[RISCV] Add missing vscale x 1 cost model entries and tests.

[craig.topper]

More tests

[reames]

LGTM

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

 //===-- RISCVTargetTransformInfo.cpp - RISC-V specific TTI ----------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 

 // for the respective intrinsics.  The costs in this table are simply
 // instruction counts with the following adjustments made:
 // * One vsetvli is considered free.
 static const CostTblEntry VectorIntrinsicCostTable[]{
     {Intrinsic::floor, MVT::v2f32, 9},
     {Intrinsic::floor, MVT::v4f32, 9},
     {Intrinsic::floor, MVT::v8f32, 9},
     {Intrinsic::floor, MVT::v16f32, 9},
+    {Intrinsic::floor, MVT::nxv1f32, 9},
     {Intrinsic::floor, MVT::nxv2f32, 9},
     {Intrinsic::floor, MVT::nxv4f32, 9},
     {Intrinsic::floor, MVT::nxv8f32, 9},
     {Intrinsic::floor, MVT::nxv16f32, 9},
     {Intrinsic::floor, MVT::v2f64, 9},
     {Intrinsic::floor, MVT::v4f64, 9},
     {Intrinsic::floor, MVT::v8f64, 9},
     {Intrinsic::floor, MVT::v16f64, 9},
     {Intrinsic::floor, MVT::nxv1f64, 9},
     {Intrinsic::floor, MVT::nxv2f64, 9},
     {Intrinsic::floor, MVT::nxv4f64, 9},
     {Intrinsic::floor, MVT::nxv8f64, 9},
     {Intrinsic::ceil, MVT::v2f32, 9},
     {Intrinsic::ceil, MVT::v4f32, 9},
     {Intrinsic::ceil, MVT::v8f32, 9},
     {Intrinsic::ceil, MVT::v16f32, 9},
+    {Intrinsic::ceil, MVT::nxv1f32, 9},
     {Intrinsic::ceil, MVT::nxv2f32, 9},
     {Intrinsic::ceil, MVT::nxv4f32, 9},
     {Intrinsic::ceil, MVT::nxv8f32, 9},
     {Intrinsic::ceil, MVT::nxv16f32, 9},
     {Intrinsic::ceil, MVT::v2f64, 9},
     {Intrinsic::ceil, MVT::v4f64, 9},
     {Intrinsic::ceil, MVT::v8f64, 9},
     {Intrinsic::ceil, MVT::v16f64, 9},
     {Intrinsic::ceil, MVT::nxv1f64, 9},
     {Intrinsic::ceil, MVT::nxv2f64, 9},
     {Intrinsic::ceil, MVT::nxv4f64, 9},
     {Intrinsic::ceil, MVT::nxv8f64, 9},
     {Intrinsic::trunc, MVT::v2f32, 7},
     {Intrinsic::trunc, MVT::v4f32, 7},
     {Intrinsic::trunc, MVT::v8f32, 7},
     {Intrinsic::trunc, MVT::v16f32, 7},
+    {Intrinsic::trunc, MVT::nxv1f32, 7},
     {Intrinsic::trunc, MVT::nxv2f32, 7},
     {Intrinsic::trunc, MVT::nxv4f32, 7},
     {Intrinsic::trunc, MVT::nxv8f32, 7},
     {Intrinsic::trunc, MVT::nxv16f32, 7},
     {Intrinsic::trunc, MVT::v2f64, 7},
     {Intrinsic::trunc, MVT::v4f64, 7},
     {Intrinsic::trunc, MVT::v8f64, 7},
     {Intrinsic::trunc, MVT::v16f64, 7},
     {Intrinsic::trunc, MVT::nxv1f64, 7},
     {Intrinsic::trunc, MVT::nxv2f64, 7},
     {Intrinsic::trunc, MVT::nxv4f64, 7},
     {Intrinsic::trunc, MVT::nxv8f64, 7},
     {Intrinsic::round, MVT::v2f32, 9},
     {Intrinsic::round, MVT::v4f32, 9},
     {Intrinsic::round, MVT::v8f32, 9},
     {Intrinsic::round, MVT::v16f32, 9},
+    {Intrinsic::round, MVT::nxv1f32, 9},
     {Intrinsic::round, MVT::nxv2f32, 9},
     {Intrinsic::round, MVT::nxv4f32, 9},
     {Intrinsic::round, MVT::nxv8f32, 9},
     {Intrinsic::round, MVT::nxv16f32, 9},
     {Intrinsic::round, MVT::v2f64, 9},
     {Intrinsic::round, MVT::v4f64, 9},
     {Intrinsic::round, MVT::v8f64, 9},
     {Intrinsic::round, MVT::v16f64, 9},
     {Intrinsic::round, MVT::nxv1f64, 9},
     {Intrinsic::round, MVT::nxv2f64, 9},
     {Intrinsic::round, MVT::nxv4f64, 9},
     {Intrinsic::round, MVT::nxv8f64, 9},
     {Intrinsic::roundeven, MVT::v2f32, 9},
     {Intrinsic::roundeven, MVT::v4f32, 9},
     {Intrinsic::roundeven, MVT::v8f32, 9},
     {Intrinsic::roundeven, MVT::v16f32, 9},
+    {Intrinsic::roundeven, MVT::nxv1f32, 9},
     {Intrinsic::roundeven, MVT::nxv2f32, 9},
     {Intrinsic::roundeven, MVT::nxv4f32, 9},
     {Intrinsic::roundeven, MVT::nxv8f32, 9},
     {Intrinsic::roundeven, MVT::nxv16f32, 9},
     {Intrinsic::roundeven, MVT::v2f64, 9},
     {Intrinsic::roundeven, MVT::v4f64, 9},
     {Intrinsic::roundeven, MVT::v8f64, 9},
     {Intrinsic::roundeven, MVT::v16f64, 9},
     {Intrinsic::roundeven, MVT::nxv1f64, 9},
     {Intrinsic::roundeven, MVT::nxv2f64, 9},
     {Intrinsic::roundeven, MVT::nxv4f64, 9},
     {Intrinsic::roundeven, MVT::nxv8f64, 9},
     {Intrinsic::fabs, MVT::v2f32, 1},
     {Intrinsic::fabs, MVT::v4f32, 1},
     {Intrinsic::fabs, MVT::v8f32, 1},
     {Intrinsic::fabs, MVT::v16f32, 1},
+    {Intrinsic::fabs, MVT::nxv1f32, 1},
     {Intrinsic::fabs, MVT::nxv2f32, 1},
     {Intrinsic::fabs, MVT::nxv4f32, 1},
     {Intrinsic::fabs, MVT::nxv8f32, 1},
     {Intrinsic::fabs, MVT::nxv16f32, 1},
     {Intrinsic::fabs, MVT::v2f64, 1},
     {Intrinsic::fabs, MVT::v4f64, 1},
     {Intrinsic::fabs, MVT::v8f64, 1},
     {Intrinsic::fabs, MVT::v16f64, 1},
     {Intrinsic::fabs, MVT::nxv1f64, 1},
     {Intrinsic::fabs, MVT::nxv2f64, 1},
     {Intrinsic::fabs, MVT::nxv4f64, 1},
     {Intrinsic::fabs, MVT::nxv8f64, 1},
     {Intrinsic::sqrt, MVT::v2f32, 1},
     {Intrinsic::sqrt, MVT::v4f32, 1},
     {Intrinsic::sqrt, MVT::v8f32, 1},
     {Intrinsic::sqrt, MVT::v16f32, 1},
+    {Intrinsic::sqrt, MVT::nxv1f32, 1},
     {Intrinsic::sqrt, MVT::nxv2f32, 1},
     {Intrinsic::sqrt, MVT::nxv4f32, 1},
     {Intrinsic::sqrt, MVT::nxv8f32, 1},
     {Intrinsic::sqrt, MVT::nxv16f32, 1},
     {Intrinsic::sqrt, MVT::v2f64, 1},
     {Intrinsic::sqrt, MVT::v4f64, 1},
     {Intrinsic::sqrt, MVT::v8f64, 1},
     {Intrinsic::sqrt, MVT::v16f64, 1},
     {Intrinsic::sqrt, MVT::nxv1f64, 1},
     {Intrinsic::sqrt, MVT::nxv2f64, 1},
     {Intrinsic::sqrt, MVT::nxv4f64, 1},
     {Intrinsic::sqrt, MVT::nxv8f64, 1},
     {Intrinsic::bswap, MVT::v2i16, 3},
     {Intrinsic::bswap, MVT::v4i16, 3},
     {Intrinsic::bswap, MVT::v8i16, 3},
     {Intrinsic::bswap, MVT::v16i16, 3},
+    {Intrinsic::bswap, MVT::nxv1i16, 3},
     {Intrinsic::bswap, MVT::nxv2i16, 3},
     {Intrinsic::bswap, MVT::nxv4i16, 3},
     {Intrinsic::bswap, MVT::nxv8i16, 3},
     {Intrinsic::bswap, MVT::nxv16i16, 3},
     {Intrinsic::bswap, MVT::v2i32, 12},
     {Intrinsic::bswap, MVT::v4i32, 12},
     {Intrinsic::bswap, MVT::v8i32, 12},
     {Intrinsic::bswap, MVT::v16i32, 12},
+    {Intrinsic::bswap, MVT::nxv1i32, 12},
     {Intrinsic::bswap, MVT::nxv2i32, 12},
     {Intrinsic::bswap, MVT::nxv4i32, 12},
     {Intrinsic::bswap, MVT::nxv8i32, 12},
     {Intrinsic::bswap, MVT::nxv16i32, 12},
     {Intrinsic::bswap, MVT::v2i64, 31},
     {Intrinsic::bswap, MVT::v4i64, 31},
     {Intrinsic::bswap, MVT::v8i64, 31},
     {Intrinsic::bswap, MVT::v16i64, 31},
+    {Intrinsic::bswap, MVT::nxv1i64, 31},
     {Intrinsic::bswap, MVT::nxv2i64, 31},
     {Intrinsic::bswap, MVT::nxv4i64, 31},
     {Intrinsic::bswap, MVT::nxv8i64, 31},
     {Intrinsic::bitreverse, MVT::v2i8, 17},
     {Intrinsic::bitreverse, MVT::v4i8, 17},
     {Intrinsic::bitreverse, MVT::v8i8, 17},
     {Intrinsic::bitreverse, MVT::v16i8, 17},
+    {Intrinsic::bitreverse, MVT::nxv1i8, 17},
     {Intrinsic::bitreverse, MVT::nxv2i8, 17},
     {Intrinsic::bitreverse, MVT::nxv4i8, 17},
     {Intrinsic::bitreverse, MVT::nxv8i8, 17},
     {Intrinsic::bitreverse, MVT::nxv16i8, 17},
     {Intrinsic::bitreverse, MVT::v2i16, 24},
     {Intrinsic::bitreverse, MVT::v4i16, 24},
     {Intrinsic::bitreverse, MVT::v8i16, 24},
     {Intrinsic::bitreverse, MVT::v16i16, 24},
+    {Intrinsic::bitreverse, MVT::nxv1i16, 24},
     {Intrinsic::bitreverse, MVT::nxv2i16, 24},
     {Intrinsic::bitreverse, MVT::nxv4i16, 24},
     {Intrinsic::bitreverse, MVT::nxv8i16, 24},
     {Intrinsic::bitreverse, MVT::nxv16i16, 24},
     {Intrinsic::bitreverse, MVT::v2i32, 33},
     {Intrinsic::bitreverse, MVT::v4i32, 33},
     {Intrinsic::bitreverse, MVT::v8i32, 33},
     {Intrinsic::bitreverse, MVT::v16i32, 33},
+    {Intrinsic::bitreverse, MVT::nxv1i32, 33},
     {Intrinsic::bitreverse, MVT::nxv2i32, 33},
     {Intrinsic::bitreverse, MVT::nxv4i32, 33},
     {Intrinsic::bitreverse, MVT::nxv8i32, 33},
     {Intrinsic::bitreverse, MVT::nxv16i32, 33},
     {Intrinsic::bitreverse, MVT::v2i64, 52},
     {Intrinsic::bitreverse, MVT::v4i64, 52},
     {Intrinsic::bitreverse, MVT::v8i64, 52},
     {Intrinsic::bitreverse, MVT::v16i64, 52},
+    {Intrinsic::bitreverse, MVT::nxv1i64, 52},
     {Intrinsic::bitreverse, MVT::nxv2i64, 52},
     {Intrinsic::bitreverse, MVT::nxv4i64, 52},
     {Intrinsic::bitreverse, MVT::nxv8i64, 52},
     {Intrinsic::ctpop, MVT::v2i8, 12},
     {Intrinsic::ctpop, MVT::v4i8, 12},
     {Intrinsic::ctpop, MVT::v8i8, 12},
     {Intrinsic::ctpop, MVT::v16i8, 12},
+    {Intrinsic::ctpop, MVT::nxv1i8, 12},
     {Intrinsic::ctpop, MVT::nxv2i8, 12},
     {Intrinsic::ctpop, MVT::nxv4i8, 12},
     {Intrinsic::ctpop, MVT::nxv8i8, 12},
     {Intrinsic::ctpop, MVT::nxv16i8, 12},
     {Intrinsic::ctpop, MVT::v2i16, 19},
     {Intrinsic::ctpop, MVT::v4i16, 19},
     {Intrinsic::ctpop, MVT::v8i16, 19},
     {Intrinsic::ctpop, MVT::v16i16, 19},
+    {Intrinsic::ctpop, MVT::nxv1i16, 19},
     {Intrinsic::ctpop, MVT::nxv2i16, 19},
     {Intrinsic::ctpop, MVT::nxv4i16, 19},
     {Intrinsic::ctpop, MVT::nxv8i16, 19},
     {Intrinsic::ctpop, MVT::nxv16i16, 19},
     {Intrinsic::ctpop, MVT::v2i32, 20},
     {Intrinsic::ctpop, MVT::v4i32, 20},
     {Intrinsic::ctpop, MVT::v8i32, 20},
     {Intrinsic::ctpop, MVT::v16i32, 20},
+    {Intrinsic::ctpop, MVT::nxv1i32, 20},
     {Intrinsic::ctpop, MVT::nxv2i32, 20},
     {Intrinsic::ctpop, MVT::nxv4i32, 20},
     {Intrinsic::ctpop, MVT::nxv8i32, 20},
     {Intrinsic::ctpop, MVT::nxv16i32, 20},
     {Intrinsic::ctpop, MVT::v2i64, 21},
     {Intrinsic::ctpop, MVT::v4i64, 21},
     {Intrinsic::ctpop, MVT::v8i64, 21},
     {Intrinsic::ctpop, MVT::v16i64, 21},
+    {Intrinsic::ctpop, MVT::nxv1i64, 21},
     {Intrinsic::ctpop, MVT::nxv2i64, 21},
     {Intrinsic::ctpop, MVT::nxv4i64, 21},
     {Intrinsic::ctpop, MVT::nxv8i64, 21},
 };
 
 InstructionCost
 RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
                                     TTI::TargetCostKind CostKind) {

llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v,+f,+d -riscv-v-vector-bits-min=-1 | FileCheck %s
 
 define void @fabs() {
 ; CHECK-LABEL: 'fabs'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call float @llvm.fabs.f32(float undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x float> @llvm.fabs.v2f32(<2 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = 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: %7 = 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: %8 = 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: %9 = 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: %10 = call double @llvm.fabs.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x double> @llvm.fabs.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = 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: %16 = 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: %17 = 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: %18 = call <vscale x 8 x double> @llvm.fabs.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = 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: %7 = 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: %8 = 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: %9 = 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: %10 = 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: %11 = call double @llvm.fabs.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x double> @llvm.fabs.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = 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: %17 = 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: %18 = 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: %19 = call <vscale x 8 x double> @llvm.fabs.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.fabs.f32(float undef)
   call <2 x float> @llvm.fabs.v2f32(<2 x float> undef)
   call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
   call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
   call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.fabs.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.fabs.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.fabs.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.fabs.nvx8f32(<vscale x 8 x float> undef)
   call <vscale x 16 x float> @llvm.fabs.nvx16f32(<vscale x 16 x float> undef)
   call double @llvm.fabs.f64(double undef)
   call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
   call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
   call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
   call <16 x double> @llvm.fabs.v16f64(<16 x double> undef)
   call <vscale x 1 x double> @llvm.fabs.nvx1f64(<vscale x 1 x double> undef)
   call <vscale x 2 x double> @llvm.fabs.nvx2f64(<vscale x 2 x double> undef)
   call <vscale x 4 x double> @llvm.fabs.nvx4f64(<vscale x 4 x double> undef)
   call <vscale x 8 x double> @llvm.fabs.nvx8f64(<vscale x 8 x double> undef)
   ret void
 }
 
 define void @minnum() {
 ; CHECK-LABEL: 'minnum'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call float @llvm.minnum.f32(float undef, float undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %2 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %3 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %4 = call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x float> @llvm.minnum.v16f32(<16 x float> undef, <16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x float> @llvm.minnum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x float> @llvm.minnum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x float> @llvm.minnum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x float> @llvm.minnum.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call double @llvm.minnum.f64(double undef, double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %11 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x double> @llvm.minnum.v16f64(<16 x double> undef, <16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 1 x double> @llvm.minnum.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 2 x double> @llvm.minnum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 4 x double> @llvm.minnum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 8 x double> @llvm.minnum.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 1 x float> @llvm.minnum.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x float> @llvm.minnum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x float> @llvm.minnum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x float> @llvm.minnum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x float> @llvm.minnum.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call double @llvm.minnum.f64(double undef, double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x double> @llvm.minnum.v16f64(<16 x double> undef, <16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x double> @llvm.minnum.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x double> @llvm.minnum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x double> @llvm.minnum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x double> @llvm.minnum.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.minnum.f32(float undef, float undef)
   call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef)
   call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
   call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef)
   call <16 x float> @llvm.minnum.v16f32(<16 x float> undef, <16 x float> undef)
+  call <vscale x 1 x float> @llvm.minnum.nvx1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.minnum.nvx2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.minnum.nvx4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.minnum.nvx8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
   call <vscale x 16 x float> @llvm.minnum.nvx16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
   call double @llvm.minnum.f64(double undef, double undef)
   call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
   call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
   call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef)
   call <16 x double> @llvm.minnum.v16f64(<16 x double> undef, <16 x double> undef)
   call <vscale x 1 x double> @llvm.minnum.nvx1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
   call <vscale x 2 x double> @llvm.minnum.nvx2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
   call <vscale x 4 x double> @llvm.minnum.nvx4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
   call <vscale x 8 x double> @llvm.minnum.nvx8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
   ret void
 }
 
 define void @maxnum() {
 ; CHECK-LABEL: 'maxnum'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call float @llvm.maxnum.f32(float undef, float undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %2 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %3 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %4 = call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x float> @llvm.maxnum.v16f32(<16 x float> undef, <16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x float> @llvm.maxnum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x float> @llvm.maxnum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x float> @llvm.maxnum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x float> @llvm.maxnum.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call double @llvm.maxnum.f64(double undef, double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %11 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x double> @llvm.maxnum.v16f64(<16 x double> undef, <16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 1 x double> @llvm.maxnum.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 2 x double> @llvm.maxnum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 4 x double> @llvm.maxnum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 8 x double> @llvm.maxnum.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 1 x float> @llvm.maxnum.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x float> @llvm.maxnum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x float> @llvm.maxnum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x float> @llvm.maxnum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x float> @llvm.maxnum.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call double @llvm.maxnum.f64(double undef, double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x double> @llvm.maxnum.v16f64(<16 x double> undef, <16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x double> @llvm.maxnum.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x double> @llvm.maxnum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x double> @llvm.maxnum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x double> @llvm.maxnum.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.maxnum.f32(float undef, float undef)
   call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef)
   call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
   call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef)
   call <16 x float> @llvm.maxnum.v16f32(<16 x float> undef, <16 x float> undef)
+  call <vscale x 1 x float> @llvm.maxnum.nvx1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.maxnum.nvx2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.maxnum.nvx4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.maxnum.nvx8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
   call <vscale x 16 x float> @llvm.maxnum.nvx16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
   call double @llvm.maxnum.f64(double undef, double undef)
   call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
   call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
   call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef)
   call <16 x double> @llvm.maxnum.v16f64(<16 x double> undef, <16 x double> undef)
   call <vscale x 1 x double> @llvm.maxnum.nvx1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
   call <vscale x 2 x double> @llvm.maxnum.nvx2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
   call <vscale x 4 x double> @llvm.maxnum.nvx4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
   call <vscale x 8 x double> @llvm.maxnum.nvx8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
   ret void
 }
 
 define void @minimum() {
 ; CHECK-LABEL: 'minimum'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %1 = call float @llvm.minimum.f32(float undef, float undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %2 = call <2 x float> @llvm.minimum.v2f32(<2 x float> undef, <2 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %3 = call <4 x float> @llvm.minimum.v4f32(<4 x float> undef, <4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %4 = call <8 x float> @llvm.minimum.v8f32(<8 x float> undef, <8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %5 = call <16 x float> @llvm.minimum.v16f32(<16 x float> undef, <16 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 2 x float> @llvm.minimum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 4 x float> @llvm.minimum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 8 x float> @llvm.minimum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 16 x float> @llvm.minimum.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.minimum.f64(double undef, double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %11 = call <2 x double> @llvm.minimum.v2f64(<2 x double> undef, <2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %12 = call <4 x double> @llvm.minimum.v4f64(<4 x double> undef, <4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %13 = call <8 x double> @llvm.minimum.v8f64(<8 x double> undef, <8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %14 = call <16 x double> @llvm.minimum.v16f64(<16 x double> undef, <16 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %15 = call <vscale x 1 x double> @llvm.minimum.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 2 x double> @llvm.minimum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 4 x double> @llvm.minimum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 8 x double> @llvm.minimum.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 1 x float> @llvm.minimum.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 2 x float> @llvm.minimum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 4 x float> @llvm.minimum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 8 x float> @llvm.minimum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 16 x float> @llvm.minimum.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.minimum.f64(double undef, double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x double> @llvm.minimum.v2f64(<2 x double> undef, <2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %13 = call <4 x double> @llvm.minimum.v4f64(<4 x double> undef, <4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %14 = call <8 x double> @llvm.minimum.v8f64(<8 x double> undef, <8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %15 = call <16 x double> @llvm.minimum.v16f64(<16 x double> undef, <16 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 1 x double> @llvm.minimum.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x double> @llvm.minimum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x double> @llvm.minimum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x double> @llvm.minimum.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.minimum.f32(float undef, float undef)
   call <2 x float> @llvm.minimum.v2f32(<2 x float> undef, <2 x float> undef)
   call <4 x float> @llvm.minimum.v4f32(<4 x float> undef, <4 x float> undef)
   call <8 x float> @llvm.minimum.v8f32(<8 x float> undef, <8 x float> undef)
   call <16 x float> @llvm.minimum.v16f32(<16 x float> undef, <16 x float> undef)
+  call <vscale x 1 x float> @llvm.minimum.nvx1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.minimum.nvx2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.minimum.nvx4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.minimum.nvx8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
   call <vscale x 16 x float> @llvm.minimum.nvx16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
   call double @llvm.minimum.f64(double undef, double undef)
   call <2 x double> @llvm.minimum.v2f64(<2 x double> undef, <2 x double> undef)
   call <4 x double> @llvm.minimum.v4f64(<4 x double> undef, <4 x double> undef)
   call <8 x double> @llvm.minimum.v8f64(<8 x double> undef, <8 x double> undef)
   call <16 x double> @llvm.minimum.v16f64(<16 x double> undef, <16 x double> undef)
   call <vscale x 1 x double> @llvm.minimum.nvx1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
   call <vscale x 2 x double> @llvm.minimum.nvx2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
   call <vscale x 4 x double> @llvm.minimum.nvx4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
   call <vscale x 8 x double> @llvm.minimum.nvx8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
   ret void
 }
 
 define void @maximum() {
 ; CHECK-LABEL: 'maximum'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %1 = call float @llvm.maximum.f32(float undef, float undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %2 = call <2 x float> @llvm.maximum.v2f32(<2 x float> undef, <2 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %3 = call <4 x float> @llvm.maximum.v4f32(<4 x float> undef, <4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %4 = call <8 x float> @llvm.maximum.v8f32(<8 x float> undef, <8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %5 = call <16 x float> @llvm.maximum.v16f32(<16 x float> undef, <16 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 2 x float> @llvm.maximum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 4 x float> @llvm.maximum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 8 x float> @llvm.maximum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 16 x float> @llvm.maximum.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.maximum.f64(double undef, double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %11 = call <2 x double> @llvm.maximum.v2f64(<2 x double> undef, <2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %12 = call <4 x double> @llvm.maximum.v4f64(<4 x double> undef, <4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %13 = call <8 x double> @llvm.maximum.v8f64(<8 x double> undef, <8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %14 = call <16 x double> @llvm.maximum.v16f64(<16 x double> undef, <16 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %15 = call <vscale x 1 x double> @llvm.maximum.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 2 x double> @llvm.maximum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 4 x double> @llvm.maximum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 8 x double> @llvm.maximum.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 1 x float> @llvm.maximum.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 2 x float> @llvm.maximum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 4 x float> @llvm.maximum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 8 x float> @llvm.maximum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 16 x float> @llvm.maximum.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.maximum.f64(double undef, double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x double> @llvm.maximum.v2f64(<2 x double> undef, <2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %13 = call <4 x double> @llvm.maximum.v4f64(<4 x double> undef, <4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %14 = call <8 x double> @llvm.maximum.v8f64(<8 x double> undef, <8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %15 = call <16 x double> @llvm.maximum.v16f64(<16 x double> undef, <16 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 1 x double> @llvm.maximum.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x double> @llvm.maximum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x double> @llvm.maximum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x double> @llvm.maximum.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.maximum.f32(float undef, float undef)
   call <2 x float> @llvm.maximum.v2f32(<2 x float> undef, <2 x float> undef)
   call <4 x float> @llvm.maximum.v4f32(<4 x float> undef, <4 x float> undef)
   call <8 x float> @llvm.maximum.v8f32(<8 x float> undef, <8 x float> undef)
   call <16 x float> @llvm.maximum.v16f32(<16 x float> undef, <16 x float> undef)
+  call <vscale x 1 x float> @llvm.maximum.nvx1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.maximum.nvx2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.maximum.nvx4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.maximum.nvx8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
   call <vscale x 16 x float> @llvm.maximum.nvx16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
   call double @llvm.maximum.f64(double undef, double undef)
   call <2 x double> @llvm.maximum.v2f64(<2 x double> undef, <2 x double> undef)
   call <4 x double> @llvm.maximum.v4f64(<4 x double> undef, <4 x double> undef)
   call <8 x double> @llvm.maximum.v8f64(<8 x double> undef, <8 x double> undef)
   call <16 x double> @llvm.maximum.v16f64(<16 x double> undef, <16 x double> undef)
   call <vscale x 1 x double> @llvm.maximum.nvx1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
   call <vscale x 2 x double> @llvm.maximum.nvx2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
   call <vscale x 4 x double> @llvm.maximum.nvx4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
   call <vscale x 8 x double> @llvm.maximum.nvx8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
   ret void
 }
 
 define void @copysign() {
 ; CHECK-LABEL: 'copysign'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call float @llvm.copysign.f32(float undef, float undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %2 = call <2 x float> @llvm.copysign.v2f32(<2 x float> undef, <2 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %3 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %4 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x float> @llvm.copysign.v16f32(<16 x float> undef, <16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x float> @llvm.copysign.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x float> @llvm.copysign.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x float> @llvm.copysign.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x float> @llvm.copysign.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call double @llvm.copysign.f64(double undef, double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %11 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x double> @llvm.copysign.v8f64(<8 x double> undef, <8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x double> @llvm.copysign.v16f64(<16 x double> undef, <16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 1 x double> @llvm.copysign.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 2 x double> @llvm.copysign.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 4 x double> @llvm.copysign.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 8 x double> @llvm.copysign.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 1 x float> @llvm.copysign.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x float> @llvm.copysign.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x float> @llvm.copysign.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x float> @llvm.copysign.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x float> @llvm.copysign.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call double @llvm.copysign.f64(double undef, double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <8 x double> @llvm.copysign.v8f64(<8 x double> undef, <8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x double> @llvm.copysign.v16f64(<16 x double> undef, <16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x double> @llvm.copysign.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x double> @llvm.copysign.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x double> @llvm.copysign.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x double> @llvm.copysign.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.copysign.f32(float undef, float undef)
   call <2 x float> @llvm.copysign.v2f32(<2 x float> undef, <2 x float> undef)
   call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
   call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
   call <16 x float> @llvm.copysign.v16f32(<16 x float> undef, <16 x float> undef)
+  call <vscale x 1 x float> @llvm.copysign.nvx1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.copysign.nvx2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.copysign.nvx4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.copysign.nvx8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
   call <vscale x 16 x float> @llvm.copysign.nvx16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
   call double @llvm.copysign.f64(double undef, double undef)
   call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
   call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
   call <8 x double> @llvm.copysign.v8f64(<8 x double> undef, <8 x double> undef)
   call <16 x double> @llvm.copysign.v16f64(<16 x double> undef, <16 x double> undef)
   call <vscale x 1 x double> @llvm.copysign.nvx1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
   call <vscale x 2 x double> @llvm.copysign.nvx2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
   call <vscale x 4 x double> @llvm.copysign.nvx4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
   call <vscale x 8 x double> @llvm.copysign.nvx8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
   ret void
 }
 
 declare float @llvm.fabs.f32(float)
 declare <2 x float> @llvm.fabs.v2f32(<2 x float>)
 declare <4 x float> @llvm.fabs.v4f32(<4 x float>)
 declare <8 x float> @llvm.fabs.v8f32(<8 x float>)
 declare <16 x float> @llvm.fabs.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.fabs.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.fabs.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.fabs.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.fabs.nvx8f32(<vscale x 8 x float>)
 declare <vscale x 16 x float> @llvm.fabs.nvx16f32(<vscale x 16 x float>)
 declare double @llvm.fabs.f64(double)
 declare <2 x double> @llvm.fabs.v2f64(<2 x double>)
 declare <4 x double> @llvm.fabs.v4f64(<4 x double>)
 declare <8 x double> @llvm.fabs.v8f64(<8 x double>)
 declare <16 x double> @llvm.fabs.v16f64(<16 x double>)
 declare <vscale x 1 x double> @llvm.fabs.nvx1f64(<vscale x 1 x double>)
 declare <vscale x 2 x double> @llvm.fabs.nvx2f64(<vscale x 2 x double>)
 declare <vscale x 4 x double> @llvm.fabs.nvx4f64(<vscale x 4 x double>)
 declare <vscale x 8 x double> @llvm.fabs.nvx8f64(<vscale x 8 x double>)
 
 declare float @llvm.minnum.f32(float, float)
 declare <2 x float> @llvm.minnum.v2f32(<2 x float>, <2 x float>)
 declare <4 x float> @llvm.minnum.v4f32(<4 x float>, <4 x float>)
 declare <8 x float> @llvm.minnum.v8f32(<8 x float>, <8 x float>)
 declare <16 x float> @llvm.minnum.v16f32(<16 x float>, <16 x float>)
+declare <vscale x 1 x float> @llvm.minnum.nvx1f32(<vscale x 1 x float>, <vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.minnum.nvx2f32(<vscale x 2 x float>, <vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.minnum.nvx4f32(<vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.minnum.nvx8f32(<vscale x 8 x float>, <vscale x 8 x float>)
 declare <vscale x 16 x float> @llvm.minnum.nvx16f32(<vscale x 16 x float>, <vscale x 16 x float>)
 declare double @llvm.minnum.f64(double, double)
 declare <2 x double> @llvm.minnum.v2f64(<2 x double>, <2 x double>)
 declare <4 x double> @llvm.minnum.v4f64(<4 x double>, <4 x double>)
 declare <8 x double> @llvm.minnum.v8f64(<8 x double>, <8 x double>)
 declare <16 x double> @llvm.minnum.v16f64(<16 x double>, <16 x double>)
 declare <vscale x 1 x double> @llvm.minnum.nvx1f64(<vscale x 1 x double>, <vscale x 1 x double>)
 declare <vscale x 2 x double> @llvm.minnum.nvx2f64(<vscale x 2 x double>, <vscale x 2 x double>)
 declare <vscale x 4 x double> @llvm.minnum.nvx4f64(<vscale x 4 x double>, <vscale x 4 x double>)
 declare <vscale x 8 x double> @llvm.minnum.nvx8f64(<vscale x 8 x double>, <vscale x 8 x double>)
 
 declare float @llvm.maxnum.f32(float, float)
 declare <2 x float> @llvm.maxnum.v2f32(<2 x float>, <2 x float>)
 declare <4 x float> @llvm.maxnum.v4f32(<4 x float>, <4 x float>)
 declare <8 x float> @llvm.maxnum.v8f32(<8 x float>, <8 x float>)
 declare <16 x float> @llvm.maxnum.v16f32(<16 x float>, <16 x float>)
+declare <vscale x 1 x float> @llvm.maxnum.nvx1f32(<vscale x 1 x float>, <vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.maxnum.nvx2f32(<vscale x 2 x float>, <vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.maxnum.nvx4f32(<vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.maxnum.nvx8f32(<vscale x 8 x float>, <vscale x 8 x float>)
 declare <vscale x 16 x float> @llvm.maxnum.nvx16f32(<vscale x 16 x float>, <vscale x 16 x float>)
 declare double @llvm.maxnum.f64(double, double)
 declare <2 x double> @llvm.maxnum.v2f64(<2 x double>, <2 x double>)
 declare <4 x double> @llvm.maxnum.v4f64(<4 x double>, <4 x double>)
 declare <8 x double> @llvm.maxnum.v8f64(<8 x double>, <8 x double>)
 declare <16 x double> @llvm.maxnum.v16f64(<16 x double>, <16 x double>)
 declare <vscale x 1 x double> @llvm.maxnum.nvx1f64(<vscale x 1 x double>, <vscale x 1 x double>)
 declare <vscale x 2 x double> @llvm.maxnum.nvx2f64(<vscale x 2 x double>, <vscale x 2 x double>)
 declare <vscale x 4 x double> @llvm.maxnum.nvx4f64(<vscale x 4 x double>, <vscale x 4 x double>)
 declare <vscale x 8 x double> @llvm.maxnum.nvx8f64(<vscale x 8 x double>, <vscale x 8 x double>)
 
 declare float @llvm.minimum.f32(float, float)
 declare <2 x float> @llvm.minimum.v2f32(<2 x float>, <2 x float>)
 declare <4 x float> @llvm.minimum.v4f32(<4 x float>, <4 x float>)
 declare <8 x float> @llvm.minimum.v8f32(<8 x float>, <8 x float>)
 declare <16 x float> @llvm.minimum.v16f32(<16 x float>, <16 x float>)
+declare <vscale x 1 x float> @llvm.minimum.nvx1f32(<vscale x 1 x float>, <vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.minimum.nvx2f32(<vscale x 2 x float>, <vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.minimum.nvx4f32(<vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.minimum.nvx8f32(<vscale x 8 x float>, <vscale x 8 x float>)
 declare <vscale x 16 x float> @llvm.minimum.nvx16f32(<vscale x 16 x float>, <vscale x 16 x float>)
 declare double @llvm.minimum.f64(double, double)
 declare <2 x double> @llvm.minimum.v2f64(<2 x double>, <2 x double>)
 declare <4 x double> @llvm.minimum.v4f64(<4 x double>, <4 x double>)
 declare <8 x double> @llvm.minimum.v8f64(<8 x double>, <8 x double>)
 declare <16 x double> @llvm.minimum.v16f64(<16 x double>, <16 x double>)
 declare <vscale x 1 x double> @llvm.minimum.nvx1f64(<vscale x 1 x double>, <vscale x 1 x double>)
 declare <vscale x 2 x double> @llvm.minimum.nvx2f64(<vscale x 2 x double>, <vscale x 2 x double>)
 declare <vscale x 4 x double> @llvm.minimum.nvx4f64(<vscale x 4 x double>, <vscale x 4 x double>)
 declare <vscale x 8 x double> @llvm.minimum.nvx8f64(<vscale x 8 x double>, <vscale x 8 x double>)
 
 declare float @llvm.maximum.f32(float, float)
 declare <2 x float> @llvm.maximum.v2f32(<2 x float>, <2 x float>)
 declare <4 x float> @llvm.maximum.v4f32(<4 x float>, <4 x float>)
 declare <8 x float> @llvm.maximum.v8f32(<8 x float>, <8 x float>)
 declare <16 x float> @llvm.maximum.v16f32(<16 x float>, <16 x float>)
+declare <vscale x 1 x float> @llvm.maximum.nvx1f32(<vscale x 1 x float>, <vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.maximum.nvx2f32(<vscale x 2 x float>, <vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.maximum.nvx4f32(<vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.maximum.nvx8f32(<vscale x 8 x float>, <vscale x 8 x float>)
 declare <vscale x 16 x float> @llvm.maximum.nvx16f32(<vscale x 16 x float>, <vscale x 16 x float>)
 declare double @llvm.maximum.f64(double, double)
 declare <2 x double> @llvm.maximum.v2f64(<2 x double>, <2 x double>)
 declare <4 x double> @llvm.maximum.v4f64(<4 x double>, <4 x double>)
 declare <8 x double> @llvm.maximum.v8f64(<8 x double>, <8 x double>)
 declare <16 x double> @llvm.maximum.v16f64(<16 x double>, <16 x double>)
 declare <vscale x 1 x double> @llvm.maximum.nvx1f64(<vscale x 1 x double>, <vscale x 1 x double>)
 declare <vscale x 2 x double> @llvm.maximum.nvx2f64(<vscale x 2 x double>, <vscale x 2 x double>)
 declare <vscale x 4 x double> @llvm.maximum.nvx4f64(<vscale x 4 x double>, <vscale x 4 x double>)
 declare <vscale x 8 x double> @llvm.maximum.nvx8f64(<vscale x 8 x double>, <vscale x 8 x double>)
 
 declare float @llvm.copysign.f32(float, float)
 declare <2 x float> @llvm.copysign.v2f32(<2 x float>, <2 x float>)
 declare <4 x float> @llvm.copysign.v4f32(<4 x float>, <4 x float>)
 declare <8 x float> @llvm.copysign.v8f32(<8 x float>, <8 x float>)
 declare <16 x float> @llvm.copysign.v16f32(<16 x float>, <16 x float>)
+declare <vscale x 1 x float> @llvm.copysign.nvx1f32(<vscale x 1 x float>, <vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.copysign.nvx2f32(<vscale x 2 x float>, <vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.copysign.nvx4f32(<vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.copysign.nvx8f32(<vscale x 8 x float>, <vscale x 8 x float>)
 declare <vscale x 16 x float> @llvm.copysign.nvx16f32(<vscale x 16 x float>, <vscale x 16 x float>)
 declare double @llvm.copysign.f64(double, double)
 declare <2 x double> @llvm.copysign.v2f64(<2 x double>, <2 x double>)
 declare <4 x double> @llvm.copysign.v4f64(<4 x double>, <4 x double>)
 declare <8 x double> @llvm.copysign.v8f64(<8 x double>, <8 x double>)
 declare <16 x double> @llvm.copysign.v16f64(<16 x double>, <16 x double>)
 declare <vscale x 1 x double> @llvm.copysign.nvx1f64(<vscale x 1 x double>, <vscale x 1 x double>)
 declare <vscale x 2 x double> @llvm.copysign.nvx2f64(<vscale x 2 x double>, <vscale x 2 x double>)
 declare <vscale x 4 x double> @llvm.copysign.nvx4f64(<vscale x 4 x double>, <vscale x 4 x double>)
 declare <vscale x 8 x double> @llvm.copysign.nvx8f64(<vscale x 8 x double>, <vscale x 8 x double>)

llvm/test/Analysis/CostModel/RISCV/fp-sqrt-pow.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v,+f,+d -riscv-v-vector-bits-min=-1 | FileCheck %s
 
 define void @sqrt() {
 ; CHECK-LABEL: 'sqrt'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call float @llvm.sqrt.f32(float undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x float> @llvm.sqrt.v2f32(<2 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = 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: %7 = 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: %8 = 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: %9 = 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: %10 = call double @llvm.sqrt.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x double> @llvm.sqrt.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = 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: %16 = 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: %17 = 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: %18 = call <vscale x 8 x double> @llvm.sqrt.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = 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: %7 = 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: %8 = 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: %9 = 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: %10 = 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: %11 = call double @llvm.sqrt.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x double> @llvm.sqrt.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = 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: %17 = 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: %18 = 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: %19 = call <vscale x 8 x double> @llvm.sqrt.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.sqrt.f32(float undef)
   call <2 x float> @llvm.sqrt.v2f32(<2 x float> undef)
   call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
   call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
   call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.sqrt.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.sqrt.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.sqrt.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.sqrt.nvx8f32(<vscale x 8 x float> undef)
   call <vscale x 16 x float> @llvm.sqrt.nvx16f32(<vscale x 16 x float> undef)
   call double @llvm.sqrt.f64(double undef)
   call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
   call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
   call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
   call <16 x double> @llvm.sqrt.v16f64(<16 x double> undef)
   call <vscale x 1 x double> @llvm.sqrt.nvx1f64(<vscale x 1 x double> undef)
   call <vscale x 2 x double> @llvm.sqrt.nvx2f64(<vscale x 2 x double> undef)
   call <vscale x 4 x double> @llvm.sqrt.nvx4f64(<vscale x 4 x double> undef)
   call <vscale x 8 x double> @llvm.sqrt.nvx8f64(<vscale x 8 x double> undef)
   ret void
 }
 
 declare float @llvm.sqrt.f32(float)
 declare <2 x float> @llvm.sqrt.v2f32(<2 x float>)
 declare <4 x float> @llvm.sqrt.v4f32(<4 x float>)
 declare <8 x float> @llvm.sqrt.v8f32(<8 x float>)
 declare <16 x float> @llvm.sqrt.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.sqrt.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.sqrt.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.sqrt.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.sqrt.nvx8f32(<vscale x 8 x float>)
 declare <vscale x 16 x float> @llvm.sqrt.nvx16f32(<vscale x 16 x float>)
 declare double @llvm.sqrt.f64(double)
 declare <2 x double> @llvm.sqrt.v2f64(<2 x double>)
 declare <4 x double> @llvm.sqrt.v4f64(<4 x double>)
 declare <8 x double> @llvm.sqrt.v8f64(<8 x double>)
 declare <16 x double> @llvm.sqrt.v16f64(<16 x double>)
 declare <vscale x 1 x double> @llvm.sqrt.nvx1f64(<vscale x 1 x double>)
 declare <vscale x 2 x double> @llvm.sqrt.nvx2f64(<vscale x 2 x double>)
 declare <vscale x 4 x double> @llvm.sqrt.nvx4f64(<vscale x 4 x double>)
 declare <vscale x 8 x double> @llvm.sqrt.nvx8f64(<vscale x 8 x double>)
 
 define void @pow() {
 ; CHECK-LABEL: 'pow'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %1 = call float @llvm.pow.f32(float undef, float undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %2 = call <2 x float> @llvm.pow.v2f32(<2 x float> undef, <2 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %3 = call <4 x float> @llvm.pow.v4f32(<4 x float> undef, <4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %4 = call <8 x float> @llvm.pow.v8f32(<8 x float> undef, <8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %5 = call <16 x float> @llvm.pow.v16f32(<16 x float> undef, <16 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 2 x float> @llvm.pow.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 8 x float> @llvm.pow.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 16 x float> @llvm.pow.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.pow.f64(double undef, double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %11 = call <2 x double> @llvm.pow.v2f64(<2 x double> undef, <2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %12 = call <4 x double> @llvm.pow.v4f64(<4 x double> undef, <4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %13 = call <8 x double> @llvm.pow.v8f64(<8 x double> undef, <8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %14 = call <16 x double> @llvm.pow.v16f64(<16 x double> undef, <16 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %15 = call <vscale x 1 x double> @llvm.pow.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 2 x double> @llvm.pow.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 4 x double> @llvm.pow.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 8 x double> @llvm.pow.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 1 x float> @llvm.pow.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 2 x float> @llvm.pow.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 8 x float> @llvm.pow.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 16 x float> @llvm.pow.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.pow.f64(double undef, double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x double> @llvm.pow.v2f64(<2 x double> undef, <2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %13 = call <4 x double> @llvm.pow.v4f64(<4 x double> undef, <4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %14 = call <8 x double> @llvm.pow.v8f64(<8 x double> undef, <8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %15 = call <16 x double> @llvm.pow.v16f64(<16 x double> undef, <16 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 1 x double> @llvm.pow.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x double> @llvm.pow.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x double> @llvm.pow.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x double> @llvm.pow.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.pow.f32(float undef, float undef)
   call <2 x float> @llvm.pow.v2f32(<2 x float> undef, <2 x float> undef)
   call <4 x float> @llvm.pow.v4f32(<4 x float> undef, <4 x float> undef)
   call <8 x float> @llvm.pow.v8f32(<8 x float> undef, <8 x float> undef)
   call <16 x float> @llvm.pow.v16f32(<16 x float> undef, <16 x float> undef)
+  call <vscale x 1 x float> @llvm.pow.nvx1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.pow.nvx2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.pow.nvx4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.pow.nvx8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
   call <vscale x 16 x float> @llvm.pow.nvx16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
   call double @llvm.pow.f64(double undef, double undef)
   call <2 x double> @llvm.pow.v2f64(<2 x double> undef, <2 x double> undef)
   call <4 x double> @llvm.pow.v4f64(<4 x double> undef, <4 x double> undef)
   call <8 x double> @llvm.pow.v8f64(<8 x double> undef, <8 x double> undef)
   call <16 x double> @llvm.pow.v16f64(<16 x double> undef, <16 x double> undef)
   call <vscale x 1 x double> @llvm.pow.nvx1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
   call <vscale x 2 x double> @llvm.pow.nvx2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
   call <vscale x 4 x double> @llvm.pow.nvx4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
   call <vscale x 8 x double> @llvm.pow.nvx8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
   ret void
 }
 
 declare float @llvm.pow.f32(float, float)
 declare <2 x float> @llvm.pow.v2f32(<2 x float>, <2 x float>)
 declare <4 x float> @llvm.pow.v4f32(<4 x float>, <4 x float>)
 declare <8 x float> @llvm.pow.v8f32(<8 x float>, <8 x float>)
 declare <16 x float> @llvm.pow.v16f32(<16 x float>, <16 x float>)
+declare <vscale x 1 x float> @llvm.pow.nvx1f32(<vscale x 1 x float>, <vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.pow.nvx2f32(<vscale x 2 x float>, <vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.pow.nvx4f32(<vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.pow.nvx8f32(<vscale x 8 x float>, <vscale x 8 x float>)
 declare <vscale x 16 x float> @llvm.pow.nvx16f32(<vscale x 16 x float>, <vscale x 16 x float>)
 declare double @llvm.pow.f64(double, double)
 declare <2 x double> @llvm.pow.v2f64(<2 x double>, <2 x double>)
 declare <4 x double> @llvm.pow.v4f64(<4 x double>, <4 x double>)
 declare <8 x double> @llvm.pow.v8f64(<8 x double>, <8 x double>)
 declare <16 x double> @llvm.pow.v16f64(<16 x double>, <16 x double>)
 declare <vscale x 1 x double> @llvm.pow.nvx1f64(<vscale x 1 x double>, <vscale x 1 x double>)
 declare <vscale x 2 x double> @llvm.pow.nvx2f64(<vscale x 2 x double>, <vscale x 2 x double>)
 declare <vscale x 4 x double> @llvm.pow.nvx4f64(<vscale x 4 x double>, <vscale x 4 x double>)
 declare <vscale x 8 x double> @llvm.pow.nvx8f64(<vscale x 8 x double>, <vscale x 8 x double>)

llvm/test/Analysis/CostModel/RISCV/fround.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v,+f,+d -riscv-v-vector-bits-min=-1 | FileCheck %s
 
 define void @floor() {
 ; CHECK-LABEL: 'floor'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 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 9 for instruction: %6 = 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: %7 = 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: %8 = 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: %9 = call <vscale x 16 x float> @llvm.floor.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.floor.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %11 = call <2 x double> @llvm.floor.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %12 = call <4 x double> @llvm.floor.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %13 = call <8 x double> @llvm.floor.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %14 = call <16 x double> @llvm.floor.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %15 = 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: %16 = 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: %17 = 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: %18 = call <vscale x 8 x double> @llvm.floor.nxv8f64(<vscale x 8 x double> 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 10 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 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 1 for instruction: ret void
 ;
   call float @llvm.floor.f32(float undef)
   call <2 x float> @llvm.floor.v2f32(<2 x float> undef)
   call <4 x float> @llvm.floor.v4f32(<4 x float> undef)
   call <8 x float> @llvm.floor.v8f32(<8 x float> undef)
   call <16 x float> @llvm.floor.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.floor.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.floor.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.floor.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.floor.nvx8f32(<vscale x 8 x float> undef)
   call <vscale x 16 x float> @llvm.floor.nvx16f32(<vscale x 16 x float> undef)
   call double @llvm.floor.f64(double undef)
   call <2 x double> @llvm.floor.v2f64(<2 x double> undef)
   call <4 x double> @llvm.floor.v4f64(<4 x double> undef)
   call <8 x double> @llvm.floor.v8f64(<8 x double> undef)
   call <16 x double> @llvm.floor.v16f64(<16 x double> undef)
   call <vscale x 1 x double> @llvm.floor.nvx1f64(<vscale x 1 x double> undef)
   call <vscale x 2 x double> @llvm.floor.nvx2f64(<vscale x 2 x double> undef)
   call <vscale x 4 x double> @llvm.floor.nvx5f64(<vscale x 4 x double> undef)
   call <vscale x 8 x double> @llvm.floor.nvx8f64(<vscale x 8 x double> undef)
   ret void
 }
 
 define void @ceil() {
 ; CHECK-LABEL: 'ceil'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 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 9 for instruction: %6 = 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: %7 = 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: %8 = 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: %9 = call <vscale x 16 x float> @llvm.ceil.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.ceil.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %11 = call <2 x double> @llvm.ceil.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %12 = call <4 x double> @llvm.ceil.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %13 = call <8 x double> @llvm.ceil.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %14 = call <16 x double> @llvm.ceil.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %15 = 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: %16 = 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: %17 = 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: %18 = call <vscale x 8 x double> @llvm.ceil.nxv8f64(<vscale x 8 x double> 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 10 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 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 1 for instruction: ret void
 ;
   call float @llvm.ceil.f32(float undef)
   call <2 x float> @llvm.ceil.v2f32(<2 x float> undef)
   call <4 x float> @llvm.ceil.v4f32(<4 x float> undef)
   call <8 x float> @llvm.ceil.v8f32(<8 x float> undef)
   call <16 x float> @llvm.ceil.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.ceil.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.ceil.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.ceil.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.ceil.nvx8f32(<vscale x 8 x float> undef)
   call <vscale x 16 x float> @llvm.ceil.nvx16f32(<vscale x 16 x float> undef)
   call double @llvm.ceil.f64(double undef)
   call <2 x double> @llvm.ceil.v2f64(<2 x double> undef)
   call <4 x double> @llvm.ceil.v4f64(<4 x double> undef)
   call <8 x double> @llvm.ceil.v8f64(<8 x double> undef)
   call <16 x double> @llvm.ceil.v16f64(<16 x double> undef)
   call <vscale x 1 x double> @llvm.ceil.nvx1f64(<vscale x 1 x double> undef)
   call <vscale x 2 x double> @llvm.ceil.nvx2f64(<vscale x 2 x double> undef)
   call <vscale x 4 x double> @llvm.ceil.nvx5f64(<vscale x 4 x double> undef)
   call <vscale x 8 x double> @llvm.ceil.nvx8f64(<vscale x 8 x double> undef)
   ret void
 }
 
 define void @trunc() {
 ; CHECK-LABEL: 'trunc'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 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 7 for instruction: %6 = 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: %7 = 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: %8 = 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: %9 = call <vscale x 16 x float> @llvm.trunc.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.trunc.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %11 = call <2 x double> @llvm.trunc.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %12 = call <4 x double> @llvm.trunc.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %13 = call <8 x double> @llvm.trunc.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %14 = call <16 x double> @llvm.trunc.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %15 = 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: %16 = 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: %17 = 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: %18 = call <vscale x 8 x double> @llvm.trunc.nxv8f64(<vscale x 8 x double> 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 10 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 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 1 for instruction: ret void
 ;
   call float @llvm.trunc.f32(float undef)
   call <2 x float> @llvm.trunc.v2f32(<2 x float> undef)
   call <4 x float> @llvm.trunc.v4f32(<4 x float> undef)
   call <8 x float> @llvm.trunc.v8f32(<8 x float> undef)
   call <16 x float> @llvm.trunc.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.trunc.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.trunc.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.trunc.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.trunc.nvx8f32(<vscale x 8 x float> undef)
   call <vscale x 16 x float> @llvm.trunc.nvx16f32(<vscale x 16 x float> undef)
   call double @llvm.trunc.f64(double undef)
   call <2 x double> @llvm.trunc.v2f64(<2 x double> undef)
   call <4 x double> @llvm.trunc.v4f64(<4 x double> undef)
   call <8 x double> @llvm.trunc.v8f64(<8 x double> undef)
   call <16 x double> @llvm.trunc.v16f64(<16 x double> undef)
   call <vscale x 1 x double> @llvm.trunc.nvx1f64(<vscale x 1 x double> undef)
   call <vscale x 2 x double> @llvm.trunc.nvx2f64(<vscale x 2 x double> undef)
   call <vscale x 4 x double> @llvm.trunc.nvx5f64(<vscale x 4 x double> undef)
   call <vscale x 8 x double> @llvm.trunc.nvx8f64(<vscale x 8 x double> undef)
   ret void
 }
 
 define void @rint() {
 ; CHECK-LABEL: 'rint'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %1 = call float @llvm.rint.f32(float undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %2 = call <2 x float> @llvm.rint.v2f32(<2 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %3 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %4 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %5 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 2 x float> @llvm.rint.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 4 x float> @llvm.rint.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 8 x float> @llvm.rint.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 16 x float> @llvm.rint.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.rint.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %11 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %12 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %13 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %14 = call <16 x double> @llvm.rint.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %15 = call <vscale x 1 x double> @llvm.rint.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 2 x double> @llvm.rint.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 4 x double> @llvm.rint.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 8 x double> @llvm.rint.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 1 x float> @llvm.rint.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 2 x float> @llvm.rint.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 4 x float> @llvm.rint.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 8 x float> @llvm.rint.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost 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 10 for instruction: %11 = call double @llvm.rint.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %13 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %14 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %15 = call <16 x double> @llvm.rint.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 1 x double> @llvm.rint.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x double> @llvm.rint.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x double> @llvm.rint.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost 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 1 for instruction: ret void
 ;
   call float @llvm.rint.f32(float undef)
   call <2 x float> @llvm.rint.v2f32(<2 x float> undef)
   call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
   call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
   call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.rint.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.rint.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.rint.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.rint.nvx8f32(<vscale x 8 x float> undef)
   call <vscale x 16 x float> @llvm.rint.nvx16f32(<vscale x 16 x float> undef)
   call double @llvm.rint.f64(double undef)
   call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
   call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
   call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
   call <16 x double> @llvm.rint.v16f64(<16 x double> undef)
   call <vscale x 1 x double> @llvm.rint.nvx1f64(<vscale x 1 x double> undef)
   call <vscale x 2 x double> @llvm.rint.nvx2f64(<vscale x 2 x double> undef)
   call <vscale x 4 x double> @llvm.rint.nvx5f64(<vscale x 4 x double> undef)
   call <vscale x 8 x double> @llvm.rint.nvx8f64(<vscale x 8 x double> undef)
   ret void
 }
 
 define void @nearbyint() {
 ; CHECK-LABEL: '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 23 for instruction: %2 = call <2 x float> @llvm.nearbyint.v2f32(<2 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %3 = call <4 x float> @llvm.nearbyint.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %4 = call <8 x float> @llvm.nearbyint.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %5 = call <16 x float> @llvm.nearbyint.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 2 x float> @llvm.nearbyint.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 4 x float> @llvm.nearbyint.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 8 x float> @llvm.nearbyint.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = 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: %10 = call double @llvm.nearbyint.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %11 = call <2 x double> @llvm.nearbyint.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %12 = call <4 x double> @llvm.nearbyint.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %13 = call <8 x double> @llvm.nearbyint.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %14 = call <16 x double> @llvm.nearbyint.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %15 = call <vscale x 1 x double> @llvm.nearbyint.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 2 x double> @llvm.nearbyint.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 4 x double> @llvm.nearbyint.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 8 x double> @llvm.nearbyint.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 1 x float> @llvm.nearbyint.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 2 x float> @llvm.nearbyint.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 4 x float> @llvm.nearbyint.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 8 x float> @llvm.nearbyint.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost 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 23 for instruction: %12 = call <2 x double> @llvm.nearbyint.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %13 = call <4 x double> @llvm.nearbyint.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %14 = call <8 x double> @llvm.nearbyint.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %15 = call <16 x double> @llvm.nearbyint.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 1 x double> @llvm.nearbyint.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x double> @llvm.nearbyint.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x double> @llvm.nearbyint.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost 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 1 for instruction: ret void
 ;
   call float @llvm.nearbyint.f32(float undef)
   call <2 x float> @llvm.nearbyint.v2f32(<2 x float> undef)
   call <4 x float> @llvm.nearbyint.v4f32(<4 x float> undef)
   call <8 x float> @llvm.nearbyint.v8f32(<8 x float> undef)
   call <16 x float> @llvm.nearbyint.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.nearbyint.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.nearbyint.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.nearbyint.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.nearbyint.nvx8f32(<vscale x 8 x float> undef)
   call <vscale x 16 x float> @llvm.nearbyint.nvx16f32(<vscale x 16 x float> undef)
   call double @llvm.nearbyint.f64(double undef)
   call <2 x double> @llvm.nearbyint.v2f64(<2 x double> undef)
   call <4 x double> @llvm.nearbyint.v4f64(<4 x double> undef)
   call <8 x double> @llvm.nearbyint.v8f64(<8 x double> undef)
   call <16 x double> @llvm.nearbyint.v16f64(<16 x double> undef)
   call <vscale x 1 x double> @llvm.nearbyint.nvx1f64(<vscale x 1 x double> undef)
   call <vscale x 2 x double> @llvm.nearbyint.nvx2f64(<vscale x 2 x double> undef)
   call <vscale x 4 x double> @llvm.nearbyint.nvx5f64(<vscale x 4 x double> undef)
   call <vscale x 8 x double> @llvm.nearbyint.nvx8f64(<vscale x 8 x double> undef)
   ret void
 }
 
 define void @round() {
 ; CHECK-LABEL: 'round'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 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 9 for instruction: %6 = 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: %7 = 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: %8 = 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: %9 = call <vscale x 16 x float> @llvm.round.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.round.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %11 = call <2 x double> @llvm.round.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %12 = call <4 x double> @llvm.round.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %13 = call <8 x double> @llvm.round.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %14 = call <16 x double> @llvm.round.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %15 = 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: %16 = 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: %17 = 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: %18 = call <vscale x 8 x double> @llvm.round.nxv8f64(<vscale x 8 x double> 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 10 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 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 1 for instruction: ret void
 ;
   call float @llvm.round.f32(float undef)
   call <2 x float> @llvm.round.v2f32(<2 x float> undef)
   call <4 x float> @llvm.round.v4f32(<4 x float> undef)
   call <8 x float> @llvm.round.v8f32(<8 x float> undef)
   call <16 x float> @llvm.round.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.round.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.round.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.round.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.round.nvx8f32(<vscale x 8 x float> undef)
   call <vscale x 16 x float> @llvm.round.nvx16f32(<vscale x 16 x float> undef)
   call double @llvm.round.f64(double undef)
   call <2 x double> @llvm.round.v2f64(<2 x double> undef)
   call <4 x double> @llvm.round.v4f64(<4 x double> undef)
   call <8 x double> @llvm.round.v8f64(<8 x double> undef)
   call <16 x double> @llvm.round.v16f64(<16 x double> undef)
   call <vscale x 1 x double> @llvm.round.nvx1f64(<vscale x 1 x double> undef)
   call <vscale x 2 x double> @llvm.round.nvx2f64(<vscale x 2 x double> undef)
   call <vscale x 4 x double> @llvm.round.nvx5f64(<vscale x 4 x double> undef)
   call <vscale x 8 x double> @llvm.round.nvx8f64(<vscale x 8 x double> undef)
   ret void
 }
 
 define void @roundeven() {
 ; CHECK-LABEL: 'roundeven'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 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 9 for instruction: %6 = 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: %7 = 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: %8 = 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: %9 = call <vscale x 16 x float> @llvm.roundeven.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.roundeven.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %11 = call <2 x double> @llvm.roundeven.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %12 = call <4 x double> @llvm.roundeven.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %13 = call <8 x double> @llvm.roundeven.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %14 = call <16 x double> @llvm.roundeven.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %15 = 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: %16 = 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: %17 = 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: %18 = call <vscale x 8 x double> @llvm.roundeven.nxv8f64(<vscale x 8 x double> 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 10 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 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 1 for instruction: ret void
 ;
   call float @llvm.roundeven.f32(float undef)
   call <2 x float> @llvm.roundeven.v2f32(<2 x float> undef)
   call <4 x float> @llvm.roundeven.v4f32(<4 x float> undef)
   call <8 x float> @llvm.roundeven.v8f32(<8 x float> undef)
   call <16 x float> @llvm.roundeven.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.roundeven.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.roundeven.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.roundeven.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.roundeven.nvx8f32(<vscale x 8 x float> undef)
   call <vscale x 16 x float> @llvm.roundeven.nvx16f32(<vscale x 16 x float> undef)
   call double @llvm.roundeven.f64(double undef)
   call <2 x double> @llvm.roundeven.v2f64(<2 x double> undef)
   call <4 x double> @llvm.roundeven.v4f64(<4 x double> undef)
   call <8 x double> @llvm.roundeven.v8f64(<8 x double> undef)
   call <16 x double> @llvm.roundeven.v16f64(<16 x double> undef)
   call <vscale x 1 x double> @llvm.roundeven.nvx1f64(<vscale x 1 x double> undef)
   call <vscale x 2 x double> @llvm.roundeven.nvx2f64(<vscale x 2 x double> undef)
   call <vscale x 4 x double> @llvm.roundeven.nvx5f64(<vscale x 4 x double> undef)
   call <vscale x 8 x double> @llvm.roundeven.nvx8f64(<vscale x 8 x double> undef)
   ret void
 }
 
 declare float @llvm.floor.f32(float)
 declare <2 x float> @llvm.floor.v2f32(<2 x float>)
 declare <4 x float> @llvm.floor.v4f32(<4 x float>)
 declare <8 x float> @llvm.floor.v8f32(<8 x float>)
 declare <16 x float> @llvm.floor.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.floor.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.floor.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.floor.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.floor.nvx8f32(<vscale x 8 x float>)
 declare <vscale x 16 x float> @llvm.floor.nvx16f32(<vscale x 16 x float>)
 declare double @llvm.floor.f64(double)
 declare <2 x double> @llvm.floor.v2f64(<2 x double>)
 declare <4 x double> @llvm.floor.v4f64(<4 x double>)
 declare <8 x double> @llvm.floor.v8f64(<8 x double>)
 declare <16 x double> @llvm.floor.v16f64(<16 x double>)
 declare <vscale x 1 x double> @llvm.floor.nvx1f64(<vscale x 1 x double>)
 declare <vscale x 2 x double> @llvm.floor.nvx2f64(<vscale x 2 x double>)
 declare <vscale x 4 x double> @llvm.floor.nvx5f64(<vscale x 4 x double>)
 declare <vscale x 8 x double> @llvm.floor.nvx8f64(<vscale x 8 x double>)
 
 declare float @llvm.ceil.f32(float)
 declare <2 x float> @llvm.ceil.v2f32(<2 x float>)
 declare <4 x float> @llvm.ceil.v4f32(<4 x float>)
 declare <8 x float> @llvm.ceil.v8f32(<8 x float>)
 declare <16 x float> @llvm.ceil.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.ceil.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.ceil.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.ceil.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.ceil.nvx8f32(<vscale x 8 x float>)
 declare <vscale x 16 x float> @llvm.ceil.nvx16f32(<vscale x 16 x float>)
 declare double @llvm.ceil.f64(double)
 declare <2 x double> @llvm.ceil.v2f64(<2 x double>)
 declare <4 x double> @llvm.ceil.v4f64(<4 x double>)
 declare <8 x double> @llvm.ceil.v8f64(<8 x double>)
 declare <16 x double> @llvm.ceil.v16f64(<16 x double>)
 declare <vscale x 1 x double> @llvm.ceil.nvx1f64(<vscale x 1 x double>)
 declare <vscale x 2 x double> @llvm.ceil.nvx2f64(<vscale x 2 x double>)
 declare <vscale x 4 x double> @llvm.ceil.nvx5f64(<vscale x 4 x double>)
 declare <vscale x 8 x double> @llvm.ceil.nvx8f64(<vscale x 8 x double>)
 
 declare float @llvm.trunc.f32(float)
 declare <2 x float> @llvm.trunc.v2f32(<2 x float>)
 declare <4 x float> @llvm.trunc.v4f32(<4 x float>)
 declare <8 x float> @llvm.trunc.v8f32(<8 x float>)
 declare <16 x float> @llvm.trunc.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.trunc.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.trunc.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.trunc.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.trunc.nvx8f32(<vscale x 8 x float>)
 declare <vscale x 16 x float> @llvm.trunc.nvx16f32(<vscale x 16 x float>)
 declare double @llvm.trunc.f64(double)
 declare <2 x double> @llvm.trunc.v2f64(<2 x double>)
 declare <4 x double> @llvm.trunc.v4f64(<4 x double>)
 declare <8 x double> @llvm.trunc.v8f64(<8 x double>)
 declare <16 x double> @llvm.trunc.v16f64(<16 x double>)
 declare <vscale x 1 x double> @llvm.trunc.nvx1f64(<vscale x 1 x double>)
 declare <vscale x 2 x double> @llvm.trunc.nvx2f64(<vscale x 2 x double>)
 declare <vscale x 4 x double> @llvm.trunc.nvx5f64(<vscale x 4 x double>)
 declare <vscale x 8 x double> @llvm.trunc.nvx8f64(<vscale x 8 x double>)
 
 declare float @llvm.rint.f32(float)
 declare <2 x float> @llvm.rint.v2f32(<2 x float>)
 declare <4 x float> @llvm.rint.v4f32(<4 x float>)
 declare <8 x float> @llvm.rint.v8f32(<8 x float>)
 declare <16 x float> @llvm.rint.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.rint.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.rint.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.rint.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.rint.nvx8f32(<vscale x 8 x float>)
 declare <vscale x 16 x float> @llvm.rint.nvx16f32(<vscale x 16 x float>)
 declare double @llvm.rint.f64(double)
 declare <2 x double> @llvm.rint.v2f64(<2 x double>)
 declare <4 x double> @llvm.rint.v4f64(<4 x double>)
 declare <8 x double> @llvm.rint.v8f64(<8 x double>)
 declare <16 x double> @llvm.rint.v16f64(<16 x double>)
 declare <vscale x 1 x double> @llvm.rint.nvx1f64(<vscale x 1 x double>)
 declare <vscale x 2 x double> @llvm.rint.nvx2f64(<vscale x 2 x double>)
 declare <vscale x 4 x double> @llvm.rint.nvx5f64(<vscale x 4 x double>)
 declare <vscale x 8 x double> @llvm.rint.nvx8f64(<vscale x 8 x double>)
 
 declare float @llvm.nearbyint.f32(float)
 declare <2 x float> @llvm.nearbyint.v2f32(<2 x float>)
 declare <4 x float> @llvm.nearbyint.v4f32(<4 x float>)
 declare <8 x float> @llvm.nearbyint.v8f32(<8 x float>)
 declare <16 x float> @llvm.nearbyint.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.nearbyint.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.nearbyint.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.nearbyint.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.nearbyint.nvx8f32(<vscale x 8 x float>)
 declare <vscale x 16 x float> @llvm.nearbyint.nvx16f32(<vscale x 16 x float>)
 declare double @llvm.nearbyint.f64(double)
 declare <2 x double> @llvm.nearbyint.v2f64(<2 x double>)
 declare <4 x double> @llvm.nearbyint.v4f64(<4 x double>)
 declare <8 x double> @llvm.nearbyint.v8f64(<8 x double>)
 declare <16 x double> @llvm.nearbyint.v16f64(<16 x double>)
 declare <vscale x 1 x double> @llvm.nearbyint.nvx1f64(<vscale x 1 x double>)
 declare <vscale x 2 x double> @llvm.nearbyint.nvx2f64(<vscale x 2 x double>)
 declare <vscale x 4 x double> @llvm.nearbyint.nvx5f64(<vscale x 4 x double>)
 declare <vscale x 8 x double> @llvm.nearbyint.nvx8f64(<vscale x 8 x double>)
 
 declare float @llvm.round.f32(float)
 declare <2 x float> @llvm.round.v2f32(<2 x float>)
 declare <4 x float> @llvm.round.v4f32(<4 x float>)
 declare <8 x float> @llvm.round.v8f32(<8 x float>)
 declare <16 x float> @llvm.round.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.round.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.round.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.round.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.round.nvx8f32(<vscale x 8 x float>)
 declare <vscale x 16 x float> @llvm.round.nvx16f32(<vscale x 16 x float>)
 declare double @llvm.round.f64(double)
 declare <2 x double> @llvm.round.v2f64(<2 x double>)
 declare <4 x double> @llvm.round.v4f64(<4 x double>)
 declare <8 x double> @llvm.round.v8f64(<8 x double>)
 declare <16 x double> @llvm.round.v16f64(<16 x double>)
 declare <vscale x 1 x double> @llvm.round.nvx1f64(<vscale x 1 x double>)
 declare <vscale x 2 x double> @llvm.round.nvx2f64(<vscale x 2 x double>)
 declare <vscale x 4 x double> @llvm.round.nvx5f64(<vscale x 4 x double>)
 declare <vscale x 8 x double> @llvm.round.nvx8f64(<vscale x 8 x double>)
 
 declare float @llvm.roundeven.f32(float)
 declare <2 x float> @llvm.roundeven.v2f32(<2 x float>)
 declare <4 x float> @llvm.roundeven.v4f32(<4 x float>)
 declare <8 x float> @llvm.roundeven.v8f32(<8 x float>)
 declare <16 x float> @llvm.roundeven.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.roundeven.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.roundeven.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.roundeven.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.roundeven.nvx8f32(<vscale x 8 x float>)
 declare <vscale x 16 x float> @llvm.roundeven.nvx16f32(<vscale x 16 x float>)
 declare double @llvm.roundeven.f64(double)
 declare <2 x double> @llvm.roundeven.v2f64(<2 x double>)
 declare <4 x double> @llvm.roundeven.v4f64(<4 x double>)
 declare <8 x double> @llvm.roundeven.v8f64(<8 x double>)
 declare <16 x double> @llvm.roundeven.v16f64(<16 x double>)
 declare <vscale x 1 x double> @llvm.roundeven.nvx1f64(<vscale x 1 x double>)
 declare <vscale x 2 x double> @llvm.roundeven.nvx2f64(<vscale x 2 x double>)
 declare <vscale x 4 x double> @llvm.roundeven.nvx5f64(<vscale x 4 x double>)
 declare <vscale x 8 x double> @llvm.roundeven.nvx8f64(<vscale x 8 x double>)

llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v,+f,+d -riscv-v-vector-bits-min=-1 | FileCheck %s
 
 define void @bswap() {
 ; CHECK-LABEL: 'bswap'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %1 = call i16 @llvm.bswap.i16(i16 undef)
 ; 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 3 for instruction: %6 = 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: %7 = 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: %8 = 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: %9 = 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: %10 = call i32 @llvm.bswap.i32(i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %11 = call <2 x i32> @llvm.bswap.v2i32(<2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %12 = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %13 = call <8 x i32> @llvm.bswap.v8i32(<8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %14 = call <16 x i32> @llvm.bswap.v16i32(<16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %15 = 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: %16 = 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: %17 = 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: %18 = 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: %19 = call i64 @llvm.bswap.i64(i64 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %20 = call <2 x i64> @llvm.bswap.v2i64(<2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %21 = call <4 x i64> @llvm.bswap.v4i64(<4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %22 = call <8 x i64> @llvm.bswap.v8i64(<8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %23 = call <16 x i64> @llvm.bswap.v16i64(<16 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %24 = 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: %25 = 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: %26 = 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: %27 = call <vscale x 16 x i64> @llvm.bswap.nxv16i64(<vscale x 16 x i64> 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 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 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 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 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 1 for instruction: ret void
 ;
   call i16 @llvm.bswap.i16(i16 undef)
   call <2 x i16> @llvm.bswap.v2i16(<2 x i16> undef)
   call <4 x i16> @llvm.bswap.v4i16(<4 x i16> undef)
   call <8 x i16> @llvm.bswap.v8i16(<8 x i16> undef)
   call <16 x i16> @llvm.bswap.v16i16(<16 x i16> undef)
+  call <vscale x 1 x i16> @llvm.bswap.nvx1i16(<vscale x 1 x i16> undef)
   call <vscale x 2 x i16> @llvm.bswap.nvx2i16(<vscale x 2 x i16> undef)
   call <vscale x 4 x i16> @llvm.bswap.nvx4i16(<vscale x 4 x i16> undef)
   call <vscale x 8 x i16> @llvm.bswap.nvx8i16(<vscale x 8 x i16> undef)
   call <vscale x 16 x i16> @llvm.bswap.nvx16i16(<vscale x 16 x i16> undef)
   call i32 @llvm.bswap.i32(i32 undef)
   call <2 x i32> @llvm.bswap.v2i32(<2 x i32> undef)
   call <4 x i32> @llvm.bswap.v4i32(<4 x i32> undef)
   call <8 x i32> @llvm.bswap.v8i32(<8 x i32> undef)
   call <16 x i32> @llvm.bswap.v16i32(<16 x i32> undef)
+  call <vscale x 1 x i32> @llvm.bswap.nvx1i32(<vscale x 1 x i32> undef)
   call <vscale x 2 x i32> @llvm.bswap.nvx2i32(<vscale x 2 x i32> undef)
   call <vscale x 4 x i32> @llvm.bswap.nvx4i32(<vscale x 4 x i32> undef)
   call <vscale x 8 x i32> @llvm.bswap.nvx8i32(<vscale x 8 x i32> undef)
   call <vscale x 16 x i32> @llvm.bswap.nvx16i32(<vscale x 16 x i32> undef)
   call i64 @llvm.bswap.i64(i64 undef)
   call <2 x i64> @llvm.bswap.v2i64(<2 x i64> undef)
   call <4 x i64> @llvm.bswap.v4i64(<4 x i64> undef)
   call <8 x i64> @llvm.bswap.v8i64(<8 x i64> undef)
   call <16 x i64> @llvm.bswap.v16i64(<16 x i64> undef)
+  call <vscale x 1 x i64> @llvm.bswap.nvx1i64(<vscale x 1 x i64> undef)
   call <vscale x 2 x i64> @llvm.bswap.nvx2i64(<vscale x 2 x i64> undef)
   call <vscale x 4 x i64> @llvm.bswap.nvx4i64(<vscale x 4 x i64> undef)
   call <vscale x 8 x i64> @llvm.bswap.nvx8i64(<vscale x 8 x i64> undef)
   call <vscale x 16 x i64> @llvm.bswap.nvx16i64(<vscale x 16 x i64> undef)
   ret void
 }
 
 define void @bitreverse() {
 ; CHECK-LABEL: 'bitreverse'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %1 = call i8 @llvm.bitreverse.i8(i8 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %2 = call <2 x i8> @llvm.bitreverse.v2i8(<2 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %3 = call <4 x i8> @llvm.bitreverse.v4i8(<4 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %4 = call <8 x i8> @llvm.bitreverse.v8i8(<8 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %5 = call <16 x i8> @llvm.bitreverse.v16i8(<16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %6 = 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: %7 = 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: %8 = 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: %9 = 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: %10 = call i16 @llvm.bitreverse.i16(i16 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %11 = call <2 x i16> @llvm.bitreverse.v2i16(<2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %12 = call <4 x i16> @llvm.bitreverse.v4i16(<4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %13 = call <8 x i16> @llvm.bitreverse.v8i16(<8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %14 = call <16 x i16> @llvm.bitreverse.v16i16(<16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %15 = 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: %16 = 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: %17 = 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: %18 = 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: %19 = call i32 @llvm.bitreverse.i32(i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %20 = call <2 x i32> @llvm.bitreverse.v2i32(<2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %21 = call <4 x i32> @llvm.bitreverse.v4i32(<4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %22 = call <8 x i32> @llvm.bitreverse.v8i32(<8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %23 = call <16 x i32> @llvm.bitreverse.v16i32(<16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %24 = 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: %25 = 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: %26 = 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: %27 = 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: %28 = call i64 @llvm.bitreverse.i64(i64 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %29 = call <2 x i64> @llvm.bitreverse.v2i64(<2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %30 = call <4 x i64> @llvm.bitreverse.v4i64(<4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %31 = call <8 x i64> @llvm.bitreverse.v8i64(<8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %32 = call <16 x i64> @llvm.bitreverse.v16i64(<16 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %33 = 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: %34 = 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: %35 = 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: %36 = call <vscale x 16 x i64> @llvm.bitreverse.nxv16i64(<vscale x 16 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %6 = call <vscale x 1 x i8> @llvm.bitreverse.nxv1i8(<vscale x 1 x i8> undef)
+; 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 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 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 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 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 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 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 1 for instruction: ret void
 ;
   call i8 @llvm.bitreverse.i8(i8 undef)
   call <2 x i8> @llvm.bitreverse.v2i8(<2 x i8> undef)
   call <4 x i8> @llvm.bitreverse.v4i8(<4 x i8> undef)
   call <8 x i8> @llvm.bitreverse.v8i8(<8 x i8> undef)
   call <16 x i8> @llvm.bitreverse.v16i8(<16 x i8> undef)
+  call <vscale x 1 x i8> @llvm.bitreverse.nvx1i8(<vscale x 1 x i8> undef)
   call <vscale x 2 x i8> @llvm.bitreverse.nvx2i8(<vscale x 2 x i8> undef)
   call <vscale x 4 x i8> @llvm.bitreverse.nvx4i8(<vscale x 4 x i8> undef)
   call <vscale x 8 x i8> @llvm.bitreverse.nvx8i8(<vscale x 8 x i8> undef)
   call <vscale x 16 x i8> @llvm.bitreverse.nvx16i8(<vscale x 16 x i8> undef)
   call i16 @llvm.bitreverse.i16(i16 undef)
   call <2 x i16> @llvm.bitreverse.v2i16(<2 x i16> undef)
   call <4 x i16> @llvm.bitreverse.v4i16(<4 x i16> undef)
   call <8 x i16> @llvm.bitreverse.v8i16(<8 x i16> undef)
   call <16 x i16> @llvm.bitreverse.v16i16(<16 x i16> undef)
+  call <vscale x 1 x i16> @llvm.bitreverse.nvx1i16(<vscale x 1 x i16> undef)
   call <vscale x 2 x i16> @llvm.bitreverse.nvx2i16(<vscale x 2 x i16> undef)
   call <vscale x 4 x i16> @llvm.bitreverse.nvx4i16(<vscale x 4 x i16> undef)
   call <vscale x 8 x i16> @llvm.bitreverse.nvx8i16(<vscale x 8 x i16> undef)
   call <vscale x 16 x i16> @llvm.bitreverse.nvx16i16(<vscale x 16 x i16> undef)
   call i32 @llvm.bitreverse.i32(i32 undef)
   call <2 x i32> @llvm.bitreverse.v2i32(<2 x i32> undef)
   call <4 x i32> @llvm.bitreverse.v4i32(<4 x i32> undef)
   call <8 x i32> @llvm.bitreverse.v8i32(<8 x i32> undef)
   call <16 x i32> @llvm.bitreverse.v16i32(<16 x i32> undef)
+  call <vscale x 1 x i32> @llvm.bitreverse.nvx1i32(<vscale x 1 x i32> undef)
   call <vscale x 2 x i32> @llvm.bitreverse.nvx2i32(<vscale x 2 x i32> undef)
   call <vscale x 4 x i32> @llvm.bitreverse.nvx4i32(<vscale x 4 x i32> undef)
   call <vscale x 8 x i32> @llvm.bitreverse.nvx8i32(<vscale x 8 x i32> undef)
   call <vscale x 16 x i32> @llvm.bitreverse.nvx16i32(<vscale x 16 x i32> undef)
   call i64 @llvm.bitreverse.i64(i64 undef)
   call <2 x i64> @llvm.bitreverse.v2i64(<2 x i64> undef)
   call <4 x i64> @llvm.bitreverse.v4i64(<4 x i64> undef)
   call <8 x i64> @llvm.bitreverse.v8i64(<8 x i64> undef)
   call <16 x i64> @llvm.bitreverse.v16i64(<16 x i64> undef)
+  call <vscale x 1 x i64> @llvm.bitreverse.nvx1i64(<vscale x 1 x i64> undef)
   call <vscale x 2 x i64> @llvm.bitreverse.nvx2i64(<vscale x 2 x i64> undef)
   call <vscale x 4 x i64> @llvm.bitreverse.nvx4i64(<vscale x 4 x i64> undef)
   call <vscale x 8 x i64> @llvm.bitreverse.nvx8i64(<vscale x 8 x i64> undef)
   call <vscale x 16 x i64> @llvm.bitreverse.nvx16i64(<vscale x 16 x i64> undef)
   ret void
 }
 
 define void @ctpop() {
 ; CHECK-LABEL: 'ctpop'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %1 = call i8 @llvm.ctpop.i8(i8 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %2 = call <2 x i8> @llvm.ctpop.v2i8(<2 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %3 = call <4 x i8> @llvm.ctpop.v4i8(<4 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %4 = call <8 x i8> @llvm.ctpop.v8i8(<8 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %5 = call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %6 = call <vscale x 2 x i8> @llvm.ctpop.nxv2i8(<vscale x 2 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %7 = call <vscale x 4 x i8> @llvm.ctpop.nxv4i8(<vscale x 4 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %8 = call <vscale x 8 x i8> @llvm.ctpop.nxv8i8(<vscale x 8 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %9 = call <vscale x 16 x i8> @llvm.ctpop.nxv16i8(<vscale x 16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %10 = call i16 @llvm.ctpop.i16(i16 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %11 = call <2 x i16> @llvm.ctpop.v2i16(<2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %12 = call <4 x i16> @llvm.ctpop.v4i16(<4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %13 = call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %14 = call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %15 = call <vscale x 2 x i16> @llvm.ctpop.nxv2i16(<vscale x 2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %16 = call <vscale x 4 x i16> @llvm.ctpop.nxv4i16(<vscale x 4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %17 = call <vscale x 8 x i16> @llvm.ctpop.nxv8i16(<vscale x 8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %18 = call <vscale x 16 x i16> @llvm.ctpop.nxv16i16(<vscale x 16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %19 = call i32 @llvm.ctpop.i32(i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %20 = call <2 x i32> @llvm.ctpop.v2i32(<2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %21 = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %22 = call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %23 = call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %24 = call <vscale x 2 x i32> @llvm.ctpop.nxv2i32(<vscale x 2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %25 = call <vscale x 4 x i32> @llvm.ctpop.nxv4i32(<vscale x 4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %26 = call <vscale x 8 x i32> @llvm.ctpop.nxv8i32(<vscale x 8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %27 = call <vscale x 16 x i32> @llvm.ctpop.nxv16i32(<vscale x 16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %28 = call i64 @llvm.ctpop.i64(i64 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %29 = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %30 = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %31 = call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %32 = call <16 x i64> @llvm.ctpop.v16i64(<16 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %33 = call <vscale x 2 x i64> @llvm.ctpop.nxv2i64(<vscale x 2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %34 = call <vscale x 4 x i64> @llvm.ctpop.nxv4i64(<vscale x 4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %35 = call <vscale x 8 x i64> @llvm.ctpop.nxv8i64(<vscale x 8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %36 = call <vscale x 16 x i64> @llvm.ctpop.nxv16i64(<vscale x 16 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %6 = call <vscale x 1 x i8> @llvm.ctpop.nxv1i8(<vscale x 1 x i8> undef)
+; CHECK-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)
+; CHECK-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)
+; CHECK-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)
+; CHECK-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)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %11 = call i16 @llvm.ctpop.i16(i16 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %12 = call <2 x i16> @llvm.ctpop.v2i16(<2 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %13 = call <4 x i16> @llvm.ctpop.v4i16(<4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %14 = call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %15 = call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> undef)
+; CHECK-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)
+; CHECK-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)
+; CHECK-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)
+; CHECK-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)
+; CHECK-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)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %21 = call i32 @llvm.ctpop.i32(i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %22 = call <2 x i32> @llvm.ctpop.v2i32(<2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %23 = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %24 = call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %25 = call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> undef)
+; CHECK-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)
+; CHECK-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)
+; CHECK-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)
+; CHECK-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)
+; CHECK-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)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %31 = call i64 @llvm.ctpop.i64(i64 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %32 = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %33 = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %34 = call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %35 = call <16 x i64> @llvm.ctpop.v16i64(<16 x i64> undef)
+; CHECK-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)
+; CHECK-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)
+; CHECK-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)
+; CHECK-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)
+; CHECK-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)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call i8 @llvm.ctpop.i8(i8 undef)
   call <2 x i8> @llvm.ctpop.v2i8(<2 x i8> undef)
   call <4 x i8> @llvm.ctpop.v4i8(<4 x i8> undef)
   call <8 x i8> @llvm.ctpop.v8i8(<8 x i8> undef)
   call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> undef)
+  call <vscale x 1 x i8> @llvm.ctpop.nvx1i8(<vscale x 1 x i8> undef)
   call <vscale x 2 x i8> @llvm.ctpop.nvx2i8(<vscale x 2 x i8> undef)
   call <vscale x 4 x i8> @llvm.ctpop.nvx4i8(<vscale x 4 x i8> undef)
   call <vscale x 8 x i8> @llvm.ctpop.nvx8i8(<vscale x 8 x i8> undef)
   call <vscale x 16 x i8> @llvm.ctpop.nvx16i8(<vscale x 16 x i8> undef)
   call i16 @llvm.ctpop.i16(i16 undef)
   call <2 x i16> @llvm.ctpop.v2i16(<2 x i16> undef)
   call <4 x i16> @llvm.ctpop.v4i16(<4 x i16> undef)
   call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> undef)
   call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> undef)
+  call <vscale x 1 x i16> @llvm.ctpop.nvx1i16(<vscale x 1 x i16> undef)
   call <vscale x 2 x i16> @llvm.ctpop.nvx2i16(<vscale x 2 x i16> undef)
   call <vscale x 4 x i16> @llvm.ctpop.nvx4i16(<vscale x 4 x i16> undef)
   call <vscale x 8 x i16> @llvm.ctpop.nvx8i16(<vscale x 8 x i16> undef)
   call <vscale x 16 x i16> @llvm.ctpop.nvx16i16(<vscale x 16 x i16> undef)
   call i32 @llvm.ctpop.i32(i32 undef)
   call <2 x i32> @llvm.ctpop.v2i32(<2 x i32> undef)
   call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> undef)
   call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> undef)
   call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> undef)
+  call <vscale x 1 x i32> @llvm.ctpop.nvx1i32(<vscale x 1 x i32> undef)
   call <vscale x 2 x i32> @llvm.ctpop.nvx2i32(<vscale x 2 x i32> undef)
   call <vscale x 4 x i32> @llvm.ctpop.nvx4i32(<vscale x 4 x i32> undef)
   call <vscale x 8 x i32> @llvm.ctpop.nvx8i32(<vscale x 8 x i32> undef)
   call <vscale x 16 x i32> @llvm.ctpop.nvx16i32(<vscale x 16 x i32> undef)
   call i64 @llvm.ctpop.i64(i64 undef)
   call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> undef)
   call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> undef)
   call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> undef)
   call <16 x i64> @llvm.ctpop.v16i64(<16 x i64> undef)
+  call <vscale x 1 x i64> @llvm.ctpop.nvx1i64(<vscale x 1 x i64> undef)
   call <vscale x 2 x i64> @llvm.ctpop.nvx2i64(<vscale x 2 x i64> undef)
   call <vscale x 4 x i64> @llvm.ctpop.nvx4i64(<vscale x 4 x i64> undef)
   call <vscale x 8 x i64> @llvm.ctpop.nvx8i64(<vscale x 8 x i64> undef)
   call <vscale x 16 x i64> @llvm.ctpop.nvx16i64(<vscale x 16 x i64> undef)
   ret void
 }
 
 
 declare i16 @llvm.bswap.i16(i16)
 declare <2 x i16> @llvm.bswap.v2i16(<2 x i16>)
 declare <4 x i16> @llvm.bswap.v4i16(<4 x i16>)
 declare <8 x i16> @llvm.bswap.v8i16(<8 x i16>)
 declare <16 x i16> @llvm.bswap.v16i16(<16 x i16>)
+declare <vscale x 1 x i16> @llvm.bswap.nvx1i16(<vscale x 1 x i16>)
 declare <vscale x 2 x i16> @llvm.bswap.nvx2i16(<vscale x 2 x i16>)
 declare <vscale x 4 x i16> @llvm.bswap.nvx4i16(<vscale x 4 x i16>)
 declare <vscale x 8 x i16> @llvm.bswap.nvx8i16(<vscale x 8 x i16>)
 declare <vscale x 16 x i16> @llvm.bswap.nvx16i16(<vscale x 16 x i16>)
 declare i32 @llvm.bswap.i32(i32)
 declare <2 x i32> @llvm.bswap.v2i32(<2 x i32>)
 declare <4 x i32> @llvm.bswap.v4i32(<4 x i32>)
 declare <8 x i32> @llvm.bswap.v8i32(<8 x i32>)
 declare <16 x i32> @llvm.bswap.v16i32(<16 x i32>)
+declare <vscale x 1 x i32> @llvm.bswap.nvx1i32(<vscale x 1 x i32>)
 declare <vscale x 2 x i32> @llvm.bswap.nvx2i32(<vscale x 2 x i32>)
 declare <vscale x 4 x i32> @llvm.bswap.nvx4i32(<vscale x 4 x i32>)
 declare <vscale x 8 x i32> @llvm.bswap.nvx8i32(<vscale x 8 x i32>)
 declare <vscale x 16 x i32> @llvm.bswap.nvx16i32(<vscale x 16 x i32>)
 declare i64 @llvm.bswap.i64(i64)
 declare <2 x i64> @llvm.bswap.v2i64(<2 x i64>)
 declare <4 x i64> @llvm.bswap.v4i64(<4 x i64>)
 declare <8 x i64> @llvm.bswap.v8i64(<8 x i64>)
 declare <16 x i64> @llvm.bswap.v16i64(<16 x i64>)
+declare <vscale x 1 x i64> @llvm.bswap.nvx1i64(<vscale x 1 x i64>)
 declare <vscale x 2 x i64> @llvm.bswap.nvx2i64(<vscale x 2 x i64>)
 declare <vscale x 4 x i64> @llvm.bswap.nvx4i64(<vscale x 4 x i64>)
 declare <vscale x 8 x i64> @llvm.bswap.nvx8i64(<vscale x 8 x i64>)
 declare <vscale x 16 x i64> @llvm.bswap.nvx16i64(<vscale x 16 x i64>)
 
 declare i8 @llvm.bitreverse.i8(i8)
 declare <2 x i8> @llvm.bitreverse.v2i8(<2 x i8>)
 declare <4 x i8> @llvm.bitreverse.v4i8(<4 x i8>)
 declare <8 x i8> @llvm.bitreverse.v8i8(<8 x i8>)
 declare <16 x i8> @llvm.bitreverse.v16i8(<16 x i8>)
+declare <vscale x 1 x i8> @llvm.bitreverse.nvx1i8(<vscale x 1 x i8>)
 declare <vscale x 2 x i8> @llvm.bitreverse.nvx2i8(<vscale x 2 x i8>)
 declare <vscale x 4 x i8> @llvm.bitreverse.nvx4i8(<vscale x 4 x i8>)
 declare <vscale x 8 x i8> @llvm.bitreverse.nvx8i8(<vscale x 8 x i8>)
 declare <vscale x 16 x i8> @llvm.bitreverse.nvx16i8(<vscale x 16 x i8>)
 declare i16 @llvm.bitreverse.i16(i16)
 declare <2 x i16> @llvm.bitreverse.v2i16(<2 x i16>)
 declare <4 x i16> @llvm.bitreverse.v4i16(<4 x i16>)
 declare <8 x i16> @llvm.bitreverse.v8i16(<8 x i16>)
 declare <16 x i16> @llvm.bitreverse.v16i16(<16 x i16>)
+declare <vscale x 1 x i16> @llvm.bitreverse.nvx1i16(<vscale x 1 x i16>)
 declare <vscale x 2 x i16> @llvm.bitreverse.nvx2i16(<vscale x 2 x i16>)
 declare <vscale x 4 x i16> @llvm.bitreverse.nvx4i16(<vscale x 4 x i16>)
 declare <vscale x 8 x i16> @llvm.bitreverse.nvx8i16(<vscale x 8 x i16>)
 declare <vscale x 16 x i16> @llvm.bitreverse.nvx16i16(<vscale x 16 x i16>)
 declare i32 @llvm.bitreverse.i32(i32)
 declare <2 x i32> @llvm.bitreverse.v2i32(<2 x i32>)
 declare <4 x i32> @llvm.bitreverse.v4i32(<4 x i32>)
 declare <8 x i32> @llvm.bitreverse.v8i32(<8 x i32>)
 declare <16 x i32> @llvm.bitreverse.v16i32(<16 x i32>)
+declare <vscale x 1 x i32> @llvm.bitreverse.nvx1i32(<vscale x 1 x i32>)
 declare <vscale x 2 x i32> @llvm.bitreverse.nvx2i32(<vscale x 2 x i32>)
 declare <vscale x 4 x i32> @llvm.bitreverse.nvx4i32(<vscale x 4 x i32>)
 declare <vscale x 8 x i32> @llvm.bitreverse.nvx8i32(<vscale x 8 x i32>)
 declare <vscale x 16 x i32> @llvm.bitreverse.nvx16i32(<vscale x 16 x i32>)
 declare i64 @llvm.bitreverse.i64(i64)
 declare <2 x i64> @llvm.bitreverse.v2i64(<2 x i64>)
 declare <4 x i64> @llvm.bitreverse.v4i64(<4 x i64>)
 declare <8 x i64> @llvm.bitreverse.v8i64(<8 x i64>)
 declare <16 x i64> @llvm.bitreverse.v16i64(<16 x i64>)
+declare <vscale x 1 x i64> @llvm.bitreverse.nvx1i64(<vscale x 1 x i64>)
 declare <vscale x 2 x i64> @llvm.bitreverse.nvx2i64(<vscale x 2 x i64>)
 declare <vscale x 4 x i64> @llvm.bitreverse.nvx4i64(<vscale x 4 x i64>)
 declare <vscale x 8 x i64> @llvm.bitreverse.nvx8i64(<vscale x 8 x i64>)
 declare <vscale x 16 x i64> @llvm.bitreverse.nvx16i64(<vscale x 16 x i64>)
 
 declare i8 @llvm.ctpop.i8(i8)
 declare <2 x i8> @llvm.ctpop.v2i8(<2 x i8>)
 declare <4 x i8> @llvm.ctpop.v4i8(<4 x i8>)
 declare <8 x i8> @llvm.ctpop.v8i8(<8 x i8>)
 declare <16 x i8> @llvm.ctpop.v16i8(<16 x i8>)
+declare <vscale x 1 x i8> @llvm.ctpop.nvx1i8(<vscale x 1 x i8>)
 declare <vscale x 2 x i8> @llvm.ctpop.nvx2i8(<vscale x 2 x i8>)
 declare <vscale x 4 x i8> @llvm.ctpop.nvx4i8(<vscale x 4 x i8>)
 declare <vscale x 8 x i8> @llvm.ctpop.nvx8i8(<vscale x 8 x i8>)
 declare <vscale x 16 x i8> @llvm.ctpop.nvx16i8(<vscale x 16 x i8>)
 declare i16 @llvm.ctpop.i16(i16)
 declare <2 x i16> @llvm.ctpop.v2i16(<2 x i16>)
 declare <4 x i16> @llvm.ctpop.v4i16(<4 x i16>)
 declare <8 x i16> @llvm.ctpop.v8i16(<8 x i16>)
 declare <16 x i16> @llvm.ctpop.v16i16(<16 x i16>)
+declare <vscale x 1 x i16> @llvm.ctpop.nvx1i16(<vscale x 1 x i16>)
 declare <vscale x 2 x i16> @llvm.ctpop.nvx2i16(<vscale x 2 x i16>)
 declare <vscale x 4 x i16> @llvm.ctpop.nvx4i16(<vscale x 4 x i16>)
 declare <vscale x 8 x i16> @llvm.ctpop.nvx8i16(<vscale x 8 x i16>)
 declare <vscale x 16 x i16> @llvm.ctpop.nvx16i16(<vscale x 16 x i16>)
 declare i32 @llvm.ctpop.i32(i32)
 declare <2 x i32> @llvm.ctpop.v2i32(<2 x i32>)
 declare <4 x i32> @llvm.ctpop.v4i32(<4 x i32>)
 declare <8 x i32> @llvm.ctpop.v8i32(<8 x i32>)
 declare <16 x i32> @llvm.ctpop.v16i32(<16 x i32>)
+declare <vscale x 1 x i32> @llvm.ctpop.nvx1i32(<vscale x 1 x i32>)
 declare <vscale x 2 x i32> @llvm.ctpop.nvx2i32(<vscale x 2 x i32>)
 declare <vscale x 4 x i32> @llvm.ctpop.nvx4i32(<vscale x 4 x i32>)
 declare <vscale x 8 x i32> @llvm.ctpop.nvx8i32(<vscale x 8 x i32>)
 declare <vscale x 16 x i32> @llvm.ctpop.nvx16i32(<vscale x 16 x i32>)
 declare i64 @llvm.ctpop.i64(i64)
 declare <2 x i64> @llvm.ctpop.v2i64(<2 x i64>)
 declare <4 x i64> @llvm.ctpop.v4i64(<4 x i64>)
 declare <8 x i64> @llvm.ctpop.v8i64(<8 x i64>)
 declare <16 x i64> @llvm.ctpop.v16i64(<16 x i64>)
+declare <vscale x 1 x i64> @llvm.ctpop.nvx1i64(<vscale x 1 x i64>)
 declare <vscale x 2 x i64> @llvm.ctpop.nvx2i64(<vscale x 2 x i64>)
 declare <vscale x 4 x i64> @llvm.ctpop.nvx4i64(<vscale x 4 x i64>)
 declare <vscale x 8 x i64> @llvm.ctpop.nvx8i64(<vscale x 8 x i64>)
 declare <vscale x 16 x i64> @llvm.ctpop.nvx16i64(<vscale x 16 x i64>)