[llvm] [RISCV] Fix missing scaling by LMUL in cost model (PR #73342)
Simeon K via llvm-commits
llvm-commits at lists.llvm.org
Fri Jan 26 05:25:33 PST 2024
https://github.com/simeonkr updated https://github.com/llvm/llvm-project/pull/73342
>From 3a3d02a6faa72f5bca5bbe4fca1865bfac3e201b Mon Sep 17 00:00:00 2001
From: Simeon Krastnikov <simeon.krastnikov at imgtec.com>
Date: Fri, 24 Nov 2023 15:26:33 +0000
Subject: [PATCH 1/8] [RISCV] Fix missing scaling by LMUL in cost model
Ensure that we consistently scale by LMUL, whenever it makes sense to do
so.
---
.../Target/RISCV/RISCVTargetTransformInfo.cpp | 33 ++++++++--------
.../LoopVectorize/RISCV/illegal-type.ll | 23 +++++------
.../RISCV/riscv-vector-reverse.ll | 39 +++++++++++--------
3 files changed, 50 insertions(+), 45 deletions(-)
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 4ea3a5193089954..548911a2f7a3c6e 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -529,7 +529,8 @@ InstructionCost RISCVTTIImpl::getShuffleCost(TTI::ShuffleKind Kind,
2 + getRISCVInstructionCost(RISCV::VRGATHER_VV, LT.second, CostKind);
// Mask operation additionally required extend and truncate
InstructionCost ExtendCost = Tp->getElementType()->isIntegerTy(1) ? 3 : 0;
- return LT.first * (LenCost + GatherCost + ExtendCost);
+ return LT.first * TLI->getLMULCost(LT.second) *
+ (LenCost + GatherCost + ExtendCost);
}
}
return BaseT::getShuffleCost(Kind, Tp, Mask, CostKind, Index, SubTp);
@@ -740,7 +741,7 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
// These all use the same code.
auto LT = getTypeLegalizationCost(RetTy);
if (!LT.second.isVector() && TLI->isOperationCustom(ISD::FCEIL, LT.second))
- return LT.first * 8;
+ return LT.first * TLI->getLMULCost(LT.second) * 8;
break;
}
case Intrinsic::umin:
@@ -750,7 +751,7 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
auto LT = getTypeLegalizationCost(RetTy);
if ((ST->hasVInstructions() && LT.second.isVector()) ||
(LT.second.isScalarInteger() && ST->hasStdExtZbb()))
- return LT.first;
+ return LT.first * TLI->getLMULCost(LT.second);
break;
}
case Intrinsic::sadd_sat:
@@ -761,7 +762,7 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
case Intrinsic::sqrt: {
auto LT = getTypeLegalizationCost(RetTy);
if (ST->hasVInstructions() && LT.second.isVector())
- return LT.first;
+ return LT.first * TLI->getLMULCost(LT.second);
break;
}
case Intrinsic::ctpop: {
@@ -775,7 +776,7 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
if (ST->hasVInstructions() && LT.second.isVector()) {
// vrsub.vi v10, v8, 0
// vmax.vv v8, v8, v10
- return LT.first * 2;
+ return LT.first * TLI->getLMULCost(LT.second) * 2;
}
break;
}
@@ -783,14 +784,14 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
case Intrinsic::experimental_stepvector: {
unsigned Cost = 1; // vid
auto LT = getTypeLegalizationCost(RetTy);
- return Cost + (LT.first - 1);
+ return Cost + (LT.first - 1) * TLI->getLMULCost(LT.second);
}
case Intrinsic::vp_rint: {
// RISC-V target uses at least 5 instructions to lower rounding intrinsics.
unsigned Cost = 5;
auto LT = getTypeLegalizationCost(RetTy);
if (TLI->isOperationCustom(ISD::VP_FRINT, LT.second))
- return Cost * LT.first;
+ return Cost * LT.first * TLI->getLMULCost(LT.second);
break;
}
case Intrinsic::vp_nearbyint: {
@@ -798,7 +799,7 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
unsigned Cost = 7;
auto LT = getTypeLegalizationCost(RetTy);
if (TLI->isOperationCustom(ISD::VP_FRINT, LT.second))
- return Cost * LT.first;
+ return Cost * LT.first * TLI->getLMULCost(LT.second);
break;
}
case Intrinsic::vp_ceil:
@@ -812,7 +813,7 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
auto LT = getTypeLegalizationCost(RetTy);
unsigned VPISD = getISDForVPIntrinsicID(ICA.getID());
if (TLI->isOperationCustom(VPISD, LT.second))
- return Cost * LT.first;
+ return Cost * LT.first * TLI->getLMULCost(LT.second);
break;
}
}
@@ -823,7 +824,7 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
MVT EltTy = LT.second.getVectorElementType();
if (const auto *Entry = CostTableLookup(VectorIntrinsicCostTable,
ICA.getID(), EltTy))
- return LT.first * Entry->Cost;
+ return LT.first * TLI->getLMULCost(LT.second) * Entry->Cost;
}
}
@@ -1078,10 +1079,10 @@ InstructionCost RISCVTTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
// vmandn.mm v8, v8, v9
// vmand.mm v9, v0, v9
// vmor.mm v0, v9, v8
- return LT.first * 3;
+ return LT.first * TLI->getLMULCost(LT.second) * 3;
}
// vselect and max/min are supported natively.
- return LT.first * 1;
+ return LT.first * TLI->getLMULCost(LT.second) * 1;
}
if (ValTy->getScalarSizeInBits() == 1) {
@@ -1090,13 +1091,13 @@ InstructionCost RISCVTTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
// vmandn.mm v8, v8, v9
// vmand.mm v9, v0, v9
// vmor.mm v0, v9, v8
- return LT.first * 5;
+ return LT.first * TLI->getLMULCost(LT.second) * 5;
}
// vmv.v.x v10, a0
// vmsne.vi v0, v10, 0
// vmerge.vvm v8, v9, v8, v0
- return LT.first * 3;
+ return LT.first * TLI->getLMULCost(LT.second) * 3;
}
if ((Opcode == Instruction::ICmp || Opcode == Instruction::FCmp) &&
@@ -1105,7 +1106,7 @@ InstructionCost RISCVTTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
// Support natively.
if (CmpInst::isIntPredicate(VecPred))
- return LT.first * 1;
+ return LT.first * TLI->getLMULCost(LT.second) * 1;
// If we do not support the input floating point vector type, use the base
// one which will calculate as:
@@ -1124,7 +1125,7 @@ InstructionCost RISCVTTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
case CmpInst::FCMP_OLT:
case CmpInst::FCMP_OLE:
case CmpInst::FCMP_UNE:
- return LT.first * 1;
+ return LT.first * TLI->getLMULCost(LT.second) * 1;
// TODO: Other comparisons?
default:
break;
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/illegal-type.ll b/llvm/test/Transforms/LoopVectorize/RISCV/illegal-type.ll
index c49f7d4a5d5f13d..2a7626ab0a78075 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/illegal-type.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/illegal-type.ll
@@ -102,10 +102,10 @@ define void @uniform_store_i1(ptr noalias %dst, ptr noalias %start, i64 %N) {
; CHECK-LABEL: @uniform_store_i1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[N:%.*]], 1
-; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], 64
+; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], 32
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
-; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 64
+; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 32
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]]
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[N_VEC]], 8
; CHECK-NEXT: [[IND_END:%.*]] = getelementptr i8, ptr [[START:%.*]], i64 [[TMP1]]
@@ -116,17 +116,14 @@ define void @uniform_store_i1(ptr noalias %dst, ptr noalias %start, i64 %N) {
; CHECK-NEXT: [[POINTER_PHI:%.*]] = phi ptr [ [[START]], [[VECTOR_PH]] ], [ [[PTR_IND:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr i8, ptr [[POINTER_PHI]], <32 x i64> <i64 0, i64 8, i64 16, i64 24, i64 32, i64 40, i64 48, i64 56, i64 64, i64 72, i64 80, i64 88, i64 96, i64 104, i64 112, i64 120, i64 128, i64 136, i64 144, i64 152, i64 160, i64 168, i64 176, i64 184, i64 192, i64 200, i64 208, i64 216, i64 224, i64 232, i64 240, i64 248>
-; CHECK-NEXT: [[TMP3:%.*]] = getelementptr i8, ptr [[POINTER_PHI]], <32 x i64> <i64 256, i64 264, i64 272, i64 280, i64 288, i64 296, i64 304, i64 312, i64 320, i64 328, i64 336, i64 344, i64 352, i64 360, i64 368, i64 376, i64 384, i64 392, i64 400, i64 408, i64 416, i64 424, i64 432, i64 440, i64 448, i64 456, i64 464, i64 472, i64 480, i64 488, i64 496, i64 504>
-; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i64, <32 x ptr> [[TMP2]], i64 1
-; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i64, <32 x ptr> [[TMP3]], i64 1
-; CHECK-NEXT: [[TMP6:%.*]] = icmp eq <32 x ptr> [[TMP4]], [[BROADCAST_SPLAT]]
-; CHECK-NEXT: [[TMP7:%.*]] = icmp eq <32 x ptr> [[TMP5]], [[BROADCAST_SPLAT]]
-; CHECK-NEXT: [[TMP8:%.*]] = extractelement <32 x i1> [[TMP7]], i32 31
-; CHECK-NEXT: store i1 [[TMP8]], ptr [[DST:%.*]], align 1
-; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 64
-; CHECK-NEXT: [[PTR_IND]] = getelementptr i8, ptr [[POINTER_PHI]], i64 512
-; CHECK-NEXT: [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]]
+; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds i64, <32 x ptr> [[TMP2]], i64 1
+; CHECK-NEXT: [[TMP4:%.*]] = icmp eq <32 x ptr> [[TMP3]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT: [[TMP5:%.*]] = extractelement <32 x i1> [[TMP4]], i32 31
+; CHECK-NEXT: store i1 [[TMP5]], ptr [[DST:%.*]], align 1
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 32
+; CHECK-NEXT: [[PTR_IND]] = getelementptr i8, ptr [[POINTER_PHI]], i64 256
+; CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[END:%.*]], label [[SCALAR_PH]]
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll b/llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll
index 1bcd7a2e009e0b0..d6e452e6978a90e 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll
@@ -36,10 +36,10 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %i.0 = add nsw i32 %i.0.in8, -1
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %idxprom = zext i32 %i.0 to i64
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx = getelementptr inbounds i32, ptr %B, i64 %idxprom
-; CHECK-NEXT: LV: Found an estimated cost of 11 for VF vscale x 4 For instruction: %1 = load i32, ptr %arrayidx, align 4
+; CHECK-NEXT: LV: Found an estimated cost of 20 for VF vscale x 4 For instruction: %1 = load i32, ptr %arrayidx, align 4
; CHECK-NEXT: LV: Found an estimated cost of 2 for VF vscale x 4 For instruction: %add9 = add i32 %1, 1
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx3 = getelementptr inbounds i32, ptr %A, i64 %idxprom
-; CHECK-NEXT: LV: Found an estimated cost of 11 for VF vscale x 4 For instruction: store i32 %add9, ptr %arrayidx3, align 4
+; CHECK-NEXT: LV: Found an estimated cost of 20 for VF vscale x 4 For instruction: store i32 %add9, ptr %arrayidx3, align 4
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %cmp = icmp ugt i64 %indvars.iv, 1
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %indvars.iv.next = add nsw i64 %indvars.iv, -1
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: br i1 %cmp, label %for.body, label %for.cond.cleanup.loopexit, !llvm.loop !0
@@ -57,9 +57,11 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK: ph:
; CHECK-NEXT: EMIT vp<[[TC]]> = EXPAND SCEV (zext i32 %n to i64)
; CHECK-NEXT: No successors
-; CHECK: vector.ph:
+; CHECK-EMPTY:
+; CHECK-NEXT: vector.ph:
; CHECK-NEXT: Successor(s): vector loop
-; CHECK: <x1> vector loop: {
+; CHECK-EMPTY:
+; CHECK-NEXT: <x1> vector loop: {
; CHECK-NEXT: vector.body:
; CHECK-NEXT: EMIT vp<[[CAN_IV:%.+]]> = CANONICAL-INDUCTION
; CHECK-NEXT: vp<[[DERIVED_IV:%.+]]> = DERIVED-IV ir<%n> + vp<[[CAN_IV]]> * ir<-1>
@@ -78,7 +80,8 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: No successors
; CHECK-NEXT: }
; CHECK-NEXT: Successor(s): middle.block
-; CHECK: middle.block:
+; CHECK-EMPTY:
+; CHECK-NEXT: middle.block:
; CHECK-NEXT: No successors
; CHECK-NEXT: }
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %indvars.iv = phi i64 [ %0, %for.body.preheader ], [ %indvars.iv.next, %for.body ]
@@ -86,10 +89,10 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %i.0 = add nsw i32 %i.0.in8, -1
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %idxprom = zext i32 %i.0 to i64
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx = getelementptr inbounds i32, ptr %B, i64 %idxprom
-; CHECK-NEXT: LV: Found an estimated cost of 11 for VF vscale x 4 For instruction: %1 = load i32, ptr %arrayidx, align 4
+; CHECK-NEXT: LV: Found an estimated cost of 20 for VF vscale x 4 For instruction: %1 = load i32, ptr %arrayidx, align 4
; CHECK-NEXT: LV: Found an estimated cost of 2 for VF vscale x 4 For instruction: %add9 = add i32 %1, 1
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx3 = getelementptr inbounds i32, ptr %A, i64 %idxprom
-; CHECK-NEXT: LV: Found an estimated cost of 11 for VF vscale x 4 For instruction: store i32 %add9, ptr %arrayidx3, align 4
+; CHECK-NEXT: LV: Found an estimated cost of 20 for VF vscale x 4 For instruction: store i32 %add9, ptr %arrayidx3, align 4
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %cmp = icmp ugt i64 %indvars.iv, 1
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %indvars.iv.next = add nsw i64 %indvars.iv, -1
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: br i1 %cmp, label %for.body, label %for.cond.cleanup.loopexit, !llvm.loop !0
@@ -112,7 +115,7 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 1 registers
; CHECK-NEXT: LV: The target has 31 registers of RISCV::GPRRC register class
; CHECK-NEXT: LV: The target has 32 registers of RISCV::VRRC register class
-; CHECK-NEXT: LV: Loop cost is 28
+; CHECK-NEXT: LV: Loop cost is 46
; CHECK-NEXT: LV: IC is 1
; CHECK-NEXT: LV: VF is vscale x 4
; CHECK-NEXT: LV: Not Interleaving.
@@ -122,6 +125,7 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: Executing best plan with VF=vscale x 4, UF=1
; CHECK-NEXT: LV: Interleaving disabled by the pass manager
; CHECK-NEXT: LV: Vectorizing: innermost loop.
+; CHECK-EMPTY:
;
entry:
%cmp7 = icmp sgt i32 %n, 0
@@ -176,10 +180,10 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %i.0 = add nsw i32 %i.0.in8, -1
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %idxprom = zext i32 %i.0 to i64
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx = getelementptr inbounds float, ptr %B, i64 %idxprom
-; CHECK-NEXT: LV: Found an estimated cost of 11 for VF vscale x 4 For instruction: %1 = load float, ptr %arrayidx, align 4
+; CHECK-NEXT: LV: Found an estimated cost of 20 for VF vscale x 4 For instruction: %1 = load float, ptr %arrayidx, align 4
; CHECK-NEXT: LV: Found an estimated cost of 2 for VF vscale x 4 For instruction: %conv1 = fadd float %1, 1.000000e+00
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx3 = getelementptr inbounds float, ptr %A, i64 %idxprom
-; CHECK-NEXT: LV: Found an estimated cost of 11 for VF vscale x 4 For instruction: store float %conv1, ptr %arrayidx3, align 4
+; CHECK-NEXT: LV: Found an estimated cost of 20 for VF vscale x 4 For instruction: store float %conv1, ptr %arrayidx3, align 4
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %cmp = icmp ugt i64 %indvars.iv, 1
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %indvars.iv.next = add nsw i64 %indvars.iv, -1
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: br i1 %cmp, label %for.body, label %for.cond.cleanup.loopexit, !llvm.loop !0
@@ -197,9 +201,11 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK: ph:
; CHECK-NEXT: EMIT vp<[[TC]]> = EXPAND SCEV (zext i32 %n to i64)
; CHECK-NEXT: No successors
-; CHECK: vector.ph:
+; CHECK-EMPTY:
+; CHECK-NEXT: vector.ph:
; CHECK-NEXT: Successor(s): vector loop
-; CHECK: <x1> vector loop: {
+; CHECK-EMPTY:
+; CHECK-NEXT: <x1> vector loop: {
; CHECK-NEXT: vector.body:
; CHECK-NEXT: EMIT vp<[[CAN_IV:%.+]]> = CANONICAL-INDUCTION
; CHECK-NEXT: vp<[[DERIVED_IV:%.+]]> = DERIVED-IV ir<%n> + vp<[[CAN_IV]]> * ir<-1>
@@ -218,7 +224,8 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: No successors
; CHECK-NEXT: }
; CHECK-NEXT: Successor(s): middle.block
-; CHECK: middle.block:
+; CHECK-EMPTY:
+; CHECK-NEXT: middle.block:
; CHECK-NEXT: No successors
; CHECK-NEXT: }
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %indvars.iv = phi i64 [ %0, %for.body.preheader ], [ %indvars.iv.next, %for.body ]
@@ -226,10 +233,10 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %i.0 = add nsw i32 %i.0.in8, -1
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %idxprom = zext i32 %i.0 to i64
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx = getelementptr inbounds float, ptr %B, i64 %idxprom
-; CHECK-NEXT: LV: Found an estimated cost of 11 for VF vscale x 4 For instruction: %1 = load float, ptr %arrayidx, align 4
+; CHECK-NEXT: LV: Found an estimated cost of 20 for VF vscale x 4 For instruction: %1 = load float, ptr %arrayidx, align 4
; CHECK-NEXT: LV: Found an estimated cost of 2 for VF vscale x 4 For instruction: %conv1 = fadd float %1, 1.000000e+00
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx3 = getelementptr inbounds float, ptr %A, i64 %idxprom
-; CHECK-NEXT: LV: Found an estimated cost of 11 for VF vscale x 4 For instruction: store float %conv1, ptr %arrayidx3, align 4
+; CHECK-NEXT: LV: Found an estimated cost of 20 for VF vscale x 4 For instruction: store float %conv1, ptr %arrayidx3, align 4
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %cmp = icmp ugt i64 %indvars.iv, 1
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %indvars.iv.next = add nsw i64 %indvars.iv, -1
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: br i1 %cmp, label %for.body, label %for.cond.cleanup.loopexit, !llvm.loop !0
@@ -252,7 +259,7 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 1 registers
; CHECK-NEXT: LV: The target has 31 registers of RISCV::GPRRC register class
; CHECK-NEXT: LV: The target has 32 registers of RISCV::VRRC register class
-; CHECK-NEXT: LV: Loop cost is 28
+; CHECK-NEXT: LV: Loop cost is 46
; CHECK-NEXT: LV: IC is 1
; CHECK-NEXT: LV: VF is vscale x 4
; CHECK-NEXT: LV: Not Interleaving.
>From 2b466ca0bd2386f275e711980d7f4c401789982b Mon Sep 17 00:00:00 2001
From: Simeon Krastnikov <simeon.krastnikov at imgtec.com>
Date: Wed, 29 Nov 2023 09:53:49 +0000
Subject: [PATCH 2/8] fixup! [RISCV] Fix missing scaling by LMUL in cost model
---
llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 548911a2f7a3c6e..a2df3b76465b6af 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -784,7 +784,7 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
case Intrinsic::experimental_stepvector: {
unsigned Cost = 1; // vid
auto LT = getTypeLegalizationCost(RetTy);
- return Cost + (LT.first - 1) * TLI->getLMULCost(LT.second);
+ return (Cost + (LT.first - 1)) * TLI->getLMULCost(LT.second);
}
case Intrinsic::vp_rint: {
// RISC-V target uses at least 5 instructions to lower rounding intrinsics.
@@ -1079,7 +1079,7 @@ InstructionCost RISCVTTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
// vmandn.mm v8, v8, v9
// vmand.mm v9, v0, v9
// vmor.mm v0, v9, v8
- return LT.first * TLI->getLMULCost(LT.second) * 3;
+ return LT.first * 3;
}
// vselect and max/min are supported natively.
return LT.first * TLI->getLMULCost(LT.second) * 1;
@@ -1091,7 +1091,7 @@ InstructionCost RISCVTTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
// vmandn.mm v8, v8, v9
// vmand.mm v9, v0, v9
// vmor.mm v0, v9, v8
- return LT.first * TLI->getLMULCost(LT.second) * 5;
+ return LT.first * (2 * TLI->getLMULCost(LT.second) + 3);
}
// vmv.v.x v10, a0
>From 50f94b617fd16cd4651b6b44a9ae26ea1233a8b3 Mon Sep 17 00:00:00 2001
From: Simeon Krastnikov <simeon.krastnikov at imgtec.com>
Date: Fri, 8 Dec 2023 16:30:54 +0000
Subject: [PATCH 3/8] fixup! [RISCV] Fix missing scaling by LMUL in cost model
---
.../Target/RISCV/RISCVTargetTransformInfo.cpp | 9 +++--
.../RISCV/riscv-vector-reverse.ll | 39 ++++++++-----------
2 files changed, 21 insertions(+), 27 deletions(-)
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index a2df3b76465b6af..df93f1e13bf54fc 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -528,9 +528,10 @@ InstructionCost RISCVTTIImpl::getShuffleCost(TTI::ShuffleKind Kind,
InstructionCost GatherCost =
2 + getRISCVInstructionCost(RISCV::VRGATHER_VV, LT.second, CostKind);
// Mask operation additionally required extend and truncate
- InstructionCost ExtendCost = Tp->getElementType()->isIntegerTy(1) ? 3 : 0;
- return LT.first * TLI->getLMULCost(LT.second) *
- (LenCost + GatherCost + ExtendCost);
+ InstructionCost ExtendCost = Tp->getElementType()->isIntegerTy(1)
+ ? TLI->getLMULCost(LT.second) * 3
+ : 0;
+ return LT.first * (LenCost + GatherCost + ExtendCost);
}
}
return BaseT::getShuffleCost(Kind, Tp, Mask, CostKind, Index, SubTp);
@@ -741,7 +742,7 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
// These all use the same code.
auto LT = getTypeLegalizationCost(RetTy);
if (!LT.second.isVector() && TLI->isOperationCustom(ISD::FCEIL, LT.second))
- return LT.first * TLI->getLMULCost(LT.second) * 8;
+ return LT.first * 8;
break;
}
case Intrinsic::umin:
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll b/llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll
index d6e452e6978a90e..1bcd7a2e009e0b0 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll
@@ -36,10 +36,10 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %i.0 = add nsw i32 %i.0.in8, -1
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %idxprom = zext i32 %i.0 to i64
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx = getelementptr inbounds i32, ptr %B, i64 %idxprom
-; CHECK-NEXT: LV: Found an estimated cost of 20 for VF vscale x 4 For instruction: %1 = load i32, ptr %arrayidx, align 4
+; CHECK-NEXT: LV: Found an estimated cost of 11 for VF vscale x 4 For instruction: %1 = load i32, ptr %arrayidx, align 4
; CHECK-NEXT: LV: Found an estimated cost of 2 for VF vscale x 4 For instruction: %add9 = add i32 %1, 1
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx3 = getelementptr inbounds i32, ptr %A, i64 %idxprom
-; CHECK-NEXT: LV: Found an estimated cost of 20 for VF vscale x 4 For instruction: store i32 %add9, ptr %arrayidx3, align 4
+; CHECK-NEXT: LV: Found an estimated cost of 11 for VF vscale x 4 For instruction: store i32 %add9, ptr %arrayidx3, align 4
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %cmp = icmp ugt i64 %indvars.iv, 1
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %indvars.iv.next = add nsw i64 %indvars.iv, -1
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: br i1 %cmp, label %for.body, label %for.cond.cleanup.loopexit, !llvm.loop !0
@@ -57,11 +57,9 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK: ph:
; CHECK-NEXT: EMIT vp<[[TC]]> = EXPAND SCEV (zext i32 %n to i64)
; CHECK-NEXT: No successors
-; CHECK-EMPTY:
-; CHECK-NEXT: vector.ph:
+; CHECK: vector.ph:
; CHECK-NEXT: Successor(s): vector loop
-; CHECK-EMPTY:
-; CHECK-NEXT: <x1> vector loop: {
+; CHECK: <x1> vector loop: {
; CHECK-NEXT: vector.body:
; CHECK-NEXT: EMIT vp<[[CAN_IV:%.+]]> = CANONICAL-INDUCTION
; CHECK-NEXT: vp<[[DERIVED_IV:%.+]]> = DERIVED-IV ir<%n> + vp<[[CAN_IV]]> * ir<-1>
@@ -80,8 +78,7 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: No successors
; CHECK-NEXT: }
; CHECK-NEXT: Successor(s): middle.block
-; CHECK-EMPTY:
-; CHECK-NEXT: middle.block:
+; CHECK: middle.block:
; CHECK-NEXT: No successors
; CHECK-NEXT: }
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %indvars.iv = phi i64 [ %0, %for.body.preheader ], [ %indvars.iv.next, %for.body ]
@@ -89,10 +86,10 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %i.0 = add nsw i32 %i.0.in8, -1
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %idxprom = zext i32 %i.0 to i64
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx = getelementptr inbounds i32, ptr %B, i64 %idxprom
-; CHECK-NEXT: LV: Found an estimated cost of 20 for VF vscale x 4 For instruction: %1 = load i32, ptr %arrayidx, align 4
+; CHECK-NEXT: LV: Found an estimated cost of 11 for VF vscale x 4 For instruction: %1 = load i32, ptr %arrayidx, align 4
; CHECK-NEXT: LV: Found an estimated cost of 2 for VF vscale x 4 For instruction: %add9 = add i32 %1, 1
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx3 = getelementptr inbounds i32, ptr %A, i64 %idxprom
-; CHECK-NEXT: LV: Found an estimated cost of 20 for VF vscale x 4 For instruction: store i32 %add9, ptr %arrayidx3, align 4
+; CHECK-NEXT: LV: Found an estimated cost of 11 for VF vscale x 4 For instruction: store i32 %add9, ptr %arrayidx3, align 4
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %cmp = icmp ugt i64 %indvars.iv, 1
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %indvars.iv.next = add nsw i64 %indvars.iv, -1
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: br i1 %cmp, label %for.body, label %for.cond.cleanup.loopexit, !llvm.loop !0
@@ -115,7 +112,7 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 1 registers
; CHECK-NEXT: LV: The target has 31 registers of RISCV::GPRRC register class
; CHECK-NEXT: LV: The target has 32 registers of RISCV::VRRC register class
-; CHECK-NEXT: LV: Loop cost is 46
+; CHECK-NEXT: LV: Loop cost is 28
; CHECK-NEXT: LV: IC is 1
; CHECK-NEXT: LV: VF is vscale x 4
; CHECK-NEXT: LV: Not Interleaving.
@@ -125,7 +122,6 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: Executing best plan with VF=vscale x 4, UF=1
; CHECK-NEXT: LV: Interleaving disabled by the pass manager
; CHECK-NEXT: LV: Vectorizing: innermost loop.
-; CHECK-EMPTY:
;
entry:
%cmp7 = icmp sgt i32 %n, 0
@@ -180,10 +176,10 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %i.0 = add nsw i32 %i.0.in8, -1
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %idxprom = zext i32 %i.0 to i64
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx = getelementptr inbounds float, ptr %B, i64 %idxprom
-; CHECK-NEXT: LV: Found an estimated cost of 20 for VF vscale x 4 For instruction: %1 = load float, ptr %arrayidx, align 4
+; CHECK-NEXT: LV: Found an estimated cost of 11 for VF vscale x 4 For instruction: %1 = load float, ptr %arrayidx, align 4
; CHECK-NEXT: LV: Found an estimated cost of 2 for VF vscale x 4 For instruction: %conv1 = fadd float %1, 1.000000e+00
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx3 = getelementptr inbounds float, ptr %A, i64 %idxprom
-; CHECK-NEXT: LV: Found an estimated cost of 20 for VF vscale x 4 For instruction: store float %conv1, ptr %arrayidx3, align 4
+; CHECK-NEXT: LV: Found an estimated cost of 11 for VF vscale x 4 For instruction: store float %conv1, ptr %arrayidx3, align 4
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %cmp = icmp ugt i64 %indvars.iv, 1
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %indvars.iv.next = add nsw i64 %indvars.iv, -1
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: br i1 %cmp, label %for.body, label %for.cond.cleanup.loopexit, !llvm.loop !0
@@ -201,11 +197,9 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK: ph:
; CHECK-NEXT: EMIT vp<[[TC]]> = EXPAND SCEV (zext i32 %n to i64)
; CHECK-NEXT: No successors
-; CHECK-EMPTY:
-; CHECK-NEXT: vector.ph:
+; CHECK: vector.ph:
; CHECK-NEXT: Successor(s): vector loop
-; CHECK-EMPTY:
-; CHECK-NEXT: <x1> vector loop: {
+; CHECK: <x1> vector loop: {
; CHECK-NEXT: vector.body:
; CHECK-NEXT: EMIT vp<[[CAN_IV:%.+]]> = CANONICAL-INDUCTION
; CHECK-NEXT: vp<[[DERIVED_IV:%.+]]> = DERIVED-IV ir<%n> + vp<[[CAN_IV]]> * ir<-1>
@@ -224,8 +218,7 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: No successors
; CHECK-NEXT: }
; CHECK-NEXT: Successor(s): middle.block
-; CHECK-EMPTY:
-; CHECK-NEXT: middle.block:
+; CHECK: middle.block:
; CHECK-NEXT: No successors
; CHECK-NEXT: }
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %indvars.iv = phi i64 [ %0, %for.body.preheader ], [ %indvars.iv.next, %for.body ]
@@ -233,10 +226,10 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %i.0 = add nsw i32 %i.0.in8, -1
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %idxprom = zext i32 %i.0 to i64
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx = getelementptr inbounds float, ptr %B, i64 %idxprom
-; CHECK-NEXT: LV: Found an estimated cost of 20 for VF vscale x 4 For instruction: %1 = load float, ptr %arrayidx, align 4
+; CHECK-NEXT: LV: Found an estimated cost of 11 for VF vscale x 4 For instruction: %1 = load float, ptr %arrayidx, align 4
; CHECK-NEXT: LV: Found an estimated cost of 2 for VF vscale x 4 For instruction: %conv1 = fadd float %1, 1.000000e+00
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: %arrayidx3 = getelementptr inbounds float, ptr %A, i64 %idxprom
-; CHECK-NEXT: LV: Found an estimated cost of 20 for VF vscale x 4 For instruction: store float %conv1, ptr %arrayidx3, align 4
+; CHECK-NEXT: LV: Found an estimated cost of 11 for VF vscale x 4 For instruction: store float %conv1, ptr %arrayidx3, align 4
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %cmp = icmp ugt i64 %indvars.iv, 1
; CHECK-NEXT: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %indvars.iv.next = add nsw i64 %indvars.iv, -1
; CHECK-NEXT: LV: Found an estimated cost of 0 for VF vscale x 4 For instruction: br i1 %cmp, label %for.body, label %for.cond.cleanup.loopexit, !llvm.loop !0
@@ -259,7 +252,7 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: LV(REG): RegisterClass: RISCV::GPRRC, 1 registers
; CHECK-NEXT: LV: The target has 31 registers of RISCV::GPRRC register class
; CHECK-NEXT: LV: The target has 32 registers of RISCV::VRRC register class
-; CHECK-NEXT: LV: Loop cost is 46
+; CHECK-NEXT: LV: Loop cost is 28
; CHECK-NEXT: LV: IC is 1
; CHECK-NEXT: LV: VF is vscale x 4
; CHECK-NEXT: LV: Not Interleaving.
>From 7775999f126b82be334faffd7b803430064b59d9 Mon Sep 17 00:00:00 2001
From: Simeon Krastnikov <simeon.krastnikov at imgtec.com>
Date: Mon, 11 Dec 2023 22:03:06 +0000
Subject: [PATCH 4/8] fixup! [RISCV] Fix missing scaling by LMUL in cost model
---
llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index df93f1e13bf54fc..325046d1b8dd5a6 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -750,9 +750,10 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
case Intrinsic::smin:
case Intrinsic::smax: {
auto LT = getTypeLegalizationCost(RetTy);
- if ((ST->hasVInstructions() && LT.second.isVector()) ||
- (LT.second.isScalarInteger() && ST->hasStdExtZbb()))
+ if (ST->hasVInstructions() && LT.second.isVector())
return LT.first * TLI->getLMULCost(LT.second);
+ if (LT.second.isScalarInteger() && ST->hasStdExtZbb())
+ return LT.first;
break;
}
case Intrinsic::sadd_sat:
>From 204d3287b53e1f726cda05eb3bc5eb555c03510e Mon Sep 17 00:00:00 2001
From: Simeon Krastnikov <simeon.krastnikov at imgtec.com>
Date: Wed, 3 Jan 2024 13:55:01 +0000
Subject: [PATCH 5/8] fixup! [RISCV] Fix missing scaling by LMUL in cost model
---
llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 325046d1b8dd5a6..3bccaed5c138bb4 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -811,11 +811,10 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
case Intrinsic::vp_roundtozero: {
// Rounding with static rounding mode needs two more instructions to
// swap/write FRM than vp_rint.
- unsigned Cost = 7;
auto LT = getTypeLegalizationCost(RetTy);
unsigned VPISD = getISDForVPIntrinsicID(ICA.getID());
if (TLI->isOperationCustom(VPISD, LT.second))
- return Cost * LT.first * TLI->getLMULCost(LT.second);
+ return 5 * LT.first * TLI->getLMULCost(LT.second) + 2;
break;
}
}
>From c77cd418648fe1dc0362d21cef4747288c62f766 Mon Sep 17 00:00:00 2001
From: Simeon Krastnikov <simeon.krastnikov at imgtec.com>
Date: Fri, 19 Jan 2024 16:56:39 +0000
Subject: [PATCH 6/8] fixup! [RISCV] Fix missing scaling by LMUL in cost model
---
llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 3bccaed5c138bb4..1114ef59b25104f 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -784,9 +784,8 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
}
// TODO: add more intrinsic
case Intrinsic::experimental_stepvector: {
- unsigned Cost = 1; // vid
auto LT = getTypeLegalizationCost(RetTy);
- return (Cost + (LT.first - 1)) * TLI->getLMULCost(LT.second);
+ return LT.first * TLI->getLMULCost(LT.second);
}
case Intrinsic::vp_rint: {
// RISC-V target uses at least 5 instructions to lower rounding intrinsics.
>From 5fcf221d3d1e8f8009fbd76120d3ac51cd9cb2cd Mon Sep 17 00:00:00 2001
From: Simeon Krastnikov <simeon.krastnikov at imgtec.com>
Date: Thu, 25 Jan 2024 10:38:57 +0000
Subject: [PATCH 7/8] fixup! [RISCV] Fix missing scaling by LMUL in cost model
---
llvm/test/Analysis/CostModel/RISCV/abs.ll | 40 +-
.../CostModel/RISCV/active_lane_mask.ll | 32 +-
.../CostModel/RISCV/fp-min-max-abs.ll | 28 +-
.../Analysis/CostModel/RISCV/fp-sqrt-pow.ll | 28 +-
llvm/test/Analysis/CostModel/RISCV/fround.ll | 360 ++++++-------
.../Analysis/CostModel/RISCV/int-bit-manip.ll | 252 +++++-----
.../Analysis/CostModel/RISCV/int-min-max.ll | 120 ++---
.../Analysis/CostModel/RISCV/int-sat-math.ll | 120 ++---
llvm/test/Analysis/CostModel/RISCV/rvv-cmp.ll | 476 +++++++++---------
.../CostModel/RISCV/rvv-intrinsics.ll | 104 ++--
.../Analysis/CostModel/RISCV/rvv-select.ll | 60 +--
.../Analysis/CostModel/RISCV/rvv-shuffle.ll | 4 +-
.../Analysis/CostModel/RISCV/stepvector.ll | 62 +--
.../Transforms/SLPVectorizer/RISCV/ctpop.ll | 56 ++-
14 files changed, 889 insertions(+), 853 deletions(-)
diff --git a/llvm/test/Analysis/CostModel/RISCV/abs.ll b/llvm/test/Analysis/CostModel/RISCV/abs.ll
index c9d5c8d18df851d..c10f0b09919e709 100644
--- a/llvm/test/Analysis/CostModel/RISCV/abs.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/abs.ll
@@ -44,37 +44,37 @@ declare <vscale x 64 x i8> @llvm.abs.nxv64i8(<vscale x 64 x i8>, i1)
define i32 @abs(i32 %arg) {
; CHECK-LABEL: 'abs'
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %1 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 8 x i64> @llvm.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %2 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %3 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %4 = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %5 = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %6 = call <vscale x 8 x i64> @llvm.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <2 x i32> @llvm.abs.v2i32(<2 x i32> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <4 x i32> @llvm.abs.v4i32(<4 x i32> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %10 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %9 = call <8 x i32> @llvm.abs.v8i32(<8 x i32> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %10 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %11 = call <vscale x 2 x i32> @llvm.abs.nxv2i32(<vscale x 2 x i32> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %12 = call <vscale x 4 x i32> @llvm.abs.nxv4i32(<vscale x 4 x i32> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %13 = call <vscale x 8 x i32> @llvm.abs.nxv8i32(<vscale x 8 x i32> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %14 = call <vscale x 16 x i32> @llvm.abs.nxv16i32(<vscale x 16 x i32> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %12 = call <vscale x 4 x i32> @llvm.abs.nxv4i32(<vscale x 4 x i32> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %13 = call <vscale x 8 x i32> @llvm.abs.nxv8i32(<vscale x 8 x i32> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %14 = call <vscale x 16 x i32> @llvm.abs.nxv16i32(<vscale x 16 x i32> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <2 x i16> @llvm.abs.v2i16(<2 x i16> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %16 = call <4 x i16> @llvm.abs.v4i16(<4 x i16> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <8 x i16> @llvm.abs.v8i16(<8 x i16> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %18 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %19 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %18 = call <16 x i16> @llvm.abs.v16i16(<16 x i16> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %19 = call <32 x i16> @llvm.abs.v32i16(<32 x i16> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %20 = call <vscale x 2 x i16> @llvm.abs.nxv2i16(<vscale x 2 x i16> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %21 = call <vscale x 4 x i16> @llvm.abs.nxv4i16(<vscale x 4 x i16> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %22 = call <vscale x 8 x i16> @llvm.abs.nxv8i16(<vscale x 8 x i16> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %23 = call <vscale x 16 x i16> @llvm.abs.nxv16i16(<vscale x 16 x i16> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %24 = call <vscale x 32 x i16> @llvm.abs.nxv32i16(<vscale x 32 x i16> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %22 = call <vscale x 8 x i16> @llvm.abs.nxv8i16(<vscale x 8 x i16> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %23 = call <vscale x 16 x i16> @llvm.abs.nxv16i16(<vscale x 16 x i16> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %24 = call <vscale x 32 x i16> @llvm.abs.nxv32i16(<vscale x 32 x i16> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %25 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %26 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %27 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %28 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %27 = call <32 x i8> @llvm.abs.v32i8(<32 x i8> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %28 = call <64 x i8> @llvm.abs.v64i8(<64 x i8> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %29 = call <vscale x 8 x i8> @llvm.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %30 = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %31 = call <vscale x 32 x i8> @llvm.abs.nxv32i8(<vscale x 32 x i8> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %32 = call <vscale x 64 x i8> @llvm.abs.nxv64i8(<vscale x 64 x i8> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %30 = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %31 = call <vscale x 32 x i8> @llvm.abs.nxv32i8(<vscale x 32 x i8> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %32 = call <vscale x 64 x i8> @llvm.abs.nxv64i8(<vscale x 64 x i8> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
diff --git a/llvm/test/Analysis/CostModel/RISCV/active_lane_mask.ll b/llvm/test/Analysis/CostModel/RISCV/active_lane_mask.ll
index ba62056f5851bd4..d58ada7b4fca530 100644
--- a/llvm/test/Analysis/CostModel/RISCV/active_lane_mask.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/active_lane_mask.ll
@@ -3,28 +3,28 @@
define void @get_lane_mask() {
; CHECK-LABEL: 'get_lane_mask'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %mask_nxv1i1_i64 = call <vscale x 1 x i1> @llvm.get.active.lane.mask.nxv1i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %mask_nxv1i1_i32 = call <vscale x 1 x i1> @llvm.get.active.lane.mask.nxv1i1.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 undef, i16 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 undef, i64 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 undef, i64 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 undef, i64 undef)
diff --git a/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll b/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
index f8fe84cba3231c2..6c2e5a83ce325af 100644
--- a/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
@@ -7,30 +7,30 @@ define void @fabs() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %9 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %10 = call float @llvm.fabs.f32(float undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x float> @llvm.fabs.v2f32(<2 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %14 = call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 1 x float> @llvm.fabs.nxv1f32(<vscale x 1 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 2 x float> @llvm.fabs.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 4 x float> @llvm.fabs.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 8 x float> @llvm.fabs.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 16 x float> @llvm.fabs.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 4 x float> @llvm.fabs.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 8 x float> @llvm.fabs.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %19 = call <vscale x 16 x float> @llvm.fabs.nxv16f32(<vscale x 16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call double @llvm.fabs.f64(double undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <16 x double> @llvm.fabs.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %22 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %23 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %24 = call <16 x double> @llvm.fabs.v16f64(<16 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 1 x double> @llvm.fabs.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 2 x double> @llvm.fabs.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 4 x double> @llvm.fabs.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 8 x double> @llvm.fabs.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %26 = call <vscale x 2 x double> @llvm.fabs.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %27 = call <vscale x 4 x double> @llvm.fabs.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %28 = call <vscale x 8 x double> @llvm.fabs.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
diff --git a/llvm/test/Analysis/CostModel/RISCV/fp-sqrt-pow.ll b/llvm/test/Analysis/CostModel/RISCV/fp-sqrt-pow.ll
index 71e98e5acde89e4..c30bbd2964bd1a7 100644
--- a/llvm/test/Analysis/CostModel/RISCV/fp-sqrt-pow.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/fp-sqrt-pow.ll
@@ -7,30 +7,30 @@ define void @sqrt() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x half> @llvm.sqrt.v2f16(<2 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x half> @llvm.sqrt.v4f16(<4 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x half> @llvm.sqrt.v8f16(<8 x half> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x half> @llvm.sqrt.v16f16(<16 x half> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x half> @llvm.sqrt.v16f16(<16 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.sqrt.nxv2f16(<vscale x 2 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.sqrt.nxv4f16(<vscale x 4 x half> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.sqrt.nxv8f16(<vscale x 8 x half> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.sqrt.nxv16f16(<vscale x 16 x half> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.sqrt.nxv8f16(<vscale x 8 x half> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %9 = call <vscale x 16 x half> @llvm.sqrt.nxv16f16(<vscale x 16 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %10 = call float @llvm.sqrt.f32(float undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x float> @llvm.sqrt.v2f32(<2 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %14 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 1 x float> @llvm.sqrt.nxv1f32(<vscale x 1 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 2 x float> @llvm.sqrt.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 8 x float> @llvm.sqrt.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 16 x float> @llvm.sqrt.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 8 x float> @llvm.sqrt.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %19 = call <vscale x 16 x float> @llvm.sqrt.nxv16f32(<vscale x 16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call double @llvm.sqrt.f64(double undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <16 x double> @llvm.sqrt.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %22 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %23 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %24 = call <16 x double> @llvm.sqrt.v16f64(<16 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 1 x double> @llvm.sqrt.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 4 x double> @llvm.sqrt.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 8 x double> @llvm.sqrt.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %26 = call <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %27 = call <vscale x 4 x double> @llvm.sqrt.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %28 = call <vscale x 8 x double> @llvm.sqrt.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call half @llvm.sqrt.f16(half undef)
diff --git a/llvm/test/Analysis/CostModel/RISCV/fround.ll b/llvm/test/Analysis/CostModel/RISCV/fround.ll
index 71dd64d7651280b..db5455801c3105d 100644
--- a/llvm/test/Analysis/CostModel/RISCV/fround.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/fround.ll
@@ -6,22 +6,22 @@ define void @floor() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %1 = call float @llvm.floor.f32(float undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %2 = call <2 x float> @llvm.floor.v2f32(<2 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %3 = call <4 x float> @llvm.floor.v4f32(<4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %4 = call <8 x float> @llvm.floor.v8f32(<8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %5 = call <16 x float> @llvm.floor.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %4 = call <8 x float> @llvm.floor.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %5 = call <16 x float> @llvm.floor.v16f32(<16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %6 = call <vscale x 1 x float> @llvm.floor.nxv1f32(<vscale x 1 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %7 = call <vscale x 2 x float> @llvm.floor.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %8 = call <vscale x 4 x float> @llvm.floor.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %9 = call <vscale x 8 x float> @llvm.floor.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %10 = call <vscale x 16 x float> @llvm.floor.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %8 = call <vscale x 4 x float> @llvm.floor.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %9 = call <vscale x 8 x float> @llvm.floor.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %10 = call <vscale x 16 x float> @llvm.floor.nxv16f32(<vscale x 16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %11 = call double @llvm.floor.f64(double undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %12 = call <2 x double> @llvm.floor.v2f64(<2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %13 = call <4 x double> @llvm.floor.v4f64(<4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %14 = call <8 x double> @llvm.floor.v8f64(<8 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %15 = call <16 x double> @llvm.floor.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %13 = call <4 x double> @llvm.floor.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %14 = call <8 x double> @llvm.floor.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %15 = call <16 x double> @llvm.floor.v16f64(<16 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 1 x double> @llvm.floor.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 2 x double> @llvm.floor.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 4 x double> @llvm.floor.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %19 = call <vscale x 8 x double> @llvm.floor.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %17 = call <vscale x 2 x double> @llvm.floor.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %18 = call <vscale x 4 x double> @llvm.floor.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %19 = call <vscale x 8 x double> @llvm.floor.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call float @llvm.floor.f32(float undef)
@@ -51,22 +51,22 @@ define void @ceil() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %1 = call float @llvm.ceil.f32(float undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %2 = call <2 x float> @llvm.ceil.v2f32(<2 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %3 = call <4 x float> @llvm.ceil.v4f32(<4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %4 = call <8 x float> @llvm.ceil.v8f32(<8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %5 = call <16 x float> @llvm.ceil.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %4 = call <8 x float> @llvm.ceil.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %5 = call <16 x float> @llvm.ceil.v16f32(<16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %6 = call <vscale x 1 x float> @llvm.ceil.nxv1f32(<vscale x 1 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %7 = call <vscale x 2 x float> @llvm.ceil.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %8 = call <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %9 = call <vscale x 8 x float> @llvm.ceil.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %10 = call <vscale x 16 x float> @llvm.ceil.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %8 = call <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %9 = call <vscale x 8 x float> @llvm.ceil.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %10 = call <vscale x 16 x float> @llvm.ceil.nxv16f32(<vscale x 16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %11 = call double @llvm.ceil.f64(double undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %12 = call <2 x double> @llvm.ceil.v2f64(<2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %13 = call <4 x double> @llvm.ceil.v4f64(<4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %14 = call <8 x double> @llvm.ceil.v8f64(<8 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %15 = call <16 x double> @llvm.ceil.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %13 = call <4 x double> @llvm.ceil.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %14 = call <8 x double> @llvm.ceil.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %15 = call <16 x double> @llvm.ceil.v16f64(<16 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 1 x double> @llvm.ceil.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 4 x double> @llvm.ceil.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %19 = call <vscale x 8 x double> @llvm.ceil.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %17 = call <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %18 = call <vscale x 4 x double> @llvm.ceil.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %19 = call <vscale x 8 x double> @llvm.ceil.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call float @llvm.ceil.f32(float undef)
@@ -96,22 +96,22 @@ define void @trunc() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %1 = call float @llvm.trunc.f32(float undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %2 = call <2 x float> @llvm.trunc.v2f32(<2 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %3 = call <4 x float> @llvm.trunc.v4f32(<4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %4 = call <8 x float> @llvm.trunc.v8f32(<8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %5 = call <16 x float> @llvm.trunc.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %4 = call <8 x float> @llvm.trunc.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %5 = call <16 x float> @llvm.trunc.v16f32(<16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 1 x float> @llvm.trunc.nxv1f32(<vscale x 1 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 2 x float> @llvm.trunc.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 4 x float> @llvm.trunc.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %9 = call <vscale x 8 x float> @llvm.trunc.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call <vscale x 16 x float> @llvm.trunc.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %8 = call <vscale x 4 x float> @llvm.trunc.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %9 = call <vscale x 8 x float> @llvm.trunc.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %10 = call <vscale x 16 x float> @llvm.trunc.nxv16f32(<vscale x 16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %11 = call double @llvm.trunc.f64(double undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <2 x double> @llvm.trunc.v2f64(<2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <4 x double> @llvm.trunc.v4f64(<4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <8 x double> @llvm.trunc.v8f64(<8 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <16 x double> @llvm.trunc.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %13 = call <4 x double> @llvm.trunc.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %14 = call <8 x double> @llvm.trunc.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %15 = call <16 x double> @llvm.trunc.v16f64(<16 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 1 x double> @llvm.trunc.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 2 x double> @llvm.trunc.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %18 = call <vscale x 4 x double> @llvm.trunc.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %19 = call <vscale x 8 x double> @llvm.trunc.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %17 = call <vscale x 2 x double> @llvm.trunc.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %18 = call <vscale x 4 x double> @llvm.trunc.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %19 = call <vscale x 8 x double> @llvm.trunc.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call float @llvm.trunc.f32(float undef)
@@ -141,22 +141,22 @@ define void @rint() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %1 = call float @llvm.rint.f32(float undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %2 = call <2 x float> @llvm.rint.v2f32(<2 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %3 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %4 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %5 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %4 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %5 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 1 x float> @llvm.rint.nxv1f32(<vscale x 1 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 2 x float> @llvm.rint.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 4 x float> @llvm.rint.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %9 = call <vscale x 8 x float> @llvm.rint.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call <vscale x 16 x float> @llvm.rint.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %8 = call <vscale x 4 x float> @llvm.rint.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %9 = call <vscale x 8 x float> @llvm.rint.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %10 = call <vscale x 16 x float> @llvm.rint.nxv16f32(<vscale x 16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %11 = call double @llvm.rint.f64(double undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <16 x double> @llvm.rint.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %13 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %14 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %15 = call <16 x double> @llvm.rint.v16f64(<16 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 1 x double> @llvm.rint.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 2 x double> @llvm.rint.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %18 = call <vscale x 4 x double> @llvm.rint.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %19 = call <vscale x 8 x double> @llvm.rint.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %17 = call <vscale x 2 x double> @llvm.rint.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %18 = call <vscale x 4 x double> @llvm.rint.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %19 = call <vscale x 8 x double> @llvm.rint.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call float @llvm.rint.f32(float undef)
@@ -185,23 +185,23 @@ define void @lrint() {
; CHECK-LABEL: 'lrint'
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call i64 @llvm.lrint.i64.f32(float undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x i64> @llvm.lrint.v2i64.v2f32(<2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x i64> @llvm.lrint.v4i64.v4f32(<4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x i64> @llvm.lrint.v8i64.v8f32(<8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x i64> @llvm.lrint.v16i64.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <4 x i64> @llvm.lrint.v4i64.v4f32(<4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %4 = call <8 x i64> @llvm.lrint.v8i64.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %5 = call <16 x i64> @llvm.lrint.v16i64.v16f32(<16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 1 x i64> @llvm.lrint.nxv1i64.nxv1f32(<vscale x 1 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x i64> @llvm.lrint.nxv2i64.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x i64> @llvm.lrint.nxv4i64.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x i64> @llvm.lrint.nxv8i64.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %10 = call <vscale x 16 x i64> @llvm.lrint.nxv16i64.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 2 x i64> @llvm.lrint.nxv2i64.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %8 = call <vscale x 4 x i64> @llvm.lrint.nxv4i64.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %9 = call <vscale x 8 x i64> @llvm.lrint.nxv8i64.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %10 = call <vscale x 16 x i64> @llvm.lrint.nxv16i64.nxv16f32(<vscale x 16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call i64 @llvm.lrint.i64.f64(double undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x i64> @llvm.lrint.v2i64.v2f64(<2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x i64> @llvm.lrint.v4i64.v4f64(<4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x i64> @llvm.lrint.v8i64.v8f64(<8 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x i64> @llvm.lrint.v16i64.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %13 = call <4 x i64> @llvm.lrint.v4i64.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %14 = call <8 x i64> @llvm.lrint.v8i64.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %15 = call <16 x i64> @llvm.lrint.v16i64.v16f64(<16 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x i64> @llvm.lrint.nxv1i64.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x i64> @llvm.lrint.nxv2i64.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x i64> @llvm.lrint.nxv4i64.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x i64> @llvm.lrint.nxv8i64.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 2 x i64> @llvm.lrint.nxv2i64.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 4 x i64> @llvm.lrint.nxv4i64.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %19 = call <vscale x 8 x i64> @llvm.lrint.nxv8i64.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call i64 @llvm.lrint.i64.f32(float undef)
@@ -230,23 +230,23 @@ define void @llrint() {
; CHECK-LABEL: 'llrint'
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call i64 @llvm.llrint.i64.f32(float undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x i64> @llvm.llrint.v2i64.v2f32(<2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <4 x i64> @llvm.llrint.v4i64.v4f32(<4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %4 = call <8 x i64> @llvm.llrint.v8i64.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %5 = call <16 x i64> @llvm.llrint.v16i64.v16f32(<16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 1 x i64> @llvm.llrint.nxv1i64.nxv1f32(<vscale x 1 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x i64> @llvm.llrint.nxv2i64.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x i64> @llvm.llrint.nxv4i64.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x i64> @llvm.llrint.nxv8i64.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %10 = call <vscale x 16 x i64> @llvm.llrint.nxv16i64.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 2 x i64> @llvm.llrint.nxv2i64.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %8 = call <vscale x 4 x i64> @llvm.llrint.nxv4i64.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %9 = call <vscale x 8 x i64> @llvm.llrint.nxv8i64.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %10 = call <vscale x 16 x i64> @llvm.llrint.nxv16i64.nxv16f32(<vscale x 16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call i64 @llvm.llrint.i64.f64(double undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x i64> @llvm.llrint.v2i64.v2f64(<2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x i64> @llvm.llrint.v16i64.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %13 = call <4 x i64> @llvm.llrint.v4i64.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %14 = call <8 x i64> @llvm.llrint.v8i64.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %15 = call <16 x i64> @llvm.llrint.v16i64.v16f64(<16 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x i64> @llvm.llrint.nxv1i64.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x i64> @llvm.llrint.nxv2i64.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x i64> @llvm.llrint.nxv4i64.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x i64> @llvm.llrint.nxv8i64.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 2 x i64> @llvm.llrint.nxv2i64.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 4 x i64> @llvm.llrint.nxv4i64.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %19 = call <vscale x 8 x i64> @llvm.llrint.nxv8i64.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call i64 @llvm.llrint.i64.f32(float undef)
@@ -276,22 +276,22 @@ define void @nearbyint() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %1 = call float @llvm.nearbyint.f32(float undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %2 = call <2 x float> @llvm.nearbyint.v2f32(<2 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %3 = call <4 x float> @llvm.nearbyint.v4f32(<4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %4 = call <8 x float> @llvm.nearbyint.v8f32(<8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %5 = call <16 x float> @llvm.nearbyint.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %4 = call <8 x float> @llvm.nearbyint.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %5 = call <16 x float> @llvm.nearbyint.v16f32(<16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %6 = call <vscale x 1 x float> @llvm.nearbyint.nxv1f32(<vscale x 1 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %7 = call <vscale x 2 x float> @llvm.nearbyint.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %8 = call <vscale x 4 x float> @llvm.nearbyint.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %9 = call <vscale x 8 x float> @llvm.nearbyint.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %10 = call <vscale x 16 x float> @llvm.nearbyint.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %8 = call <vscale x 4 x float> @llvm.nearbyint.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %9 = call <vscale x 8 x float> @llvm.nearbyint.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %10 = call <vscale x 16 x float> @llvm.nearbyint.nxv16f32(<vscale x 16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.nearbyint.f64(double undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %12 = call <2 x double> @llvm.nearbyint.v2f64(<2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %13 = call <4 x double> @llvm.nearbyint.v4f64(<4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %14 = call <8 x double> @llvm.nearbyint.v8f64(<8 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %15 = call <16 x double> @llvm.nearbyint.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %13 = call <4 x double> @llvm.nearbyint.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %14 = call <8 x double> @llvm.nearbyint.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %15 = call <16 x double> @llvm.nearbyint.v16f64(<16 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 1 x double> @llvm.nearbyint.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 2 x double> @llvm.nearbyint.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 4 x double> @llvm.nearbyint.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %19 = call <vscale x 8 x double> @llvm.nearbyint.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %17 = call <vscale x 2 x double> @llvm.nearbyint.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %18 = call <vscale x 4 x double> @llvm.nearbyint.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %19 = call <vscale x 8 x double> @llvm.nearbyint.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call float @llvm.nearbyint.f32(float undef)
@@ -321,22 +321,22 @@ define void @round() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %1 = call float @llvm.round.f32(float undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %2 = call <2 x float> @llvm.round.v2f32(<2 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %3 = call <4 x float> @llvm.round.v4f32(<4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %4 = call <8 x float> @llvm.round.v8f32(<8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %5 = call <16 x float> @llvm.round.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %4 = call <8 x float> @llvm.round.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %5 = call <16 x float> @llvm.round.v16f32(<16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %6 = call <vscale x 1 x float> @llvm.round.nxv1f32(<vscale x 1 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %7 = call <vscale x 2 x float> @llvm.round.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %8 = call <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %9 = call <vscale x 8 x float> @llvm.round.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %10 = call <vscale x 16 x float> @llvm.round.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %8 = call <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %9 = call <vscale x 8 x float> @llvm.round.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %10 = call <vscale x 16 x float> @llvm.round.nxv16f32(<vscale x 16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %11 = call double @llvm.round.f64(double undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %12 = call <2 x double> @llvm.round.v2f64(<2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %13 = call <4 x double> @llvm.round.v4f64(<4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %14 = call <8 x double> @llvm.round.v8f64(<8 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %15 = call <16 x double> @llvm.round.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %13 = call <4 x double> @llvm.round.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %14 = call <8 x double> @llvm.round.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %15 = call <16 x double> @llvm.round.v16f64(<16 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 1 x double> @llvm.round.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 4 x double> @llvm.round.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %19 = call <vscale x 8 x double> @llvm.round.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %17 = call <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %18 = call <vscale x 4 x double> @llvm.round.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %19 = call <vscale x 8 x double> @llvm.round.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call float @llvm.round.f32(float undef)
@@ -366,22 +366,22 @@ define void @roundeven() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %1 = call float @llvm.roundeven.f32(float undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %2 = call <2 x float> @llvm.roundeven.v2f32(<2 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %3 = call <4 x float> @llvm.roundeven.v4f32(<4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %4 = call <8 x float> @llvm.roundeven.v8f32(<8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %5 = call <16 x float> @llvm.roundeven.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %4 = call <8 x float> @llvm.roundeven.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %5 = call <16 x float> @llvm.roundeven.v16f32(<16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %6 = call <vscale x 1 x float> @llvm.roundeven.nxv1f32(<vscale x 1 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %7 = call <vscale x 2 x float> @llvm.roundeven.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %8 = call <vscale x 4 x float> @llvm.roundeven.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %9 = call <vscale x 8 x float> @llvm.roundeven.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %10 = call <vscale x 16 x float> @llvm.roundeven.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %8 = call <vscale x 4 x float> @llvm.roundeven.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %9 = call <vscale x 8 x float> @llvm.roundeven.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %10 = call <vscale x 16 x float> @llvm.roundeven.nxv16f32(<vscale x 16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %11 = call double @llvm.roundeven.f64(double undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %12 = call <2 x double> @llvm.roundeven.v2f64(<2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %13 = call <4 x double> @llvm.roundeven.v4f64(<4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %14 = call <8 x double> @llvm.roundeven.v8f64(<8 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %15 = call <16 x double> @llvm.roundeven.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %13 = call <4 x double> @llvm.roundeven.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %14 = call <8 x double> @llvm.roundeven.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %15 = call <16 x double> @llvm.roundeven.v16f64(<16 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 1 x double> @llvm.roundeven.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 2 x double> @llvm.roundeven.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 4 x double> @llvm.roundeven.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %19 = call <vscale x 8 x double> @llvm.roundeven.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %17 = call <vscale x 2 x double> @llvm.roundeven.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %18 = call <vscale x 4 x double> @llvm.roundeven.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 72 for instruction: %19 = call <vscale x 8 x double> @llvm.roundeven.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call float @llvm.roundeven.f32(float undef)
@@ -410,21 +410,21 @@ define void @vp_ceil() {
; CHECK-LABEL: 'vp_ceil'
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %1 = call <2 x float> @llvm.vp.ceil.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %2 = call <4 x float> @llvm.vp.ceil.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %3 = call <8 x float> @llvm.vp.ceil.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %4 = call <16 x float> @llvm.vp.ceil.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %3 = call <8 x float> @llvm.vp.ceil.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %4 = call <16 x float> @llvm.vp.ceil.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %5 = call <vscale x 1 x float> @llvm.vp.ceil.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 2 x float> @llvm.vp.ceil.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 4 x float> @llvm.vp.ceil.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 8 x float> @llvm.vp.ceil.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %9 = call <vscale x 16 x float> @llvm.vp.ceil.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %7 = call <vscale x 4 x float> @llvm.vp.ceil.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %8 = call <vscale x 8 x float> @llvm.vp.ceil.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %9 = call <vscale x 16 x float> @llvm.vp.ceil.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call <2 x double> @llvm.vp.ceil.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %11 = call <4 x double> @llvm.vp.ceil.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <8 x double> @llvm.vp.ceil.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <16 x double> @llvm.vp.ceil.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %11 = call <4 x double> @llvm.vp.ceil.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %12 = call <8 x double> @llvm.vp.ceil.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %13 = call <16 x double> @llvm.vp.ceil.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <vscale x 1 x double> @llvm.vp.ceil.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <vscale x 2 x double> @llvm.vp.ceil.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 4 x double> @llvm.vp.ceil.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 8 x double> @llvm.vp.ceil.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %15 = call <vscale x 2 x double> @llvm.vp.ceil.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %16 = call <vscale x 4 x double> @llvm.vp.ceil.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %17 = call <vscale x 8 x double> @llvm.vp.ceil.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x float> @llvm.vp.ceil.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
@@ -451,21 +451,21 @@ define void @vp_floor() {
; CHECK-LABEL: 'vp_floor'
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %1 = call <2 x float> @llvm.vp.floor.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %2 = call <4 x float> @llvm.vp.floor.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %3 = call <8 x float> @llvm.vp.floor.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %4 = call <16 x float> @llvm.vp.floor.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %3 = call <8 x float> @llvm.vp.floor.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %4 = call <16 x float> @llvm.vp.floor.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %5 = call <vscale x 1 x float> @llvm.vp.floor.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 2 x float> @llvm.vp.floor.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 4 x float> @llvm.vp.floor.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 8 x float> @llvm.vp.floor.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %9 = call <vscale x 16 x float> @llvm.vp.floor.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %7 = call <vscale x 4 x float> @llvm.vp.floor.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %8 = call <vscale x 8 x float> @llvm.vp.floor.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %9 = call <vscale x 16 x float> @llvm.vp.floor.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call <2 x double> @llvm.vp.floor.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %11 = call <4 x double> @llvm.vp.floor.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <8 x double> @llvm.vp.floor.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <16 x double> @llvm.vp.floor.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %11 = call <4 x double> @llvm.vp.floor.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %12 = call <8 x double> @llvm.vp.floor.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %13 = call <16 x double> @llvm.vp.floor.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <vscale x 1 x double> @llvm.vp.floor.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <vscale x 2 x double> @llvm.vp.floor.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 4 x double> @llvm.vp.floor.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 8 x double> @llvm.vp.floor.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %15 = call <vscale x 2 x double> @llvm.vp.floor.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %16 = call <vscale x 4 x double> @llvm.vp.floor.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %17 = call <vscale x 8 x double> @llvm.vp.floor.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x float> @llvm.vp.floor.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
@@ -492,21 +492,21 @@ define void @vp_round() {
; CHECK-LABEL: 'vp_round'
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %1 = call <2 x float> @llvm.vp.round.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %2 = call <4 x float> @llvm.vp.round.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %3 = call <8 x float> @llvm.vp.round.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %4 = call <16 x float> @llvm.vp.round.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %3 = call <8 x float> @llvm.vp.round.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %4 = call <16 x float> @llvm.vp.round.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %5 = call <vscale x 1 x float> @llvm.vp.round.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 2 x float> @llvm.vp.round.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 4 x float> @llvm.vp.round.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 8 x float> @llvm.vp.round.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %9 = call <vscale x 16 x float> @llvm.vp.round.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %7 = call <vscale x 4 x float> @llvm.vp.round.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %8 = call <vscale x 8 x float> @llvm.vp.round.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %9 = call <vscale x 16 x float> @llvm.vp.round.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call <2 x double> @llvm.vp.round.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %11 = call <4 x double> @llvm.vp.round.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <8 x double> @llvm.vp.round.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <16 x double> @llvm.vp.round.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %11 = call <4 x double> @llvm.vp.round.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %12 = call <8 x double> @llvm.vp.round.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %13 = call <16 x double> @llvm.vp.round.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <vscale x 1 x double> @llvm.vp.round.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <vscale x 2 x double> @llvm.vp.round.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 4 x double> @llvm.vp.round.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 8 x double> @llvm.vp.round.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %15 = call <vscale x 2 x double> @llvm.vp.round.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %16 = call <vscale x 4 x double> @llvm.vp.round.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %17 = call <vscale x 8 x double> @llvm.vp.round.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x float> @llvm.vp.round.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
@@ -533,21 +533,21 @@ define void @vp_roundeven() {
; CHECK-LABEL: 'vp_roundeven'
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %1 = call <2 x float> @llvm.vp.roundeven.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %2 = call <4 x float> @llvm.vp.roundeven.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %3 = call <8 x float> @llvm.vp.roundeven.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %4 = call <16 x float> @llvm.vp.roundeven.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %3 = call <8 x float> @llvm.vp.roundeven.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %4 = call <16 x float> @llvm.vp.roundeven.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %5 = call <vscale x 1 x float> @llvm.vp.roundeven.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 2 x float> @llvm.vp.roundeven.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 4 x float> @llvm.vp.roundeven.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 8 x float> @llvm.vp.roundeven.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %9 = call <vscale x 16 x float> @llvm.vp.roundeven.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %7 = call <vscale x 4 x float> @llvm.vp.roundeven.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %8 = call <vscale x 8 x float> @llvm.vp.roundeven.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %9 = call <vscale x 16 x float> @llvm.vp.roundeven.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call <2 x double> @llvm.vp.roundeven.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %11 = call <4 x double> @llvm.vp.roundeven.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <8 x double> @llvm.vp.roundeven.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <16 x double> @llvm.vp.roundeven.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %11 = call <4 x double> @llvm.vp.roundeven.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %12 = call <8 x double> @llvm.vp.roundeven.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %13 = call <16 x double> @llvm.vp.roundeven.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <vscale x 1 x double> @llvm.vp.roundeven.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <vscale x 2 x double> @llvm.vp.roundeven.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 4 x double> @llvm.vp.roundeven.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 8 x double> @llvm.vp.roundeven.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %15 = call <vscale x 2 x double> @llvm.vp.roundeven.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %16 = call <vscale x 4 x double> @llvm.vp.roundeven.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %17 = call <vscale x 8 x double> @llvm.vp.roundeven.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x float> @llvm.vp.roundeven.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
@@ -574,21 +574,21 @@ define void @vp_roundtozero() {
; CHECK-LABEL: 'vp_roundtozero'
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %1 = call <2 x float> @llvm.vp.roundtozero.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %2 = call <4 x float> @llvm.vp.roundtozero.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %3 = call <8 x float> @llvm.vp.roundtozero.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %4 = call <16 x float> @llvm.vp.roundtozero.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %3 = call <8 x float> @llvm.vp.roundtozero.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %4 = call <16 x float> @llvm.vp.roundtozero.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %5 = call <vscale x 1 x float> @llvm.vp.roundtozero.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 2 x float> @llvm.vp.roundtozero.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 4 x float> @llvm.vp.roundtozero.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 8 x float> @llvm.vp.roundtozero.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %9 = call <vscale x 16 x float> @llvm.vp.roundtozero.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %7 = call <vscale x 4 x float> @llvm.vp.roundtozero.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %8 = call <vscale x 8 x float> @llvm.vp.roundtozero.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %9 = call <vscale x 16 x float> @llvm.vp.roundtozero.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call <2 x double> @llvm.vp.roundtozero.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %11 = call <4 x double> @llvm.vp.roundtozero.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <8 x double> @llvm.vp.roundtozero.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <16 x double> @llvm.vp.roundtozero.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %11 = call <4 x double> @llvm.vp.roundtozero.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %12 = call <8 x double> @llvm.vp.roundtozero.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %13 = call <16 x double> @llvm.vp.roundtozero.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <vscale x 1 x double> @llvm.vp.roundtozero.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <vscale x 2 x double> @llvm.vp.roundtozero.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 4 x double> @llvm.vp.roundtozero.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 8 x double> @llvm.vp.roundtozero.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %15 = call <vscale x 2 x double> @llvm.vp.roundtozero.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %16 = call <vscale x 4 x double> @llvm.vp.roundtozero.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %17 = call <vscale x 8 x double> @llvm.vp.roundtozero.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x float> @llvm.vp.roundtozero.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
@@ -615,21 +615,21 @@ define void @vp_rint() {
; CHECK-LABEL: 'vp_rint'
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %1 = call <2 x float> @llvm.vp.rint.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %2 = call <4 x float> @llvm.vp.rint.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %3 = call <8 x float> @llvm.vp.rint.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %4 = call <16 x float> @llvm.vp.rint.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %3 = call <8 x float> @llvm.vp.rint.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %4 = call <16 x float> @llvm.vp.rint.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %5 = call <vscale x 1 x float> @llvm.vp.rint.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %6 = call <vscale x 2 x float> @llvm.vp.rint.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %7 = call <vscale x 4 x float> @llvm.vp.rint.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %8 = call <vscale x 8 x float> @llvm.vp.rint.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %9 = call <vscale x 16 x float> @llvm.vp.rint.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %7 = call <vscale x 4 x float> @llvm.vp.rint.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %8 = call <vscale x 8 x float> @llvm.vp.rint.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %9 = call <vscale x 16 x float> @llvm.vp.rint.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %10 = call <2 x double> @llvm.vp.rint.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %11 = call <4 x double> @llvm.vp.rint.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %12 = call <8 x double> @llvm.vp.rint.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %13 = call <16 x double> @llvm.vp.rint.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %11 = call <4 x double> @llvm.vp.rint.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %12 = call <8 x double> @llvm.vp.rint.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %13 = call <16 x double> @llvm.vp.rint.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %14 = call <vscale x 1 x double> @llvm.vp.rint.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %15 = call <vscale x 2 x double> @llvm.vp.rint.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %16 = call <vscale x 4 x double> @llvm.vp.rint.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %17 = call <vscale x 8 x double> @llvm.vp.rint.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %15 = call <vscale x 2 x double> @llvm.vp.rint.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %16 = call <vscale x 4 x double> @llvm.vp.rint.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %17 = call <vscale x 8 x double> @llvm.vp.rint.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x float> @llvm.vp.rint.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
@@ -656,21 +656,21 @@ define void @vp_nearbyint() {
; CHECK-LABEL: 'vp_nearbyint'
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %1 = call <2 x float> @llvm.vp.nearbyint.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %2 = call <4 x float> @llvm.vp.nearbyint.v4f32(<4 x float> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %3 = call <8 x float> @llvm.vp.nearbyint.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %4 = call <16 x float> @llvm.vp.nearbyint.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %3 = call <8 x float> @llvm.vp.nearbyint.v8f32(<8 x float> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %4 = call <16 x float> @llvm.vp.nearbyint.v16f32(<16 x float> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %5 = call <vscale x 1 x float> @llvm.vp.nearbyint.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 2 x float> @llvm.vp.nearbyint.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 4 x float> @llvm.vp.nearbyint.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 8 x float> @llvm.vp.nearbyint.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %9 = call <vscale x 16 x float> @llvm.vp.nearbyint.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %7 = call <vscale x 4 x float> @llvm.vp.nearbyint.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %8 = call <vscale x 8 x float> @llvm.vp.nearbyint.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %9 = call <vscale x 16 x float> @llvm.vp.nearbyint.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call <2 x double> @llvm.vp.nearbyint.v2f64(<2 x double> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %11 = call <4 x double> @llvm.vp.nearbyint.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <8 x double> @llvm.vp.nearbyint.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <16 x double> @llvm.vp.nearbyint.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %11 = call <4 x double> @llvm.vp.nearbyint.v4f64(<4 x double> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %12 = call <8 x double> @llvm.vp.nearbyint.v8f64(<8 x double> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %13 = call <16 x double> @llvm.vp.nearbyint.v16f64(<16 x double> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <vscale x 1 x double> @llvm.vp.nearbyint.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <vscale x 2 x double> @llvm.vp.nearbyint.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 4 x double> @llvm.vp.nearbyint.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 8 x double> @llvm.vp.nearbyint.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %15 = call <vscale x 2 x double> @llvm.vp.nearbyint.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %16 = call <vscale x 4 x double> @llvm.vp.nearbyint.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %17 = call <vscale x 8 x double> @llvm.vp.nearbyint.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x float> @llvm.vp.nearbyint.v2f32(<2 x float> undef, <2 x i1> undef, i32 undef)
diff --git a/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll b/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll
index 380f65b19b8fa16..def39b01de74709 100644
--- a/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll
@@ -9,32 +9,32 @@ define void @bswap() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %2 = call <2 x i16> @llvm.bswap.v2i16(<2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %3 = call <4 x i16> @llvm.bswap.v4i16(<4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %4 = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %5 = call <16 x i16> @llvm.bswap.v16i16(<16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %5 = call <16 x i16> @llvm.bswap.v16i16(<16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %6 = call <vscale x 1 x i16> @llvm.bswap.nxv1i16(<vscale x 1 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %7 = call <vscale x 2 x i16> @llvm.bswap.nxv2i16(<vscale x 2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %8 = call <vscale x 4 x i16> @llvm.bswap.nxv4i16(<vscale x 4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %9 = call <vscale x 8 x i16> @llvm.bswap.nxv8i16(<vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %10 = call <vscale x 16 x i16> @llvm.bswap.nxv16i16(<vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %9 = call <vscale x 8 x i16> @llvm.bswap.nxv8i16(<vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %10 = call <vscale x 16 x i16> @llvm.bswap.nxv16i16(<vscale x 16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %11 = call i32 @llvm.bswap.i32(i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %12 = call <2 x i32> @llvm.bswap.v2i32(<2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %13 = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %14 = call <8 x i32> @llvm.bswap.v8i32(<8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %15 = call <16 x i32> @llvm.bswap.v16i32(<16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %14 = call <8 x i32> @llvm.bswap.v8i32(<8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %15 = call <16 x i32> @llvm.bswap.v16i32(<16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %16 = call <vscale x 1 x i32> @llvm.bswap.nxv1i32(<vscale x 1 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %17 = call <vscale x 2 x i32> @llvm.bswap.nxv2i32(<vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %18 = call <vscale x 4 x i32> @llvm.bswap.nxv4i32(<vscale x 4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %19 = call <vscale x 8 x i32> @llvm.bswap.nxv8i32(<vscale x 8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %20 = call <vscale x 16 x i32> @llvm.bswap.nxv16i32(<vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %18 = call <vscale x 4 x i32> @llvm.bswap.nxv4i32(<vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %19 = call <vscale x 8 x i32> @llvm.bswap.nxv8i32(<vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %20 = call <vscale x 16 x i32> @llvm.bswap.nxv16i32(<vscale x 16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %21 = call i64 @llvm.bswap.i64(i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %22 = call <2 x i64> @llvm.bswap.v2i64(<2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %23 = call <4 x i64> @llvm.bswap.v4i64(<4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %24 = call <8 x i64> @llvm.bswap.v8i64(<8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %25 = call <16 x i64> @llvm.bswap.v16i64(<16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %23 = call <4 x i64> @llvm.bswap.v4i64(<4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %24 = call <8 x i64> @llvm.bswap.v8i64(<8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 248 for instruction: %25 = call <16 x i64> @llvm.bswap.v16i64(<16 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %26 = call <vscale x 1 x i64> @llvm.bswap.nxv1i64(<vscale x 1 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %27 = call <vscale x 2 x i64> @llvm.bswap.nxv2i64(<vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %28 = call <vscale x 4 x i64> @llvm.bswap.nxv4i64(<vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %29 = call <vscale x 8 x i64> @llvm.bswap.nxv8i64(<vscale x 8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %30 = call <vscale x 16 x i64> @llvm.bswap.nxv16i64(<vscale x 16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %27 = call <vscale x 2 x i64> @llvm.bswap.nxv2i64(<vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %28 = call <vscale x 4 x i64> @llvm.bswap.nxv4i64(<vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 248 for instruction: %29 = call <vscale x 8 x i64> @llvm.bswap.nxv8i64(<vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 496 for instruction: %30 = call <vscale x 16 x i64> @llvm.bswap.nxv16i64(<vscale x 16 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call i16 @llvm.bswap.i16(i16 undef)
@@ -81,37 +81,37 @@ define void @bitreverse() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %7 = call <vscale x 2 x i8> @llvm.bitreverse.nxv2i8(<vscale x 2 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %8 = call <vscale x 4 x i8> @llvm.bitreverse.nxv4i8(<vscale x 4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %9 = call <vscale x 8 x i8> @llvm.bitreverse.nxv8i8(<vscale x 8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %10 = call <vscale x 16 x i8> @llvm.bitreverse.nxv16i8(<vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %10 = call <vscale x 16 x i8> @llvm.bitreverse.nxv16i8(<vscale x 16 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %11 = call i16 @llvm.bitreverse.i16(i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %12 = call <2 x i16> @llvm.bitreverse.v2i16(<2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %13 = call <4 x i16> @llvm.bitreverse.v4i16(<4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %14 = call <8 x i16> @llvm.bitreverse.v8i16(<8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %15 = call <16 x i16> @llvm.bitreverse.v16i16(<16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %15 = call <16 x i16> @llvm.bitreverse.v16i16(<16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %16 = call <vscale x 1 x i16> @llvm.bitreverse.nxv1i16(<vscale x 1 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %17 = call <vscale x 2 x i16> @llvm.bitreverse.nxv2i16(<vscale x 2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %18 = call <vscale x 4 x i16> @llvm.bitreverse.nxv4i16(<vscale x 4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %19 = call <vscale x 8 x i16> @llvm.bitreverse.nxv8i16(<vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %20 = call <vscale x 16 x i16> @llvm.bitreverse.nxv16i16(<vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %19 = call <vscale x 8 x i16> @llvm.bitreverse.nxv8i16(<vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %20 = call <vscale x 16 x i16> @llvm.bitreverse.nxv16i16(<vscale x 16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %21 = call i32 @llvm.bitreverse.i32(i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %22 = call <2 x i32> @llvm.bitreverse.v2i32(<2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %23 = call <4 x i32> @llvm.bitreverse.v4i32(<4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %24 = call <8 x i32> @llvm.bitreverse.v8i32(<8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %25 = call <16 x i32> @llvm.bitreverse.v16i32(<16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %24 = call <8 x i32> @llvm.bitreverse.v8i32(<8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 132 for instruction: %25 = call <16 x i32> @llvm.bitreverse.v16i32(<16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %26 = call <vscale x 1 x i32> @llvm.bitreverse.nxv1i32(<vscale x 1 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %27 = call <vscale x 2 x i32> @llvm.bitreverse.nxv2i32(<vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %28 = call <vscale x 4 x i32> @llvm.bitreverse.nxv4i32(<vscale x 4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %29 = call <vscale x 8 x i32> @llvm.bitreverse.nxv8i32(<vscale x 8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %30 = call <vscale x 16 x i32> @llvm.bitreverse.nxv16i32(<vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %28 = call <vscale x 4 x i32> @llvm.bitreverse.nxv4i32(<vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 132 for instruction: %29 = call <vscale x 8 x i32> @llvm.bitreverse.nxv8i32(<vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 264 for instruction: %30 = call <vscale x 16 x i32> @llvm.bitreverse.nxv16i32(<vscale x 16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %31 = call i64 @llvm.bitreverse.i64(i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %32 = call <2 x i64> @llvm.bitreverse.v2i64(<2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %33 = call <4 x i64> @llvm.bitreverse.v4i64(<4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %34 = call <8 x i64> @llvm.bitreverse.v8i64(<8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %35 = call <16 x i64> @llvm.bitreverse.v16i64(<16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %33 = call <4 x i64> @llvm.bitreverse.v4i64(<4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 208 for instruction: %34 = call <8 x i64> @llvm.bitreverse.v8i64(<8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 416 for instruction: %35 = call <16 x i64> @llvm.bitreverse.v16i64(<16 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %36 = call <vscale x 1 x i64> @llvm.bitreverse.nxv1i64(<vscale x 1 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %37 = call <vscale x 2 x i64> @llvm.bitreverse.nxv2i64(<vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %38 = call <vscale x 4 x i64> @llvm.bitreverse.nxv4i64(<vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %39 = call <vscale x 8 x i64> @llvm.bitreverse.nxv8i64(<vscale x 8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %40 = call <vscale x 16 x i64> @llvm.bitreverse.nxv16i64(<vscale x 16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %37 = call <vscale x 2 x i64> @llvm.bitreverse.nxv2i64(<vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 208 for instruction: %38 = call <vscale x 4 x i64> @llvm.bitreverse.nxv4i64(<vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 416 for instruction: %39 = call <vscale x 8 x i64> @llvm.bitreverse.nxv8i64(<vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 832 for instruction: %40 = call <vscale x 16 x i64> @llvm.bitreverse.nxv16i64(<vscale x 16 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call i8 @llvm.bitreverse.i8(i8 undef)
@@ -168,37 +168,37 @@ define void @ctpop() {
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %7 = call <vscale x 2 x i8> @llvm.ctpop.nxv2i8(<vscale x 2 x i8> undef)
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %8 = call <vscale x 4 x i8> @llvm.ctpop.nxv4i8(<vscale x 4 x i8> undef)
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %9 = call <vscale x 8 x i8> @llvm.ctpop.nxv8i8(<vscale x 8 x i8> undef)
-; NOZVBB-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %10 = call <vscale x 16 x i8> @llvm.ctpop.nxv16i8(<vscale x 16 x i8> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %10 = call <vscale x 16 x i8> @llvm.ctpop.nxv16i8(<vscale x 16 x i8> undef)
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %11 = call i16 @llvm.ctpop.i16(i16 undef)
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %12 = call <2 x i16> @llvm.ctpop.v2i16(<2 x i16> undef)
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %13 = call <4 x i16> @llvm.ctpop.v4i16(<4 x i16> undef)
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %14 = call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> undef)
-; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %15 = call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %15 = call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> undef)
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %16 = call <vscale x 1 x i16> @llvm.ctpop.nxv1i16(<vscale x 1 x i16> undef)
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %17 = call <vscale x 2 x i16> @llvm.ctpop.nxv2i16(<vscale x 2 x i16> undef)
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %18 = call <vscale x 4 x i16> @llvm.ctpop.nxv4i16(<vscale x 4 x i16> undef)
-; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %19 = call <vscale x 8 x i16> @llvm.ctpop.nxv8i16(<vscale x 8 x i16> undef)
-; NOZVBB-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %20 = call <vscale x 16 x i16> @llvm.ctpop.nxv16i16(<vscale x 16 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %19 = call <vscale x 8 x i16> @llvm.ctpop.nxv8i16(<vscale x 8 x i16> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %20 = call <vscale x 16 x i16> @llvm.ctpop.nxv16i16(<vscale x 16 x i16> undef)
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %21 = call i32 @llvm.ctpop.i32(i32 undef)
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %22 = call <2 x i32> @llvm.ctpop.v2i32(<2 x i32> undef)
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %23 = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> undef)
-; NOZVBB-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %24 = call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> undef)
-; NOZVBB-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %25 = call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %24 = call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %25 = call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> undef)
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %26 = call <vscale x 1 x i32> @llvm.ctpop.nxv1i32(<vscale x 1 x i32> undef)
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %27 = call <vscale x 2 x i32> @llvm.ctpop.nxv2i32(<vscale x 2 x i32> undef)
-; NOZVBB-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %28 = call <vscale x 4 x i32> @llvm.ctpop.nxv4i32(<vscale x 4 x i32> undef)
-; NOZVBB-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %29 = call <vscale x 8 x i32> @llvm.ctpop.nxv8i32(<vscale x 8 x i32> undef)
-; NOZVBB-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %30 = call <vscale x 16 x i32> @llvm.ctpop.nxv16i32(<vscale x 16 x i32> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %28 = call <vscale x 4 x i32> @llvm.ctpop.nxv4i32(<vscale x 4 x i32> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %29 = call <vscale x 8 x i32> @llvm.ctpop.nxv8i32(<vscale x 8 x i32> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %30 = call <vscale x 16 x i32> @llvm.ctpop.nxv16i32(<vscale x 16 x i32> undef)
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %31 = call i64 @llvm.ctpop.i64(i64 undef)
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %32 = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> undef)
-; NOZVBB-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %33 = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> undef)
-; NOZVBB-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %34 = call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> undef)
-; NOZVBB-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %35 = call <16 x i64> @llvm.ctpop.v16i64(<16 x i64> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %33 = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %34 = call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 168 for instruction: %35 = call <16 x i64> @llvm.ctpop.v16i64(<16 x i64> undef)
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %36 = call <vscale x 1 x i64> @llvm.ctpop.nxv1i64(<vscale x 1 x i64> undef)
-; NOZVBB-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %37 = call <vscale x 2 x i64> @llvm.ctpop.nxv2i64(<vscale x 2 x i64> undef)
-; NOZVBB-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %38 = call <vscale x 4 x i64> @llvm.ctpop.nxv4i64(<vscale x 4 x i64> undef)
-; NOZVBB-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %39 = call <vscale x 8 x i64> @llvm.ctpop.nxv8i64(<vscale x 8 x i64> undef)
-; NOZVBB-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %40 = call <vscale x 16 x i64> @llvm.ctpop.nxv16i64(<vscale x 16 x i64> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %37 = call <vscale x 2 x i64> @llvm.ctpop.nxv2i64(<vscale x 2 x i64> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %38 = call <vscale x 4 x i64> @llvm.ctpop.nxv4i64(<vscale x 4 x i64> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 168 for instruction: %39 = call <vscale x 8 x i64> @llvm.ctpop.nxv8i64(<vscale x 8 x i64> undef)
+; NOZVBB-NEXT: Cost Model: Found an estimated cost of 336 for instruction: %40 = call <vscale x 16 x i64> @llvm.ctpop.nxv16i64(<vscale x 16 x i64> undef)
; NOZVBB-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVBB-LABEL: 'ctpop'
@@ -292,30 +292,30 @@ define void @vp_bswap() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %1 = call <2 x i16> @llvm.vp.bswap.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %2 = call <4 x i16> @llvm.vp.bswap.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %3 = call <8 x i16> @llvm.vp.bswap.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %4 = call <16 x i16> @llvm.vp.bswap.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %4 = call <16 x i16> @llvm.vp.bswap.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %5 = call <vscale x 1 x i16> @llvm.vp.bswap.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %6 = call <vscale x 2 x i16> @llvm.vp.bswap.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %7 = call <vscale x 4 x i16> @llvm.vp.bswap.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %8 = call <vscale x 8 x i16> @llvm.vp.bswap.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %9 = call <vscale x 16 x i16> @llvm.vp.bswap.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %8 = call <vscale x 8 x i16> @llvm.vp.bswap.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %9 = call <vscale x 16 x i16> @llvm.vp.bswap.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %10 = call <2 x i32> @llvm.vp.bswap.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %11 = call <4 x i32> @llvm.vp.bswap.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %12 = call <8 x i32> @llvm.vp.bswap.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %13 = call <16 x i32> @llvm.vp.bswap.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %12 = call <8 x i32> @llvm.vp.bswap.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %13 = call <16 x i32> @llvm.vp.bswap.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %14 = call <vscale x 1 x i32> @llvm.vp.bswap.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %15 = call <vscale x 2 x i32> @llvm.vp.bswap.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %16 = call <vscale x 4 x i32> @llvm.vp.bswap.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %17 = call <vscale x 8 x i32> @llvm.vp.bswap.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %18 = call <vscale x 16 x i32> @llvm.vp.bswap.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %16 = call <vscale x 4 x i32> @llvm.vp.bswap.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %17 = call <vscale x 8 x i32> @llvm.vp.bswap.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %18 = call <vscale x 16 x i32> @llvm.vp.bswap.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %19 = call <2 x i64> @llvm.vp.bswap.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %20 = call <4 x i64> @llvm.vp.bswap.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %21 = call <8 x i64> @llvm.vp.bswap.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %22 = call <16 x i64> @llvm.vp.bswap.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %20 = call <4 x i64> @llvm.vp.bswap.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %21 = call <8 x i64> @llvm.vp.bswap.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 248 for instruction: %22 = call <16 x i64> @llvm.vp.bswap.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %23 = call <vscale x 1 x i64> @llvm.vp.bswap.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %24 = call <vscale x 2 x i64> @llvm.vp.bswap.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %25 = call <vscale x 4 x i64> @llvm.vp.bswap.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %26 = call <vscale x 8 x i64> @llvm.vp.bswap.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %27 = call <vscale x 16 x i64> @llvm.vp.bswap.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %24 = call <vscale x 2 x i64> @llvm.vp.bswap.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %25 = call <vscale x 4 x i64> @llvm.vp.bswap.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 248 for instruction: %26 = call <vscale x 8 x i64> @llvm.vp.bswap.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 496 for instruction: %27 = call <vscale x 16 x i64> @llvm.vp.bswap.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x i16> @llvm.vp.bswap.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
@@ -353,39 +353,39 @@ define void @vp_ctpop() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %1 = call <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %2 = call <4 x i16> @llvm.vp.ctpop.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %3 = call <8 x i16> @llvm.vp.ctpop.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %4 = call <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %4 = call <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %5 = call <vscale x 1 x i16> @llvm.vp.ctpop.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %6 = call <vscale x 2 x i16> @llvm.vp.ctpop.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %7 = call <vscale x 4 x i16> @llvm.vp.ctpop.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %8 = call <vscale x 8 x i16> @llvm.vp.ctpop.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %9 = call <vscale x 16 x i16> @llvm.vp.ctpop.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %8 = call <vscale x 8 x i16> @llvm.vp.ctpop.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %9 = call <vscale x 16 x i16> @llvm.vp.ctpop.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %10 = call <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %11 = call <4 x i16> @llvm.vp.ctpop.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %12 = call <8 x i16> @llvm.vp.ctpop.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %13 = call <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %13 = call <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %14 = call <vscale x 1 x i16> @llvm.vp.ctpop.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %15 = call <vscale x 2 x i16> @llvm.vp.ctpop.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %16 = call <vscale x 4 x i16> @llvm.vp.ctpop.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %17 = call <vscale x 8 x i16> @llvm.vp.ctpop.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %18 = call <vscale x 16 x i16> @llvm.vp.ctpop.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %17 = call <vscale x 8 x i16> @llvm.vp.ctpop.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %18 = call <vscale x 16 x i16> @llvm.vp.ctpop.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %19 = call <2 x i32> @llvm.vp.ctpop.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %20 = call <4 x i32> @llvm.vp.ctpop.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %21 = call <8 x i32> @llvm.vp.ctpop.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %22 = call <16 x i32> @llvm.vp.ctpop.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %21 = call <8 x i32> @llvm.vp.ctpop.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %22 = call <16 x i32> @llvm.vp.ctpop.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %23 = call <vscale x 1 x i32> @llvm.vp.ctpop.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %24 = call <vscale x 2 x i32> @llvm.vp.ctpop.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %25 = call <vscale x 4 x i32> @llvm.vp.ctpop.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %26 = call <vscale x 8 x i32> @llvm.vp.ctpop.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %27 = call <vscale x 16 x i32> @llvm.vp.ctpop.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %25 = call <vscale x 4 x i32> @llvm.vp.ctpop.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 80 for instruction: %26 = call <vscale x 8 x i32> @llvm.vp.ctpop.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 160 for instruction: %27 = call <vscale x 16 x i32> @llvm.vp.ctpop.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %28 = call <2 x i64> @llvm.vp.ctpop.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %29 = call <4 x i64> @llvm.vp.ctpop.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %30 = call <8 x i64> @llvm.vp.ctpop.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %31 = call <16 x i64> @llvm.vp.ctpop.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %29 = call <4 x i64> @llvm.vp.ctpop.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %30 = call <8 x i64> @llvm.vp.ctpop.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 168 for instruction: %31 = call <16 x i64> @llvm.vp.ctpop.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %32 = call <vscale x 1 x i64> @llvm.vp.ctpop.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %33 = call <vscale x 2 x i64> @llvm.vp.ctpop.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %34 = call <vscale x 4 x i64> @llvm.vp.ctpop.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %35 = call <vscale x 8 x i64> @llvm.vp.ctpop.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %36 = call <vscale x 16 x i64> @llvm.vp.ctpop.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %33 = call <vscale x 2 x i64> @llvm.vp.ctpop.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %34 = call <vscale x 4 x i64> @llvm.vp.ctpop.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 168 for instruction: %35 = call <vscale x 8 x i64> @llvm.vp.ctpop.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 336 for instruction: %36 = call <vscale x 16 x i64> @llvm.vp.ctpop.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
@@ -437,47 +437,47 @@ define void @vp_ctlz() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %6 = call <vscale x 2 x i8> @llvm.vp.ctlz.nxv2i8(<vscale x 2 x i8> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %7 = call <vscale x 4 x i8> @llvm.vp.ctlz.nxv4i8(<vscale x 4 x i8> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %8 = call <vscale x 8 x i8> @llvm.vp.ctlz.nxv8i8(<vscale x 8 x i8> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %9 = call <vscale x 16 x i8> @llvm.vp.ctlz.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %10 = call <vscale x 32 x i8> @llvm.vp.ctlz.nxv32i8(<vscale x 32 x i8> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %11 = call <vscale x 64 x i8> @llvm.vp.ctlz.nxv64i8(<vscale x 64 x i8> undef, i1 false, <vscale x 64 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %9 = call <vscale x 16 x i8> @llvm.vp.ctlz.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %10 = call <vscale x 32 x i8> @llvm.vp.ctlz.nxv32i8(<vscale x 32 x i8> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 152 for instruction: %11 = call <vscale x 64 x i8> @llvm.vp.ctlz.nxv64i8(<vscale x 64 x i8> undef, i1 false, <vscale x 64 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %12 = call <2 x i16> @llvm.vp.ctlz.v2i16(<2 x i16> undef, i1 false, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %13 = call <4 x i16> @llvm.vp.ctlz.v4i16(<4 x i16> undef, i1 false, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %14 = call <8 x i16> @llvm.vp.ctlz.v8i16(<8 x i16> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %15 = call <16 x i16> @llvm.vp.ctlz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %15 = call <16 x i16> @llvm.vp.ctlz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %16 = call <vscale x 1 x i16> @llvm.vp.ctlz.nxv1i16(<vscale x 1 x i16> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %17 = call <vscale x 2 x i16> @llvm.vp.ctlz.nxv2i16(<vscale x 2 x i16> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %18 = call <vscale x 4 x i16> @llvm.vp.ctlz.nxv4i16(<vscale x 4 x i16> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %19 = call <vscale x 8 x i16> @llvm.vp.ctlz.nxv8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %20 = call <vscale x 16 x i16> @llvm.vp.ctlz.nxv16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %21 = call <vscale x 32 x i16> @llvm.vp.ctlz.nxv32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %19 = call <vscale x 8 x i16> @llvm.vp.ctlz.nxv8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %20 = call <vscale x 16 x i16> @llvm.vp.ctlz.nxv16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 224 for instruction: %21 = call <vscale x 32 x i16> @llvm.vp.ctlz.nxv32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %22 = call <2 x i16> @llvm.vp.ctlz.v2i16(<2 x i16> undef, i1 false, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %23 = call <4 x i16> @llvm.vp.ctlz.v4i16(<4 x i16> undef, i1 false, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %24 = call <8 x i16> @llvm.vp.ctlz.v8i16(<8 x i16> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %25 = call <16 x i16> @llvm.vp.ctlz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %25 = call <16 x i16> @llvm.vp.ctlz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %26 = call <vscale x 1 x i16> @llvm.vp.ctlz.nxv1i16(<vscale x 1 x i16> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %27 = call <vscale x 2 x i16> @llvm.vp.ctlz.nxv2i16(<vscale x 2 x i16> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %28 = call <vscale x 4 x i16> @llvm.vp.ctlz.nxv4i16(<vscale x 4 x i16> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %29 = call <vscale x 8 x i16> @llvm.vp.ctlz.nxv8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %30 = call <vscale x 16 x i16> @llvm.vp.ctlz.nxv16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %31 = call <vscale x 32 x i16> @llvm.vp.ctlz.nxv32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %29 = call <vscale x 8 x i16> @llvm.vp.ctlz.nxv8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %30 = call <vscale x 16 x i16> @llvm.vp.ctlz.nxv16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 224 for instruction: %31 = call <vscale x 32 x i16> @llvm.vp.ctlz.nxv32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %32 = call <2 x i32> @llvm.vp.ctlz.v2i32(<2 x i32> undef, i1 false, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %33 = call <4 x i32> @llvm.vp.ctlz.v4i32(<4 x i32> undef, i1 false, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %34 = call <8 x i32> @llvm.vp.ctlz.v8i32(<8 x i32> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %35 = call <16 x i32> @llvm.vp.ctlz.v16i32(<16 x i32> undef, i1 false, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %34 = call <8 x i32> @llvm.vp.ctlz.v8i32(<8 x i32> undef, i1 false, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %35 = call <16 x i32> @llvm.vp.ctlz.v16i32(<16 x i32> undef, i1 false, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %36 = call <vscale x 1 x i32> @llvm.vp.ctlz.nxv1i32(<vscale x 1 x i32> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %37 = call <vscale x 2 x i32> @llvm.vp.ctlz.nxv2i32(<vscale x 2 x i32> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %38 = call <vscale x 4 x i32> @llvm.vp.ctlz.nxv4i32(<vscale x 4 x i32> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %39 = call <vscale x 8 x i32> @llvm.vp.ctlz.nxv8i32(<vscale x 8 x i32> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %40 = call <vscale x 16 x i32> @llvm.vp.ctlz.nxv16i32(<vscale x 16 x i32> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %38 = call <vscale x 4 x i32> @llvm.vp.ctlz.nxv4i32(<vscale x 4 x i32> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %39 = call <vscale x 8 x i32> @llvm.vp.ctlz.nxv8i32(<vscale x 8 x i32> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 248 for instruction: %40 = call <vscale x 16 x i32> @llvm.vp.ctlz.nxv16i32(<vscale x 16 x i32> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %41 = call <2 x i64> @llvm.vp.ctlz.v2i64(<2 x i64> undef, i1 false, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %42 = call <4 x i64> @llvm.vp.ctlz.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %43 = call <8 x i64> @llvm.vp.ctlz.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %44 = call <16 x i64> @llvm.vp.ctlz.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %42 = call <4 x i64> @llvm.vp.ctlz.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %43 = call <8 x i64> @llvm.vp.ctlz.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 280 for instruction: %44 = call <16 x i64> @llvm.vp.ctlz.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %45 = call <vscale x 1 x i64> @llvm.vp.ctlz.nxv1i64(<vscale x 1 x i64> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %46 = call <vscale x 2 x i64> @llvm.vp.ctlz.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %47 = call <vscale x 4 x i64> @llvm.vp.ctlz.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 35 for instruction: %48 = call <vscale x 8 x i64> @llvm.vp.ctlz.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %49 = call <vscale x 16 x i64> @llvm.vp.ctlz.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 70 for instruction: %46 = call <vscale x 2 x i64> @llvm.vp.ctlz.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 140 for instruction: %47 = call <vscale x 4 x i64> @llvm.vp.ctlz.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 280 for instruction: %48 = call <vscale x 8 x i64> @llvm.vp.ctlz.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 560 for instruction: %49 = call <vscale x 16 x i64> @llvm.vp.ctlz.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x i8> @llvm.vp.ctlz.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
@@ -542,47 +542,47 @@ define void @vp_cttz() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %6 = call <vscale x 2 x i8> @llvm.vp.cttz.nxv2i8(<vscale x 2 x i8> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %7 = call <vscale x 4 x i8> @llvm.vp.cttz.nxv4i8(<vscale x 4 x i8> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %8 = call <vscale x 8 x i8> @llvm.vp.cttz.nxv8i8(<vscale x 8 x i8> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %9 = call <vscale x 16 x i8> @llvm.vp.cttz.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %10 = call <vscale x 32 x i8> @llvm.vp.cttz.nxv32i8(<vscale x 32 x i8> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %11 = call <vscale x 64 x i8> @llvm.vp.cttz.nxv64i8(<vscale x 64 x i8> undef, i1 false, <vscale x 64 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %9 = call <vscale x 16 x i8> @llvm.vp.cttz.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %10 = call <vscale x 32 x i8> @llvm.vp.cttz.nxv32i8(<vscale x 32 x i8> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %11 = call <vscale x 64 x i8> @llvm.vp.cttz.nxv64i8(<vscale x 64 x i8> undef, i1 false, <vscale x 64 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x i16> @llvm.vp.cttz.v2i16(<2 x i16> undef, i1 false, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %13 = call <4 x i16> @llvm.vp.cttz.v4i16(<4 x i16> undef, i1 false, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %14 = call <8 x i16> @llvm.vp.cttz.v8i16(<8 x i16> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %15 = call <16 x i16> @llvm.vp.cttz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %15 = call <16 x i16> @llvm.vp.cttz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %16 = call <vscale x 1 x i16> @llvm.vp.cttz.nxv1i16(<vscale x 1 x i16> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %17 = call <vscale x 2 x i16> @llvm.vp.cttz.nxv2i16(<vscale x 2 x i16> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %18 = call <vscale x 4 x i16> @llvm.vp.cttz.nxv4i16(<vscale x 4 x i16> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %19 = call <vscale x 8 x i16> @llvm.vp.cttz.nxv8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %20 = call <vscale x 16 x i16> @llvm.vp.cttz.nxv16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %21 = call <vscale x 32 x i16> @llvm.vp.cttz.nxv32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %19 = call <vscale x 8 x i16> @llvm.vp.cttz.nxv8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %20 = call <vscale x 16 x i16> @llvm.vp.cttz.nxv16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %21 = call <vscale x 32 x i16> @llvm.vp.cttz.nxv32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %22 = call <2 x i16> @llvm.vp.cttz.v2i16(<2 x i16> undef, i1 false, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %23 = call <4 x i16> @llvm.vp.cttz.v4i16(<4 x i16> undef, i1 false, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %24 = call <8 x i16> @llvm.vp.cttz.v8i16(<8 x i16> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %25 = call <16 x i16> @llvm.vp.cttz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %25 = call <16 x i16> @llvm.vp.cttz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %26 = call <vscale x 1 x i16> @llvm.vp.cttz.nxv1i16(<vscale x 1 x i16> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %27 = call <vscale x 2 x i16> @llvm.vp.cttz.nxv2i16(<vscale x 2 x i16> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %28 = call <vscale x 4 x i16> @llvm.vp.cttz.nxv4i16(<vscale x 4 x i16> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %29 = call <vscale x 8 x i16> @llvm.vp.cttz.nxv8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %30 = call <vscale x 16 x i16> @llvm.vp.cttz.nxv16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %31 = call <vscale x 32 x i16> @llvm.vp.cttz.nxv32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %29 = call <vscale x 8 x i16> @llvm.vp.cttz.nxv8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %30 = call <vscale x 16 x i16> @llvm.vp.cttz.nxv16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %31 = call <vscale x 32 x i16> @llvm.vp.cttz.nxv32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %32 = call <2 x i32> @llvm.vp.cttz.v2i32(<2 x i32> undef, i1 false, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %33 = call <4 x i32> @llvm.vp.cttz.v4i32(<4 x i32> undef, i1 false, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %34 = call <8 x i32> @llvm.vp.cttz.v8i32(<8 x i32> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %35 = call <16 x i32> @llvm.vp.cttz.v16i32(<16 x i32> undef, i1 false, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %34 = call <8 x i32> @llvm.vp.cttz.v8i32(<8 x i32> undef, i1 false, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %35 = call <16 x i32> @llvm.vp.cttz.v16i32(<16 x i32> undef, i1 false, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %36 = call <vscale x 1 x i32> @llvm.vp.cttz.nxv1i32(<vscale x 1 x i32> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %37 = call <vscale x 2 x i32> @llvm.vp.cttz.nxv2i32(<vscale x 2 x i32> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %38 = call <vscale x 4 x i32> @llvm.vp.cttz.nxv4i32(<vscale x 4 x i32> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %39 = call <vscale x 8 x i32> @llvm.vp.cttz.nxv8i32(<vscale x 8 x i32> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %40 = call <vscale x 16 x i32> @llvm.vp.cttz.nxv16i32(<vscale x 16 x i32> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %38 = call <vscale x 4 x i32> @llvm.vp.cttz.nxv4i32(<vscale x 4 x i32> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %39 = call <vscale x 8 x i32> @llvm.vp.cttz.nxv8i32(<vscale x 8 x i32> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %40 = call <vscale x 16 x i32> @llvm.vp.cttz.nxv16i32(<vscale x 16 x i32> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %41 = call <2 x i64> @llvm.vp.cttz.v2i64(<2 x i64> undef, i1 false, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %42 = call <4 x i64> @llvm.vp.cttz.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %43 = call <8 x i64> @llvm.vp.cttz.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %44 = call <16 x i64> @llvm.vp.cttz.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %42 = call <4 x i64> @llvm.vp.cttz.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %43 = call <8 x i64> @llvm.vp.cttz.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 200 for instruction: %44 = call <16 x i64> @llvm.vp.cttz.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %45 = call <vscale x 1 x i64> @llvm.vp.cttz.nxv1i64(<vscale x 1 x i64> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %46 = call <vscale x 2 x i64> @llvm.vp.cttz.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %47 = call <vscale x 4 x i64> @llvm.vp.cttz.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %48 = call <vscale x 8 x i64> @llvm.vp.cttz.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %49 = call <vscale x 16 x i64> @llvm.vp.cttz.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %46 = call <vscale x 2 x i64> @llvm.vp.cttz.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %47 = call <vscale x 4 x i64> @llvm.vp.cttz.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 200 for instruction: %48 = call <vscale x 8 x i64> @llvm.vp.cttz.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 400 for instruction: %49 = call <vscale x 16 x i64> @llvm.vp.cttz.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x i8> @llvm.vp.cttz.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
diff --git a/llvm/test/Analysis/CostModel/RISCV/int-min-max.ll b/llvm/test/Analysis/CostModel/RISCV/int-min-max.ll
index ec669c986c15039..79cf1c84ed494e3 100644
--- a/llvm/test/Analysis/CostModel/RISCV/int-min-max.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/int-min-max.ll
@@ -12,36 +12,36 @@ define void @smax() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x i8> @llvm.smax.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x i8> @llvm.smax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x i8> @llvm.smax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %10 = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %11 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x i16> @llvm.smax.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x i16> @llvm.smax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x i16> @llvm.smax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x i16> @llvm.smax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <vscale x 16 x i16> @llvm.smax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %19 = call <vscale x 8 x i16> @llvm.smax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %20 = call <vscale x 16 x i16> @llvm.smax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %21 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %24 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %25 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 1 x i32> @llvm.smax.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 2 x i32> @llvm.smax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <vscale x 8 x i32> @llvm.smax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <vscale x 16 x i32> @llvm.smax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %28 = call <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %29 = call <vscale x 8 x i32> @llvm.smax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %30 = call <vscale x 16 x i32> @llvm.smax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %31 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <16 x i64> @llvm.smax.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %33 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %34 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %35 = call <16 x i64> @llvm.smax.v16i64(<16 x i64> undef, <16 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %36 = call <vscale x 1 x i64> @llvm.smax.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %37 = call <vscale x 2 x i64> @llvm.smax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %38 = call <vscale x 4 x i64> @llvm.smax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %39 = call <vscale x 8 x i64> @llvm.smax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %37 = call <vscale x 2 x i64> @llvm.smax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %38 = call <vscale x 4 x i64> @llvm.smax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %39 = call <vscale x 8 x i64> @llvm.smax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call i8 @llvm.smax.i8(i8 undef, i8 undef)
@@ -97,36 +97,36 @@ define void @smin() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x i8> @llvm.smin.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x i8> @llvm.smin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x i8> @llvm.smin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x i8> @llvm.smin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %10 = call <vscale x 16 x i8> @llvm.smin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %11 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x i16> @llvm.smin.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x i16> @llvm.smin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x i16> @llvm.smin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x i16> @llvm.smin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <vscale x 16 x i16> @llvm.smin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %19 = call <vscale x 8 x i16> @llvm.smin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %20 = call <vscale x 16 x i16> @llvm.smin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %21 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %24 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %25 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 1 x i32> @llvm.smin.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 2 x i32> @llvm.smin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <vscale x 8 x i32> @llvm.smin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <vscale x 16 x i32> @llvm.smin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %28 = call <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %29 = call <vscale x 8 x i32> @llvm.smin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %30 = call <vscale x 16 x i32> @llvm.smin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %31 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <16 x i64> @llvm.smin.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %33 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %34 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %35 = call <16 x i64> @llvm.smin.v16i64(<16 x i64> undef, <16 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %36 = call <vscale x 1 x i64> @llvm.smin.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %37 = call <vscale x 2 x i64> @llvm.smin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %38 = call <vscale x 4 x i64> @llvm.smin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %39 = call <vscale x 8 x i64> @llvm.smin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %37 = call <vscale x 2 x i64> @llvm.smin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %38 = call <vscale x 4 x i64> @llvm.smin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %39 = call <vscale x 8 x i64> @llvm.smin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call i8 @llvm.smin.i8(i8 undef, i8 undef)
@@ -182,36 +182,36 @@ define void @umax() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x i8> @llvm.umax.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x i8> @llvm.umax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x i8> @llvm.umax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x i8> @llvm.umax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %10 = call <vscale x 16 x i8> @llvm.umax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %11 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x i16> @llvm.umax.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x i16> @llvm.umax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x i16> @llvm.umax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x i16> @llvm.umax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <vscale x 16 x i16> @llvm.umax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %19 = call <vscale x 8 x i16> @llvm.umax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %20 = call <vscale x 16 x i16> @llvm.umax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %21 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %24 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %25 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 1 x i32> @llvm.umax.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 2 x i32> @llvm.umax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <vscale x 8 x i32> @llvm.umax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <vscale x 16 x i32> @llvm.umax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %28 = call <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %29 = call <vscale x 8 x i32> @llvm.umax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %30 = call <vscale x 16 x i32> @llvm.umax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %31 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <16 x i64> @llvm.umax.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %33 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %34 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %35 = call <16 x i64> @llvm.umax.v16i64(<16 x i64> undef, <16 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %36 = call <vscale x 1 x i64> @llvm.umax.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %37 = call <vscale x 2 x i64> @llvm.umax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %38 = call <vscale x 4 x i64> @llvm.umax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %39 = call <vscale x 8 x i64> @llvm.umax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %37 = call <vscale x 2 x i64> @llvm.umax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %38 = call <vscale x 4 x i64> @llvm.umax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %39 = call <vscale x 8 x i64> @llvm.umax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call i8 @llvm.umax.i8(i8 undef, i8 undef)
@@ -267,36 +267,36 @@ define void @umin() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x i8> @llvm.umin.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x i8> @llvm.umin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x i8> @llvm.umin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x i8> @llvm.umin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %10 = call <vscale x 16 x i8> @llvm.umin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %11 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x i16> @llvm.umin.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x i16> @llvm.umin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x i16> @llvm.umin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x i16> @llvm.umin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <vscale x 16 x i16> @llvm.umin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %19 = call <vscale x 8 x i16> @llvm.umin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %20 = call <vscale x 16 x i16> @llvm.umin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %21 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %24 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %25 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 1 x i32> @llvm.umin.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 2 x i32> @llvm.umin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <vscale x 8 x i32> @llvm.umin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <vscale x 16 x i32> @llvm.umin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %28 = call <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %29 = call <vscale x 8 x i32> @llvm.umin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %30 = call <vscale x 16 x i32> @llvm.umin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %31 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <16 x i64> @llvm.umin.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %33 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %34 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %35 = call <16 x i64> @llvm.umin.v16i64(<16 x i64> undef, <16 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %36 = call <vscale x 1 x i64> @llvm.umin.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %37 = call <vscale x 2 x i64> @llvm.umin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %38 = call <vscale x 4 x i64> @llvm.umin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %39 = call <vscale x 8 x i64> @llvm.umin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %37 = call <vscale x 2 x i64> @llvm.umin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %38 = call <vscale x 4 x i64> @llvm.umin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %39 = call <vscale x 8 x i64> @llvm.umin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call i8 @llvm.umin.i8(i8 undef, i8 undef)
diff --git a/llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll b/llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll
index 541534d2778aa87..32b956c29de1adf 100644
--- a/llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll
@@ -11,33 +11,33 @@ define void @sadd.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.sadd.sat.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.sadd.sat.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.sadd.sat.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.sadd.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x i8> @llvm.sadd.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.sadd.sat.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.sadd.sat.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.sadd.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.sadd.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 8 x i16> @llvm.sadd.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 16 x i16> @llvm.sadd.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %19 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %22 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %23 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.sadd.sat.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.sadd.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.sadd.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.sadd.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %25 = call <vscale x 4 x i32> @llvm.sadd.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %26 = call <vscale x 8 x i32> @llvm.sadd.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %27 = call <vscale x 16 x i32> @llvm.sadd.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %28 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.sadd.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.sadd.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.sadd.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.sadd.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %30 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %31 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %32 = call <16 x i64> @llvm.sadd.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %33 = call <vscale x 2 x i64> @llvm.sadd.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %34 = call <vscale x 4 x i64> @llvm.sadd.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %35 = call <vscale x 8 x i64> @llvm.sadd.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
@@ -88,33 +88,33 @@ define void @uadd.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.uadd.sat.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.uadd.sat.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.uadd.sat.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.uadd.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x i8> @llvm.uadd.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %10 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.uadd.sat.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.uadd.sat.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.uadd.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.uadd.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 8 x i16> @llvm.uadd.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 16 x i16> @llvm.uadd.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %19 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %22 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %23 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.uadd.sat.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.uadd.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.uadd.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.uadd.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %25 = call <vscale x 4 x i32> @llvm.uadd.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %26 = call <vscale x 8 x i32> @llvm.uadd.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %27 = call <vscale x 16 x i32> @llvm.uadd.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %28 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.uadd.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.uadd.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.uadd.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.uadd.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %30 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %31 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %32 = call <16 x i64> @llvm.uadd.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %33 = call <vscale x 2 x i64> @llvm.uadd.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %34 = call <vscale x 4 x i64> @llvm.uadd.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %35 = call <vscale x 8 x i64> @llvm.uadd.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
@@ -165,33 +165,33 @@ define void @usub.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.usub.sat.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.usub.sat.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.usub.sat.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.usub.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x i8> @llvm.usub.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %10 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.usub.sat.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.usub.sat.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.usub.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.usub.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 8 x i16> @llvm.usub.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 16 x i16> @llvm.usub.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %19 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %22 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %23 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.usub.sat.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.usub.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.usub.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.usub.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %25 = call <vscale x 4 x i32> @llvm.usub.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %26 = call <vscale x 8 x i32> @llvm.usub.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %27 = call <vscale x 16 x i32> @llvm.usub.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %28 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.usub.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.usub.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.usub.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.usub.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %30 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %31 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %32 = call <16 x i64> @llvm.usub.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %33 = call <vscale x 2 x i64> @llvm.usub.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %34 = call <vscale x 4 x i64> @llvm.usub.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %35 = call <vscale x 8 x i64> @llvm.usub.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
@@ -242,33 +242,33 @@ define void @ssub.sat() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.ssub.sat.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.ssub.sat.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.ssub.sat.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.ssub.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x i8> @llvm.ssub.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.ssub.sat.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.ssub.sat.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.ssub.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.ssub.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 8 x i16> @llvm.ssub.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 16 x i16> @llvm.ssub.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %19 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %22 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %23 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.ssub.sat.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.ssub.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.ssub.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.ssub.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %25 = call <vscale x 4 x i32> @llvm.ssub.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %26 = call <vscale x 8 x i32> @llvm.ssub.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %27 = call <vscale x 16 x i32> @llvm.ssub.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %28 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.ssub.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.ssub.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.ssub.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.ssub.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %30 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %31 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %32 = call <16 x i64> @llvm.ssub.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %33 = call <vscale x 2 x i64> @llvm.ssub.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %34 = call <vscale x 4 x i64> @llvm.ssub.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %35 = call <vscale x 8 x i64> @llvm.ssub.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)
diff --git a/llvm/test/Analysis/CostModel/RISCV/rvv-cmp.ll b/llvm/test/Analysis/CostModel/RISCV/rvv-cmp.ll
index 27d24faf0a8daee..3c0f30c1d56add1 100644
--- a/llvm/test/Analysis/CostModel/RISCV/rvv-cmp.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/rvv-cmp.ll
@@ -9,38 +9,38 @@ define void @icmp_eq() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8 = icmp eq <4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8 = icmp eq <8 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8 = icmp eq <16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8 = icmp eq <32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v32i8 = icmp eq <32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i8 = icmp eq <vscale x 1 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i8 = icmp eq <vscale x 2 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i8 = icmp eq <vscale x 4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i8 = icmp eq <vscale x 8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i8 = icmp eq <vscale x 16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv32i8 = icmp eq <vscale x 32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv16i8 = icmp eq <vscale x 16 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv32i8 = icmp eq <vscale x 32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16 = icmp eq <2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16 = icmp eq <4 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16 = icmp eq <8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16 = icmp eq <16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16i16 = icmp eq <16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i16 = icmp eq <vscale x 1 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i16 = icmp eq <vscale x 2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i16 = icmp eq <vscale x 4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i16 = icmp eq <vscale x 8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i16 = icmp eq <vscale x 16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8i16 = icmp eq <vscale x 8 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16i16 = icmp eq <vscale x 16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32 = icmp eq <2 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32 = icmp eq <4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32 = icmp eq <8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32 = icmp eq <16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i32 = icmp eq <8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i32 = icmp eq <16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i32 = icmp eq <vscale x 1 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i32 = icmp eq <vscale x 2 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i32 = icmp eq <vscale x 4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i32 = icmp eq <vscale x 8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i32 = icmp eq <vscale x 16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4i32 = icmp eq <vscale x 4 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8i32 = icmp eq <vscale x 8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16i32 = icmp eq <vscale x 16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64 = icmp eq <2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64 = icmp eq <4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64 = icmp eq <8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i64 = icmp eq <4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i64 = icmp eq <8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i64 = icmp eq <vscale x 1 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i64 = icmp eq <vscale x 2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i64 = icmp eq <vscale x 4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i64 = icmp eq <vscale x 8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i64 = icmp eq <vscale x 2 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i64 = icmp eq <vscale x 4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i64 = icmp eq <vscale x 8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2i8 = icmp eq <2 x i8> undef, undef
@@ -96,38 +96,38 @@ define void @icmp_ne() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8 = icmp ne <4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8 = icmp ne <8 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8 = icmp ne <16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8 = icmp ne <32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v32i8 = icmp ne <32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i8 = icmp ne <vscale x 1 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i8 = icmp ne <vscale x 2 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i8 = icmp ne <vscale x 4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i8 = icmp ne <vscale x 8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i8 = icmp ne <vscale x 16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv32i8 = icmp ne <vscale x 32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv16i8 = icmp ne <vscale x 16 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv32i8 = icmp ne <vscale x 32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16 = icmp ne <2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16 = icmp ne <4 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16 = icmp ne <8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16 = icmp ne <16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16i16 = icmp ne <16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i16 = icmp ne <vscale x 1 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i16 = icmp ne <vscale x 2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i16 = icmp ne <vscale x 4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i16 = icmp ne <vscale x 8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i16 = icmp ne <vscale x 16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8i16 = icmp ne <vscale x 8 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16i16 = icmp ne <vscale x 16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32 = icmp ne <2 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32 = icmp ne <4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32 = icmp ne <8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32 = icmp ne <16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i32 = icmp ne <8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i32 = icmp ne <16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i32 = icmp ne <vscale x 1 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i32 = icmp ne <vscale x 2 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i32 = icmp ne <vscale x 4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i32 = icmp ne <vscale x 8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i32 = icmp ne <vscale x 16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4i32 = icmp ne <vscale x 4 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8i32 = icmp ne <vscale x 8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16i32 = icmp ne <vscale x 16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64 = icmp ne <2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64 = icmp ne <4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64 = icmp ne <8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i64 = icmp ne <4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i64 = icmp ne <8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i64 = icmp ne <vscale x 1 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i64 = icmp ne <vscale x 2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i64 = icmp ne <vscale x 4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i64 = icmp ne <vscale x 8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i64 = icmp ne <vscale x 2 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i64 = icmp ne <vscale x 4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i64 = icmp ne <vscale x 8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2i8 = icmp ne <2 x i8> undef, undef
@@ -183,38 +183,38 @@ define void @icmp_ugt() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8 = icmp ugt <4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8 = icmp ugt <8 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8 = icmp ugt <16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8 = icmp ugt <32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v32i8 = icmp ugt <32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i8 = icmp ugt <vscale x 1 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i8 = icmp ugt <vscale x 2 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i8 = icmp ugt <vscale x 4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i8 = icmp ugt <vscale x 8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i8 = icmp ugt <vscale x 16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv32i8 = icmp ugt <vscale x 32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv16i8 = icmp ugt <vscale x 16 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv32i8 = icmp ugt <vscale x 32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16 = icmp ugt <2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16 = icmp ugt <4 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16 = icmp ugt <8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16 = icmp ugt <16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16i16 = icmp ugt <16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i16 = icmp ugt <vscale x 1 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i16 = icmp ugt <vscale x 2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i16 = icmp ugt <vscale x 4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i16 = icmp ugt <vscale x 8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i16 = icmp ugt <vscale x 16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8i16 = icmp ugt <vscale x 8 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16i16 = icmp ugt <vscale x 16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32 = icmp ugt <2 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32 = icmp ugt <4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32 = icmp ugt <8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32 = icmp ugt <16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i32 = icmp ugt <8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i32 = icmp ugt <16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i32 = icmp ugt <vscale x 1 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i32 = icmp ugt <vscale x 2 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i32 = icmp ugt <vscale x 4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i32 = icmp ugt <vscale x 8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i32 = icmp ugt <vscale x 16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4i32 = icmp ugt <vscale x 4 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8i32 = icmp ugt <vscale x 8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16i32 = icmp ugt <vscale x 16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64 = icmp ugt <2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64 = icmp ugt <4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64 = icmp ugt <8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i64 = icmp ugt <4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i64 = icmp ugt <8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i64 = icmp ugt <vscale x 1 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i64 = icmp ugt <vscale x 2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i64 = icmp ugt <vscale x 4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i64 = icmp ugt <vscale x 8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i64 = icmp ugt <vscale x 2 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i64 = icmp ugt <vscale x 4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i64 = icmp ugt <vscale x 8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2i8 = icmp ugt <2 x i8> undef, undef
@@ -270,38 +270,38 @@ define void @icmp_uge() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8 = icmp uge <4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8 = icmp uge <8 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8 = icmp uge <16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8 = icmp uge <32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v32i8 = icmp uge <32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i8 = icmp uge <vscale x 1 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i8 = icmp uge <vscale x 2 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i8 = icmp uge <vscale x 4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i8 = icmp uge <vscale x 8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i8 = icmp uge <vscale x 16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv32i8 = icmp uge <vscale x 32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv16i8 = icmp uge <vscale x 16 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv32i8 = icmp uge <vscale x 32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16 = icmp uge <2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16 = icmp uge <4 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16 = icmp uge <8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16 = icmp uge <16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16i16 = icmp uge <16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i16 = icmp uge <vscale x 1 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i16 = icmp uge <vscale x 2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i16 = icmp uge <vscale x 4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i16 = icmp uge <vscale x 8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i16 = icmp uge <vscale x 16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8i16 = icmp uge <vscale x 8 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16i16 = icmp uge <vscale x 16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32 = icmp uge <2 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32 = icmp uge <4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32 = icmp uge <8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32 = icmp uge <16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i32 = icmp uge <8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i32 = icmp uge <16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i32 = icmp uge <vscale x 1 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i32 = icmp uge <vscale x 2 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i32 = icmp uge <vscale x 4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i32 = icmp uge <vscale x 8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i32 = icmp uge <vscale x 16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4i32 = icmp uge <vscale x 4 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8i32 = icmp uge <vscale x 8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16i32 = icmp uge <vscale x 16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64 = icmp uge <2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64 = icmp uge <4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64 = icmp uge <8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i64 = icmp uge <4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i64 = icmp uge <8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i64 = icmp uge <vscale x 1 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i64 = icmp uge <vscale x 2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i64 = icmp uge <vscale x 4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i64 = icmp uge <vscale x 8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i64 = icmp uge <vscale x 2 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i64 = icmp uge <vscale x 4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i64 = icmp uge <vscale x 8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2i8 = icmp uge <2 x i8> undef, undef
@@ -357,38 +357,38 @@ define void @icmp_ult() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8 = icmp ult <4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8 = icmp ult <8 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8 = icmp ult <16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8 = icmp ult <32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v32i8 = icmp ult <32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i8 = icmp ult <vscale x 1 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i8 = icmp ult <vscale x 2 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i8 = icmp ult <vscale x 4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i8 = icmp ult <vscale x 8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i8 = icmp ult <vscale x 16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv32i8 = icmp ult <vscale x 32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv16i8 = icmp ult <vscale x 16 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv32i8 = icmp ult <vscale x 32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16 = icmp ult <2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16 = icmp ult <4 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16 = icmp ult <8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16 = icmp ult <16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16i16 = icmp ult <16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i16 = icmp ult <vscale x 1 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i16 = icmp ult <vscale x 2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i16 = icmp ult <vscale x 4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i16 = icmp ult <vscale x 8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i16 = icmp ult <vscale x 16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8i16 = icmp ult <vscale x 8 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16i16 = icmp ult <vscale x 16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32 = icmp ult <2 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32 = icmp ult <4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32 = icmp ult <8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32 = icmp ult <16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i32 = icmp ult <8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i32 = icmp ult <16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i32 = icmp ult <vscale x 1 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i32 = icmp ult <vscale x 2 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i32 = icmp ult <vscale x 4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i32 = icmp ult <vscale x 8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i32 = icmp ult <vscale x 16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4i32 = icmp ult <vscale x 4 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8i32 = icmp ult <vscale x 8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16i32 = icmp ult <vscale x 16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64 = icmp ult <2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64 = icmp ult <4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64 = icmp ult <8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i64 = icmp ult <4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i64 = icmp ult <8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i64 = icmp ult <vscale x 1 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i64 = icmp ult <vscale x 2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i64 = icmp ult <vscale x 4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i64 = icmp ult <vscale x 8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i64 = icmp ult <vscale x 2 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i64 = icmp ult <vscale x 4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i64 = icmp ult <vscale x 8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2i8 = icmp ult <2 x i8> undef, undef
@@ -444,38 +444,38 @@ define void @icmp_ule() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8 = icmp ule <4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8 = icmp ule <8 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8 = icmp ule <16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8 = icmp ule <32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v32i8 = icmp ule <32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i8 = icmp ule <vscale x 1 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i8 = icmp ule <vscale x 2 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i8 = icmp ule <vscale x 4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i8 = icmp ule <vscale x 8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i8 = icmp ule <vscale x 16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv32i8 = icmp ule <vscale x 32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv16i8 = icmp ule <vscale x 16 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv32i8 = icmp ule <vscale x 32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16 = icmp ule <2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16 = icmp ule <4 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16 = icmp ule <8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16 = icmp ule <16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16i16 = icmp ule <16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i16 = icmp ule <vscale x 1 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i16 = icmp ule <vscale x 2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i16 = icmp ule <vscale x 4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i16 = icmp ule <vscale x 8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i16 = icmp ule <vscale x 16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8i16 = icmp ule <vscale x 8 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16i16 = icmp ule <vscale x 16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32 = icmp ule <2 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32 = icmp ule <4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32 = icmp ule <8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32 = icmp ule <16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i32 = icmp ule <8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i32 = icmp ule <16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i32 = icmp ule <vscale x 1 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i32 = icmp ule <vscale x 2 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i32 = icmp ule <vscale x 4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i32 = icmp ule <vscale x 8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i32 = icmp ule <vscale x 16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4i32 = icmp ule <vscale x 4 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8i32 = icmp ule <vscale x 8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16i32 = icmp ule <vscale x 16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64 = icmp ule <2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64 = icmp ule <4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64 = icmp ule <8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i64 = icmp ule <4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i64 = icmp ule <8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i64 = icmp ule <vscale x 1 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i64 = icmp ule <vscale x 2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i64 = icmp ule <vscale x 4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i64 = icmp ule <vscale x 8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i64 = icmp ule <vscale x 2 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i64 = icmp ule <vscale x 4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i64 = icmp ule <vscale x 8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2i8 = icmp ule <2 x i8> undef, undef
@@ -531,38 +531,38 @@ define void @icmp_sgt() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8 = icmp sgt <4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8 = icmp sgt <8 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8 = icmp sgt <16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8 = icmp sgt <32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v32i8 = icmp sgt <32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i8 = icmp sgt <vscale x 1 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i8 = icmp sgt <vscale x 2 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i8 = icmp sgt <vscale x 4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i8 = icmp sgt <vscale x 8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i8 = icmp sgt <vscale x 16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv32i8 = icmp sgt <vscale x 32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv16i8 = icmp sgt <vscale x 16 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv32i8 = icmp sgt <vscale x 32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16 = icmp sgt <2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16 = icmp sgt <4 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16 = icmp sgt <8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16 = icmp sgt <16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16i16 = icmp sgt <16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i16 = icmp sgt <vscale x 1 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i16 = icmp sgt <vscale x 2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i16 = icmp sgt <vscale x 4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i16 = icmp sgt <vscale x 8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i16 = icmp sgt <vscale x 16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8i16 = icmp sgt <vscale x 8 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16i16 = icmp sgt <vscale x 16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32 = icmp sgt <2 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32 = icmp sgt <4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32 = icmp sgt <8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32 = icmp sgt <16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i32 = icmp sgt <8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i32 = icmp sgt <16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i32 = icmp sgt <vscale x 1 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i32 = icmp sgt <vscale x 2 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i32 = icmp sgt <vscale x 4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i32 = icmp sgt <vscale x 8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i32 = icmp sgt <vscale x 16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4i32 = icmp sgt <vscale x 4 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8i32 = icmp sgt <vscale x 8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16i32 = icmp sgt <vscale x 16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64 = icmp sgt <2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64 = icmp sgt <4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64 = icmp sgt <8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i64 = icmp sgt <4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i64 = icmp sgt <8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i64 = icmp sgt <vscale x 1 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i64 = icmp sgt <vscale x 2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i64 = icmp sgt <vscale x 4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i64 = icmp sgt <vscale x 8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i64 = icmp sgt <vscale x 2 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i64 = icmp sgt <vscale x 4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i64 = icmp sgt <vscale x 8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2i8 = icmp sgt <2 x i8> undef, undef
@@ -618,38 +618,38 @@ define void @icmp_sge() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8 = icmp sge <4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8 = icmp sge <8 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8 = icmp sge <16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8 = icmp sge <32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v32i8 = icmp sge <32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i8 = icmp sge <vscale x 1 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i8 = icmp sge <vscale x 2 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i8 = icmp sge <vscale x 4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i8 = icmp sge <vscale x 8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i8 = icmp sge <vscale x 16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv32i8 = icmp sge <vscale x 32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv16i8 = icmp sge <vscale x 16 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv32i8 = icmp sge <vscale x 32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16 = icmp sge <2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16 = icmp sge <4 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16 = icmp sge <8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16 = icmp sge <16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16i16 = icmp sge <16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i16 = icmp sge <vscale x 1 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i16 = icmp sge <vscale x 2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i16 = icmp sge <vscale x 4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i16 = icmp sge <vscale x 8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i16 = icmp sge <vscale x 16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8i16 = icmp sge <vscale x 8 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16i16 = icmp sge <vscale x 16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32 = icmp sge <2 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32 = icmp sge <4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32 = icmp sge <8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32 = icmp sge <16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i32 = icmp sge <8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i32 = icmp sge <16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i32 = icmp sge <vscale x 1 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i32 = icmp sge <vscale x 2 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i32 = icmp sge <vscale x 4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i32 = icmp sge <vscale x 8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i32 = icmp sge <vscale x 16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4i32 = icmp sge <vscale x 4 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8i32 = icmp sge <vscale x 8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16i32 = icmp sge <vscale x 16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64 = icmp sge <2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64 = icmp sge <4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64 = icmp sge <8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i64 = icmp sge <4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i64 = icmp sge <8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i64 = icmp sge <vscale x 1 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i64 = icmp sge <vscale x 2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i64 = icmp sge <vscale x 4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i64 = icmp sge <vscale x 8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i64 = icmp sge <vscale x 2 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i64 = icmp sge <vscale x 4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i64 = icmp sge <vscale x 8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2i8 = icmp sge <2 x i8> undef, undef
@@ -705,38 +705,38 @@ define void @icmp_slt() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8 = icmp slt <4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8 = icmp slt <8 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8 = icmp slt <16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8 = icmp slt <32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v32i8 = icmp slt <32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i8 = icmp slt <vscale x 1 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i8 = icmp slt <vscale x 2 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i8 = icmp slt <vscale x 4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i8 = icmp slt <vscale x 8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i8 = icmp slt <vscale x 16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv32i8 = icmp slt <vscale x 32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv16i8 = icmp slt <vscale x 16 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv32i8 = icmp slt <vscale x 32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16 = icmp slt <2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16 = icmp slt <4 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16 = icmp slt <8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16 = icmp slt <16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16i16 = icmp slt <16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i16 = icmp slt <vscale x 1 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i16 = icmp slt <vscale x 2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i16 = icmp slt <vscale x 4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i16 = icmp slt <vscale x 8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i16 = icmp slt <vscale x 16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8i16 = icmp slt <vscale x 8 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16i16 = icmp slt <vscale x 16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32 = icmp slt <2 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32 = icmp slt <4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32 = icmp slt <8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32 = icmp slt <16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i32 = icmp slt <8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i32 = icmp slt <16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i32 = icmp slt <vscale x 1 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i32 = icmp slt <vscale x 2 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i32 = icmp slt <vscale x 4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i32 = icmp slt <vscale x 8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i32 = icmp slt <vscale x 16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4i32 = icmp slt <vscale x 4 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8i32 = icmp slt <vscale x 8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16i32 = icmp slt <vscale x 16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64 = icmp slt <2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64 = icmp slt <4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64 = icmp slt <8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i64 = icmp slt <4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i64 = icmp slt <8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i64 = icmp slt <vscale x 1 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i64 = icmp slt <vscale x 2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i64 = icmp slt <vscale x 4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i64 = icmp slt <vscale x 8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i64 = icmp slt <vscale x 2 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i64 = icmp slt <vscale x 4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i64 = icmp slt <vscale x 8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2i8 = icmp slt <2 x i8> undef, undef
@@ -792,38 +792,38 @@ define void @icmp_sle() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i8 = icmp sle <4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i8 = icmp sle <8 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i8 = icmp sle <16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v32i8 = icmp sle <32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v32i8 = icmp sle <32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i8 = icmp sle <vscale x 1 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i8 = icmp sle <vscale x 2 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i8 = icmp sle <vscale x 4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i8 = icmp sle <vscale x 8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i8 = icmp sle <vscale x 16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv32i8 = icmp sle <vscale x 32 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv16i8 = icmp sle <vscale x 16 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv32i8 = icmp sle <vscale x 32 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i16 = icmp sle <2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i16 = icmp sle <4 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i16 = icmp sle <8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i16 = icmp sle <16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16i16 = icmp sle <16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i16 = icmp sle <vscale x 1 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i16 = icmp sle <vscale x 2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i16 = icmp sle <vscale x 4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i16 = icmp sle <vscale x 8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i16 = icmp sle <vscale x 16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8i16 = icmp sle <vscale x 8 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16i16 = icmp sle <vscale x 16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i32 = icmp sle <2 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i32 = icmp sle <4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i32 = icmp sle <8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16i32 = icmp sle <16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8i32 = icmp sle <8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16i32 = icmp sle <16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i32 = icmp sle <vscale x 1 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i32 = icmp sle <vscale x 2 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i32 = icmp sle <vscale x 4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i32 = icmp sle <vscale x 8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16i32 = icmp sle <vscale x 16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4i32 = icmp sle <vscale x 4 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8i32 = icmp sle <vscale x 8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16i32 = icmp sle <vscale x 16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2i64 = icmp sle <2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4i64 = icmp sle <4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8i64 = icmp sle <8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4i64 = icmp sle <4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8i64 = icmp sle <8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1i64 = icmp sle <vscale x 1 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2i64 = icmp sle <vscale x 2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4i64 = icmp sle <vscale x 4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8i64 = icmp sle <vscale x 8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2i64 = icmp sle <vscale x 2 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4i64 = icmp sle <vscale x 4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8i64 = icmp sle <vscale x 8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2i8 = icmp sle <2 x i8> undef, undef
@@ -878,28 +878,28 @@ define void @fcmp_oeq() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f16 = fcmp oeq <2 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f16 = fcmp oeq <4 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f16 = fcmp oeq <8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f16 = fcmp oeq <16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16f16 = fcmp oeq <16 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f16 = fcmp oeq <vscale x 1 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f16 = fcmp oeq <vscale x 2 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f16 = fcmp oeq <vscale x 4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8f16 = fcmp oeq <vscale x 8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16f16 = fcmp oeq <vscale x 16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8f16 = fcmp oeq <vscale x 8 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16f16 = fcmp oeq <vscale x 16 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32 = fcmp oeq <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32 = fcmp oeq <4 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32 = fcmp oeq <8 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32 = fcmp oeq <16 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f32 = fcmp oeq <8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16f32 = fcmp oeq <16 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f32 = fcmp oeq <vscale x 1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f32 = fcmp oeq <vscale x 2 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f32 = fcmp oeq <vscale x 4 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8f32 = fcmp oeq <vscale x 8 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16f32 = fcmp oeq <vscale x 16 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4f32 = fcmp oeq <vscale x 4 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8f32 = fcmp oeq <vscale x 8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16f32 = fcmp oeq <vscale x 16 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f64 = fcmp oeq <2 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f64 = fcmp oeq <4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f64 = fcmp oeq <8 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4f64 = fcmp oeq <4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8f64 = fcmp oeq <8 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f64 = fcmp oeq <vscale x 1 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f64 = fcmp oeq <vscale x 2 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f64 = fcmp oeq <vscale x 4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8f64 = fcmp oeq <vscale x 8 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2f64 = fcmp oeq <vscale x 2 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4f64 = fcmp oeq <vscale x 4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8f64 = fcmp oeq <vscale x 8 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2f16 = fcmp oeq <2 x half> undef, undef
@@ -1004,28 +1004,28 @@ define void @fcmp_olt() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f16 = fcmp olt <2 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f16 = fcmp olt <4 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f16 = fcmp olt <8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f16 = fcmp olt <16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16f16 = fcmp olt <16 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f16 = fcmp olt <vscale x 1 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f16 = fcmp olt <vscale x 2 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f16 = fcmp olt <vscale x 4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8f16 = fcmp olt <vscale x 8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16f16 = fcmp olt <vscale x 16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8f16 = fcmp olt <vscale x 8 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16f16 = fcmp olt <vscale x 16 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32 = fcmp olt <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32 = fcmp olt <4 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32 = fcmp olt <8 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32 = fcmp olt <16 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f32 = fcmp olt <8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16f32 = fcmp olt <16 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f32 = fcmp olt <vscale x 1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f32 = fcmp olt <vscale x 2 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f32 = fcmp olt <vscale x 4 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8f32 = fcmp olt <vscale x 8 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16f32 = fcmp olt <vscale x 16 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4f32 = fcmp olt <vscale x 4 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8f32 = fcmp olt <vscale x 8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16f32 = fcmp olt <vscale x 16 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f64 = fcmp olt <2 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f64 = fcmp olt <4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f64 = fcmp olt <8 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4f64 = fcmp olt <4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8f64 = fcmp olt <8 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f64 = fcmp olt <vscale x 1 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f64 = fcmp olt <vscale x 2 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f64 = fcmp olt <vscale x 4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8f64 = fcmp olt <vscale x 8 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2f64 = fcmp olt <vscale x 2 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4f64 = fcmp olt <vscale x 4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8f64 = fcmp olt <vscale x 8 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2f16 = fcmp olt <2 x half> undef, undef
@@ -1067,28 +1067,28 @@ define void @fcmp_ole() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f16 = fcmp ole <2 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f16 = fcmp ole <4 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f16 = fcmp ole <8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f16 = fcmp ole <16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16f16 = fcmp ole <16 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f16 = fcmp ole <vscale x 1 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f16 = fcmp ole <vscale x 2 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f16 = fcmp ole <vscale x 4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8f16 = fcmp ole <vscale x 8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16f16 = fcmp ole <vscale x 16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8f16 = fcmp ole <vscale x 8 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16f16 = fcmp ole <vscale x 16 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32 = fcmp ole <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32 = fcmp ole <4 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32 = fcmp ole <8 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32 = fcmp ole <16 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f32 = fcmp ole <8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16f32 = fcmp ole <16 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f32 = fcmp ole <vscale x 1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f32 = fcmp ole <vscale x 2 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f32 = fcmp ole <vscale x 4 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8f32 = fcmp ole <vscale x 8 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16f32 = fcmp ole <vscale x 16 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4f32 = fcmp ole <vscale x 4 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8f32 = fcmp ole <vscale x 8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16f32 = fcmp ole <vscale x 16 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f64 = fcmp ole <2 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f64 = fcmp ole <4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f64 = fcmp ole <8 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4f64 = fcmp ole <4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8f64 = fcmp ole <8 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f64 = fcmp ole <vscale x 1 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f64 = fcmp ole <vscale x 2 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f64 = fcmp ole <vscale x 4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8f64 = fcmp ole <vscale x 8 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2f64 = fcmp ole <vscale x 2 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4f64 = fcmp ole <vscale x 4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8f64 = fcmp ole <vscale x 8 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2f16 = fcmp ole <2 x half> undef, undef
@@ -1130,28 +1130,28 @@ define void @fcmp_ogt() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f16 = fcmp ogt <2 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f16 = fcmp ogt <4 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f16 = fcmp ogt <8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f16 = fcmp ogt <16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16f16 = fcmp ogt <16 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f16 = fcmp ogt <vscale x 1 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f16 = fcmp ogt <vscale x 2 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f16 = fcmp ogt <vscale x 4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8f16 = fcmp ogt <vscale x 8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16f16 = fcmp ogt <vscale x 16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8f16 = fcmp ogt <vscale x 8 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16f16 = fcmp ogt <vscale x 16 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32 = fcmp ogt <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32 = fcmp ogt <4 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32 = fcmp ogt <8 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32 = fcmp ogt <16 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f32 = fcmp ogt <8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16f32 = fcmp ogt <16 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f32 = fcmp ogt <vscale x 1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f32 = fcmp ogt <vscale x 2 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f32 = fcmp ogt <vscale x 4 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8f32 = fcmp ogt <vscale x 8 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16f32 = fcmp ogt <vscale x 16 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4f32 = fcmp ogt <vscale x 4 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8f32 = fcmp ogt <vscale x 8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16f32 = fcmp ogt <vscale x 16 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f64 = fcmp ogt <2 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f64 = fcmp ogt <4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f64 = fcmp ogt <8 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4f64 = fcmp ogt <4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8f64 = fcmp ogt <8 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f64 = fcmp ogt <vscale x 1 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f64 = fcmp ogt <vscale x 2 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f64 = fcmp ogt <vscale x 4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8f64 = fcmp ogt <vscale x 8 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2f64 = fcmp ogt <vscale x 2 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4f64 = fcmp ogt <vscale x 4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8f64 = fcmp ogt <vscale x 8 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2f16 = fcmp ogt <2 x half> undef, undef
@@ -1193,28 +1193,28 @@ define void @fcmp_oge() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f16 = fcmp oge <2 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f16 = fcmp oge <4 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f16 = fcmp oge <8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f16 = fcmp oge <16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16f16 = fcmp oge <16 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f16 = fcmp oge <vscale x 1 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f16 = fcmp oge <vscale x 2 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f16 = fcmp oge <vscale x 4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8f16 = fcmp oge <vscale x 8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16f16 = fcmp oge <vscale x 16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8f16 = fcmp oge <vscale x 8 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16f16 = fcmp oge <vscale x 16 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32 = fcmp oge <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32 = fcmp oge <4 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32 = fcmp oge <8 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32 = fcmp oge <16 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f32 = fcmp oge <8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16f32 = fcmp oge <16 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f32 = fcmp oge <vscale x 1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f32 = fcmp oge <vscale x 2 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f32 = fcmp oge <vscale x 4 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8f32 = fcmp oge <vscale x 8 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16f32 = fcmp oge <vscale x 16 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4f32 = fcmp oge <vscale x 4 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8f32 = fcmp oge <vscale x 8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16f32 = fcmp oge <vscale x 16 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f64 = fcmp oge <2 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f64 = fcmp oge <4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f64 = fcmp oge <8 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4f64 = fcmp oge <4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8f64 = fcmp oge <8 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f64 = fcmp oge <vscale x 1 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f64 = fcmp oge <vscale x 2 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f64 = fcmp oge <vscale x 4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8f64 = fcmp oge <vscale x 8 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2f64 = fcmp oge <vscale x 2 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4f64 = fcmp oge <vscale x 4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8f64 = fcmp oge <vscale x 8 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2f16 = fcmp oge <2 x half> undef, undef
@@ -1319,28 +1319,28 @@ define void @fcmp_une() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f16 = fcmp une <2 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f16 = fcmp une <4 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f16 = fcmp une <8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f16 = fcmp une <16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v16f16 = fcmp une <16 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f16 = fcmp une <vscale x 1 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f16 = fcmp une <vscale x 2 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f16 = fcmp une <vscale x 4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8f16 = fcmp une <vscale x 8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16f16 = fcmp une <vscale x 16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv8f16 = fcmp une <vscale x 8 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv16f16 = fcmp une <vscale x 16 x half> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f32 = fcmp une <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f32 = fcmp une <4 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f32 = fcmp une <8 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v16f32 = fcmp une <16 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v8f32 = fcmp une <8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v16f32 = fcmp une <16 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f32 = fcmp une <vscale x 1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f32 = fcmp une <vscale x 2 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f32 = fcmp une <vscale x 4 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8f32 = fcmp une <vscale x 8 x float> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv16f32 = fcmp une <vscale x 16 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv4f32 = fcmp une <vscale x 4 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv8f32 = fcmp une <vscale x 8 x float> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv16f32 = fcmp une <vscale x 16 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2f64 = fcmp une <2 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v4f64 = fcmp une <4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v8f64 = fcmp une <8 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v4f64 = fcmp une <4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v8f64 = fcmp une <8 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv1f64 = fcmp une <vscale x 1 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv2f64 = fcmp une <vscale x 2 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv4f64 = fcmp une <vscale x 4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %nxv8f64 = fcmp une <vscale x 8 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %nxv2f64 = fcmp une <vscale x 2 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %nxv4f64 = fcmp une <vscale x 4 x double> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %nxv8f64 = fcmp une <vscale x 8 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%v2f16 = fcmp une <2 x half> undef, undef
diff --git a/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll b/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
index 43a03404e8db659..442d431b9165fe6 100644
--- a/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
@@ -50,36 +50,36 @@ define void @vp_fshr() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 2 x i8> @llvm.vp.fshr.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 4 x i8> @llvm.vp.fshr.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 8 x i8> @llvm.vp.fshr.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %9 = call <vscale x 16 x i8> @llvm.vp.fshr.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call <vscale x 32 x i8> @llvm.vp.fshr.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %11 = call <vscale x 64 x i8> @llvm.vp.fshr.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %9 = call <vscale x 16 x i8> @llvm.vp.fshr.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %10 = call <vscale x 32 x i8> @llvm.vp.fshr.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %11 = call <vscale x 64 x i8> @llvm.vp.fshr.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <2 x i16> @llvm.vp.fshr.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <4 x i16> @llvm.vp.fshr.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <8 x i16> @llvm.vp.fshr.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <16 x i16> @llvm.vp.fshr.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %15 = call <16 x i16> @llvm.vp.fshr.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 1 x i16> @llvm.vp.fshr.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef, <vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 2 x i16> @llvm.vp.fshr.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %18 = call <vscale x 4 x i16> @llvm.vp.fshr.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %19 = call <vscale x 8 x i16> @llvm.vp.fshr.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %20 = call <vscale x 16 x i16> @llvm.vp.fshr.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %21 = call <vscale x 32 x i16> @llvm.vp.fshr.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %19 = call <vscale x 8 x i16> @llvm.vp.fshr.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %20 = call <vscale x 16 x i16> @llvm.vp.fshr.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %21 = call <vscale x 32 x i16> @llvm.vp.fshr.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %22 = call <2 x i32> @llvm.vp.fshr.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %23 = call <4 x i32> @llvm.vp.fshr.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %24 = call <8 x i32> @llvm.vp.fshr.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %25 = call <16 x i32> @llvm.vp.fshr.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %24 = call <8 x i32> @llvm.vp.fshr.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %25 = call <16 x i32> @llvm.vp.fshr.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %26 = call <vscale x 1 x i32> @llvm.vp.fshr.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %27 = call <vscale x 2 x i32> @llvm.vp.fshr.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %28 = call <vscale x 4 x i32> @llvm.vp.fshr.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %29 = call <vscale x 8 x i32> @llvm.vp.fshr.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %30 = call <vscale x 16 x i32> @llvm.vp.fshr.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %28 = call <vscale x 4 x i32> @llvm.vp.fshr.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %29 = call <vscale x 8 x i32> @llvm.vp.fshr.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %30 = call <vscale x 16 x i32> @llvm.vp.fshr.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %31 = call <2 x i64> @llvm.vp.fshr.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %32 = call <4 x i64> @llvm.vp.fshr.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %33 = call <8 x i64> @llvm.vp.fshr.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %34 = call <16 x i64> @llvm.vp.fshr.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %32 = call <4 x i64> @llvm.vp.fshr.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %33 = call <8 x i64> @llvm.vp.fshr.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %34 = call <16 x i64> @llvm.vp.fshr.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %35 = call <vscale x 1 x i64> @llvm.vp.fshr.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %36 = call <vscale x 2 x i64> @llvm.vp.fshr.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %37 = call <vscale x 4 x i64> @llvm.vp.fshr.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %38 = call <vscale x 8 x i64> @llvm.vp.fshr.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %36 = call <vscale x 2 x i64> @llvm.vp.fshr.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %37 = call <vscale x 4 x i64> @llvm.vp.fshr.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %38 = call <vscale x 8 x i64> @llvm.vp.fshr.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x i8> @llvm.vp.fshr.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
@@ -133,36 +133,36 @@ define void @vp_fshl() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 2 x i8> @llvm.vp.fshl.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 4 x i8> @llvm.vp.fshl.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 8 x i8> @llvm.vp.fshl.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %9 = call <vscale x 16 x i8> @llvm.vp.fshl.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %10 = call <vscale x 32 x i8> @llvm.vp.fshl.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %11 = call <vscale x 64 x i8> @llvm.vp.fshl.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %9 = call <vscale x 16 x i8> @llvm.vp.fshl.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %10 = call <vscale x 32 x i8> @llvm.vp.fshl.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %11 = call <vscale x 64 x i8> @llvm.vp.fshl.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <2 x i16> @llvm.vp.fshl.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <4 x i16> @llvm.vp.fshl.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <8 x i16> @llvm.vp.fshl.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <16 x i16> @llvm.vp.fshl.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %15 = call <16 x i16> @llvm.vp.fshl.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 1 x i16> @llvm.vp.fshl.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef, <vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 2 x i16> @llvm.vp.fshl.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %18 = call <vscale x 4 x i16> @llvm.vp.fshl.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %19 = call <vscale x 8 x i16> @llvm.vp.fshl.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %20 = call <vscale x 16 x i16> @llvm.vp.fshl.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %21 = call <vscale x 32 x i16> @llvm.vp.fshl.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %19 = call <vscale x 8 x i16> @llvm.vp.fshl.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %20 = call <vscale x 16 x i16> @llvm.vp.fshl.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %21 = call <vscale x 32 x i16> @llvm.vp.fshl.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %22 = call <2 x i32> @llvm.vp.fshl.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %23 = call <4 x i32> @llvm.vp.fshl.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %24 = call <8 x i32> @llvm.vp.fshl.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %25 = call <16 x i32> @llvm.vp.fshl.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %24 = call <8 x i32> @llvm.vp.fshl.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %25 = call <16 x i32> @llvm.vp.fshl.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %26 = call <vscale x 1 x i32> @llvm.vp.fshl.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %27 = call <vscale x 2 x i32> @llvm.vp.fshl.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %28 = call <vscale x 4 x i32> @llvm.vp.fshl.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %29 = call <vscale x 8 x i32> @llvm.vp.fshl.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %30 = call <vscale x 16 x i32> @llvm.vp.fshl.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %28 = call <vscale x 4 x i32> @llvm.vp.fshl.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %29 = call <vscale x 8 x i32> @llvm.vp.fshl.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %30 = call <vscale x 16 x i32> @llvm.vp.fshl.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %31 = call <2 x i64> @llvm.vp.fshl.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %32 = call <4 x i64> @llvm.vp.fshl.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %33 = call <8 x i64> @llvm.vp.fshl.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %34 = call <16 x i64> @llvm.vp.fshl.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %32 = call <4 x i64> @llvm.vp.fshl.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %33 = call <8 x i64> @llvm.vp.fshl.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %34 = call <16 x i64> @llvm.vp.fshl.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %35 = call <vscale x 1 x i64> @llvm.vp.fshl.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %36 = call <vscale x 2 x i64> @llvm.vp.fshl.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %37 = call <vscale x 4 x i64> @llvm.vp.fshl.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %38 = call <vscale x 8 x i64> @llvm.vp.fshl.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %36 = call <vscale x 2 x i64> @llvm.vp.fshl.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %37 = call <vscale x 4 x i64> @llvm.vp.fshl.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %38 = call <vscale x 8 x i64> @llvm.vp.fshl.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x i8> @llvm.vp.fshl.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
@@ -289,28 +289,28 @@ define void @abs() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <2 x i64> @llvm.vp.abs.v2i64(<2 x i64> undef, i1 false, <2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %10 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %11 = call <4 x i64> @llvm.vp.abs.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %12 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x i64> @llvm.vp.abs.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %14 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x i64> @llvm.vp.abs.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %16 = call <16 x i64> @llvm.abs.v16i64(<16 x i64> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %11 = call <4 x i64> @llvm.vp.abs.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %12 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %13 = call <8 x i64> @llvm.vp.abs.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %14 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %15 = call <16 x i64> @llvm.vp.abs.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %16 = call <16 x i64> @llvm.abs.v16i64(<16 x i64> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 2 x i8> @llvm.vp.abs.nxv2i8(<vscale x 2 x i8> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %18 = call <vscale x 2 x i8> @llvm.abs.nxv2i8(<vscale x 2 x i8> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %19 = call <vscale x 4 x i8> @llvm.vp.abs.nxv4i8(<vscale x 4 x i8> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %20 = call <vscale x 4 x i8> @llvm.abs.nxv4i8(<vscale x 4 x i8> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %21 = call <vscale x 8 x i8> @llvm.vp.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %22 = call <vscale x 8 x i8> @llvm.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %23 = call <vscale x 16 x i8> @llvm.vp.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %24 = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %25 = call <vscale x 2 x i64> @llvm.vp.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %26 = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %27 = call <vscale x 4 x i64> @llvm.vp.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %28 = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %29 = call <vscale x 8 x i64> @llvm.vp.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %30 = call <vscale x 8 x i64> @llvm.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %31 = call <vscale x 16 x i64> @llvm.vp.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %32 = call <vscale x 16 x i64> @llvm.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %23 = call <vscale x 16 x i8> @llvm.vp.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %24 = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %25 = call <vscale x 2 x i64> @llvm.vp.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %26 = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %27 = call <vscale x 4 x i64> @llvm.vp.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %28 = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %29 = call <vscale x 8 x i64> @llvm.vp.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %30 = call <vscale x 8 x i64> @llvm.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %31 = call <vscale x 16 x i64> @llvm.vp.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %32 = call <vscale x 16 x i64> @llvm.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call <2 x i8> @llvm.vp.abs.v2i8(<2 x i8> undef, i1 0, <2 x i1> undef, i32 undef)
diff --git a/llvm/test/Analysis/CostModel/RISCV/rvv-select.ll b/llvm/test/Analysis/CostModel/RISCV/rvv-select.ll
index 264a74116449aaa..b80096b057a668b 100644
--- a/llvm/test/Analysis/CostModel/RISCV/rvv-select.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/rvv-select.ll
@@ -22,8 +22,8 @@ define void @select() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %15 = select i1 undef, <vscale x 2 x i1> undef, <vscale x 2 x i1> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %16 = select i1 undef, <vscale x 4 x i1> undef, <vscale x 4 x i1> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %17 = select i1 undef, <vscale x 8 x i1> undef, <vscale x 8 x i1> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %18 = select i1 undef, <vscale x 16 x i1> undef, <vscale x 16 x i1> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %19 = select i1 undef, <vscale x 32 x i1> undef, <vscale x 32 x i1> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %18 = select i1 undef, <vscale x 16 x i1> undef, <vscale x 16 x i1> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %19 = select i1 undef, <vscale x 32 x i1> undef, <vscale x 32 x i1> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %20 = select <vscale x 1 x i1> undef, <vscale x 1 x i1> undef, <vscale x 1 x i1> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %21 = select <vscale x 2 x i1> undef, <vscale x 2 x i1> undef, <vscale x 2 x i1> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %22 = select <vscale x 4 x i1> undef, <vscale x 4 x i1> undef, <vscale x 4 x i1> undef
@@ -47,14 +47,14 @@ define void @select() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %40 = select i1 undef, <vscale x 2 x i8> undef, <vscale x 2 x i8> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %41 = select i1 undef, <vscale x 4 x i8> undef, <vscale x 4 x i8> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %42 = select i1 undef, <vscale x 8 x i8> undef, <vscale x 8 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %43 = select i1 undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %44 = select i1 undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %43 = select i1 undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %44 = select i1 undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %45 = select <vscale x 1 x i1> undef, <vscale x 1 x i8> undef, <vscale x 1 x i8> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %46 = select <vscale x 2 x i1> undef, <vscale x 2 x i8> undef, <vscale x 2 x i8> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %47 = select <vscale x 4 x i1> undef, <vscale x 4 x i8> undef, <vscale x 4 x i8> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %48 = select <vscale x 8 x i1> undef, <vscale x 8 x i8> undef, <vscale x 8 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %49 = select <vscale x 16 x i1> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %50 = select <vscale x 32 x i1> undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %49 = select <vscale x 16 x i1> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %50 = select <vscale x 32 x i1> undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %51 = select i1 undef, i16 undef, i16 undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %52 = select i1 undef, <1 x i16> undef, <1 x i16> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %53 = select i1 undef, <2 x i16> undef, <2 x i16> undef
@@ -71,15 +71,15 @@ define void @select() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %64 = select i1 undef, <vscale x 1 x i16> undef, <vscale x 1 x i16> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %65 = select i1 undef, <vscale x 2 x i16> undef, <vscale x 2 x i16> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %66 = select i1 undef, <vscale x 4 x i16> undef, <vscale x 4 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %67 = select i1 undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %68 = select i1 undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %69 = select i1 undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %67 = select i1 undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %68 = select i1 undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %69 = select i1 undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %70 = select <vscale x 1 x i1> undef, <vscale x 1 x i16> undef, <vscale x 1 x i16> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %71 = select <vscale x 2 x i1> undef, <vscale x 2 x i16> undef, <vscale x 2 x i16> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %72 = select <vscale x 4 x i1> undef, <vscale x 4 x i16> undef, <vscale x 4 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %73 = select <vscale x 8 x i1> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %74 = select <vscale x 16 x i1> undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %75 = select <vscale x 32 x i1> undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %73 = select <vscale x 8 x i1> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %74 = select <vscale x 16 x i1> undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %75 = select <vscale x 32 x i1> undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %76 = select i1 undef, i32 undef, i32 undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %77 = select i1 undef, <1 x i32> undef, <1 x i32> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %78 = select i1 undef, <2 x i32> undef, <2 x i32> undef
@@ -95,16 +95,16 @@ define void @select() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %88 = select <32 x i1> undef, <32 x i32> undef, <32 x i32> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %89 = select i1 undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %90 = select i1 undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %91 = select i1 undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %92 = select i1 undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %93 = select i1 undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %94 = select i1 undef, <vscale x 32 x i32> undef, <vscale x 32 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %91 = select i1 undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %92 = select i1 undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %93 = select i1 undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %94 = select i1 undef, <vscale x 32 x i32> undef, <vscale x 32 x i32> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %95 = select <vscale x 1 x i1> undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %96 = select <vscale x 2 x i1> undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %97 = select <vscale x 4 x i1> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %98 = select <vscale x 8 x i1> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %99 = select <vscale x 16 x i1> undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %100 = select <vscale x 32 x i1> undef, <vscale x 32 x i32> undef, <vscale x 32 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %97 = select <vscale x 4 x i1> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %98 = select <vscale x 8 x i1> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %99 = select <vscale x 16 x i1> undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %100 = select <vscale x 32 x i1> undef, <vscale x 32 x i32> undef, <vscale x 32 x i32> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %101 = select i1 undef, i64 undef, i64 undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %102 = select i1 undef, <1 x i64> undef, <1 x i64> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %103 = select i1 undef, <2 x i64> undef, <2 x i64> undef
@@ -119,17 +119,17 @@ define void @select() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %112 = select <16 x i1> undef, <16 x i64> undef, <16 x i64> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %113 = select <32 x i1> undef, <32 x i64> undef, <32 x i64> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %114 = select i1 undef, <vscale x 1 x i64> undef, <vscale x 1 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %115 = select i1 undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %116 = select i1 undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %117 = select i1 undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %118 = select i1 undef, <vscale x 16 x i64> undef, <vscale x 16 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %119 = select i1 undef, <vscale x 32 x i64> undef, <vscale x 32 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %115 = select i1 undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %116 = select i1 undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %117 = select i1 undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %118 = select i1 undef, <vscale x 16 x i64> undef, <vscale x 16 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %119 = select i1 undef, <vscale x 32 x i64> undef, <vscale x 32 x i64> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %120 = select <vscale x 1 x i1> undef, <vscale x 1 x i64> undef, <vscale x 1 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %121 = select <vscale x 2 x i1> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %122 = select <vscale x 4 x i1> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %123 = select <vscale x 8 x i1> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %124 = select <vscale x 16 x i1> undef, <vscale x 16 x i64> undef, <vscale x 16 x i64> undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %125 = select <vscale x 32 x i1> undef, <vscale x 32 x i64> undef, <vscale x 32 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %121 = select <vscale x 2 x i1> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %122 = select <vscale x 4 x i1> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %123 = select <vscale x 8 x i1> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %124 = select <vscale x 16 x i1> undef, <vscale x 16 x i64> undef, <vscale x 16 x i64> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %125 = select <vscale x 32 x i1> undef, <vscale x 32 x i64> undef, <vscale x 32 x i64> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
select i1 undef, i1 undef, i1 undef
diff --git a/llvm/test/Analysis/CostModel/RISCV/rvv-shuffle.ll b/llvm/test/Analysis/CostModel/RISCV/rvv-shuffle.ll
index bd9f6af89a5cd95..74743300915209f 100644
--- a/llvm/test/Analysis/CostModel/RISCV/rvv-shuffle.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/rvv-shuffle.ll
@@ -91,7 +91,7 @@ define void @vector_reverse() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 69 for instruction: %reverse_nxv8i64 = call <vscale x 8 x i64> @llvm.experimental.vector.reverse.nxv8i64(<vscale x 8 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 138 for instruction: %reverse_nxv16i64 = call <vscale x 16 x i64> @llvm.experimental.vector.reverse.nxv16i64(<vscale x 16 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 276 for instruction: %reverse_nxv32i64 = call <vscale x 32 x i64> @llvm.experimental.vector.reverse.nxv32i64(<vscale x 32 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.experimental.vector.reverse.nxv16i1(<vscale x 16 x i1> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.experimental.vector.reverse.nxv16i1(<vscale x 16 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.experimental.vector.reverse.nxv8i1(<vscale x 8 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.experimental.vector.reverse.nxv4i1(<vscale x 4 x i1> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.experimental.vector.reverse.nxv2i1(<vscale x 2 x i1> undef)
@@ -111,7 +111,7 @@ define void @vector_reverse() {
; SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %reverse_nxv8i64 = call <vscale x 8 x i64> @llvm.experimental.vector.reverse.nxv8i64(<vscale x 8 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %reverse_nxv16i64 = call <vscale x 16 x i64> @llvm.experimental.vector.reverse.nxv16i64(<vscale x 16 x i64> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %reverse_nxv32i64 = call <vscale x 32 x i64> @llvm.experimental.vector.reverse.nxv32i64(<vscale x 32 x i64> undef)
-; SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.experimental.vector.reverse.nxv16i1(<vscale x 16 x i1> undef)
+; SIZE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.experimental.vector.reverse.nxv16i1(<vscale x 16 x i1> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.experimental.vector.reverse.nxv8i1(<vscale x 8 x i1> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.experimental.vector.reverse.nxv4i1(<vscale x 4 x i1> undef)
; SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.experimental.vector.reverse.nxv2i1(<vscale x 2 x i1> undef)
diff --git a/llvm/test/Analysis/CostModel/RISCV/stepvector.ll b/llvm/test/Analysis/CostModel/RISCV/stepvector.ll
index 7d29d2c0cfa6288..c540208df6ff39f 100644
--- a/llvm/test/Analysis/CostModel/RISCV/stepvector.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/stepvector.ll
@@ -12,43 +12,43 @@ define void @stepvector() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 8 x i8> @llvm.experimental.stepvector.nxv8i8()
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 8 x i8> @llvm.experimental.stepvector.nxv8i8()
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 8 x i8> @llvm.experimental.stepvector.nxv8i8()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 16 x i8> @llvm.experimental.stepvector.nxv16i8()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 32 x i8> @llvm.experimental.stepvector.nxv32i8()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 64 x i8> @llvm.experimental.stepvector.nxv64i8()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 16 x i8> @llvm.experimental.stepvector.nxv16i8()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %9 = call <vscale x 32 x i8> @llvm.experimental.stepvector.nxv32i8()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %10 = call <vscale x 64 x i8> @llvm.experimental.stepvector.nxv64i8()
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <vscale x 1 x i16> @llvm.experimental.stepvector.nxv1i16()
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <vscale x 2 x i16> @llvm.experimental.stepvector.nxv2i16()
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <vscale x 4 x i16> @llvm.experimental.stepvector.nxv4i16()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <vscale x 8 x i16> @llvm.experimental.stepvector.nxv8i16()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <vscale x 32 x i16> @llvm.experimental.stepvector.nxv32i16()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %14 = call <vscale x 8 x i16> @llvm.experimental.stepvector.nxv8i16()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %15 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %16 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %17 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %19 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %20 = call <vscale x 32 x i16> @llvm.experimental.stepvector.nxv32i16()
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <vscale x 1 x i32> @llvm.experimental.stepvector.nxv1i32()
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <vscale x 2 x i32> @llvm.experimental.stepvector.nxv2i32()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <vscale x 4 x i32> @llvm.experimental.stepvector.nxv4i32()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 8 x i32> @llvm.experimental.stepvector.nxv8i32()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %23 = call <vscale x 4 x i32> @llvm.experimental.stepvector.nxv4i32()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %24 = call <vscale x 8 x i32> @llvm.experimental.stepvector.nxv8i32()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %25 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %26 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %27 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %28 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %29 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <vscale x 1 x i64> @llvm.experimental.stepvector.nxv1i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %31 = call <vscale x 2 x i64> @llvm.experimental.stepvector.nxv2i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %36 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %37 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %38 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %39 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %40 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %41 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %42 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %43 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %44 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %31 = call <vscale x 2 x i64> @llvm.experimental.stepvector.nxv2i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %32 = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %33 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %34 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %35 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %36 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %37 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %38 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %39 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %40 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %41 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %42 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %43 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %44 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%zero = call <vscale x 1 x i8> @llvm.experimental.stepvector.nxv1i8()
diff --git a/llvm/test/Transforms/SLPVectorizer/RISCV/ctpop.ll b/llvm/test/Transforms/SLPVectorizer/RISCV/ctpop.ll
index 6502693ada79062..88d6536debf8c96 100644
--- a/llvm/test/Transforms/SLPVectorizer/RISCV/ctpop.ll
+++ b/llvm/test/Transforms/SLPVectorizer/RISCV/ctpop.ll
@@ -1,8 +1,12 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
-; RUN: opt < %s -passes=slp-vectorizer -S -mtriple=riscv32 -mattr=+m,+v | FileCheck %s
-; RUN: opt < %s -passes=slp-vectorizer -S -mtriple=riscv64 -mattr=+m,+v | FileCheck %s
-; RUN: opt < %s -passes=slp-vectorizer -S -mtriple=riscv32 -mattr=+v,+zvbb | FileCheck %s
-; RUN: opt < %s -passes=slp-vectorizer -S -mtriple=riscv64 -mattr=+v,+zvbb | FileCheck %s
+; RUN: opt < %s -passes=slp-vectorizer -S -mtriple=riscv32 -mattr=+m,+v \
+; RUN: | FileCheck %s --check-prefixes=CHECK,RV32
+; RUN: opt < %s -passes=slp-vectorizer -S -mtriple=riscv64 -mattr=+m,+v \
+; RUN: | FileCheck %s --check-prefixes=CHECK,RV64
+; RUN: opt < %s -passes=slp-vectorizer -S -mtriple=riscv32 -mattr=+v,+zvbb \
+; RUN: | FileCheck %s --check-prefixes=CHECK,ZVBB
+; RUN: opt < %s -passes=slp-vectorizer -S -mtriple=riscv64 -mattr=+v,+zvbb \
+; RUN: | FileCheck %s --check-prefixes=CHECK,ZVBB32
define <4 x i8> @ctpop_v4i8(ptr %a) {
; CHECK-LABEL: define <4 x i8> @ctpop_v4i8
@@ -80,12 +84,44 @@ entry:
}
define <4 x i64> @ctpop_v4i64(ptr %a) {
-; CHECK-LABEL: define <4 x i64> @ctpop_v4i64
-; CHECK-SAME: (ptr [[A:%.*]]) #[[ATTR0]] {
-; CHECK-NEXT: entry:
-; CHECK-NEXT: [[TMP0:%.*]] = load <4 x i64>, ptr [[A]], align 32
-; CHECK-NEXT: [[TMP1:%.*]] = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> [[TMP0]])
-; CHECK-NEXT: ret <4 x i64> [[TMP1]]
+; RV32-LABEL: define <4 x i64> @ctpop_v4i64
+; RV32-SAME: (ptr [[A:%.*]]) #[[ATTR0]] {
+; RV32-NEXT: entry:
+; RV32-NEXT: [[TMP0:%.*]] = load <4 x i64>, ptr [[A]], align 32
+; RV32-NEXT: [[TMP1:%.*]] = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> [[TMP0]])
+; RV32-NEXT: ret <4 x i64> [[TMP1]]
+;
+; RV64-LABEL: define <4 x i64> @ctpop_v4i64
+; RV64-SAME: (ptr [[A:%.*]]) #[[ATTR0]] {
+; RV64-NEXT: entry:
+; RV64-NEXT: [[TMP0:%.*]] = load <4 x i64>, ptr [[A]], align 32
+; RV64-NEXT: [[VECEXT:%.*]] = extractelement <4 x i64> [[TMP0]], i32 0
+; RV64-NEXT: [[TMP1:%.*]] = call i64 @llvm.ctpop.i64(i64 [[VECEXT]])
+; RV64-NEXT: [[VECINS:%.*]] = insertelement <4 x i64> undef, i64 [[TMP1]], i64 0
+; RV64-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x i64> [[TMP0]], i32 1
+; RV64-NEXT: [[TMP2:%.*]] = call i64 @llvm.ctpop.i64(i64 [[VECEXT_1]])
+; RV64-NEXT: [[VECINS_1:%.*]] = insertelement <4 x i64> [[VECINS]], i64 [[TMP2]], i64 1
+; RV64-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x i64> [[TMP0]], i32 2
+; RV64-NEXT: [[TMP3:%.*]] = call i64 @llvm.ctpop.i64(i64 [[VECEXT_2]])
+; RV64-NEXT: [[VECINS_2:%.*]] = insertelement <4 x i64> [[VECINS_1]], i64 [[TMP3]], i64 2
+; RV64-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x i64> [[TMP0]], i32 3
+; RV64-NEXT: [[TMP4:%.*]] = call i64 @llvm.ctpop.i64(i64 [[VECEXT_3]])
+; RV64-NEXT: [[VECINS_3:%.*]] = insertelement <4 x i64> [[VECINS_2]], i64 [[TMP4]], i64 3
+; RV64-NEXT: ret <4 x i64> [[VECINS_3]]
+;
+; ZVBB-LABEL: define <4 x i64> @ctpop_v4i64
+; ZVBB-SAME: (ptr [[A:%.*]]) #[[ATTR0]] {
+; ZVBB-NEXT: entry:
+; ZVBB-NEXT: [[TMP0:%.*]] = load <4 x i64>, ptr [[A]], align 32
+; ZVBB-NEXT: [[TMP1:%.*]] = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> [[TMP0]])
+; ZVBB-NEXT: ret <4 x i64> [[TMP1]]
+;
+; ZVBB32-LABEL: define <4 x i64> @ctpop_v4i64
+; ZVBB32-SAME: (ptr [[A:%.*]]) #[[ATTR0]] {
+; ZVBB32-NEXT: entry:
+; ZVBB32-NEXT: [[TMP0:%.*]] = load <4 x i64>, ptr [[A]], align 32
+; ZVBB32-NEXT: [[TMP1:%.*]] = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> [[TMP0]])
+; ZVBB32-NEXT: ret <4 x i64> [[TMP1]]
;
entry:
%0 = load <4 x i64>, ptr %a
>From 1cd6c55c2fe784ab39b4d275b7b7183ce9cf735c Mon Sep 17 00:00:00 2001
From: Simeon Krastnikov <simeon.krastnikov at imgtec.com>
Date: Fri, 26 Jan 2024 13:23:31 +0000
Subject: [PATCH 8/8] fixup! [RISCV] Fix missing scaling by LMUL in cost model
---
llvm/test/Transforms/SLPVectorizer/RISCV/ctpop.ll | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/llvm/test/Transforms/SLPVectorizer/RISCV/ctpop.ll b/llvm/test/Transforms/SLPVectorizer/RISCV/ctpop.ll
index 88d6536debf8c96..b59fa2f898a3e18 100644
--- a/llvm/test/Transforms/SLPVectorizer/RISCV/ctpop.ll
+++ b/llvm/test/Transforms/SLPVectorizer/RISCV/ctpop.ll
@@ -6,7 +6,7 @@
; RUN: opt < %s -passes=slp-vectorizer -S -mtriple=riscv32 -mattr=+v,+zvbb \
; RUN: | FileCheck %s --check-prefixes=CHECK,ZVBB
; RUN: opt < %s -passes=slp-vectorizer -S -mtriple=riscv64 -mattr=+v,+zvbb \
-; RUN: | FileCheck %s --check-prefixes=CHECK,ZVBB32
+; RUN: | FileCheck %s --check-prefixes=CHECK,ZVBB64
define <4 x i8> @ctpop_v4i8(ptr %a) {
; CHECK-LABEL: define <4 x i8> @ctpop_v4i8
@@ -116,12 +116,12 @@ define <4 x i64> @ctpop_v4i64(ptr %a) {
; ZVBB-NEXT: [[TMP1:%.*]] = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> [[TMP0]])
; ZVBB-NEXT: ret <4 x i64> [[TMP1]]
;
-; ZVBB32-LABEL: define <4 x i64> @ctpop_v4i64
-; ZVBB32-SAME: (ptr [[A:%.*]]) #[[ATTR0]] {
-; ZVBB32-NEXT: entry:
-; ZVBB32-NEXT: [[TMP0:%.*]] = load <4 x i64>, ptr [[A]], align 32
-; ZVBB32-NEXT: [[TMP1:%.*]] = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> [[TMP0]])
-; ZVBB32-NEXT: ret <4 x i64> [[TMP1]]
+; ZVBB64-LABEL: define <4 x i64> @ctpop_v4i64
+; ZVBB64-SAME: (ptr [[A:%.*]]) #[[ATTR0]] {
+; ZVBB64-NEXT: entry:
+; ZVBB64-NEXT: [[TMP0:%.*]] = load <4 x i64>, ptr [[A]], align 32
+; ZVBB64-NEXT: [[TMP1:%.*]] = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> [[TMP0]])
+; ZVBB64-NEXT: ret <4 x i64> [[TMP1]]
;
entry:
%0 = load <4 x i64>, ptr %a
More information about the llvm-commits
mailing list