0x4 0x00 0x00 0x00 0x00)}})
+; CHECK-NEXT: DW_AT_name ("r")
+;
+; CHECK: .debug_loc contents:
+; CHECK: [[I]]:
+; CHECK-NEXT: ({{.*}}, {{.*}}): DW_OP_reg5 RDI, DW_OP_piece 0x4, DW_OP_lit0, DW_OP_stack_value, DW_OP_piece 0x4
+; CHECK: [[F]]:
+; CHECK-NEXT: ({{.*}}, {{.*}}): DW_OP_reg17 XMM0, DW_OP_piece 0x4, {{DW_OP_lit0, DW_OP_stack_value, DW_OP_piece 0x4|DW_OP_implicit_value 0x4 0x00 0x00 0x00 0x00}}
+
+source_filename = "stack-value-piece.c"
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.12.0"
+
+%struct.I = type { i32, i32 }
+%struct.F = type { float, float }
+
+; Function Attrs: nounwind readnone ssp uwtable
+define i64 @i(i32 %i) local_unnamed_addr #0 !dbg !7 {
+entry:
+ tail call void @llvm.dbg.value(metadata i32 %i, metadata !18, metadata !22), !dbg !21
+ tail call void @llvm.dbg.value(metadata i32 0, metadata !18, metadata !23), !dbg !21
+ %retval.sroa.0.0.insert.ext = zext i32 %i to i64, !dbg !24
+ ret i64 %retval.sroa.0.0.insert.ext, !dbg !24
+}
+
+; Function Attrs: nounwind readnone
+declare void @llvm.dbg.declare(metadata, metadata, metadata) #1
+
+; Function Attrs: nounwind readnone ssp uwtable
+define <2 x float> @f(float %f) local_unnamed_addr #0 !dbg !25 {
+entry:
+ tail call void @llvm.dbg.value(metadata float %f, metadata !36, metadata !22), !dbg !38
+ tail call void @llvm.dbg.value(metadata float 0.000000e+00, metadata !36, metadata !23), !dbg !38
+ %retval.sroa.0.0.vec.insert = insertelement <2 x float> poison, float %f, i32 0, !dbg !39
+ %retval.sroa.0.4.vec.insert = insertelement <2 x float> %retval.sroa.0.0.vec.insert, float 0.000000e+00, i32 1, !dbg !39
+ ret <2 x float> %retval.sroa.0.4.vec.insert, !dbg !40
+}
+
+; Function Attrs: nounwind readnone
+declare void @llvm.dbg.value(metadata, metadata, metadata) #1
+
+attributes #0 = { nounwind readnone ssp uwtable }
+attributes #1 = { nounwind readnone }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5}
+!llvm.ident = !{!6}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang version 4.0.0 (trunk 285655) (llvm/trunk 285654)", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !2)
+!1 = !DIFile(filename: "stack-value-piece.c", directory: "/")
+!2 = !{}
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{i32 1, !"PIC Level", i32 2}
+!6 = !{!"clang version 4.0.0 (trunk 285655) (llvm/trunk 285654)"}
+!7 = distinct !DISubprogram(name: "i", scope: !1, file: !1, line: 2, type: !8, isLocal: false, isDefinition: true, scopeLine: 2, flags: DIFlagPrototyped, isOptimized: true, unit: !0)
+!8 = !DISubroutineType(types: !9)
+!9 = !{!10, !14}
+!10 = !DIDerivedType(tag: DW_TAG_typedef, name: "I", file: !1, line: 1, baseType: !11)
+!11 = distinct !DICompositeType(tag: DW_TAG_structure_type, file: !1, line: 1, size: 64, elements: !12)
+!12 = !{!13, !15}
+!13 = !DIDerivedType(tag: DW_TAG_member, name: "a", scope: !11, file: !1, line: 1, baseType: !14, size: 32)
+!14 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+!15 = !DIDerivedType(tag: DW_TAG_member, name: "b", scope: !11, file: !1, line: 1, baseType: !14, size: 32, offset: 32)
+!18 = !DILocalVariable(name: "r", scope: !7, file: !1, line: 3, type: !10)
+!19 = !DIExpression()
+!20 = !DILocation(line: 2, column: 9, scope: !7)
+!21 = !DILocation(line: 3, column: 5, scope: !7)
+!22 = !DIExpression(DW_OP_LLVM_fragment, 0, 32)
+!23 = !DIExpression(DW_OP_LLVM_fragment, 32, 32)
+!24 = !DILocation(line: 5, column: 1, scope: !7)
+!25 = distinct !DISubprogram(name: "f", scope: !1, file: !1, line: 8, type: !26, isLocal: false, isDefinition: true, scopeLine: 8, flags: DIFlagPrototyped, isOptimized: true, unit: !0)
+!26 = !DISubroutineType(types: !27)
+!27 = !{!28, !32}
+!28 = !DIDerivedType(tag: DW_TAG_typedef, name: "F", file: !1, line: 7, baseType: !29)
+!29 = distinct !DICompositeType(tag: DW_TAG_structure_type, file: !1, line: 7, size: 64, elements: !30)
+!30 = !{!31, !33}
+!31 = !DIDerivedType(tag: DW_TAG_member, name: "a", scope: !29, file: !1, line: 7, baseType: !32, size: 32)
+!32 = !DIBasicType(name: "float", size: 32, encoding: DW_ATE_float)
+!33 = !DIDerivedType(tag: DW_TAG_member, name: "b", scope: !29, file: !1, line: 7, baseType: !32, size: 32, offset: 32)
+!36 = !DILocalVariable(name: "r", scope: !25, file: !1, line: 9, type: !28)
+!37 = !DILocation(line: 8, column: 11, scope: !25)
+!38 = !DILocation(line: 9, column: 5, scope: !25)
+!39 = !DILocation(line: 10, column: 10, scope: !25)
+!40 = !DILocation(line: 11, column: 1, scope: !25)
diff --git a/llvm/test/Other/scalable-vectors-core-ir.ll b/llvm/test/Other/scalable-vectors-core-ir.ll
index 60cbab3cdff6..f04184a41766 100644
--- a/llvm/test/Other/scalable-vectors-core-ir.ll
+++ b/llvm/test/Other/scalable-vectors-core-ir.ll
@@ -200,6 +200,16 @@ define <vscale x 8 x half> @shufflevector(half %val) {
ret <vscale x 8 x half> %r
}
+define <vscale x 8 x half> @shufflevector2(half %val) {
+; CHECK-LABEL: @shufflevector
+; CHECK: %insvec = insertelement <vscale x 8 x half> poison, half %val, i32 0
+; CHECK-NEXT: %r = shufflevector <vscale x 8 x half> %insvec, <vscale x 8 x half> undef, <vscale x 8 x i32> zeroinitializer
+; CHECK-NEXT: ret <vscale x 8 x half> %r
+ %insvec = insertelement <vscale x 8 x half> poison, half %val, i32 0
+ %r = shufflevector <vscale x 8 x half> %insvec, <vscale x 8 x half> undef, <vscale x 8 x i32> zeroinitializer
+ ret <vscale x 8 x half> %r
+}
+
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;; Memory Access and Addressing Operations
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
@@ -390,4 +400,4 @@ define <vscale x 4 x i32> @call(<vscale x 4 x i32> %val) {
; CHECK-NEXT: ret <vscale x 4 x i32> %r
%r = call <vscale x 4 x i32> @callee(<vscale x 4 x i32> %val)
ret <vscale x 4 x i32> %r
-}
\ No newline at end of file
+}
More information about the llvm-commits
mailing list