[llvm] 7de7f50 - [InstCombine][X86] Fold blendv(x,y,shuffle(bitcast(sext(m)))) -> select(shuffle(m),x,y) (#96882)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Jul 3 04:21:35 PDT 2024
Author: Simon Pilgrim
Date: 2024-07-03T12:21:31+01:00
New Revision: 7de7f50fc9d76ced7a971a66abf59aab6f9e5be6
URL: https://github.com/llvm/llvm-project/commit/7de7f50fc9d76ced7a971a66abf59aab6f9e5be6
DIFF: https://github.com/llvm/llvm-project/commit/7de7f50fc9d76ced7a971a66abf59aab6f9e5be6.diff
LOG: [InstCombine][X86] Fold blendv(x,y,shuffle(bitcast(sext(m)))) -> select(shuffle(m),x,y) (#96882)
We already handle blendv(x,y,bitcast(sext(m))) -> select(m,x,y) cases, but this adds support for peeking through one-use shuffles as well. VectorCombine should already have canonicalized the IR to shuffle(bitcast(...)) for us.
The particular use case is where we have split generic 256/512-bit code to use target-specific blendv intrinsics (e.g. AVX1 spoofing AVX2 256-bit ops).
Fixes #58895
Added:
Modified:
llvm/lib/Target/X86/X86InstCombineIntrinsic.cpp
llvm/test/Transforms/PhaseOrdering/X86/blendv-select.ll
llvm/test/Transforms/PhaseOrdering/X86/pr67803.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/X86/X86InstCombineIntrinsic.cpp b/llvm/lib/Target/X86/X86InstCombineIntrinsic.cpp
index b00c8cc16fe0f..0397fb299d27b 100644
--- a/llvm/lib/Target/X86/X86InstCombineIntrinsic.cpp
+++ b/llvm/lib/Target/X86/X86InstCombineIntrinsic.cpp
@@ -2800,6 +2800,23 @@ X86TTIImpl::instCombineIntrinsic(InstCombiner &IC, IntrinsicInst &II) const {
return SelectInst::Create(NewSelector, Op1, Op0, "blendv");
}
+ // Peek through a one-use shuffle - VectorCombine should have simplified
+ // this for cases where we're splitting wider vectors to use blendv
+ // intrinsics.
+ Value *MaskSrc = nullptr;
+ ArrayRef<int> ShuffleMask;
+ if (match(Mask, PatternMatch::m_OneUse(PatternMatch::m_Shuffle(
+ PatternMatch::m_Value(MaskSrc), PatternMatch::m_Undef(),
+ PatternMatch::m_Mask(ShuffleMask))))) {
+ // Bail if the shuffle was irregular or contains undefs.
+ int NumElts = cast<FixedVectorType>(MaskSrc->getType())->getNumElements();
+ if (NumElts < ShuffleMask.size() || !isPowerOf2_32(NumElts) ||
+ any_of(ShuffleMask,
+ [NumElts](int M) { return M < 0 || M >= NumElts; }))
+ break;
+ Mask = MaskSrc;
+ }
+
// Convert to a vector select if we can bypass casts and find a boolean
// vector condition value.
Value *BoolVec;
@@ -2809,11 +2826,26 @@ X86TTIImpl::instCombineIntrinsic(InstCombiner &IC, IntrinsicInst &II) const {
BoolVec->getType()->getScalarSizeInBits() == 1) {
auto *MaskTy = cast<FixedVectorType>(Mask->getType());
auto *OpTy = cast<FixedVectorType>(II.getType());
+ unsigned NumMaskElts = MaskTy->getNumElements();
+ unsigned NumOperandElts = OpTy->getNumElements();
+
+ // If we peeked through a shuffle, reapply the shuffle to the bool vector.
+ if (MaskSrc) {
+ unsigned NumMaskSrcElts =
+ cast<FixedVectorType>(MaskSrc->getType())->getNumElements();
+ NumMaskElts = (ShuffleMask.size() * NumMaskElts) / NumMaskSrcElts;
+ // Multiple mask bits maps to the same operand element - bail out.
+ if (NumMaskElts > NumOperandElts)
+ break;
+ SmallVector<int> ScaledMask;
+ if (!llvm::scaleShuffleMaskElts(NumMaskElts, ShuffleMask, ScaledMask))
+ break;
+ BoolVec = IC.Builder.CreateShuffleVector(BoolVec, ScaledMask);
+ MaskTy = FixedVectorType::get(MaskTy->getElementType(), NumMaskElts);
+ }
assert(MaskTy->getPrimitiveSizeInBits() ==
OpTy->getPrimitiveSizeInBits() &&
"Not expecting mask and operands with
diff erent sizes");
- unsigned NumMaskElts = MaskTy->getNumElements();
- unsigned NumOperandElts = OpTy->getNumElements();
if (NumMaskElts == NumOperandElts) {
return SelectInst::Create(BoolVec, Op1, Op0);
diff --git a/llvm/test/Transforms/PhaseOrdering/X86/blendv-select.ll b/llvm/test/Transforms/PhaseOrdering/X86/blendv-select.ll
index bccd189d12a82..67c9c333987f6 100644
--- a/llvm/test/Transforms/PhaseOrdering/X86/blendv-select.ll
+++ b/llvm/test/Transforms/PhaseOrdering/X86/blendv-select.ll
@@ -4,7 +4,7 @@
; RUN: opt < %s -O3 -S -mtriple=x86_64-- -mcpu=x86-64-v4 | FileCheck %s
;
-; TODO: PR58895 - replace shuffled _mm_blendv_epi8+icmp with select+icmp
+; PR58895 - replace shuffled _mm_blendv_epi8+icmp with select+icmp
;
;
@@ -13,21 +13,21 @@
define <4 x double> @x86_pblendvb_v4f64_v2f64(<4 x double> %a, <4 x double> %b, <4 x double> %c, <4 x double> %d) {
; CHECK-LABEL: @x86_pblendvb_v4f64_v2f64(
-; CHECK-NEXT: [[A_BC:%.*]] = bitcast <4 x double> [[A:%.*]] to <32 x i8>
-; CHECK-NEXT: [[B_BC:%.*]] = bitcast <4 x double> [[B:%.*]] to <32 x i8>
-; CHECK-NEXT: [[A_LO:%.*]] = shufflevector <32 x i8> [[A_BC]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[B_LO:%.*]] = shufflevector <32 x i8> [[B_BC]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[A_HI:%.*]] = shufflevector <32 x i8> [[A_BC]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[B_HI:%.*]] = shufflevector <32 x i8> [[B_BC]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
; CHECK-NEXT: [[CMP:%.*]] = fcmp olt <4 x double> [[C:%.*]], [[D:%.*]]
-; CHECK-NEXT: [[SEXT:%.*]] = sext <4 x i1> [[CMP]] to <4 x i64>
-; CHECK-NEXT: [[SEXT_BC:%.*]] = bitcast <4 x i64> [[SEXT]] to <32 x i8>
-; CHECK-NEXT: [[SEXT_LO:%.*]] = shufflevector <32 x i8> [[SEXT_BC]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[SEXT_HI:%.*]] = shufflevector <32 x i8> [[SEXT_BC]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[SEL_LO:%.*]] = tail call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> [[A_LO]], <16 x i8> [[B_LO]], <16 x i8> [[SEXT_LO]])
-; CHECK-NEXT: [[SEL_HI:%.*]] = tail call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> [[A_HI]], <16 x i8> [[B_HI]], <16 x i8> [[SEXT_HI]])
-; CHECK-NEXT: [[CONCAT:%.*]] = shufflevector <16 x i8> [[SEL_LO]], <16 x i8> [[SEL_HI]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[RES:%.*]] = bitcast <32 x i8> [[CONCAT]] to <4 x double>
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x i1> [[CMP]], <4 x i1> poison, <2 x i32> <i32 0, i32 1>
+; CHECK-NEXT: [[TMP2:%.*]] = bitcast <4 x double> [[A:%.*]] to <4 x i64>
+; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i64> [[TMP2]], <4 x i64> poison, <2 x i32> <i32 0, i32 1>
+; CHECK-NEXT: [[TMP4:%.*]] = bitcast <4 x double> [[B:%.*]] to <4 x i64>
+; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x i64> [[TMP4]], <4 x i64> poison, <2 x i32> <i32 0, i32 1>
+; CHECK-NEXT: [[TMP6:%.*]] = select <2 x i1> [[TMP1]], <2 x i64> [[TMP5]], <2 x i64> [[TMP3]]
+; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <4 x i1> [[CMP]], <4 x i1> poison, <2 x i32> <i32 2, i32 3>
+; CHECK-NEXT: [[TMP8:%.*]] = bitcast <4 x double> [[A]] to <4 x i64>
+; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <4 x i64> [[TMP8]], <4 x i64> poison, <2 x i32> <i32 2, i32 3>
+; CHECK-NEXT: [[TMP10:%.*]] = bitcast <4 x double> [[B]] to <4 x i64>
+; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <4 x i64> [[TMP10]], <4 x i64> poison, <2 x i32> <i32 2, i32 3>
+; CHECK-NEXT: [[TMP12:%.*]] = select <2 x i1> [[TMP7]], <2 x i64> [[TMP11]], <2 x i64> [[TMP9]]
+; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <2 x i64> [[TMP6]], <2 x i64> [[TMP12]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT: [[RES:%.*]] = bitcast <4 x i64> [[TMP13]] to <4 x double>
; CHECK-NEXT: ret <4 x double> [[RES]]
;
%a.bc = bitcast <4 x double> %a to <32 x i8>
@@ -50,21 +50,21 @@ define <4 x double> @x86_pblendvb_v4f64_v2f64(<4 x double> %a, <4 x double> %b,
define <8 x float> @x86_pblendvb_v8f32_v4f32(<8 x float> %a, <8 x float> %b, <8 x float> %c, <8 x float> %d) {
; CHECK-LABEL: @x86_pblendvb_v8f32_v4f32(
-; CHECK-NEXT: [[A_BC:%.*]] = bitcast <8 x float> [[A:%.*]] to <32 x i8>
-; CHECK-NEXT: [[B_BC:%.*]] = bitcast <8 x float> [[B:%.*]] to <32 x i8>
-; CHECK-NEXT: [[A_LO:%.*]] = shufflevector <32 x i8> [[A_BC]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[B_LO:%.*]] = shufflevector <32 x i8> [[B_BC]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[A_HI:%.*]] = shufflevector <32 x i8> [[A_BC]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[B_HI:%.*]] = shufflevector <32 x i8> [[B_BC]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
; CHECK-NEXT: [[CMP:%.*]] = fcmp olt <8 x float> [[C:%.*]], [[D:%.*]]
-; CHECK-NEXT: [[SEXT:%.*]] = sext <8 x i1> [[CMP]] to <8 x i32>
-; CHECK-NEXT: [[SEXT_BC:%.*]] = bitcast <8 x i32> [[SEXT]] to <32 x i8>
-; CHECK-NEXT: [[SEXT_LO:%.*]] = shufflevector <32 x i8> [[SEXT_BC]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[SEXT_HI:%.*]] = shufflevector <32 x i8> [[SEXT_BC]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[SEL_LO:%.*]] = tail call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> [[A_LO]], <16 x i8> [[B_LO]], <16 x i8> [[SEXT_LO]])
-; CHECK-NEXT: [[SEL_HI:%.*]] = tail call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> [[A_HI]], <16 x i8> [[B_HI]], <16 x i8> [[SEXT_HI]])
-; CHECK-NEXT: [[CONCAT:%.*]] = shufflevector <16 x i8> [[SEL_LO]], <16 x i8> [[SEL_HI]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[RES:%.*]] = bitcast <32 x i8> [[CONCAT]] to <8 x float>
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x i1> [[CMP]], <8 x i1> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT: [[TMP2:%.*]] = bitcast <8 x float> [[A:%.*]] to <8 x i32>
+; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[TMP2]], <8 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT: [[TMP4:%.*]] = bitcast <8 x float> [[B:%.*]] to <8 x i32>
+; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <8 x i32> [[TMP4]], <8 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT: [[TMP6:%.*]] = select <4 x i1> [[TMP1]], <4 x i32> [[TMP5]], <4 x i32> [[TMP3]]
+; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <8 x i1> [[CMP]], <8 x i1> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP8:%.*]] = bitcast <8 x float> [[A]] to <8 x i32>
+; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <8 x i32> [[TMP8]], <8 x i32> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP10:%.*]] = bitcast <8 x float> [[B]] to <8 x i32>
+; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <8 x i32> [[TMP10]], <8 x i32> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP12:%.*]] = select <4 x i1> [[TMP7]], <4 x i32> [[TMP11]], <4 x i32> [[TMP9]]
+; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <4 x i32> [[TMP6]], <4 x i32> [[TMP12]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[RES:%.*]] = bitcast <8 x i32> [[TMP13]] to <8 x float>
; CHECK-NEXT: ret <8 x float> [[RES]]
;
%a.bc = bitcast <8 x float> %a to <32 x i8>
@@ -87,22 +87,9 @@ define <8 x float> @x86_pblendvb_v8f32_v4f32(<8 x float> %a, <8 x float> %b, <8
define <4 x i64> @x86_pblendvb_v4i64_v2i64(<4 x i64> %a, <4 x i64> %b, <4 x i64> %c, <4 x i64> %d) {
; CHECK-LABEL: @x86_pblendvb_v4i64_v2i64(
-; CHECK-NEXT: [[A_BC:%.*]] = bitcast <4 x i64> [[A:%.*]] to <32 x i8>
-; CHECK-NEXT: [[B_BC:%.*]] = bitcast <4 x i64> [[B:%.*]] to <32 x i8>
-; CHECK-NEXT: [[A_LO:%.*]] = shufflevector <32 x i8> [[A_BC]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[B_LO:%.*]] = shufflevector <32 x i8> [[B_BC]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[A_HI:%.*]] = shufflevector <32 x i8> [[A_BC]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[B_HI:%.*]] = shufflevector <32 x i8> [[B_BC]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
; CHECK-NEXT: [[CMP:%.*]] = icmp slt <4 x i64> [[C:%.*]], [[D:%.*]]
-; CHECK-NEXT: [[SEXT:%.*]] = sext <4 x i1> [[CMP]] to <4 x i64>
-; CHECK-NEXT: [[SEXT_BC:%.*]] = bitcast <4 x i64> [[SEXT]] to <32 x i8>
-; CHECK-NEXT: [[SEXT_LO:%.*]] = shufflevector <32 x i8> [[SEXT_BC]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[SEXT_HI:%.*]] = shufflevector <32 x i8> [[SEXT_BC]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[SEL_LO:%.*]] = tail call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> [[A_LO]], <16 x i8> [[B_LO]], <16 x i8> [[SEXT_LO]])
-; CHECK-NEXT: [[SEL_HI:%.*]] = tail call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> [[A_HI]], <16 x i8> [[B_HI]], <16 x i8> [[SEXT_HI]])
-; CHECK-NEXT: [[CONCAT:%.*]] = shufflevector <16 x i8> [[SEL_LO]], <16 x i8> [[SEL_HI]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[RES:%.*]] = bitcast <32 x i8> [[CONCAT]] to <4 x i64>
-; CHECK-NEXT: ret <4 x i64> [[RES]]
+; CHECK-NEXT: [[TMP1:%.*]] = select <4 x i1> [[CMP]], <4 x i64> [[B:%.*]], <4 x i64> [[A:%.*]]
+; CHECK-NEXT: ret <4 x i64> [[TMP1]]
;
%a.bc = bitcast <4 x i64> %a to <32 x i8>
%b.bc = bitcast <4 x i64> %b to <32 x i8>
@@ -124,23 +111,23 @@ define <4 x i64> @x86_pblendvb_v4i64_v2i64(<4 x i64> %a, <4 x i64> %b, <4 x i64>
define <4 x i64> @x86_pblendvb_v8i32_v4i32(<4 x i64> %a, <4 x i64> %b, <4 x i64> %c, <4 x i64> %d) {
; CHECK-LABEL: @x86_pblendvb_v8i32_v4i32(
-; CHECK-NEXT: [[A_BC:%.*]] = bitcast <4 x i64> [[A:%.*]] to <32 x i8>
-; CHECK-NEXT: [[B_BC:%.*]] = bitcast <4 x i64> [[B:%.*]] to <32 x i8>
; CHECK-NEXT: [[C_BC:%.*]] = bitcast <4 x i64> [[C:%.*]] to <8 x i32>
; CHECK-NEXT: [[D_BC:%.*]] = bitcast <4 x i64> [[D:%.*]] to <8 x i32>
-; CHECK-NEXT: [[A_LO:%.*]] = shufflevector <32 x i8> [[A_BC]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[B_LO:%.*]] = shufflevector <32 x i8> [[B_BC]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[A_HI:%.*]] = shufflevector <32 x i8> [[A_BC]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[B_HI:%.*]] = shufflevector <32 x i8> [[B_BC]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
; CHECK-NEXT: [[CMP:%.*]] = icmp slt <8 x i32> [[C_BC]], [[D_BC]]
-; CHECK-NEXT: [[SEXT:%.*]] = sext <8 x i1> [[CMP]] to <8 x i32>
-; CHECK-NEXT: [[SEXT_BC:%.*]] = bitcast <8 x i32> [[SEXT]] to <32 x i8>
-; CHECK-NEXT: [[SEXT_LO:%.*]] = shufflevector <32 x i8> [[SEXT_BC]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[SEXT_HI:%.*]] = shufflevector <32 x i8> [[SEXT_BC]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[SEL_LO:%.*]] = tail call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> [[A_LO]], <16 x i8> [[B_LO]], <16 x i8> [[SEXT_LO]])
-; CHECK-NEXT: [[SEL_HI:%.*]] = tail call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> [[A_HI]], <16 x i8> [[B_HI]], <16 x i8> [[SEXT_HI]])
-; CHECK-NEXT: [[CONCAT:%.*]] = shufflevector <16 x i8> [[SEL_LO]], <16 x i8> [[SEL_HI]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[RES:%.*]] = bitcast <32 x i8> [[CONCAT]] to <4 x i64>
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x i1> [[CMP]], <8 x i1> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT: [[TMP2:%.*]] = bitcast <4 x i64> [[A:%.*]] to <8 x i32>
+; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[TMP2]], <8 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT: [[TMP4:%.*]] = bitcast <4 x i64> [[B:%.*]] to <8 x i32>
+; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <8 x i32> [[TMP4]], <8 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT: [[TMP6:%.*]] = select <4 x i1> [[TMP1]], <4 x i32> [[TMP5]], <4 x i32> [[TMP3]]
+; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <8 x i1> [[CMP]], <8 x i1> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP8:%.*]] = bitcast <4 x i64> [[A]] to <8 x i32>
+; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <8 x i32> [[TMP8]], <8 x i32> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP10:%.*]] = bitcast <4 x i64> [[B]] to <8 x i32>
+; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <8 x i32> [[TMP10]], <8 x i32> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP12:%.*]] = select <4 x i1> [[TMP7]], <4 x i32> [[TMP11]], <4 x i32> [[TMP9]]
+; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <4 x i32> [[TMP6]], <4 x i32> [[TMP12]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[RES:%.*]] = bitcast <8 x i32> [[TMP13]] to <4 x i64>
; CHECK-NEXT: ret <4 x i64> [[RES]]
;
%a.bc = bitcast <4 x i64> %a to <32 x i8>
@@ -165,23 +152,23 @@ define <4 x i64> @x86_pblendvb_v8i32_v4i32(<4 x i64> %a, <4 x i64> %b, <4 x i64>
define <4 x i64> @x86_pblendvb_v16i16_v8i16(<4 x i64> %a, <4 x i64> %b, <4 x i64> %c, <4 x i64> %d) {
; CHECK-LABEL: @x86_pblendvb_v16i16_v8i16(
-; CHECK-NEXT: [[A_BC:%.*]] = bitcast <4 x i64> [[A:%.*]] to <32 x i8>
-; CHECK-NEXT: [[B_BC:%.*]] = bitcast <4 x i64> [[B:%.*]] to <32 x i8>
; CHECK-NEXT: [[C_BC:%.*]] = bitcast <4 x i64> [[C:%.*]] to <16 x i16>
; CHECK-NEXT: [[D_BC:%.*]] = bitcast <4 x i64> [[D:%.*]] to <16 x i16>
-; CHECK-NEXT: [[A_LO:%.*]] = shufflevector <32 x i8> [[A_BC]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[B_LO:%.*]] = shufflevector <32 x i8> [[B_BC]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[A_HI:%.*]] = shufflevector <32 x i8> [[A_BC]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[B_HI:%.*]] = shufflevector <32 x i8> [[B_BC]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
; CHECK-NEXT: [[CMP:%.*]] = icmp slt <16 x i16> [[C_BC]], [[D_BC]]
-; CHECK-NEXT: [[SEXT:%.*]] = sext <16 x i1> [[CMP]] to <16 x i16>
-; CHECK-NEXT: [[SEXT_BC:%.*]] = bitcast <16 x i16> [[SEXT]] to <32 x i8>
-; CHECK-NEXT: [[SEXT_LO:%.*]] = shufflevector <32 x i8> [[SEXT_BC]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[SEXT_HI:%.*]] = shufflevector <32 x i8> [[SEXT_BC]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[SEL_LO:%.*]] = tail call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> [[A_LO]], <16 x i8> [[B_LO]], <16 x i8> [[SEXT_LO]])
-; CHECK-NEXT: [[SEL_HI:%.*]] = tail call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> [[A_HI]], <16 x i8> [[B_HI]], <16 x i8> [[SEXT_HI]])
-; CHECK-NEXT: [[CONCAT:%.*]] = shufflevector <16 x i8> [[SEL_LO]], <16 x i8> [[SEL_HI]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[RES:%.*]] = bitcast <32 x i8> [[CONCAT]] to <4 x i64>
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <16 x i1> [[CMP]], <16 x i1> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP2:%.*]] = bitcast <4 x i64> [[A:%.*]] to <16 x i16>
+; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <16 x i16> [[TMP2]], <16 x i16> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP4:%.*]] = bitcast <4 x i64> [[B:%.*]] to <16 x i16>
+; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <16 x i16> [[TMP4]], <16 x i16> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP6:%.*]] = select <8 x i1> [[TMP1]], <8 x i16> [[TMP5]], <8 x i16> [[TMP3]]
+; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <16 x i1> [[CMP]], <16 x i1> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT: [[TMP8:%.*]] = bitcast <4 x i64> [[A]] to <16 x i16>
+; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <16 x i16> [[TMP8]], <16 x i16> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT: [[TMP10:%.*]] = bitcast <4 x i64> [[B]] to <16 x i16>
+; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <16 x i16> [[TMP10]], <16 x i16> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT: [[TMP12:%.*]] = select <8 x i1> [[TMP7]], <8 x i16> [[TMP11]], <8 x i16> [[TMP9]]
+; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <8 x i16> [[TMP6]], <8 x i16> [[TMP12]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT: [[RES:%.*]] = bitcast <16 x i16> [[TMP13]] to <4 x i64>
; CHECK-NEXT: ret <4 x i64> [[RES]]
;
%a.bc = bitcast <4 x i64> %a to <32 x i8>
@@ -210,17 +197,8 @@ define <4 x i64> @x86_pblendvb_v32i8_v16i8(<4 x i64> %a, <4 x i64> %b, <4 x i64>
; CHECK-NEXT: [[B_BC:%.*]] = bitcast <4 x i64> [[B:%.*]] to <32 x i8>
; CHECK-NEXT: [[C_BC:%.*]] = bitcast <4 x i64> [[C:%.*]] to <32 x i8>
; CHECK-NEXT: [[D_BC:%.*]] = bitcast <4 x i64> [[D:%.*]] to <32 x i8>
-; CHECK-NEXT: [[A_LO:%.*]] = shufflevector <32 x i8> [[A_BC]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[B_LO:%.*]] = shufflevector <32 x i8> [[B_BC]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[A_HI:%.*]] = shufflevector <32 x i8> [[A_BC]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[B_HI:%.*]] = shufflevector <32 x i8> [[B_BC]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
; CHECK-NEXT: [[CMP:%.*]] = icmp slt <32 x i8> [[C_BC]], [[D_BC]]
-; CHECK-NEXT: [[SEXT:%.*]] = sext <32 x i1> [[CMP]] to <32 x i8>
-; CHECK-NEXT: [[SEXT_LO:%.*]] = shufflevector <32 x i8> [[SEXT]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[SEXT_HI:%.*]] = shufflevector <32 x i8> [[SEXT]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[SEL_LO:%.*]] = tail call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> [[A_LO]], <16 x i8> [[B_LO]], <16 x i8> [[SEXT_LO]])
-; CHECK-NEXT: [[SEL_HI:%.*]] = tail call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> [[A_HI]], <16 x i8> [[B_HI]], <16 x i8> [[SEXT_HI]])
-; CHECK-NEXT: [[CONCAT:%.*]] = shufflevector <16 x i8> [[SEL_LO]], <16 x i8> [[SEL_HI]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
+; CHECK-NEXT: [[CONCAT:%.*]] = select <32 x i1> [[CMP]], <32 x i8> [[B_BC]], <32 x i8> [[A_BC]]
; CHECK-NEXT: [[RES:%.*]] = bitcast <32 x i8> [[CONCAT]] to <4 x i64>
; CHECK-NEXT: ret <4 x i64> [[RES]]
;
@@ -249,21 +227,21 @@ define <4 x i64> @x86_pblendvb_v32i8_v16i8(<4 x i64> %a, <4 x i64> %b, <4 x i64>
define <8 x double> @x86_pblendvb_v8f64_v4f64(<8 x double> %a, <8 x double> %b, <8 x double> %c, <8 x double> %d) {
; CHECK-LABEL: @x86_pblendvb_v8f64_v4f64(
-; CHECK-NEXT: [[A_BC:%.*]] = bitcast <8 x double> [[A:%.*]] to <64 x i8>
-; CHECK-NEXT: [[B_BC:%.*]] = bitcast <8 x double> [[B:%.*]] to <64 x i8>
-; CHECK-NEXT: [[A_LO:%.*]] = shufflevector <64 x i8> [[A_BC]], <64 x i8> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[B_LO:%.*]] = shufflevector <64 x i8> [[B_BC]], <64 x i8> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[A_HI:%.*]] = shufflevector <64 x i8> [[A_BC]], <64 x i8> poison, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT: [[B_HI:%.*]] = shufflevector <64 x i8> [[B_BC]], <64 x i8> poison, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
; CHECK-NEXT: [[CMP:%.*]] = fcmp olt <8 x double> [[C:%.*]], [[D:%.*]]
-; CHECK-NEXT: [[SEXT:%.*]] = sext <8 x i1> [[CMP]] to <8 x i64>
-; CHECK-NEXT: [[SEXT_BC:%.*]] = bitcast <8 x i64> [[SEXT]] to <64 x i8>
-; CHECK-NEXT: [[SEXT_LO:%.*]] = shufflevector <64 x i8> [[SEXT_BC]], <64 x i8> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[SEXT_HI:%.*]] = shufflevector <64 x i8> [[SEXT_BC]], <64 x i8> poison, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT: [[SEL_LO:%.*]] = tail call <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8> [[A_LO]], <32 x i8> [[B_LO]], <32 x i8> [[SEXT_LO]])
-; CHECK-NEXT: [[SEL_HI:%.*]] = tail call <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8> [[A_HI]], <32 x i8> [[B_HI]], <32 x i8> [[SEXT_HI]])
-; CHECK-NEXT: [[CONCAT:%.*]] = shufflevector <32 x i8> [[SEL_LO]], <32 x i8> [[SEL_HI]], <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT: [[RES:%.*]] = bitcast <64 x i8> [[CONCAT]] to <8 x double>
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x i1> [[CMP]], <8 x i1> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT: [[TMP2:%.*]] = bitcast <8 x double> [[A:%.*]] to <8 x i64>
+; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <8 x i64> [[TMP2]], <8 x i64> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT: [[TMP4:%.*]] = bitcast <8 x double> [[B:%.*]] to <8 x i64>
+; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <8 x i64> [[TMP4]], <8 x i64> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT: [[TMP6:%.*]] = select <4 x i1> [[TMP1]], <4 x i64> [[TMP5]], <4 x i64> [[TMP3]]
+; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <8 x i1> [[CMP]], <8 x i1> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP8:%.*]] = bitcast <8 x double> [[A]] to <8 x i64>
+; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <8 x i64> [[TMP8]], <8 x i64> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP10:%.*]] = bitcast <8 x double> [[B]] to <8 x i64>
+; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <8 x i64> [[TMP10]], <8 x i64> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP12:%.*]] = select <4 x i1> [[TMP7]], <4 x i64> [[TMP11]], <4 x i64> [[TMP9]]
+; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <4 x i64> [[TMP6]], <4 x i64> [[TMP12]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[RES:%.*]] = bitcast <8 x i64> [[TMP13]] to <8 x double>
; CHECK-NEXT: ret <8 x double> [[RES]]
;
%a.bc = bitcast <8 x double> %a to <64 x i8>
@@ -286,21 +264,21 @@ define <8 x double> @x86_pblendvb_v8f64_v4f64(<8 x double> %a, <8 x double> %b,
define <16 x float> @x86_pblendvb_v16f32_v8f32(<16 x float> %a, <16 x float> %b, <16 x float> %c, <16 x float> %d) {
; CHECK-LABEL: @x86_pblendvb_v16f32_v8f32(
-; CHECK-NEXT: [[A_BC:%.*]] = bitcast <16 x float> [[A:%.*]] to <64 x i8>
-; CHECK-NEXT: [[B_BC:%.*]] = bitcast <16 x float> [[B:%.*]] to <64 x i8>
-; CHECK-NEXT: [[A_LO:%.*]] = shufflevector <64 x i8> [[A_BC]], <64 x i8> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[B_LO:%.*]] = shufflevector <64 x i8> [[B_BC]], <64 x i8> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[A_HI:%.*]] = shufflevector <64 x i8> [[A_BC]], <64 x i8> poison, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT: [[B_HI:%.*]] = shufflevector <64 x i8> [[B_BC]], <64 x i8> poison, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
; CHECK-NEXT: [[CMP:%.*]] = fcmp olt <16 x float> [[C:%.*]], [[D:%.*]]
-; CHECK-NEXT: [[SEXT:%.*]] = sext <16 x i1> [[CMP]] to <16 x i32>
-; CHECK-NEXT: [[SEXT_BC:%.*]] = bitcast <16 x i32> [[SEXT]] to <64 x i8>
-; CHECK-NEXT: [[SEXT_LO:%.*]] = shufflevector <64 x i8> [[SEXT_BC]], <64 x i8> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[SEXT_HI:%.*]] = shufflevector <64 x i8> [[SEXT_BC]], <64 x i8> poison, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT: [[SEL_LO:%.*]] = tail call <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8> [[A_LO]], <32 x i8> [[B_LO]], <32 x i8> [[SEXT_LO]])
-; CHECK-NEXT: [[SEL_HI:%.*]] = tail call <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8> [[A_HI]], <32 x i8> [[B_HI]], <32 x i8> [[SEXT_HI]])
-; CHECK-NEXT: [[CONCAT:%.*]] = shufflevector <32 x i8> [[SEL_LO]], <32 x i8> [[SEL_HI]], <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT: [[RES:%.*]] = bitcast <64 x i8> [[CONCAT]] to <16 x float>
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <16 x i1> [[CMP]], <16 x i1> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP2:%.*]] = bitcast <16 x float> [[A:%.*]] to <16 x i32>
+; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <16 x i32> [[TMP2]], <16 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP4:%.*]] = bitcast <16 x float> [[B:%.*]] to <16 x i32>
+; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <16 x i32> [[TMP4]], <16 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP6:%.*]] = select <8 x i1> [[TMP1]], <8 x i32> [[TMP5]], <8 x i32> [[TMP3]]
+; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <16 x i1> [[CMP]], <16 x i1> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT: [[TMP8:%.*]] = bitcast <16 x float> [[A]] to <16 x i32>
+; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <16 x i32> [[TMP8]], <16 x i32> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT: [[TMP10:%.*]] = bitcast <16 x float> [[B]] to <16 x i32>
+; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <16 x i32> [[TMP10]], <16 x i32> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT: [[TMP12:%.*]] = select <8 x i1> [[TMP7]], <8 x i32> [[TMP11]], <8 x i32> [[TMP9]]
+; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <8 x i32> [[TMP6]], <8 x i32> [[TMP12]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT: [[RES:%.*]] = bitcast <16 x i32> [[TMP13]] to <16 x float>
; CHECK-NEXT: ret <16 x float> [[RES]]
;
%a.bc = bitcast <16 x float> %a to <64 x i8>
@@ -323,22 +301,9 @@ define <16 x float> @x86_pblendvb_v16f32_v8f32(<16 x float> %a, <16 x float> %b,
define <8 x i64> @x86_pblendvb_v8i64_v4i64(<8 x i64> %a, <8 x i64> %b, <8 x i64> %c, <8 x i64> %d) {
; CHECK-LABEL: @x86_pblendvb_v8i64_v4i64(
-; CHECK-NEXT: [[A_BC:%.*]] = bitcast <8 x i64> [[A:%.*]] to <64 x i8>
-; CHECK-NEXT: [[B_BC:%.*]] = bitcast <8 x i64> [[B:%.*]] to <64 x i8>
-; CHECK-NEXT: [[A_LO:%.*]] = shufflevector <64 x i8> [[A_BC]], <64 x i8> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[B_LO:%.*]] = shufflevector <64 x i8> [[B_BC]], <64 x i8> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[A_HI:%.*]] = shufflevector <64 x i8> [[A_BC]], <64 x i8> poison, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT: [[B_HI:%.*]] = shufflevector <64 x i8> [[B_BC]], <64 x i8> poison, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
; CHECK-NEXT: [[CMP:%.*]] = icmp slt <8 x i64> [[C:%.*]], [[D:%.*]]
-; CHECK-NEXT: [[SEXT:%.*]] = sext <8 x i1> [[CMP]] to <8 x i64>
-; CHECK-NEXT: [[SEXT_BC:%.*]] = bitcast <8 x i64> [[SEXT]] to <64 x i8>
-; CHECK-NEXT: [[SEXT_LO:%.*]] = shufflevector <64 x i8> [[SEXT_BC]], <64 x i8> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[SEXT_HI:%.*]] = shufflevector <64 x i8> [[SEXT_BC]], <64 x i8> poison, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT: [[SEL_LO:%.*]] = tail call <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8> [[A_LO]], <32 x i8> [[B_LO]], <32 x i8> [[SEXT_LO]])
-; CHECK-NEXT: [[SEL_HI:%.*]] = tail call <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8> [[A_HI]], <32 x i8> [[B_HI]], <32 x i8> [[SEXT_HI]])
-; CHECK-NEXT: [[CONCAT:%.*]] = shufflevector <32 x i8> [[SEL_LO]], <32 x i8> [[SEL_HI]], <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT: [[RES:%.*]] = bitcast <64 x i8> [[CONCAT]] to <8 x i64>
-; CHECK-NEXT: ret <8 x i64> [[RES]]
+; CHECK-NEXT: [[TMP1:%.*]] = select <8 x i1> [[CMP]], <8 x i64> [[B:%.*]], <8 x i64> [[A:%.*]]
+; CHECK-NEXT: ret <8 x i64> [[TMP1]]
;
%a.bc = bitcast <8 x i64> %a to <64 x i8>
%b.bc = bitcast <8 x i64> %b to <64 x i8>
@@ -360,23 +325,23 @@ define <8 x i64> @x86_pblendvb_v8i64_v4i64(<8 x i64> %a, <8 x i64> %b, <8 x i64>
define <8 x i64> @x86_pblendvb_v16i32_v8i32(<8 x i64> %a, <8 x i64> %b, <8 x i64> %c, <8 x i64> %d) {
; CHECK-LABEL: @x86_pblendvb_v16i32_v8i32(
-; CHECK-NEXT: [[A_BC:%.*]] = bitcast <8 x i64> [[A:%.*]] to <64 x i8>
-; CHECK-NEXT: [[B_BC:%.*]] = bitcast <8 x i64> [[B:%.*]] to <64 x i8>
-; CHECK-NEXT: [[C_BC:%.*]] = bitcast <8 x i64> [[A]] to <16 x i32>
-; CHECK-NEXT: [[D_BC:%.*]] = bitcast <8 x i64> [[B]] to <16 x i32>
-; CHECK-NEXT: [[A_LO:%.*]] = shufflevector <64 x i8> [[A_BC]], <64 x i8> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[B_LO:%.*]] = shufflevector <64 x i8> [[B_BC]], <64 x i8> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[A_HI:%.*]] = shufflevector <64 x i8> [[A_BC]], <64 x i8> poison, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT: [[B_HI:%.*]] = shufflevector <64 x i8> [[B_BC]], <64 x i8> poison, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
+; CHECK-NEXT: [[C_BC:%.*]] = bitcast <8 x i64> [[A:%.*]] to <16 x i32>
+; CHECK-NEXT: [[D_BC:%.*]] = bitcast <8 x i64> [[B:%.*]] to <16 x i32>
; CHECK-NEXT: [[CMP:%.*]] = icmp slt <16 x i32> [[C_BC]], [[D_BC]]
-; CHECK-NEXT: [[SEXT:%.*]] = sext <16 x i1> [[CMP]] to <16 x i32>
-; CHECK-NEXT: [[SEXT_BC:%.*]] = bitcast <16 x i32> [[SEXT]] to <64 x i8>
-; CHECK-NEXT: [[SEXT_LO:%.*]] = shufflevector <64 x i8> [[SEXT_BC]], <64 x i8> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[SEXT_HI:%.*]] = shufflevector <64 x i8> [[SEXT_BC]], <64 x i8> poison, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT: [[SEL_LO:%.*]] = tail call <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8> [[A_LO]], <32 x i8> [[B_LO]], <32 x i8> [[SEXT_LO]])
-; CHECK-NEXT: [[SEL_HI:%.*]] = tail call <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8> [[A_HI]], <32 x i8> [[B_HI]], <32 x i8> [[SEXT_HI]])
-; CHECK-NEXT: [[CONCAT:%.*]] = shufflevector <32 x i8> [[SEL_LO]], <32 x i8> [[SEL_HI]], <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT: [[RES:%.*]] = bitcast <64 x i8> [[CONCAT]] to <8 x i64>
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <16 x i1> [[CMP]], <16 x i1> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP2:%.*]] = bitcast <8 x i64> [[A]] to <16 x i32>
+; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <16 x i32> [[TMP2]], <16 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP4:%.*]] = bitcast <8 x i64> [[B]] to <16 x i32>
+; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <16 x i32> [[TMP4]], <16 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP6:%.*]] = select <8 x i1> [[TMP1]], <8 x i32> [[TMP5]], <8 x i32> [[TMP3]]
+; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <16 x i1> [[CMP]], <16 x i1> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT: [[TMP8:%.*]] = bitcast <8 x i64> [[A]] to <16 x i32>
+; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <16 x i32> [[TMP8]], <16 x i32> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT: [[TMP10:%.*]] = bitcast <8 x i64> [[B]] to <16 x i32>
+; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <16 x i32> [[TMP10]], <16 x i32> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT: [[TMP12:%.*]] = select <8 x i1> [[TMP7]], <8 x i32> [[TMP11]], <8 x i32> [[TMP9]]
+; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <8 x i32> [[TMP6]], <8 x i32> [[TMP12]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT: [[RES:%.*]] = bitcast <16 x i32> [[TMP13]] to <8 x i64>
; CHECK-NEXT: ret <8 x i64> [[RES]]
;
%a.bc = bitcast <8 x i64> %a to <64 x i8>
@@ -401,23 +366,23 @@ define <8 x i64> @x86_pblendvb_v16i32_v8i32(<8 x i64> %a, <8 x i64> %b, <8 x i64
define <8 x i64> @x86_pblendvb_v32i16_v16i16(<8 x i64> %a, <8 x i64> %b, <8 x i64> %c, <8 x i64> %d) {
; CHECK-LABEL: @x86_pblendvb_v32i16_v16i16(
-; CHECK-NEXT: [[A_BC:%.*]] = bitcast <8 x i64> [[A:%.*]] to <64 x i8>
-; CHECK-NEXT: [[B_BC:%.*]] = bitcast <8 x i64> [[B:%.*]] to <64 x i8>
; CHECK-NEXT: [[C_BC:%.*]] = bitcast <8 x i64> [[C:%.*]] to <32 x i16>
; CHECK-NEXT: [[D_BC:%.*]] = bitcast <8 x i64> [[D:%.*]] to <32 x i16>
-; CHECK-NEXT: [[A_LO:%.*]] = shufflevector <64 x i8> [[A_BC]], <64 x i8> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[B_LO:%.*]] = shufflevector <64 x i8> [[B_BC]], <64 x i8> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[A_HI:%.*]] = shufflevector <64 x i8> [[A_BC]], <64 x i8> poison, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT: [[B_HI:%.*]] = shufflevector <64 x i8> [[B_BC]], <64 x i8> poison, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
; CHECK-NEXT: [[CMP:%.*]] = icmp slt <32 x i16> [[C_BC]], [[D_BC]]
-; CHECK-NEXT: [[SEXT:%.*]] = sext <32 x i1> [[CMP]] to <32 x i16>
-; CHECK-NEXT: [[SEXT_BC:%.*]] = bitcast <32 x i16> [[SEXT]] to <64 x i8>
-; CHECK-NEXT: [[SEXT_LO:%.*]] = shufflevector <64 x i8> [[SEXT_BC]], <64 x i8> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[SEXT_HI:%.*]] = shufflevector <64 x i8> [[SEXT_BC]], <64 x i8> poison, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT: [[SEL_LO:%.*]] = tail call <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8> [[A_LO]], <32 x i8> [[B_LO]], <32 x i8> [[SEXT_LO]])
-; CHECK-NEXT: [[SEL_HI:%.*]] = tail call <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8> [[A_HI]], <32 x i8> [[B_HI]], <32 x i8> [[SEXT_HI]])
-; CHECK-NEXT: [[CONCAT:%.*]] = shufflevector <32 x i8> [[SEL_LO]], <32 x i8> [[SEL_HI]], <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT: [[RES:%.*]] = bitcast <64 x i8> [[CONCAT]] to <8 x i64>
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <32 x i1> [[CMP]], <32 x i1> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT: [[TMP2:%.*]] = bitcast <8 x i64> [[A:%.*]] to <32 x i16>
+; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <32 x i16> [[TMP2]], <32 x i16> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT: [[TMP4:%.*]] = bitcast <8 x i64> [[B:%.*]] to <32 x i16>
+; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <32 x i16> [[TMP4]], <32 x i16> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT: [[TMP6:%.*]] = select <16 x i1> [[TMP1]], <16 x i16> [[TMP5]], <16 x i16> [[TMP3]]
+; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <32 x i1> [[CMP]], <32 x i1> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
+; CHECK-NEXT: [[TMP8:%.*]] = bitcast <8 x i64> [[A]] to <32 x i16>
+; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <32 x i16> [[TMP8]], <32 x i16> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
+; CHECK-NEXT: [[TMP10:%.*]] = bitcast <8 x i64> [[B]] to <32 x i16>
+; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <32 x i16> [[TMP10]], <32 x i16> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
+; CHECK-NEXT: [[TMP12:%.*]] = select <16 x i1> [[TMP7]], <16 x i16> [[TMP11]], <16 x i16> [[TMP9]]
+; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <16 x i16> [[TMP6]], <16 x i16> [[TMP12]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
+; CHECK-NEXT: [[RES:%.*]] = bitcast <32 x i16> [[TMP13]] to <8 x i64>
; CHECK-NEXT: ret <8 x i64> [[RES]]
;
%a.bc = bitcast <8 x i64> %a to <64 x i8>
@@ -446,17 +411,8 @@ define <8 x i64> @x86_pblendvb_v64i8_v32i8(<8 x i64> %a, <8 x i64> %b, <8 x i64>
; CHECK-NEXT: [[B_BC:%.*]] = bitcast <8 x i64> [[B:%.*]] to <64 x i8>
; CHECK-NEXT: [[C_BC:%.*]] = bitcast <8 x i64> [[C:%.*]] to <64 x i8>
; CHECK-NEXT: [[D_BC:%.*]] = bitcast <8 x i64> [[D:%.*]] to <64 x i8>
-; CHECK-NEXT: [[A_LO:%.*]] = shufflevector <64 x i8> [[A_BC]], <64 x i8> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[B_LO:%.*]] = shufflevector <64 x i8> [[B_BC]], <64 x i8> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[A_HI:%.*]] = shufflevector <64 x i8> [[A_BC]], <64 x i8> poison, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT: [[B_HI:%.*]] = shufflevector <64 x i8> [[B_BC]], <64 x i8> poison, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
; CHECK-NEXT: [[CMP:%.*]] = icmp slt <64 x i8> [[C_BC]], [[D_BC]]
-; CHECK-NEXT: [[SEXT:%.*]] = sext <64 x i1> [[CMP]] to <64 x i8>
-; CHECK-NEXT: [[SEXT_LO:%.*]] = shufflevector <64 x i8> [[SEXT]], <64 x i8> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[SEXT_HI:%.*]] = shufflevector <64 x i8> [[SEXT]], <64 x i8> poison, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT: [[SEL_LO:%.*]] = tail call <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8> [[A_LO]], <32 x i8> [[B_LO]], <32 x i8> [[SEXT_LO]])
-; CHECK-NEXT: [[SEL_HI:%.*]] = tail call <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8> [[A_HI]], <32 x i8> [[B_HI]], <32 x i8> [[SEXT_HI]])
-; CHECK-NEXT: [[CONCAT:%.*]] = shufflevector <32 x i8> [[SEL_LO]], <32 x i8> [[SEL_HI]], <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
+; CHECK-NEXT: [[CONCAT:%.*]] = select <64 x i1> [[CMP]], <64 x i8> [[B_BC]], <64 x i8> [[A_BC]]
; CHECK-NEXT: [[RES:%.*]] = bitcast <64 x i8> [[CONCAT]] to <8 x i64>
; CHECK-NEXT: ret <8 x i64> [[RES]]
;
diff --git a/llvm/test/Transforms/PhaseOrdering/X86/pr67803.ll b/llvm/test/Transforms/PhaseOrdering/X86/pr67803.ll
index c7818e8254b2e..7b690341fb805 100644
--- a/llvm/test/Transforms/PhaseOrdering/X86/pr67803.ll
+++ b/llvm/test/Transforms/PhaseOrdering/X86/pr67803.ll
@@ -9,23 +9,26 @@ define <4 x i64> @PR67803(<4 x i64> %x, <4 x i64> %y, <4 x i64> %a, <4 x i64> %b
; CHECK-NEXT: [[TMP0:%.*]] = bitcast <4 x i64> [[X:%.*]] to <8 x i32>
; CHECK-NEXT: [[TMP1:%.*]] = bitcast <4 x i64> [[Y:%.*]] to <8 x i32>
; CHECK-NEXT: [[TMP2:%.*]] = icmp sgt <8 x i32> [[TMP0]], [[TMP1]]
-; CHECK-NEXT: [[TMP3:%.*]] = sext <8 x i1> [[TMP2]] to <8 x i32>
-; CHECK-NEXT: [[TMP4:%.*]] = bitcast <4 x i64> [[A:%.*]] to <32 x i8>
-; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <32 x i8> [[TMP4]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[TMP6:%.*]] = bitcast <4 x i64> [[B:%.*]] to <32 x i8>
-; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <32 x i8> [[TMP6]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[TMP8:%.*]] = bitcast <8 x i32> [[TMP3]] to <32 x i8>
-; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <32 x i8> [[TMP8]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT: [[TMP10:%.*]] = tail call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> [[TMP5]], <16 x i8> [[TMP7]], <16 x i8> [[TMP9]])
-; CHECK-NEXT: [[TMP11:%.*]] = bitcast <4 x i64> [[A]] to <32 x i8>
-; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <32 x i8> [[TMP11]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[TMP13:%.*]] = bitcast <4 x i64> [[B]] to <32 x i8>
-; CHECK-NEXT: [[TMP14:%.*]] = shufflevector <32 x i8> [[TMP13]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[TMP15:%.*]] = bitcast <8 x i32> [[TMP3]] to <32 x i8>
-; CHECK-NEXT: [[TMP16:%.*]] = shufflevector <32 x i8> [[TMP15]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[TMP17:%.*]] = tail call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> [[TMP12]], <16 x i8> [[TMP14]], <16 x i8> [[TMP16]])
-; CHECK-NEXT: [[TMP18:%.*]] = shufflevector <16 x i8> [[TMP10]], <16 x i8> [[TMP17]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT: [[SHUFFLE_I23:%.*]] = bitcast <32 x i8> [[TMP18]] to <4 x i64>
+; CHECK-NEXT: [[TMP3:%.*]] = bitcast <4 x i64> [[A:%.*]] to <32 x i8>
+; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <32 x i8> [[TMP3]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT: [[TMP5:%.*]] = bitcast <4 x i64> [[B:%.*]] to <32 x i8>
+; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <32 x i8> [[TMP5]], <32 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <8 x i1> [[TMP2]], <8 x i1> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT: [[TMP8:%.*]] = bitcast <16 x i8> [[TMP4]] to <4 x i32>
+; CHECK-NEXT: [[TMP9:%.*]] = bitcast <16 x i8> [[TMP6]] to <4 x i32>
+; CHECK-NEXT: [[TMP10:%.*]] = select <4 x i1> [[TMP7]], <4 x i32> [[TMP9]], <4 x i32> [[TMP8]]
+; CHECK-NEXT: [[TMP11:%.*]] = bitcast <4 x i32> [[TMP10]] to <16 x i8>
+; CHECK-NEXT: [[TMP12:%.*]] = bitcast <4 x i64> [[A]] to <32 x i8>
+; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <32 x i8> [[TMP12]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
+; CHECK-NEXT: [[TMP14:%.*]] = bitcast <4 x i64> [[B]] to <32 x i8>
+; CHECK-NEXT: [[TMP15:%.*]] = shufflevector <32 x i8> [[TMP14]], <32 x i8> poison, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
+; CHECK-NEXT: [[TMP16:%.*]] = shufflevector <8 x i1> [[TMP2]], <8 x i1> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT: [[TMP17:%.*]] = bitcast <16 x i8> [[TMP13]] to <4 x i32>
+; CHECK-NEXT: [[TMP18:%.*]] = bitcast <16 x i8> [[TMP15]] to <4 x i32>
+; CHECK-NEXT: [[TMP19:%.*]] = select <4 x i1> [[TMP16]], <4 x i32> [[TMP18]], <4 x i32> [[TMP17]]
+; CHECK-NEXT: [[TMP20:%.*]] = bitcast <4 x i32> [[TMP19]] to <16 x i8>
+; CHECK-NEXT: [[TMP21:%.*]] = shufflevector <16 x i8> [[TMP11]], <16 x i8> [[TMP20]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
+; CHECK-NEXT: [[SHUFFLE_I23:%.*]] = bitcast <32 x i8> [[TMP21]] to <4 x i64>
; CHECK-NEXT: ret <4 x i64> [[SHUFFLE_I23]]
;
entry:
More information about the llvm-commits
mailing list