; 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 --check-prefixes=CHECK,NOZVBB
; Vector ctpop exists only under ZVBB
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v,+f,+d,+zvbb -riscv-v-vector-bits-min=-1 | FileCheck %s --check-prefixes=CHECK,ZVBB

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 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 0 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 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 0 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() {
; NOZVBB-LABEL: 'ctpop'
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %1 = call i8 @llvm.ctpop.i8(i8 undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %2 = call <2 x i8> @llvm.ctpop.v2i8(<2 x i8> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %3 = call <4 x i8> @llvm.ctpop.v4i8(<4 x i8> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %4 = call <8 x i8> @llvm.ctpop.v8i8(<8 x i8> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %5 = call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> undef)
; NOZVBB-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)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %7 = call <vscale x 2 x i8> @llvm.ctpop.nxv2i8(<vscale x 2 x i8> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %8 = call <vscale x 4 x i8> @llvm.ctpop.nxv4i8(<vscale x 4 x i8> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %9 = call <vscale x 8 x i8> @llvm.ctpop.nxv8i8(<vscale x 8 x i8> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %10 = call <vscale x 16 x i8> @llvm.ctpop.nxv16i8(<vscale x 16 x i8> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %11 = call i16 @llvm.ctpop.i16(i16 undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %12 = call <2 x i16> @llvm.ctpop.v2i16(<2 x i16> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %13 = call <4 x i16> @llvm.ctpop.v4i16(<4 x i16> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %14 = call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %15 = call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %16 = call <vscale x 1 x i16> @llvm.ctpop.nxv1i16(<vscale x 1 x i16> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %17 = call <vscale x 2 x i16> @llvm.ctpop.nxv2i16(<vscale x 2 x i16> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %18 = call <vscale x 4 x i16> @llvm.ctpop.nxv4i16(<vscale x 4 x i16> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %19 = call <vscale x 8 x i16> @llvm.ctpop.nxv8i16(<vscale x 8 x i16> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %20 = call <vscale x 16 x i16> @llvm.ctpop.nxv16i16(<vscale x 16 x i16> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %21 = call i32 @llvm.ctpop.i32(i32 undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %22 = call <2 x i32> @llvm.ctpop.v2i32(<2 x i32> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %23 = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %24 = call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %25 = call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %26 = call <vscale x 1 x i32> @llvm.ctpop.nxv1i32(<vscale x 1 x i32> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %27 = call <vscale x 2 x i32> @llvm.ctpop.nxv2i32(<vscale x 2 x i32> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %28 = call <vscale x 4 x i32> @llvm.ctpop.nxv4i32(<vscale x 4 x i32> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %29 = call <vscale x 8 x i32> @llvm.ctpop.nxv8i32(<vscale x 8 x i32> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %30 = call <vscale x 16 x i32> @llvm.ctpop.nxv16i32(<vscale x 16 x i32> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %31 = call i64 @llvm.ctpop.i64(i64 undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %32 = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %33 = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %34 = call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %35 = call <16 x i64> @llvm.ctpop.v16i64(<16 x i64> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %36 = call <vscale x 1 x i64> @llvm.ctpop.nxv1i64(<vscale x 1 x i64> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %37 = call <vscale x 2 x i64> @llvm.ctpop.nxv2i64(<vscale x 2 x i64> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %38 = call <vscale x 4 x i64> @llvm.ctpop.nxv4i64(<vscale x 4 x i64> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %39 = call <vscale x 8 x i64> @llvm.ctpop.nxv8i64(<vscale x 8 x i64> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %40 = call <vscale x 16 x i64> @llvm.ctpop.nxv16i64(<vscale x 16 x i64> undef)
; NOZVBB-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; ZVBB-LABEL: 'ctpop'
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %1 = call i8 @llvm.ctpop.i8(i8 undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x i8> @llvm.ctpop.v2i8(<2 x i8> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x i8> @llvm.ctpop.v4i8(<4 x i8> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x i8> @llvm.ctpop.v8i8(<8 x i8> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 1 x i8> @llvm.ctpop.nxv1i8(<vscale x 1 x i8> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x i8> @llvm.ctpop.nxv2i8(<vscale x 2 x i8> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x i8> @llvm.ctpop.nxv4i8(<vscale x 4 x i8> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x i8> @llvm.ctpop.nxv8i8(<vscale x 8 x i8> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x i8> @llvm.ctpop.nxv16i8(<vscale x 16 x i8> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %11 = call i16 @llvm.ctpop.i16(i16 undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x i16> @llvm.ctpop.v2i16(<2 x i16> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x i16> @llvm.ctpop.v4i16(<4 x i16> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x i16> @llvm.ctpop.nxv1i16(<vscale x 1 x i16> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x i16> @llvm.ctpop.nxv2i16(<vscale x 2 x i16> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x i16> @llvm.ctpop.nxv4i16(<vscale x 4 x i16> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x i16> @llvm.ctpop.nxv8i16(<vscale x 8 x i16> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call <vscale x 16 x i16> @llvm.ctpop.nxv16i16(<vscale x 16 x i16> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %21 = call i32 @llvm.ctpop.i32(i32 undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <2 x i32> @llvm.ctpop.v2i32(<2 x i32> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 1 x i32> @llvm.ctpop.nxv1i32(<vscale x 1 x i32> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 2 x i32> @llvm.ctpop.nxv2i32(<vscale x 2 x i32> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 4 x i32> @llvm.ctpop.nxv4i32(<vscale x 4 x i32> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = call <vscale x 8 x i32> @llvm.ctpop.nxv8i32(<vscale x 8 x i32> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = call <vscale x 16 x i32> @llvm.ctpop.nxv16i32(<vscale x 16 x i32> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %31 = call i64 @llvm.ctpop.i64(i64 undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %32 = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %33 = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = call <16 x i64> @llvm.ctpop.v16i64(<16 x i64> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %36 = call <vscale x 1 x i64> @llvm.ctpop.nxv1i64(<vscale x 1 x i64> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %37 = call <vscale x 2 x i64> @llvm.ctpop.nxv2i64(<vscale x 2 x i64> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %38 = call <vscale x 4 x i64> @llvm.ctpop.nxv4i64(<vscale x 4 x i64> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %39 = call <vscale x 8 x i64> @llvm.ctpop.nxv8i64(<vscale x 8 x i64> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %40 = call <vscale x 16 x i64> @llvm.ctpop.nxv16i64(<vscale x 16 x i64> undef)
; ZVBB-NEXT:  Cost Model: Found an estimated cost of 0 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
}

define void @vp_bswap() {
; CHECK-LABEL: 'vp_bswap'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %1 = call <2 x i16> @llvm.vp.bswap.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %2 = call <4 x i16> @llvm.vp.bswap.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %3 = call <8 x i16> @llvm.vp.bswap.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %4 = call <16 x i16> @llvm.vp.bswap.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %5 = call <vscale x 1 x i16> @llvm.vp.bswap.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %6 = call <vscale x 2 x i16> @llvm.vp.bswap.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %7 = call <vscale x 4 x i16> @llvm.vp.bswap.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %8 = call <vscale x 8 x i16> @llvm.vp.bswap.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %9 = call <vscale x 16 x i16> @llvm.vp.bswap.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %10 = call <2 x i32> @llvm.vp.bswap.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %11 = call <4 x i32> @llvm.vp.bswap.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %12 = call <8 x i32> @llvm.vp.bswap.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %13 = call <16 x i32> @llvm.vp.bswap.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %14 = call <vscale x 1 x i32> @llvm.vp.bswap.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %15 = call <vscale x 2 x i32> @llvm.vp.bswap.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %16 = call <vscale x 4 x i32> @llvm.vp.bswap.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %17 = call <vscale x 8 x i32> @llvm.vp.bswap.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %18 = call <vscale x 16 x i32> @llvm.vp.bswap.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %19 = call <2 x i64> @llvm.vp.bswap.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %20 = call <4 x i64> @llvm.vp.bswap.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %21 = call <8 x i64> @llvm.vp.bswap.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %22 = call <16 x i64> @llvm.vp.bswap.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %23 = call <vscale x 1 x i64> @llvm.vp.bswap.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %24 = call <vscale x 2 x i64> @llvm.vp.bswap.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %25 = call <vscale x 4 x i64> @llvm.vp.bswap.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %26 = call <vscale x 8 x i64> @llvm.vp.bswap.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %27 = call <vscale x 16 x i64> @llvm.vp.bswap.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  call <2 x i16> @llvm.vp.bswap.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
  call <4 x i16> @llvm.vp.bswap.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
  call <8 x i16> @llvm.vp.bswap.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
  call <16 x i16> @llvm.vp.bswap.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
  call <vscale x 1 x i16> @llvm.vp.bswap.nvx1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
  call <vscale x 2 x i16> @llvm.vp.bswap.nvx2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
  call <vscale x 4 x i16> @llvm.vp.bswap.nvx4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
  call <vscale x 8 x i16> @llvm.vp.bswap.nvx8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
  call <vscale x 16 x i16> @llvm.vp.bswap.nvx16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
  call <2 x i32> @llvm.vp.bswap.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
  call <4 x i32> @llvm.vp.bswap.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
  call <8 x i32> @llvm.vp.bswap.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
  call <16 x i32> @llvm.vp.bswap.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
  call <vscale x 1 x i32> @llvm.vp.bswap.nvx1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
  call <vscale x 2 x i32> @llvm.vp.bswap.nvx2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
  call <vscale x 4 x i32> @llvm.vp.bswap.nvx4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
  call <vscale x 8 x i32> @llvm.vp.bswap.nvx8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
  call <vscale x 16 x i32> @llvm.vp.bswap.nvx16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
  call <2 x i64> @llvm.vp.bswap.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
  call <4 x i64> @llvm.vp.bswap.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
  call <8 x i64> @llvm.vp.bswap.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
  call <16 x i64> @llvm.vp.bswap.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
  call <vscale x 1 x i64> @llvm.vp.bswap.nvx1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
  call <vscale x 2 x i64> @llvm.vp.bswap.nvx2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
  call <vscale x 4 x i64> @llvm.vp.bswap.nvx4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
  call <vscale x 8 x i64> @llvm.vp.bswap.nvx8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
  call <vscale x 16 x i64> @llvm.vp.bswap.nvx16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
  ret void
}

define void @vp_ctpop() {
; CHECK-LABEL: 'vp_ctpop'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %1 = call <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %2 = call <4 x i16> @llvm.vp.ctpop.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %3 = call <8 x i16> @llvm.vp.ctpop.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %4 = call <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %5 = call <vscale x 1 x i16> @llvm.vp.ctpop.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %6 = call <vscale x 2 x i16> @llvm.vp.ctpop.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %7 = call <vscale x 4 x i16> @llvm.vp.ctpop.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %8 = call <vscale x 8 x i16> @llvm.vp.ctpop.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %9 = call <vscale x 16 x i16> @llvm.vp.ctpop.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %10 = call <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %11 = call <4 x i16> @llvm.vp.ctpop.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %12 = call <8 x i16> @llvm.vp.ctpop.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %13 = call <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %14 = call <vscale x 1 x i16> @llvm.vp.ctpop.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %15 = call <vscale x 2 x i16> @llvm.vp.ctpop.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %16 = call <vscale x 4 x i16> @llvm.vp.ctpop.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %17 = call <vscale x 8 x i16> @llvm.vp.ctpop.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %18 = call <vscale x 16 x i16> @llvm.vp.ctpop.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %19 = call <2 x i32> @llvm.vp.ctpop.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %20 = call <4 x i32> @llvm.vp.ctpop.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %21 = call <8 x i32> @llvm.vp.ctpop.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %22 = call <16 x i32> @llvm.vp.ctpop.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %23 = call <vscale x 1 x i32> @llvm.vp.ctpop.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %24 = call <vscale x 2 x i32> @llvm.vp.ctpop.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %25 = call <vscale x 4 x i32> @llvm.vp.ctpop.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %26 = call <vscale x 8 x i32> @llvm.vp.ctpop.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %27 = call <vscale x 16 x i32> @llvm.vp.ctpop.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %28 = call <2 x i64> @llvm.vp.ctpop.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %29 = call <4 x i64> @llvm.vp.ctpop.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %30 = call <8 x i64> @llvm.vp.ctpop.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %31 = call <16 x i64> @llvm.vp.ctpop.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %32 = call <vscale x 1 x i64> @llvm.vp.ctpop.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %33 = call <vscale x 2 x i64> @llvm.vp.ctpop.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %34 = call <vscale x 4 x i64> @llvm.vp.ctpop.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %35 = call <vscale x 8 x i64> @llvm.vp.ctpop.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %36 = call <vscale x 16 x i64> @llvm.vp.ctpop.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  call <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
  call <4 x i16> @llvm.vp.ctpop.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
  call <8 x i16> @llvm.vp.ctpop.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
  call <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
  call <vscale x 1 x i16> @llvm.vp.ctpop.nvx1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
  call <vscale x 2 x i16> @llvm.vp.ctpop.nvx2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
  call <vscale x 4 x i16> @llvm.vp.ctpop.nvx4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
  call <vscale x 8 x i16> @llvm.vp.ctpop.nvx8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
  call <vscale x 16 x i16> @llvm.vp.ctpop.nvx16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
  call <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16> undef, <2 x i1> undef, i32 undef)
  call <4 x i16> @llvm.vp.ctpop.v4i16(<4 x i16> undef, <4 x i1> undef, i32 undef)
  call <8 x i16> @llvm.vp.ctpop.v8i16(<8 x i16> undef, <8 x i1> undef, i32 undef)
  call <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16> undef, <16 x i1> undef, i32 undef)
  call <vscale x 1 x i16> @llvm.vp.ctpop.nvx1i16(<vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
  call <vscale x 2 x i16> @llvm.vp.ctpop.nvx2i16(<vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
  call <vscale x 4 x i16> @llvm.vp.ctpop.nvx4i16(<vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
  call <vscale x 8 x i16> @llvm.vp.ctpop.nvx8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
  call <vscale x 16 x i16> @llvm.vp.ctpop.nvx16i16(<vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
  call <2 x i32> @llvm.vp.ctpop.v2i32(<2 x i32> undef, <2 x i1> undef, i32 undef)
  call <4 x i32> @llvm.vp.ctpop.v4i32(<4 x i32> undef, <4 x i1> undef, i32 undef)
  call <8 x i32> @llvm.vp.ctpop.v8i32(<8 x i32> undef, <8 x i1> undef, i32 undef)
  call <16 x i32> @llvm.vp.ctpop.v16i32(<16 x i32> undef, <16 x i1> undef, i32 undef)
  call <vscale x 1 x i32> @llvm.vp.ctpop.nvx1i32(<vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
  call <vscale x 2 x i32> @llvm.vp.ctpop.nvx2i32(<vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
  call <vscale x 4 x i32> @llvm.vp.ctpop.nvx4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
  call <vscale x 8 x i32> @llvm.vp.ctpop.nvx8i32(<vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
  call <vscale x 16 x i32> @llvm.vp.ctpop.nvx16i32(<vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
  call <2 x i64> @llvm.vp.ctpop.v2i64(<2 x i64> undef, <2 x i1> undef, i32 undef)
  call <4 x i64> @llvm.vp.ctpop.v4i64(<4 x i64> undef, <4 x i1> undef, i32 undef)
  call <8 x i64> @llvm.vp.ctpop.v8i64(<8 x i64> undef, <8 x i1> undef, i32 undef)
  call <16 x i64> @llvm.vp.ctpop.v16i64(<16 x i64> undef, <16 x i1> undef, i32 undef)
  call <vscale x 1 x i64> @llvm.vp.ctpop.nvx1i64(<vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
  call <vscale x 2 x i64> @llvm.vp.ctpop.nvx2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
  call <vscale x 4 x i64> @llvm.vp.ctpop.nvx4i64(<vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
  call <vscale x 8 x i64> @llvm.vp.ctpop.nvx8i64(<vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
  call <vscale x 16 x i64> @llvm.vp.ctpop.nvx16i64(<vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
  ret void
}

define void @vp_ctlz() {
; CHECK-LABEL: 'vp_ctlz'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %1 = call <2 x i8> @llvm.vp.ctlz.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %2 = call <4 x i8> @llvm.vp.ctlz.v4i8(<4 x i8> undef, i1 false, <4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %3 = call <8 x i8> @llvm.vp.ctlz.v8i8(<8 x i8> undef, i1 false, <8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %4 = call <16 x i8> @llvm.vp.ctlz.v16i8(<16 x i8> undef, i1 false, <16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %5 = call <vscale x 1 x i8> @llvm.vp.ctlz.nxv1i8(<vscale x 1 x i8> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %6 = call <vscale x 2 x i8> @llvm.vp.ctlz.nxv2i8(<vscale x 2 x i8> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %7 = call <vscale x 4 x i8> @llvm.vp.ctlz.nxv4i8(<vscale x 4 x i8> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %8 = call <vscale x 8 x i8> @llvm.vp.ctlz.nxv8i8(<vscale x 8 x i8> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %9 = call <vscale x 16 x i8> @llvm.vp.ctlz.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %10 = call <vscale x 32 x i8> @llvm.vp.ctlz.nxv32i8(<vscale x 32 x i8> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %11 = call <vscale x 64 x i8> @llvm.vp.ctlz.nxv64i8(<vscale x 64 x i8> undef, i1 false, <vscale x 64 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %12 = call <2 x i16> @llvm.vp.ctlz.v2i16(<2 x i16> undef, i1 false, <2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %13 = call <4 x i16> @llvm.vp.ctlz.v4i16(<4 x i16> undef, i1 false, <4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %14 = call <8 x i16> @llvm.vp.ctlz.v8i16(<8 x i16> undef, i1 false, <8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %15 = call <16 x i16> @llvm.vp.ctlz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %16 = call <vscale x 1 x i16> @llvm.vp.ctlz.nxv1i16(<vscale x 1 x i16> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %17 = call <vscale x 2 x i16> @llvm.vp.ctlz.nxv2i16(<vscale x 2 x i16> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %18 = call <vscale x 4 x i16> @llvm.vp.ctlz.nxv4i16(<vscale x 4 x i16> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %19 = call <vscale x 8 x i16> @llvm.vp.ctlz.nxv8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %20 = call <vscale x 16 x i16> @llvm.vp.ctlz.nxv16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %21 = call <vscale x 32 x i16> @llvm.vp.ctlz.nxv32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %22 = call <2 x i16> @llvm.vp.ctlz.v2i16(<2 x i16> undef, i1 false, <2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %23 = call <4 x i16> @llvm.vp.ctlz.v4i16(<4 x i16> undef, i1 false, <4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %24 = call <8 x i16> @llvm.vp.ctlz.v8i16(<8 x i16> undef, i1 false, <8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %25 = call <16 x i16> @llvm.vp.ctlz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %26 = call <vscale x 1 x i16> @llvm.vp.ctlz.nxv1i16(<vscale x 1 x i16> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %27 = call <vscale x 2 x i16> @llvm.vp.ctlz.nxv2i16(<vscale x 2 x i16> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %28 = call <vscale x 4 x i16> @llvm.vp.ctlz.nxv4i16(<vscale x 4 x i16> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %29 = call <vscale x 8 x i16> @llvm.vp.ctlz.nxv8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %30 = call <vscale x 16 x i16> @llvm.vp.ctlz.nxv16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %31 = call <vscale x 32 x i16> @llvm.vp.ctlz.nxv32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %32 = call <2 x i32> @llvm.vp.ctlz.v2i32(<2 x i32> undef, i1 false, <2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %33 = call <4 x i32> @llvm.vp.ctlz.v4i32(<4 x i32> undef, i1 false, <4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %34 = call <8 x i32> @llvm.vp.ctlz.v8i32(<8 x i32> undef, i1 false, <8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %35 = call <16 x i32> @llvm.vp.ctlz.v16i32(<16 x i32> undef, i1 false, <16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %36 = call <vscale x 1 x i32> @llvm.vp.ctlz.nxv1i32(<vscale x 1 x i32> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %37 = call <vscale x 2 x i32> @llvm.vp.ctlz.nxv2i32(<vscale x 2 x i32> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %38 = call <vscale x 4 x i32> @llvm.vp.ctlz.nxv4i32(<vscale x 4 x i32> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %39 = call <vscale x 8 x i32> @llvm.vp.ctlz.nxv8i32(<vscale x 8 x i32> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %40 = call <vscale x 16 x i32> @llvm.vp.ctlz.nxv16i32(<vscale x 16 x i32> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %41 = call <2 x i64> @llvm.vp.ctlz.v2i64(<2 x i64> undef, i1 false, <2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %42 = call <4 x i64> @llvm.vp.ctlz.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %43 = call <8 x i64> @llvm.vp.ctlz.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %44 = call <16 x i64> @llvm.vp.ctlz.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %45 = call <vscale x 1 x i64> @llvm.vp.ctlz.nxv1i64(<vscale x 1 x i64> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %46 = call <vscale x 2 x i64> @llvm.vp.ctlz.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %47 = call <vscale x 4 x i64> @llvm.vp.ctlz.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %48 = call <vscale x 8 x i64> @llvm.vp.ctlz.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 70 for instruction: %49 = call <vscale x 16 x i64> @llvm.vp.ctlz.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  call <2 x i8> @llvm.vp.ctlz.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
  call <4 x i8> @llvm.vp.ctlz.v4i8(<4 x i8> undef, i1 false, <4 x i1> undef, i32 undef)
  call <8 x i8> @llvm.vp.ctlz.v8i8(<8 x i8> undef, i1 false, <8 x i1> undef, i32 undef)
  call <16 x i8> @llvm.vp.ctlz.v16i8(<16 x i8> undef, i1 false, <16 x i1> undef, i32 undef)
  call <vscale x 1 x i8> @llvm.vp.ctlz.nvx1i8(<vscale x 1 x i8> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
  call <vscale x 2 x i8> @llvm.vp.ctlz.nvx2i8(<vscale x 2 x i8> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
  call <vscale x 4 x i8> @llvm.vp.ctlz.nvx4i8(<vscale x 4 x i8> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
  call <vscale x 8 x i8> @llvm.vp.ctlz.nvx8i8(<vscale x 8 x i8> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
  call <vscale x 16 x i8> @llvm.vp.ctlz.nvx16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
  call <vscale x 32 x i8> @llvm.vp.ctlz.nvx32i8(<vscale x 32 x i8> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
  call <vscale x 64 x i8> @llvm.vp.ctlz.nvx64i8(<vscale x 64 x i8> undef, i1 false, <vscale x 64 x i1> undef, i32 undef)
  call <2 x i16> @llvm.vp.ctlz.v2i16(<2 x i16> undef, i1 false, <2 x i1> undef, i32 undef)
  call <4 x i16> @llvm.vp.ctlz.v4i16(<4 x i16> undef, i1 false, <4 x i1> undef, i32 undef)
  call <8 x i16> @llvm.vp.ctlz.v8i16(<8 x i16> undef, i1 false, <8 x i1> undef, i32 undef)
  call <16 x i16> @llvm.vp.ctlz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
  call <vscale x 1 x i16> @llvm.vp.ctlz.nvx1i16(<vscale x 1 x i16> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
  call <vscale x 2 x i16> @llvm.vp.ctlz.nvx2i16(<vscale x 2 x i16> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
  call <vscale x 4 x i16> @llvm.vp.ctlz.nvx4i16(<vscale x 4 x i16> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
  call <vscale x 8 x i16> @llvm.vp.ctlz.nvx8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
  call <vscale x 16 x i16> @llvm.vp.ctlz.nvx16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
  call <vscale x 32 x i16> @llvm.vp.ctlz.nvx32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
  call <2 x i16> @llvm.vp.ctlz.v2i16(<2 x i16> undef, i1 false, <2 x i1> undef, i32 undef)
  call <4 x i16> @llvm.vp.ctlz.v4i16(<4 x i16> undef, i1 false, <4 x i1> undef, i32 undef)
  call <8 x i16> @llvm.vp.ctlz.v8i16(<8 x i16> undef, i1 false, <8 x i1> undef, i32 undef)
  call <16 x i16> @llvm.vp.ctlz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
  call <vscale x 1 x i16> @llvm.vp.ctlz.nvx1i16(<vscale x 1 x i16> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
  call <vscale x 2 x i16> @llvm.vp.ctlz.nvx2i16(<vscale x 2 x i16> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
  call <vscale x 4 x i16> @llvm.vp.ctlz.nvx4i16(<vscale x 4 x i16> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
  call <vscale x 8 x i16> @llvm.vp.ctlz.nvx8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
  call <vscale x 16 x i16> @llvm.vp.ctlz.nvx16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
  call <vscale x 32 x i16> @llvm.vp.ctlz.nvx32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
  call <2 x i32> @llvm.vp.ctlz.v2i32(<2 x i32> undef, i1 false, <2 x i1> undef, i32 undef)
  call <4 x i32> @llvm.vp.ctlz.v4i32(<4 x i32> undef, i1 false, <4 x i1> undef, i32 undef)
  call <8 x i32> @llvm.vp.ctlz.v8i32(<8 x i32> undef, i1 false, <8 x i1> undef, i32 undef)
  call <16 x i32> @llvm.vp.ctlz.v16i32(<16 x i32> undef, i1 false, <16 x i1> undef, i32 undef)
  call <vscale x 1 x i32> @llvm.vp.ctlz.nvx1i32(<vscale x 1 x i32> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
  call <vscale x 2 x i32> @llvm.vp.ctlz.nvx2i32(<vscale x 2 x i32> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
  call <vscale x 4 x i32> @llvm.vp.ctlz.nvx4i32(<vscale x 4 x i32> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
  call <vscale x 8 x i32> @llvm.vp.ctlz.nvx8i32(<vscale x 8 x i32> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
  call <vscale x 16 x i32> @llvm.vp.ctlz.nvx16i32(<vscale x 16 x i32> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
  call <2 x i64> @llvm.vp.ctlz.v2i64(<2 x i64> undef, i1 false, <2 x i1> undef, i32 undef)
  call <4 x i64> @llvm.vp.ctlz.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
  call <8 x i64> @llvm.vp.ctlz.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
  call <16 x i64> @llvm.vp.ctlz.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
  call <vscale x 1 x i64> @llvm.vp.ctlz.nvx1i64(<vscale x 1 x i64> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
  call <vscale x 2 x i64> @llvm.vp.ctlz.nvx2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
  call <vscale x 4 x i64> @llvm.vp.ctlz.nvx4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
  call <vscale x 8 x i64> @llvm.vp.ctlz.nvx8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
  call <vscale x 16 x i64> @llvm.vp.ctlz.nvx16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
  ret void
}

define void @vp_cttz() {
; CHECK-LABEL: 'vp_cttz'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %1 = call <2 x i8> @llvm.vp.cttz.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %2 = call <4 x i8> @llvm.vp.cttz.v4i8(<4 x i8> undef, i1 false, <4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %3 = call <8 x i8> @llvm.vp.cttz.v8i8(<8 x i8> undef, i1 false, <8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %4 = call <16 x i8> @llvm.vp.cttz.v16i8(<16 x i8> undef, i1 false, <16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %5 = call <vscale x 1 x i8> @llvm.vp.cttz.nxv1i8(<vscale x 1 x i8> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %6 = call <vscale x 2 x i8> @llvm.vp.cttz.nxv2i8(<vscale x 2 x i8> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %7 = call <vscale x 4 x i8> @llvm.vp.cttz.nxv4i8(<vscale x 4 x i8> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %8 = call <vscale x 8 x i8> @llvm.vp.cttz.nxv8i8(<vscale x 8 x i8> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %9 = call <vscale x 16 x i8> @llvm.vp.cttz.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %10 = call <vscale x 32 x i8> @llvm.vp.cttz.nxv32i8(<vscale x 32 x i8> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %11 = call <vscale x 64 x i8> @llvm.vp.cttz.nxv64i8(<vscale x 64 x i8> undef, i1 false, <vscale x 64 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x i16> @llvm.vp.cttz.v2i16(<2 x i16> undef, i1 false, <2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %13 = call <4 x i16> @llvm.vp.cttz.v4i16(<4 x i16> undef, i1 false, <4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %14 = call <8 x i16> @llvm.vp.cttz.v8i16(<8 x i16> undef, i1 false, <8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %15 = call <16 x i16> @llvm.vp.cttz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %16 = call <vscale x 1 x i16> @llvm.vp.cttz.nxv1i16(<vscale x 1 x i16> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %17 = call <vscale x 2 x i16> @llvm.vp.cttz.nxv2i16(<vscale x 2 x i16> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %18 = call <vscale x 4 x i16> @llvm.vp.cttz.nxv4i16(<vscale x 4 x i16> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %19 = call <vscale x 8 x i16> @llvm.vp.cttz.nxv8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %20 = call <vscale x 16 x i16> @llvm.vp.cttz.nxv16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %21 = call <vscale x 32 x i16> @llvm.vp.cttz.nxv32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %22 = call <2 x i16> @llvm.vp.cttz.v2i16(<2 x i16> undef, i1 false, <2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %23 = call <4 x i16> @llvm.vp.cttz.v4i16(<4 x i16> undef, i1 false, <4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %24 = call <8 x i16> @llvm.vp.cttz.v8i16(<8 x i16> undef, i1 false, <8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %25 = call <16 x i16> @llvm.vp.cttz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %26 = call <vscale x 1 x i16> @llvm.vp.cttz.nxv1i16(<vscale x 1 x i16> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %27 = call <vscale x 2 x i16> @llvm.vp.cttz.nxv2i16(<vscale x 2 x i16> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %28 = call <vscale x 4 x i16> @llvm.vp.cttz.nxv4i16(<vscale x 4 x i16> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %29 = call <vscale x 8 x i16> @llvm.vp.cttz.nxv8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %30 = call <vscale x 16 x i16> @llvm.vp.cttz.nxv16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %31 = call <vscale x 32 x i16> @llvm.vp.cttz.nxv32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %32 = call <2 x i32> @llvm.vp.cttz.v2i32(<2 x i32> undef, i1 false, <2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %33 = call <4 x i32> @llvm.vp.cttz.v4i32(<4 x i32> undef, i1 false, <4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %34 = call <8 x i32> @llvm.vp.cttz.v8i32(<8 x i32> undef, i1 false, <8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %35 = call <16 x i32> @llvm.vp.cttz.v16i32(<16 x i32> undef, i1 false, <16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %36 = call <vscale x 1 x i32> @llvm.vp.cttz.nxv1i32(<vscale x 1 x i32> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %37 = call <vscale x 2 x i32> @llvm.vp.cttz.nxv2i32(<vscale x 2 x i32> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %38 = call <vscale x 4 x i32> @llvm.vp.cttz.nxv4i32(<vscale x 4 x i32> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %39 = call <vscale x 8 x i32> @llvm.vp.cttz.nxv8i32(<vscale x 8 x i32> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %40 = call <vscale x 16 x i32> @llvm.vp.cttz.nxv16i32(<vscale x 16 x i32> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %41 = call <2 x i64> @llvm.vp.cttz.v2i64(<2 x i64> undef, i1 false, <2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %42 = call <4 x i64> @llvm.vp.cttz.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %43 = call <8 x i64> @llvm.vp.cttz.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %44 = call <16 x i64> @llvm.vp.cttz.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %45 = call <vscale x 1 x i64> @llvm.vp.cttz.nxv1i64(<vscale x 1 x i64> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %46 = call <vscale x 2 x i64> @llvm.vp.cttz.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %47 = call <vscale x 4 x i64> @llvm.vp.cttz.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %48 = call <vscale x 8 x i64> @llvm.vp.cttz.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 50 for instruction: %49 = call <vscale x 16 x i64> @llvm.vp.cttz.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  call <2 x i8> @llvm.vp.cttz.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
  call <4 x i8> @llvm.vp.cttz.v4i8(<4 x i8> undef, i1 false, <4 x i1> undef, i32 undef)
  call <8 x i8> @llvm.vp.cttz.v8i8(<8 x i8> undef, i1 false, <8 x i1> undef, i32 undef)
  call <16 x i8> @llvm.vp.cttz.v16i8(<16 x i8> undef, i1 false, <16 x i1> undef, i32 undef)
  call <vscale x 1 x i8> @llvm.vp.cttz.nvx1i8(<vscale x 1 x i8> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
  call <vscale x 2 x i8> @llvm.vp.cttz.nvx2i8(<vscale x 2 x i8> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
  call <vscale x 4 x i8> @llvm.vp.cttz.nvx4i8(<vscale x 4 x i8> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
  call <vscale x 8 x i8> @llvm.vp.cttz.nvx8i8(<vscale x 8 x i8> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
  call <vscale x 16 x i8> @llvm.vp.cttz.nvx16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
  call <vscale x 32 x i8> @llvm.vp.cttz.nvx32i8(<vscale x 32 x i8> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
  call <vscale x 64 x i8> @llvm.vp.cttz.nvx64i8(<vscale x 64 x i8> undef, i1 false, <vscale x 64 x i1> undef, i32 undef)
  call <2 x i16> @llvm.vp.cttz.v2i16(<2 x i16> undef, i1 false, <2 x i1> undef, i32 undef)
  call <4 x i16> @llvm.vp.cttz.v4i16(<4 x i16> undef, i1 false, <4 x i1> undef, i32 undef)
  call <8 x i16> @llvm.vp.cttz.v8i16(<8 x i16> undef, i1 false, <8 x i1> undef, i32 undef)
  call <16 x i16> @llvm.vp.cttz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
  call <vscale x 1 x i16> @llvm.vp.cttz.nvx1i16(<vscale x 1 x i16> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
  call <vscale x 2 x i16> @llvm.vp.cttz.nvx2i16(<vscale x 2 x i16> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
  call <vscale x 4 x i16> @llvm.vp.cttz.nvx4i16(<vscale x 4 x i16> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
  call <vscale x 8 x i16> @llvm.vp.cttz.nvx8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
  call <vscale x 16 x i16> @llvm.vp.cttz.nvx16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
  call <vscale x 32 x i16> @llvm.vp.cttz.nvx32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
  call <2 x i16> @llvm.vp.cttz.v2i16(<2 x i16> undef, i1 false, <2 x i1> undef, i32 undef)
  call <4 x i16> @llvm.vp.cttz.v4i16(<4 x i16> undef, i1 false, <4 x i1> undef, i32 undef)
  call <8 x i16> @llvm.vp.cttz.v8i16(<8 x i16> undef, i1 false, <8 x i1> undef, i32 undef)
  call <16 x i16> @llvm.vp.cttz.v16i16(<16 x i16> undef, i1 false, <16 x i1> undef, i32 undef)
  call <vscale x 1 x i16> @llvm.vp.cttz.nvx1i16(<vscale x 1 x i16> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
  call <vscale x 2 x i16> @llvm.vp.cttz.nvx2i16(<vscale x 2 x i16> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
  call <vscale x 4 x i16> @llvm.vp.cttz.nvx4i16(<vscale x 4 x i16> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
  call <vscale x 8 x i16> @llvm.vp.cttz.nvx8i16(<vscale x 8 x i16> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
  call <vscale x 16 x i16> @llvm.vp.cttz.nvx16i16(<vscale x 16 x i16> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
  call <vscale x 32 x i16> @llvm.vp.cttz.nvx32i16(<vscale x 32 x i16> undef, i1 false, <vscale x 32 x i1> undef, i32 undef)
  call <2 x i32> @llvm.vp.cttz.v2i32(<2 x i32> undef, i1 false, <2 x i1> undef, i32 undef)
  call <4 x i32> @llvm.vp.cttz.v4i32(<4 x i32> undef, i1 false, <4 x i1> undef, i32 undef)
  call <8 x i32> @llvm.vp.cttz.v8i32(<8 x i32> undef, i1 false, <8 x i1> undef, i32 undef)
  call <16 x i32> @llvm.vp.cttz.v16i32(<16 x i32> undef, i1 false, <16 x i1> undef, i32 undef)
  call <vscale x 1 x i32> @llvm.vp.cttz.nvx1i32(<vscale x 1 x i32> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
  call <vscale x 2 x i32> @llvm.vp.cttz.nvx2i32(<vscale x 2 x i32> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
  call <vscale x 4 x i32> @llvm.vp.cttz.nvx4i32(<vscale x 4 x i32> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
  call <vscale x 8 x i32> @llvm.vp.cttz.nvx8i32(<vscale x 8 x i32> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
  call <vscale x 16 x i32> @llvm.vp.cttz.nvx16i32(<vscale x 16 x i32> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
  call <2 x i64> @llvm.vp.cttz.v2i64(<2 x i64> undef, i1 false, <2 x i1> undef, i32 undef)
  call <4 x i64> @llvm.vp.cttz.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
  call <8 x i64> @llvm.vp.cttz.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
  call <16 x i64> @llvm.vp.cttz.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
  call <vscale x 1 x i64> @llvm.vp.cttz.nvx1i64(<vscale x 1 x i64> undef, i1 false, <vscale x 1 x i1> undef, i32 undef)
  call <vscale x 2 x i64> @llvm.vp.cttz.nvx2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
  call <vscale x 4 x i64> @llvm.vp.cttz.nvx4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
  call <vscale x 8 x i64> @llvm.vp.cttz.nvx8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
  call <vscale x 16 x i64> @llvm.vp.cttz.nvx16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 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>)

declare <2 x i16> @llvm.vp.bswap.v2i16(<2 x i16>, <2 x i1>, i32)
declare <4 x i16> @llvm.vp.bswap.v4i16(<4 x i16>, <4 x i1>, i32)
declare <8 x i16> @llvm.vp.bswap.v8i16(<8 x i16>, <8 x i1>, i32)
declare <16 x i16> @llvm.vp.bswap.v16i16(<16 x i16>, <16 x i1>, i32)
declare <vscale x 1 x i16> @llvm.vp.bswap.nvx1i16(<vscale x 1 x i16>, <vscale x 1 x i1>, i32)
declare <vscale x 2 x i16> @llvm.vp.bswap.nvx2i16(<vscale x 2 x i16>, <vscale x 2 x i1>, i32)
declare <vscale x 4 x i16> @llvm.vp.bswap.nvx4i16(<vscale x 4 x i16>, <vscale x 4 x i1>, i32)
declare <vscale x 8 x i16> @llvm.vp.bswap.nvx8i16(<vscale x 8 x i16>, <vscale x 8 x i1>, i32)
declare <vscale x 16 x i16> @llvm.vp.bswap.nvx16i16(<vscale x 16 x i16>, <vscale x 16 x i1>, i32)
declare <2 x i32> @llvm.vp.bswap.v2i32(<2 x i32>, <2 x i1>, i32)
declare <4 x i32> @llvm.vp.bswap.v4i32(<4 x i32>, <4 x i1>, i32)
declare <8 x i32> @llvm.vp.bswap.v8i32(<8 x i32>, <8 x i1>, i32)
declare <16 x i32> @llvm.vp.bswap.v16i32(<16 x i32>, <16 x i1>, i32)
declare <vscale x 1 x i32> @llvm.vp.bswap.nvx1i32(<vscale x 1 x i32>, <vscale x 1 x i1>, i32)
declare <vscale x 2 x i32> @llvm.vp.bswap.nvx2i32(<vscale x 2 x i32>, <vscale x 2 x i1>, i32)
declare <vscale x 4 x i32> @llvm.vp.bswap.nvx4i32(<vscale x 4 x i32>, <vscale x 4 x i1>, i32)
declare <vscale x 8 x i32> @llvm.vp.bswap.nvx8i32(<vscale x 8 x i32>, <vscale x 8 x i1>, i32)
declare <vscale x 16 x i32> @llvm.vp.bswap.nvx16i32(<vscale x 16 x i32>, <vscale x 16 x i1>, i32)
declare <2 x i64> @llvm.vp.bswap.v2i64(<2 x i64>, <2 x i1>, i32)
declare <4 x i64> @llvm.vp.bswap.v4i64(<4 x i64>, <4 x i1>, i32)
declare <8 x i64> @llvm.vp.bswap.v8i64(<8 x i64>, <8 x i1>, i32)
declare <16 x i64> @llvm.vp.bswap.v16i64(<16 x i64>, <16 x i1>, i32)
declare <vscale x 1 x i64> @llvm.vp.bswap.nvx1i64(<vscale x 1 x i64>, <vscale x 1 x i1>, i32)
declare <vscale x 2 x i64> @llvm.vp.bswap.nvx2i64(<vscale x 2 x i64>, <vscale x 2 x i1>, i32)
declare <vscale x 4 x i64> @llvm.vp.bswap.nvx4i64(<vscale x 4 x i64>, <vscale x 4 x i1>, i32)
declare <vscale x 8 x i64> @llvm.vp.bswap.nvx8i64(<vscale x 8 x i64>, <vscale x 8 x i1>, i32)
declare <vscale x 16 x i64> @llvm.vp.bswap.nvx16i64(<vscale x 16 x i64>, <vscale x 16 x i1>, i32)

declare <2 x i8> @llvm.vp.ctpop.v2i8(<2 x i8>, <2 x i1>, i32)
declare <4 x i8> @llvm.vp.ctpop.v4i8(<4 x i8>, <4 x i1>, i32)
declare <8 x i8> @llvm.vp.ctpop.v8i8(<8 x i8>, <8 x i1>, i32)
declare <16 x i8> @llvm.vp.ctpop.v16i8(<16 x i8>, <16 x i1>, i32)
declare <vscale x 1 x i8> @llvm.vp.ctpop.nvx1i8(<vscale x 1 x i8>, <vscale x 1 x i1>, i32)
declare <vscale x 2 x i8> @llvm.vp.ctpop.nvx2i8(<vscale x 2 x i8>, <vscale x 2 x i1>, i32)
declare <vscale x 4 x i8> @llvm.vp.ctpop.nvx4i8(<vscale x 4 x i8>, <vscale x 4 x i1>, i32)
declare <vscale x 8 x i8> @llvm.vp.ctpop.nvx8i8(<vscale x 8 x i8>, <vscale x 8 x i1>, i32)
declare <vscale x 16 x i8> @llvm.vp.ctpop.nvx16i8(<vscale x 16 x i8>, <vscale x 16 x i1>, i32)
declare <2 x i16> @llvm.vp.ctpop.v2i16(<2 x i16>, <2 x i1>, i32)
declare <4 x i16> @llvm.vp.ctpop.v4i16(<4 x i16>, <4 x i1>, i32)
declare <8 x i16> @llvm.vp.ctpop.v8i16(<8 x i16>, <8 x i1>, i32)
declare <16 x i16> @llvm.vp.ctpop.v16i16(<16 x i16>, <16 x i1>, i32)
declare <vscale x 1 x i16> @llvm.vp.ctpop.nvx1i16(<vscale x 1 x i16>, <vscale x 1 x i1>, i32)
declare <vscale x 2 x i16> @llvm.vp.ctpop.nvx2i16(<vscale x 2 x i16>, <vscale x 2 x i1>, i32)
declare <vscale x 4 x i16> @llvm.vp.ctpop.nvx4i16(<vscale x 4 x i16>, <vscale x 4 x i1>, i32)
declare <vscale x 8 x i16> @llvm.vp.ctpop.nvx8i16(<vscale x 8 x i16>, <vscale x 8 x i1>, i32)
declare <vscale x 16 x i16> @llvm.vp.ctpop.nvx16i16(<vscale x 16 x i16>, <vscale x 16 x i1>, i32)
declare <2 x i32> @llvm.vp.ctpop.v2i32(<2 x i32>, <2 x i1>, i32)
declare <4 x i32> @llvm.vp.ctpop.v4i32(<4 x i32>, <4 x i1>, i32)
declare <8 x i32> @llvm.vp.ctpop.v8i32(<8 x i32>, <8 x i1>, i32)
declare <16 x i32> @llvm.vp.ctpop.v16i32(<16 x i32>, <16 x i1>, i32)
declare <vscale x 1 x i32> @llvm.vp.ctpop.nvx1i32(<vscale x 1 x i32>, <vscale x 1 x i1>, i32)
declare <vscale x 2 x i32> @llvm.vp.ctpop.nvx2i32(<vscale x 2 x i32>, <vscale x 2 x i1>, i32)
declare <vscale x 4 x i32> @llvm.vp.ctpop.nvx4i32(<vscale x 4 x i32>, <vscale x 4 x i1>, i32)
declare <vscale x 8 x i32> @llvm.vp.ctpop.nvx8i32(<vscale x 8 x i32>, <vscale x 8 x i1>, i32)
declare <vscale x 16 x i32> @llvm.vp.ctpop.nvx16i32(<vscale x 16 x i32>, <vscale x 16 x i1>, i32)
declare <2 x i64> @llvm.vp.ctpop.v2i64(<2 x i64>, <2 x i1>, i32)
declare <4 x i64> @llvm.vp.ctpop.v4i64(<4 x i64>, <4 x i1>, i32)
declare <8 x i64> @llvm.vp.ctpop.v8i64(<8 x i64>, <8 x i1>, i32)
declare <16 x i64> @llvm.vp.ctpop.v16i64(<16 x i64>, <16 x i1>, i32)
declare <vscale x 1 x i64> @llvm.vp.ctpop.nvx1i64(<vscale x 1 x i64>, <vscale x 1 x i1>, i32)
declare <vscale x 2 x i64> @llvm.vp.ctpop.nvx2i64(<vscale x 2 x i64>, <vscale x 2 x i1>, i32)
declare <vscale x 4 x i64> @llvm.vp.ctpop.nvx4i64(<vscale x 4 x i64>, <vscale x 4 x i1>, i32)
declare <vscale x 8 x i64> @llvm.vp.ctpop.nvx8i64(<vscale x 8 x i64>, <vscale x 8 x i1>, i32)
declare <vscale x 16 x i64> @llvm.vp.ctpop.nvx16i64(<vscale x 16 x i64>, <vscale x 16 x i1>, i32)

declare <2 x i8> @llvm.vp.ctlz.v2i8(<2 x i8>, i1 immarg, <2 x i1>, i32)
declare <4 x i8> @llvm.vp.ctlz.v4i8(<4 x i8>, i1 immarg, <4 x i1>, i32)
declare <8 x i8> @llvm.vp.ctlz.v8i8(<8 x i8>, i1 immarg, <8 x i1>, i32)
declare <16 x i8> @llvm.vp.ctlz.v16i8(<16 x i8>, i1 immarg, <16 x i1>, i32)
declare <vscale x 1 x i8> @llvm.vp.ctlz.nvx1i8(<vscale x 1 x i8>, i1 immarg, <vscale x 1 x i1>, i32)
declare <vscale x 2 x i8> @llvm.vp.ctlz.nvx2i8(<vscale x 2 x i8>, i1 immarg, <vscale x 2 x i1>, i32)
declare <vscale x 4 x i8> @llvm.vp.ctlz.nvx4i8(<vscale x 4 x i8>, i1 immarg, <vscale x 4 x i1>, i32)
declare <vscale x 8 x i8> @llvm.vp.ctlz.nvx8i8(<vscale x 8 x i8>, i1 immarg, <vscale x 8 x i1>, i32)
declare <vscale x 16 x i8> @llvm.vp.ctlz.nvx16i8(<vscale x 16 x i8>, i1 immarg, <vscale x 16 x i1>, i32)
declare <vscale x 32 x i8> @llvm.vp.ctlz.nvx32i8(<vscale x 32 x i8>, i1 immarg, <vscale x 32 x i1>, i32)
declare <vscale x 64 x i8> @llvm.vp.ctlz.nvx64i8(<vscale x 64 x i8>, i1 immarg, <vscale x 64 x i1>, i32)
declare <2 x i16> @llvm.vp.ctlz.v2i16(<2 x i16>, i1 immarg, <2 x i1>, i32)
declare <4 x i16> @llvm.vp.ctlz.v4i16(<4 x i16>, i1 immarg, <4 x i1>, i32)
declare <8 x i16> @llvm.vp.ctlz.v8i16(<8 x i16>, i1 immarg, <8 x i1>, i32)
declare <16 x i16> @llvm.vp.ctlz.v16i16(<16 x i16>, i1 immarg, <16 x i1>, i32)
declare <vscale x 1 x i16> @llvm.vp.ctlz.nvx1i16(<vscale x 1 x i16>, i1 immarg, <vscale x 1 x i1>, i32)
declare <vscale x 2 x i16> @llvm.vp.ctlz.nvx2i16(<vscale x 2 x i16>, i1 immarg, <vscale x 2 x i1>, i32)
declare <vscale x 4 x i16> @llvm.vp.ctlz.nvx4i16(<vscale x 4 x i16>, i1 immarg, <vscale x 4 x i1>, i32)
declare <vscale x 8 x i16> @llvm.vp.ctlz.nvx8i16(<vscale x 8 x i16>, i1 immarg, <vscale x 8 x i1>, i32)
declare <vscale x 16 x i16> @llvm.vp.ctlz.nvx16i16(<vscale x 16 x i16>, i1 immarg, <vscale x 16 x i1>, i32)
declare <vscale x 32 x i16> @llvm.vp.ctlz.nvx32i16(<vscale x 32 x i16>, i1 immarg, <vscale x 32 x i1>, i32)
declare <2 x i32> @llvm.vp.ctlz.v2i32(<2 x i32>, i1 immarg, <2 x i1>, i32)
declare <4 x i32> @llvm.vp.ctlz.v4i32(<4 x i32>, i1 immarg, <4 x i1>, i32)
declare <8 x i32> @llvm.vp.ctlz.v8i32(<8 x i32>, i1 immarg, <8 x i1>, i32)
declare <16 x i32> @llvm.vp.ctlz.v16i32(<16 x i32>, i1 immarg, <16 x i1>, i32)
declare <vscale x 1 x i32> @llvm.vp.ctlz.nvx1i32(<vscale x 1 x i32>, i1 immarg, <vscale x 1 x i1>, i32)
declare <vscale x 2 x i32> @llvm.vp.ctlz.nvx2i32(<vscale x 2 x i32>, i1 immarg, <vscale x 2 x i1>, i32)
declare <vscale x 4 x i32> @llvm.vp.ctlz.nvx4i32(<vscale x 4 x i32>, i1 immarg, <vscale x 4 x i1>, i32)
declare <vscale x 8 x i32> @llvm.vp.ctlz.nvx8i32(<vscale x 8 x i32>, i1 immarg, <vscale x 8 x i1>, i32)
declare <vscale x 16 x i32> @llvm.vp.ctlz.nvx16i32(<vscale x 16 x i32>, i1 immarg, <vscale x 16 x i1>, i32)
declare <2 x i64> @llvm.vp.ctlz.v2i64(<2 x i64>, i1 immarg, <2 x i1>, i32)
declare <4 x i64> @llvm.vp.ctlz.v4i64(<4 x i64>, i1 immarg, <4 x i1>, i32)
declare <8 x i64> @llvm.vp.ctlz.v8i64(<8 x i64>, i1 immarg, <8 x i1>, i32)
declare <16 x i64> @llvm.vp.ctlz.v16i64(<16 x i64>, i1 immarg, <16 x i1>, i32)
declare <vscale x 1 x i64> @llvm.vp.ctlz.nvx1i64(<vscale x 1 x i64>, i1 immarg, <vscale x 1 x i1>, i32)
declare <vscale x 2 x i64> @llvm.vp.ctlz.nvx2i64(<vscale x 2 x i64>, i1 immarg, <vscale x 2 x i1>, i32)
declare <vscale x 4 x i64> @llvm.vp.ctlz.nvx4i64(<vscale x 4 x i64>, i1 immarg, <vscale x 4 x i1>, i32)
declare <vscale x 8 x i64> @llvm.vp.ctlz.nvx8i64(<vscale x 8 x i64>, i1 immarg, <vscale x 8 x i1>, i32)
declare <vscale x 16 x i64> @llvm.vp.ctlz.nvx16i64(<vscale x 16 x i64>, i1 immarg, <vscale x 16 x i1>, i32)

declare <2 x i8> @llvm.vp.cttz.v2i8(<2 x i8>, i1 immarg, <2 x i1>, i32)
declare <4 x i8> @llvm.vp.cttz.v4i8(<4 x i8>, i1 immarg, <4 x i1>, i32)
declare <8 x i8> @llvm.vp.cttz.v8i8(<8 x i8>, i1 immarg, <8 x i1>, i32)
declare <16 x i8> @llvm.vp.cttz.v16i8(<16 x i8>, i1 immarg, <16 x i1>, i32)
declare <vscale x 1 x i8> @llvm.vp.cttz.nvx1i8(<vscale x 1 x i8>, i1 immarg, <vscale x 1 x i1>, i32)
declare <vscale x 2 x i8> @llvm.vp.cttz.nvx2i8(<vscale x 2 x i8>, i1 immarg, <vscale x 2 x i1>, i32)
declare <vscale x 4 x i8> @llvm.vp.cttz.nvx4i8(<vscale x 4 x i8>, i1 immarg, <vscale x 4 x i1>, i32)
declare <vscale x 8 x i8> @llvm.vp.cttz.nvx8i8(<vscale x 8 x i8>, i1 immarg, <vscale x 8 x i1>, i32)
declare <vscale x 16 x i8> @llvm.vp.cttz.nvx16i8(<vscale x 16 x i8>, i1 immarg, <vscale x 16 x i1>, i32)
declare <vscale x 32 x i8> @llvm.vp.cttz.nvx32i8(<vscale x 32 x i8>, i1 immarg, <vscale x 32 x i1>, i32)
declare <vscale x 64 x i8> @llvm.vp.cttz.nvx64i8(<vscale x 64 x i8>, i1 immarg, <vscale x 64 x i1>, i32)
declare <2 x i16> @llvm.vp.cttz.v2i16(<2 x i16>, i1 immarg, <2 x i1>, i32)
declare <4 x i16> @llvm.vp.cttz.v4i16(<4 x i16>, i1 immarg, <4 x i1>, i32)
declare <8 x i16> @llvm.vp.cttz.v8i16(<8 x i16>, i1 immarg, <8 x i1>, i32)
declare <16 x i16> @llvm.vp.cttz.v16i16(<16 x i16>, i1 immarg, <16 x i1>, i32)
declare <vscale x 1 x i16> @llvm.vp.cttz.nvx1i16(<vscale x 1 x i16>, i1 immarg, <vscale x 1 x i1>, i32)
declare <vscale x 2 x i16> @llvm.vp.cttz.nvx2i16(<vscale x 2 x i16>, i1 immarg, <vscale x 2 x i1>, i32)
declare <vscale x 4 x i16> @llvm.vp.cttz.nvx4i16(<vscale x 4 x i16>, i1 immarg, <vscale x 4 x i1>, i32)
declare <vscale x 8 x i16> @llvm.vp.cttz.nvx8i16(<vscale x 8 x i16>, i1 immarg, <vscale x 8 x i1>, i32)
declare <vscale x 16 x i16> @llvm.vp.cttz.nvx16i16(<vscale x 16 x i16>, i1 immarg, <vscale x 16 x i1>, i32)
declare <vscale x 32 x i16> @llvm.vp.cttz.nvx32i16(<vscale x 32 x i16>, i1 immarg, <vscale x 32 x i1>, i32)
declare <2 x i32> @llvm.vp.cttz.v2i32(<2 x i32>, i1 immarg, <2 x i1>, i32)
declare <4 x i32> @llvm.vp.cttz.v4i32(<4 x i32>, i1 immarg, <4 x i1>, i32)
declare <8 x i32> @llvm.vp.cttz.v8i32(<8 x i32>, i1 immarg, <8 x i1>, i32)
declare <16 x i32> @llvm.vp.cttz.v16i32(<16 x i32>, i1 immarg, <16 x i1>, i32)
declare <vscale x 1 x i32> @llvm.vp.cttz.nvx1i32(<vscale x 1 x i32>, i1 immarg, <vscale x 1 x i1>, i32)
declare <vscale x 2 x i32> @llvm.vp.cttz.nvx2i32(<vscale x 2 x i32>, i1 immarg, <vscale x 2 x i1>, i32)
declare <vscale x 4 x i32> @llvm.vp.cttz.nvx4i32(<vscale x 4 x i32>, i1 immarg, <vscale x 4 x i1>, i32)
declare <vscale x 8 x i32> @llvm.vp.cttz.nvx8i32(<vscale x 8 x i32>, i1 immarg, <vscale x 8 x i1>, i32)
declare <vscale x 16 x i32> @llvm.vp.cttz.nvx16i32(<vscale x 16 x i32>, i1 immarg, <vscale x 16 x i1>, i32)
declare <2 x i64> @llvm.vp.cttz.v2i64(<2 x i64>, i1 immarg, <2 x i1>, i32)
declare <4 x i64> @llvm.vp.cttz.v4i64(<4 x i64>, i1 immarg, <4 x i1>, i32)
declare <8 x i64> @llvm.vp.cttz.v8i64(<8 x i64>, i1 immarg, <8 x i1>, i32)
declare <16 x i64> @llvm.vp.cttz.v16i64(<16 x i64>, i1 immarg, <16 x i1>, i32)
declare <vscale x 1 x i64> @llvm.vp.cttz.nvx1i64(<vscale x 1 x i64>, i1 immarg, <vscale x 1 x i1>, i32)
declare <vscale x 2 x i64> @llvm.vp.cttz.nvx2i64(<vscale x 2 x i64>, i1 immarg, <vscale x 2 x i1>, i32)
declare <vscale x 4 x i64> @llvm.vp.cttz.nvx4i64(<vscale x 4 x i64>, i1 immarg, <vscale x 4 x i1>, i32)
declare <vscale x 8 x i64> @llvm.vp.cttz.nvx8i64(<vscale x 8 x i64>, i1 immarg, <vscale x 8 x i1>, i32)
declare <vscale x 16 x i64> @llvm.vp.cttz.nvx16i64(<vscale x 16 x i64>, i1 immarg, <vscale x 16 x i1>, i32)