[llvm] [TTI][RISCV] Implement cost of some intrinsics with LMUL (PR #117874)

via llvm-commits llvm-commits at lists.llvm.org
Sun Dec 1 20:26:02 PST 2024


https://github.com/LiqinWeng updated https://github.com/llvm/llvm-project/pull/117874

>From 48ce8de1f0c476df8bc13f131bc45fd69c43b722 Mon Sep 17 00:00:00 2001
From: LiqinWeng <liqin.weng at spacemit.com>
Date: Wed, 27 Nov 2024 20:25:06 +0800
Subject: [PATCH 1/4] [TTI][RISCV] Implement cost of some intrinsics with LMUL

Intrinsics include: sadd_sat/ssub_sat/uadd_sat/usub_sat/fabs/fsqrt/cttz/ctlz/ctpop
---
 .../Target/RISCV/RISCVTargetTransformInfo.cpp |  70 +++++++++-
 .../CostModel/RISCV/fp-min-max-abs.ll         |  56 ++++----
 .../Analysis/CostModel/RISCV/fp-sqrt-pow.ll   |  34 ++---
 .../Analysis/CostModel/RISCV/int-bit-manip.ll | 108 ++++++++--------
 .../Analysis/CostModel/RISCV/int-sat-math.ll  | 120 +++++++++---------
 5 files changed, 229 insertions(+), 159 deletions(-)

diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 8f0ef69258b165..e2cd71fb5a9f40 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -1013,20 +1013,78 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
   case Intrinsic::sadd_sat:
   case Intrinsic::ssub_sat:
   case Intrinsic::uadd_sat:
-  case Intrinsic::usub_sat:
-  case Intrinsic::fabs:
+  case Intrinsic::usub_sat: {
+    auto LT = getTypeLegalizationCost(RetTy);
+    if (ST->hasVInstructions() && LT.second.isVector()) {
+      unsigned Op;
+      switch (ICA.getID()) {
+      case Intrinsic::sadd_sat:
+        Op = RISCV::VSADD_VV;
+        break;
+      case Intrinsic::ssub_sat:
+        Op = RISCV::VSSUBU_VV;
+        break;
+      case Intrinsic::uadd_sat:
+        Op = RISCV::VSADDU_VV;
+        break;
+      case Intrinsic::usub_sat:
+        Op = RISCV::VSSUBU_VV;
+        break;
+      }
+      return LT.first * getRISCVInstructionCost(Op, LT.second, CostKind);
+    }
+    break;
+  }
+  case Intrinsic::fabs: {
+    auto LT = getTypeLegalizationCost(RetTy);
+    // FIXME: not get the correct cost about the llvm.sqrt.vxbf16
+    // LT.second is promote llvm::MVT::f32
+    if (ST->hasVInstructions() && LT.second.isVector()) {
+      // lui a0, 8
+      // addi a0, a0, -1
+      // vsetvli a1, zero, e16, m1, ta, ma
+      // vand.vx v8, v8, a0
+      if (LT.second.getVectorElementType() == MVT::bf16 ||
+          (LT.second.getVectorElementType() == MVT::f16 &&
+           !ST->hasVInstructionsF16()))
+        return LT.first * getRISCVInstructionCost(RISCV::VAND_VX, LT.second,
+                                                  CostKind) +
+               2;
+      else
+        return LT.first *
+               getRISCVInstructionCost(RISCV::VFSGNJX_VV, LT.second, CostKind);
+    }
+    break;
+  }
   case Intrinsic::sqrt: {
     auto LT = getTypeLegalizationCost(RetTy);
-    if (ST->hasVInstructions() && LT.second.isVector())
-      return LT.first;
+    // FIXME: not get the correct cost about the llvm.sqrt.vxbf16
+    // LT.second is promote llvm::MVT::f32
+    if (ST->hasVInstructions() && LT.second.isVector()) {
+      SmallVector<unsigned, 3> Opcodes;
+      if (LT.second.getVectorElementType() == MVT::bf16)
+        Opcodes = {RISCV::VFWCVTBF16_F_F_V, RISCV::VFSQRT_V,
+                   RISCV::VFNCVTBF16_F_F_W};
+      else if (LT.second.getVectorElementType() == MVT::f16 &&
+               !ST->hasVInstructionsF16())
+        Opcodes = {RISCV::VFWCVT_F_F_V, RISCV::VFSQRT_V, RISCV::VFNCVT_F_F_W};
+      else
+        Opcodes = {RISCV::VFSQRT_V};
+      return LT.first *
+             getRISCVInstructionCost(RISCV::VFSQRT_V, LT.second, CostKind);
+    }
     break;
   }
   case Intrinsic::cttz:
   case Intrinsic::ctlz:
   case Intrinsic::ctpop: {
     auto LT = getTypeLegalizationCost(RetTy);
-    if (ST->hasVInstructions() && ST->hasStdExtZvbb() && LT.second.isVector())
-      return LT.first;
+    if (ST->hasVInstructions() && ST->hasStdExtZvbb() && LT.second.isVector()) {
+      unsigned Op = (Intrinsic::cttz)   ? RISCV::VCTZ_V
+                    : (Intrinsic::ctlz) ? RISCV::VCLZ_V
+                                        : RISCV::VCPOP_V;
+      return LT.first * getRISCVInstructionCost(Op, LT.second, CostKind);
+    }
     break;
   }
   case Intrinsic::abs: {
diff --git a/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll b/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
index 0b2c8da4438da2..6259c31a08bc1f 100644
--- a/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
@@ -7,22 +7,22 @@ define void @fabs() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call float @llvm.fabs.f32(float undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x float> @llvm.fabs.v2f32(<2 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %4 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %5 = call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 1 x float> @llvm.fabs.nxv1f32(<vscale x 1 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x float> @llvm.fabs.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x float> @llvm.fabs.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x float> @llvm.fabs.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x float> @llvm.fabs.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 4 x float> @llvm.fabs.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %9 = call <vscale x 8 x float> @llvm.fabs.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %10 = call <vscale x 16 x float> @llvm.fabs.nxv16f32(<vscale x 16 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call double @llvm.fabs.f64(double undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x double> @llvm.fabs.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %14 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %15 = call <16 x double> @llvm.fabs.v16f64(<16 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x double> @llvm.fabs.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x double> @llvm.fabs.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x double> @llvm.fabs.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x double> @llvm.fabs.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 2 x double> @llvm.fabs.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 4 x double> @llvm.fabs.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %19 = call <vscale x 8 x double> @llvm.fabs.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call float @llvm.fabs.f32(float undef)
@@ -48,17 +48,29 @@ define void @fabs() {
 }
 
 define void @fabs_f16() {
-; CHECK-LABEL: 'fabs_f16'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call half @llvm.fabs.f16(half undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+; ZVFH-LABEL: 'fabs_f16'
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call half @llvm.fabs.f16(half undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %9 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; ZVFHMIN-LABEL: 'fabs_f16'
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call half @llvm.fabs.f16(half undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %2 = call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %3 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %4 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %5 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %6 = call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %7 = call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %8 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %9 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call half @llvm.fabs.f16(half undef)
   call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
diff --git a/llvm/test/Analysis/CostModel/RISCV/fp-sqrt-pow.ll b/llvm/test/Analysis/CostModel/RISCV/fp-sqrt-pow.ll
index be9c19dc59a852..446627f6bf3c0e 100644
--- a/llvm/test/Analysis/CostModel/RISCV/fp-sqrt-pow.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/fp-sqrt-pow.ll
@@ -8,30 +8,30 @@ define void @sqrt() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x bfloat> @llvm.sqrt.v2bf16(<2 x bfloat> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x bfloat> @llvm.sqrt.v4bf16(<4 x bfloat> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x bfloat> @llvm.sqrt.v8bf16(<8 x bfloat> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x bfloat> @llvm.sqrt.v16bf16(<16 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x bfloat> @llvm.sqrt.v16bf16(<16 x bfloat> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x bfloat> @llvm.sqrt.nxv2bf16(<vscale x 2 x bfloat> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x bfloat> @llvm.sqrt.nxv4bf16(<vscale x 4 x bfloat> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.sqrt.nxv8bf16(<vscale x 8 x bfloat> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.sqrt.nxv16bf16(<vscale x 16 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x bfloat> @llvm.sqrt.nxv8bf16(<vscale x 8 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %9 = call <vscale x 16 x bfloat> @llvm.sqrt.nxv16bf16(<vscale x 16 x bfloat> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call float @llvm.sqrt.f32(float undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x float> @llvm.sqrt.v2f32(<2 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %14 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 1 x float> @llvm.sqrt.nxv1f32(<vscale x 1 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 2 x float> @llvm.sqrt.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 8 x float> @llvm.sqrt.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 16 x float> @llvm.sqrt.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 8 x float> @llvm.sqrt.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %19 = call <vscale x 16 x float> @llvm.sqrt.nxv16f32(<vscale x 16 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call double @llvm.sqrt.f64(double undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <16 x double> @llvm.sqrt.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %22 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %23 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %24 = call <16 x double> @llvm.sqrt.v16f64(<16 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 1 x double> @llvm.sqrt.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 4 x double> @llvm.sqrt.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 8 x double> @llvm.sqrt.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %26 = call <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %27 = call <vscale x 4 x double> @llvm.sqrt.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %28 = call <vscale x 8 x double> @llvm.sqrt.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call bfloat @llvm.sqrt.bf16(bfloat undef)
@@ -71,11 +71,11 @@ define void @sqrt_f16() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x half> @llvm.sqrt.v2f16(<2 x half> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x half> @llvm.sqrt.v4f16(<4 x half> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x half> @llvm.sqrt.v8f16(<8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x half> @llvm.sqrt.v16f16(<16 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x half> @llvm.sqrt.v16f16(<16 x half> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.sqrt.nxv2f16(<vscale x 2 x half> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.sqrt.nxv4f16(<vscale x 4 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x half> @llvm.sqrt.nxv8f16(<vscale x 8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x half> @llvm.sqrt.nxv16f16(<vscale x 16 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.sqrt.nxv8f16(<vscale x 8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %9 = call <vscale x 16 x half> @llvm.sqrt.nxv16f16(<vscale x 16 x half> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call half @llvm.sqrt.f16(half undef)
diff --git a/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll b/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll
index 55db70ce1e9125..5f2728f93d551c 100644
--- a/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll
@@ -209,37 +209,37 @@ define void @ctlz() {
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.ctlz.nxv2i8(<vscale x 2 x i8> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.ctlz.nxv4i8(<vscale x 4 x i8> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.ctlz.nxv8i8(<vscale x 8 x i8> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.ctlz.nxv16i8(<vscale x 16 x i8> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 32 x i8> @llvm.ctlz.nxv32i8(<vscale x 32 x i8> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call <vscale x 64 x i8> @llvm.ctlz.nxv64i8(<vscale x 64 x i8> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x i8> @llvm.ctlz.nxv16i8(<vscale x 16 x i8> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %10 = call <vscale x 32 x i8> @llvm.ctlz.nxv32i8(<vscale x 32 x i8> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %11 = call <vscale x 64 x i8> @llvm.ctlz.nxv64i8(<vscale x 64 x i8> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x i16> @llvm.ctlz.v2i16(<2 x i16> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x i16> @llvm.ctlz.v4i16(<4 x i16> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x i16> @llvm.ctlz.v8i16(<8 x i16> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x i16> @llvm.ctlz.v16i16(<16 x i16> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x i16> @llvm.ctlz.v16i16(<16 x i16> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x i16> @llvm.ctlz.nxv1i16(<vscale x 1 x i16> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x i16> @llvm.ctlz.nxv2i16(<vscale x 2 x i16> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x i16> @llvm.ctlz.nxv4i16(<vscale x 4 x i16> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x i16> @llvm.ctlz.nxv8i16(<vscale x 8 x i16> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call <vscale x 16 x i16> @llvm.ctlz.nxv16i16(<vscale x 16 x i16> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = call <vscale x 32 x i16> @llvm.ctlz.nxv32i16(<vscale x 32 x i16> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = call <vscale x 8 x i16> @llvm.ctlz.nxv8i16(<vscale x 8 x i16> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %20 = call <vscale x 16 x i16> @llvm.ctlz.nxv16i16(<vscale x 16 x i16> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %21 = call <vscale x 32 x i16> @llvm.ctlz.nxv32i16(<vscale x 32 x i16> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <2 x i32> @llvm.ctlz.v2i32(<2 x i32> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <8 x i32> @llvm.ctlz.v8i32(<8 x i32> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <16 x i32> @llvm.ctlz.v16i32(<16 x i32> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %24 = call <8 x i32> @llvm.ctlz.v8i32(<8 x i32> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %25 = call <16 x i32> @llvm.ctlz.v16i32(<16 x i32> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 1 x i32> @llvm.ctlz.nxv1i32(<vscale x 1 x i32> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 2 x i32> @llvm.ctlz.nxv2i32(<vscale x 2 x i32> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 4 x i32> @llvm.ctlz.nxv4i32(<vscale x 4 x i32> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = call <vscale x 8 x i32> @llvm.ctlz.nxv8i32(<vscale x 8 x i32> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = call <vscale x 16 x i32> @llvm.ctlz.nxv16i32(<vscale x 16 x i32> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %28 = call <vscale x 4 x i32> @llvm.ctlz.nxv4i32(<vscale x 4 x i32> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %29 = call <vscale x 8 x i32> @llvm.ctlz.nxv8i32(<vscale x 8 x i32> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %30 = call <vscale x 16 x i32> @llvm.ctlz.nxv16i32(<vscale x 16 x i32> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %31 = call <2 x i64> @llvm.ctlz.v2i64(<2 x i64> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %32 = call <4 x i64> @llvm.ctlz.v4i64(<4 x i64> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %33 = call <8 x i64> @llvm.ctlz.v8i64(<8 x i64> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = call <16 x i64> @llvm.ctlz.v16i64(<16 x i64> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %32 = call <4 x i64> @llvm.ctlz.v4i64(<4 x i64> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %33 = call <8 x i64> @llvm.ctlz.v8i64(<8 x i64> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %34 = call <16 x i64> @llvm.ctlz.v16i64(<16 x i64> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 1 x i64> @llvm.ctlz.nxv1i64(<vscale x 1 x i64> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %36 = call <vscale x 2 x i64> @llvm.ctlz.nxv2i64(<vscale x 2 x i64> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %37 = call <vscale x 4 x i64> @llvm.ctlz.nxv4i64(<vscale x 4 x i64> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %38 = call <vscale x 8 x i64> @llvm.ctlz.nxv8i64(<vscale x 8 x i64> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %39 = call <vscale x 16 x i64> @llvm.ctlz.nxv16i64(<vscale x 16 x i64> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %36 = call <vscale x 2 x i64> @llvm.ctlz.nxv2i64(<vscale x 2 x i64> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %37 = call <vscale x 4 x i64> @llvm.ctlz.nxv4i64(<vscale x 4 x i64> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %38 = call <vscale x 8 x i64> @llvm.ctlz.nxv8i64(<vscale x 8 x i64> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %39 = call <vscale x 16 x i64> @llvm.ctlz.nxv16i64(<vscale x 16 x i64> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call <2 x i8> @llvm.ctlz.v2i8(<2 x i8> undef, i1 false)
@@ -336,37 +336,37 @@ define void @cttz() {
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.cttz.nxv2i8(<vscale x 2 x i8> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.cttz.nxv4i8(<vscale x 4 x i8> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.cttz.nxv8i8(<vscale x 8 x i8> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.cttz.nxv16i8(<vscale x 16 x i8> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 32 x i8> @llvm.cttz.nxv32i8(<vscale x 32 x i8> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call <vscale x 64 x i8> @llvm.cttz.nxv64i8(<vscale x 64 x i8> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x i8> @llvm.cttz.nxv16i8(<vscale x 16 x i8> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %10 = call <vscale x 32 x i8> @llvm.cttz.nxv32i8(<vscale x 32 x i8> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %11 = call <vscale x 64 x i8> @llvm.cttz.nxv64i8(<vscale x 64 x i8> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x i16> @llvm.cttz.v2i16(<2 x i16> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x i16> @llvm.cttz.v4i16(<4 x i16> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x i16> @llvm.cttz.v8i16(<8 x i16> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x i16> @llvm.cttz.v16i16(<16 x i16> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x i16> @llvm.cttz.v16i16(<16 x i16> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x i16> @llvm.cttz.nxv1i16(<vscale x 1 x i16> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x i16> @llvm.cttz.nxv2i16(<vscale x 2 x i16> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x i16> @llvm.cttz.nxv4i16(<vscale x 4 x i16> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x i16> @llvm.cttz.nxv8i16(<vscale x 8 x i16> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call <vscale x 16 x i16> @llvm.cttz.nxv16i16(<vscale x 16 x i16> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = call <vscale x 32 x i16> @llvm.cttz.nxv32i16(<vscale x 32 x i16> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = call <vscale x 8 x i16> @llvm.cttz.nxv8i16(<vscale x 8 x i16> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %20 = call <vscale x 16 x i16> @llvm.cttz.nxv16i16(<vscale x 16 x i16> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %21 = call <vscale x 32 x i16> @llvm.cttz.nxv32i16(<vscale x 32 x i16> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <2 x i32> @llvm.cttz.v2i32(<2 x i32> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <8 x i32> @llvm.cttz.v8i32(<8 x i32> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <16 x i32> @llvm.cttz.v16i32(<16 x i32> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %24 = call <8 x i32> @llvm.cttz.v8i32(<8 x i32> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %25 = call <16 x i32> @llvm.cttz.v16i32(<16 x i32> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 1 x i32> @llvm.cttz.nxv1i32(<vscale x 1 x i32> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 2 x i32> @llvm.cttz.nxv2i32(<vscale x 2 x i32> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = call <vscale x 8 x i32> @llvm.cttz.nxv8i32(<vscale x 8 x i32> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = call <vscale x 16 x i32> @llvm.cttz.nxv16i32(<vscale x 16 x i32> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %28 = call <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %29 = call <vscale x 8 x i32> @llvm.cttz.nxv8i32(<vscale x 8 x i32> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %30 = call <vscale x 16 x i32> @llvm.cttz.nxv16i32(<vscale x 16 x i32> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %31 = call <2 x i64> @llvm.cttz.v2i64(<2 x i64> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %32 = call <4 x i64> @llvm.cttz.v4i64(<4 x i64> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %33 = call <8 x i64> @llvm.cttz.v8i64(<8 x i64> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = call <16 x i64> @llvm.cttz.v16i64(<16 x i64> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %32 = call <4 x i64> @llvm.cttz.v4i64(<4 x i64> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %33 = call <8 x i64> @llvm.cttz.v8i64(<8 x i64> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %34 = call <16 x i64> @llvm.cttz.v16i64(<16 x i64> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 1 x i64> @llvm.cttz.nxv1i64(<vscale x 1 x i64> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %36 = call <vscale x 2 x i64> @llvm.cttz.nxv2i64(<vscale x 2 x i64> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %37 = call <vscale x 4 x i64> @llvm.cttz.nxv4i64(<vscale x 4 x i64> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %38 = call <vscale x 8 x i64> @llvm.cttz.nxv8i64(<vscale x 8 x i64> undef, i1 false)
-; ZVBB-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %39 = call <vscale x 16 x i64> @llvm.cttz.nxv16i64(<vscale x 16 x i64> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %36 = call <vscale x 2 x i64> @llvm.cttz.nxv2i64(<vscale x 2 x i64> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %37 = call <vscale x 4 x i64> @llvm.cttz.nxv4i64(<vscale x 4 x i64> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %38 = call <vscale x 8 x i64> @llvm.cttz.nxv8i64(<vscale x 8 x i64> undef, i1 false)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %39 = call <vscale x 16 x i64> @llvm.cttz.nxv16i64(<vscale x 16 x i64> undef, i1 false)
 ; ZVBB-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call <2 x i8> @llvm.cttz.v2i8(<2 x i8> undef, i1 false)
@@ -465,37 +465,37 @@ define void @ctpop() {
 ; 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 2 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 2 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 2 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 4 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 2 for instruction: %24 = call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> undef)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 4 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 2 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 4 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 8 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 2 for instruction: %33 = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> undef)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %34 = call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> undef)
+; ZVBB-NEXT:  Cost Model: Found an estimated cost of 8 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 2 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 4 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 8 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 16 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)
diff --git a/llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll b/llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll
index be6b7c57d22523..0758eb204be488 100644
--- a/llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/int-sat-math.ll
@@ -11,33 +11,33 @@ define void @sadd.sat() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.sadd.sat.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.sadd.sat.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.sadd.sat.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.sadd.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x i8> @llvm.sadd.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %10 = call i16 @llvm.sadd.sat.i16(i16 undef, i16 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.sadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.sadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.sadd.sat.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.sadd.sat.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.sadd.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.sadd.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 8 x i16> @llvm.sadd.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 16 x i16> @llvm.sadd.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %19 = call i32 @llvm.sadd.sat.i32(i32 undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.sadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %22 = call <8 x i32> @llvm.sadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %23 = call <16 x i32> @llvm.sadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.sadd.sat.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.sadd.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.sadd.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.sadd.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %25 = call <vscale x 4 x i32> @llvm.sadd.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %26 = call <vscale x 8 x i32> @llvm.sadd.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %27 = call <vscale x 16 x i32> @llvm.sadd.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %28 = call i64 @llvm.sadd.sat.i64(i64 undef, i64 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.sadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.sadd.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.sadd.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.sadd.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.sadd.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %30 = call <4 x i64> @llvm.sadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %31 = call <8 x i64> @llvm.sadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %32 = call <16 x i64> @llvm.sadd.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %33 = call <vscale x 2 x i64> @llvm.sadd.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %34 = call <vscale x 4 x i64> @llvm.sadd.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %35 = call <vscale x 8 x i64> @llvm.sadd.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call i8 @llvm.sadd.sat.i8(i8 undef, i8 undef)
@@ -88,33 +88,33 @@ define void @uadd.sat() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.uadd.sat.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.uadd.sat.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.uadd.sat.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.uadd.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x i8> @llvm.uadd.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %10 = call i16 @llvm.uadd.sat.i16(i16 undef, i16 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.uadd.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.uadd.sat.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.uadd.sat.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.uadd.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.uadd.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 8 x i16> @llvm.uadd.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 16 x i16> @llvm.uadd.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %19 = call i32 @llvm.uadd.sat.i32(i32 undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.uadd.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %22 = call <8 x i32> @llvm.uadd.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %23 = call <16 x i32> @llvm.uadd.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.uadd.sat.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.uadd.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.uadd.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.uadd.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %25 = call <vscale x 4 x i32> @llvm.uadd.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %26 = call <vscale x 8 x i32> @llvm.uadd.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %27 = call <vscale x 16 x i32> @llvm.uadd.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %28 = call i64 @llvm.uadd.sat.i64(i64 undef, i64 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.uadd.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.uadd.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.uadd.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.uadd.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.uadd.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %30 = call <4 x i64> @llvm.uadd.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %31 = call <8 x i64> @llvm.uadd.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %32 = call <16 x i64> @llvm.uadd.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %33 = call <vscale x 2 x i64> @llvm.uadd.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %34 = call <vscale x 4 x i64> @llvm.uadd.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %35 = call <vscale x 8 x i64> @llvm.uadd.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call i8 @llvm.uadd.sat.i8(i8 undef, i8 undef)
@@ -165,33 +165,33 @@ define void @usub.sat() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.usub.sat.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.usub.sat.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.usub.sat.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.usub.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x i8> @llvm.usub.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %10 = call i16 @llvm.usub.sat.i16(i16 undef, i16 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.usub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.usub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.usub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.usub.sat.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.usub.sat.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.usub.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.usub.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 8 x i16> @llvm.usub.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 16 x i16> @llvm.usub.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %19 = call i32 @llvm.usub.sat.i32(i32 undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.usub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %22 = call <8 x i32> @llvm.usub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %23 = call <16 x i32> @llvm.usub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.usub.sat.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.usub.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.usub.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.usub.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %25 = call <vscale x 4 x i32> @llvm.usub.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %26 = call <vscale x 8 x i32> @llvm.usub.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %27 = call <vscale x 16 x i32> @llvm.usub.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %28 = call i64 @llvm.usub.sat.i64(i64 undef, i64 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.usub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.usub.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.usub.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.usub.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.usub.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %30 = call <4 x i64> @llvm.usub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %31 = call <8 x i64> @llvm.usub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %32 = call <16 x i64> @llvm.usub.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %33 = call <vscale x 2 x i64> @llvm.usub.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %34 = call <vscale x 4 x i64> @llvm.usub.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %35 = call <vscale x 8 x i64> @llvm.usub.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call i8 @llvm.usub.sat.i8(i8 undef, i8 undef)
@@ -242,33 +242,33 @@ define void @ssub.sat() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.ssub.sat.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.ssub.sat.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.ssub.sat.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.ssub.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x i8> @llvm.ssub.sat.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %10 = call i16 @llvm.ssub.sat.i16(i16 undef, i16 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> undef, <2 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> undef, <4 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.ssub.sat.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.ssub.sat.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.ssub.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.ssub.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 8 x i16> @llvm.ssub.sat.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 16 x i16> @llvm.ssub.sat.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %19 = call i32 @llvm.ssub.sat.i32(i32 undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> undef, <2 x i32> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %22 = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %23 = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.ssub.sat.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.ssub.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.ssub.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.ssub.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %25 = call <vscale x 4 x i32> @llvm.ssub.sat.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %26 = call <vscale x 8 x i32> @llvm.ssub.sat.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %27 = call <vscale x 16 x i32> @llvm.ssub.sat.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %28 = call i64 @llvm.ssub.sat.i64(i64 undef, i64 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.ssub.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.ssub.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.ssub.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.ssub.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %30 = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %31 = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %32 = call <16 x i64> @llvm.ssub.sat.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %33 = call <vscale x 2 x i64> @llvm.ssub.sat.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %34 = call <vscale x 4 x i64> @llvm.ssub.sat.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %35 = call <vscale x 8 x i64> @llvm.ssub.sat.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call i8 @llvm.ssub.sat.i8(i8 undef, i8 undef)

>From daf8269f15339dc6acbfcf78b5d59638ec302e64 Mon Sep 17 00:00:00 2001
From: LiqinWeng <liqin.weng at spacemit.com>
Date: Fri, 29 Nov 2024 13:37:53 +0800
Subject: [PATCH 2/4] remove the fp15 && bf16 implement

---
 .../Target/RISCV/RISCVTargetTransformInfo.cpp | 61 ++++++++-----------
 .../CostModel/RISCV/fp-min-max-abs.ll         | 52 ++++++++--------
 2 files changed, 52 insertions(+), 61 deletions(-)

diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index e2cd71fb5a9f40..a0ceca9c350f3f 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -1035,43 +1035,21 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
     }
     break;
   }
-  case Intrinsic::fabs: {
-    auto LT = getTypeLegalizationCost(RetTy);
-    // FIXME: not get the correct cost about the llvm.sqrt.vxbf16
-    // LT.second is promote llvm::MVT::f32
-    if (ST->hasVInstructions() && LT.second.isVector()) {
-      // lui a0, 8
-      // addi a0, a0, -1
-      // vsetvli a1, zero, e16, m1, ta, ma
-      // vand.vx v8, v8, a0
-      if (LT.second.getVectorElementType() == MVT::bf16 ||
-          (LT.second.getVectorElementType() == MVT::f16 &&
-           !ST->hasVInstructionsF16()))
-        return LT.first * getRISCVInstructionCost(RISCV::VAND_VX, LT.second,
-                                                  CostKind) +
-               2;
-      else
-        return LT.first *
-               getRISCVInstructionCost(RISCV::VFSGNJX_VV, LT.second, CostKind);
-    }
-    break;
-  }
+  case Intrinsic::fabs:
   case Intrinsic::sqrt: {
     auto LT = getTypeLegalizationCost(RetTy);
-    // FIXME: not get the correct cost about the llvm.sqrt.vxbf16
-    // LT.second is promote llvm::MVT::f32
+    // TODO: add f16/bf16, bf16 with zvfhbmin && f16 with zvfhmin
     if (ST->hasVInstructions() && LT.second.isVector()) {
-      SmallVector<unsigned, 3> Opcodes;
-      if (LT.second.getVectorElementType() == MVT::bf16)
-        Opcodes = {RISCV::VFWCVTBF16_F_F_V, RISCV::VFSQRT_V,
-                   RISCV::VFNCVTBF16_F_F_W};
-      else if (LT.second.getVectorElementType() == MVT::f16 &&
-               !ST->hasVInstructionsF16())
-        Opcodes = {RISCV::VFWCVT_F_F_V, RISCV::VFSQRT_V, RISCV::VFNCVT_F_F_W};
-      else
-        Opcodes = {RISCV::VFSQRT_V};
-      return LT.first *
-             getRISCVInstructionCost(RISCV::VFSQRT_V, LT.second, CostKind);
+      unsigned Op;
+      switch (ICA.getID()) {
+      case Intrinsic::fabs:
+        Op = RISCV::VFSGNJX_VV;
+        break;
+      case Intrinsic::sqrt:
+        Op = RISCV::VFSQRT_V;
+        break;
+      }
+      return LT.first * getRISCVInstructionCost(Op, LT.second, CostKind);
     }
     break;
   }
@@ -1080,9 +1058,18 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
   case Intrinsic::ctpop: {
     auto LT = getTypeLegalizationCost(RetTy);
     if (ST->hasVInstructions() && ST->hasStdExtZvbb() && LT.second.isVector()) {
-      unsigned Op = (Intrinsic::cttz)   ? RISCV::VCTZ_V
-                    : (Intrinsic::ctlz) ? RISCV::VCLZ_V
-                                        : RISCV::VCPOP_V;
+      unsigned Op;
+      switch (ICA.getID()) {
+      case Intrinsic::cttz:
+        Op = RISCV::VCTZ_V;
+        break;
+      case Intrinsic::ctlz:
+        Op = RISCV::VCLZ_V;
+        break;
+      case Intrinsic::ctpop:
+        Op = RISCV::VCPOP_V;
+        break;
+      }
       return LT.first * getRISCVInstructionCost(Op, LT.second, CostKind);
     }
     break;
diff --git a/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll b/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
index 6259c31a08bc1f..0c3296e80340d8 100644
--- a/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
@@ -1,6 +1,6 @@
 ; 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,+zfh,+zvfh | FileCheck %s --check-prefixes=CHECK,ZVFH
-; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v,+f,+d,+zfh,+zvfhmin | FileCheck %s --check-prefixes=CHECK,ZVFHMIN
+; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v,+f,+d,+zfh,+zvfhmin,+zvfhbmin | FileCheck %s --check-prefixes=CHECK,ZVFHMIN
 
 define void @fabs() {
 ; CHECK-LABEL: 'fabs'
@@ -48,35 +48,39 @@ define void @fabs() {
 }
 
 define void @fabs_f16() {
-; ZVFH-LABEL: 'fabs_f16'
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call half @llvm.fabs.f16(half undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %9 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
-;
-; ZVFHMIN-LABEL: 'fabs_f16'
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call half @llvm.fabs.f16(half undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %2 = call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %3 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %4 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %5 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %6 = call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %7 = call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %8 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %9 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-LABEL: 'fabs_f16'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call half @llvm.fabs.f16(half undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %2 = call <2 x bfloat> @llvm.fabs.v2bf16(<2 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %3 = call <4 x bfloat> @llvm.fabs.v4bf16(<4 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %4 = call <8 x bfloat> @llvm.fabs.v8bf16(<8 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %5 = call <16 x bfloat> @llvm.fabs.v16bf16(<16 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %9 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 2 x bfloat> @llvm.fabs.nxv2bf16(<vscale x 2 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %11 = call <vscale x 4 x bfloat> @llvm.fabs.nxv4bf16(<vscale x 4 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %12 = call <vscale x 8 x bfloat> @llvm.fabs.nxv8bf16(<vscale x 8 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %13 = call <vscale x 16 x bfloat> @llvm.fabs.nxv16bf16(<vscale x 16 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %16 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %17 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call half @llvm.fabs.f16(half undef)
+  call <2 x bfloat> @llvm.fabs.v2f16(<2 x bfloat> undef)
+  call <4 x bfloat> @llvm.fabs.v4f16(<4 x bfloat> undef)
+  call <8 x bfloat> @llvm.fabs.v8f16(<8 x bfloat> undef)
+  call <16 x bfloat> @llvm.fabs.v16f16(<16 x bfloat> undef)
   call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
   call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
   call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
   call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
+  call <vscale x 2 x bfloat> @llvm.fabs.nxv2f16(<vscale x 2 x bfloat> undef)
+  call <vscale x 4 x bfloat> @llvm.fabs.nxv4f16(<vscale x 4 x bfloat> undef)
+  call <vscale x 8 x bfloat> @llvm.fabs.nxv8f16(<vscale x 8 x bfloat> undef)
+  call <vscale x 16 x bfloat> @llvm.fabs.nxv16f16(<vscale x 16 x bfloat> undef)
   call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> undef)
   call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> undef)
   call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)

>From d3e0c4a35b8b9d1641602353e203ad7e107ab85c Mon Sep 17 00:00:00 2001
From: LiqinWeng <liqin.weng at spacemit.com>
Date: Sun, 1 Dec 2024 11:11:41 +0800
Subject: [PATCH 3/4] fix the comments

---
 .../Target/RISCV/RISCVTargetTransformInfo.cpp |  2 +-
 .../CostModel/RISCV/fp-min-max-abs.ll         | 60 ++++++++++++-------
 2 files changed, 41 insertions(+), 21 deletions(-)

diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index a0ceca9c350f3f..abc37cec23ba7d 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -1038,7 +1038,7 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
   case Intrinsic::fabs:
   case Intrinsic::sqrt: {
     auto LT = getTypeLegalizationCost(RetTy);
-    // TODO: add f16/bf16, bf16 with zvfhbmin && f16 with zvfhmin
+    // TODO: add f16/bf16, bf16 with zvfbfmin && f16 with zvfhmin
     if (ST->hasVInstructions() && LT.second.isVector()) {
       unsigned Op;
       switch (ICA.getID()) {
diff --git a/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll b/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
index 0c3296e80340d8..f80d6dac58532a 100644
--- a/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
@@ -1,6 +1,6 @@
 ; 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,+zfh,+zvfh | FileCheck %s --check-prefixes=CHECK,ZVFH
-; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v,+f,+d,+zfh,+zvfhmin,+zvfhbmin | FileCheck %s --check-prefixes=CHECK,ZVFHMIN
+; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v,+f,+d,+zfh,+zvfhmin,+zvfbfmin | FileCheck %s --check-prefixes=CHECK,ZVFHMIN
 
 define void @fabs() {
 ; CHECK-LABEL: 'fabs'
@@ -48,25 +48,45 @@ define void @fabs() {
 }
 
 define void @fabs_f16() {
-; CHECK-LABEL: 'fabs_f16'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call half @llvm.fabs.f16(half undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %2 = call <2 x bfloat> @llvm.fabs.v2bf16(<2 x bfloat> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %3 = call <4 x bfloat> @llvm.fabs.v4bf16(<4 x bfloat> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %4 = call <8 x bfloat> @llvm.fabs.v8bf16(<8 x bfloat> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %5 = call <16 x bfloat> @llvm.fabs.v16bf16(<16 x bfloat> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %9 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 2 x bfloat> @llvm.fabs.nxv2bf16(<vscale x 2 x bfloat> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %11 = call <vscale x 4 x bfloat> @llvm.fabs.nxv4bf16(<vscale x 4 x bfloat> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %12 = call <vscale x 8 x bfloat> @llvm.fabs.nxv8bf16(<vscale x 8 x bfloat> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %13 = call <vscale x 16 x bfloat> @llvm.fabs.nxv16bf16(<vscale x 16 x bfloat> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %16 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %17 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+; ZVFH-LABEL: 'fabs_f16'
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call half @llvm.fabs.f16(half undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %2 = call <2 x bfloat> @llvm.fabs.v2bf16(<2 x bfloat> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %3 = call <4 x bfloat> @llvm.fabs.v4bf16(<4 x bfloat> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %4 = call <8 x bfloat> @llvm.fabs.v8bf16(<8 x bfloat> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %5 = call <16 x bfloat> @llvm.fabs.v16bf16(<16 x bfloat> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %9 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
+; ZVFH-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 2 x bfloat> @llvm.fabs.nxv2bf16(<vscale x 2 x bfloat> undef)
+; ZVFH-NEXT:  Cost Model: Invalid cost for instruction: %11 = call <vscale x 4 x bfloat> @llvm.fabs.nxv4bf16(<vscale x 4 x bfloat> undef)
+; ZVFH-NEXT:  Cost Model: Invalid cost for instruction: %12 = call <vscale x 8 x bfloat> @llvm.fabs.nxv8bf16(<vscale x 8 x bfloat> undef)
+; ZVFH-NEXT:  Cost Model: Invalid cost for instruction: %13 = call <vscale x 16 x bfloat> @llvm.fabs.nxv16bf16(<vscale x 16 x bfloat> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %16 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %17 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
+; ZVFH-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; ZVFHMIN-LABEL: 'fabs_f16'
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call half @llvm.fabs.f16(half undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x bfloat> @llvm.fabs.v2bf16(<2 x bfloat> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x bfloat> @llvm.fabs.v4bf16(<4 x bfloat> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x bfloat> @llvm.fabs.v8bf16(<8 x bfloat> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x bfloat> @llvm.fabs.v16bf16(<16 x bfloat> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %9 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 2 x bfloat> @llvm.fabs.nxv2bf16(<vscale x 2 x bfloat> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call <vscale x 4 x bfloat> @llvm.fabs.nxv4bf16(<vscale x 4 x bfloat> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <vscale x 8 x bfloat> @llvm.fabs.nxv8bf16(<vscale x 8 x bfloat> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %13 = call <vscale x 16 x bfloat> @llvm.fabs.nxv16bf16(<vscale x 16 x bfloat> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %16 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %17 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
+; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call half @llvm.fabs.f16(half undef)
   call <2 x bfloat> @llvm.fabs.v2f16(<2 x bfloat> undef)

>From 20d9d79e7692742cb28ff715ed0ebb3037fc25bb Mon Sep 17 00:00:00 2001
From: LiqinWeng <liqin.weng at spacemit.com>
Date: Mon, 2 Dec 2024 12:25:32 +0800
Subject: [PATCH 4/4] address the comment

---
 .../CostModel/RISCV/fp-min-max-abs.ll         | 60 +++++++------------
 1 file changed, 20 insertions(+), 40 deletions(-)

diff --git a/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll b/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
index f80d6dac58532a..19928ad4ca4a3c 100644
--- a/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
@@ -1,5 +1,5 @@
 ; 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,+zfh,+zvfh | FileCheck %s --check-prefixes=CHECK,ZVFH
+; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v,+f,+d,+zfh,+zvfh,+zvfbfmin | FileCheck %s --check-prefixes=CHECK,ZVFH
 ; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v,+f,+d,+zfh,+zvfhmin,+zvfbfmin | FileCheck %s --check-prefixes=CHECK,ZVFHMIN
 
 define void @fabs() {
@@ -48,45 +48,25 @@ define void @fabs() {
 }
 
 define void @fabs_f16() {
-; ZVFH-LABEL: 'fabs_f16'
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call half @llvm.fabs.f16(half undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %2 = call <2 x bfloat> @llvm.fabs.v2bf16(<2 x bfloat> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %3 = call <4 x bfloat> @llvm.fabs.v4bf16(<4 x bfloat> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %4 = call <8 x bfloat> @llvm.fabs.v8bf16(<8 x bfloat> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %5 = call <16 x bfloat> @llvm.fabs.v16bf16(<16 x bfloat> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %9 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
-; ZVFH-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 2 x bfloat> @llvm.fabs.nxv2bf16(<vscale x 2 x bfloat> undef)
-; ZVFH-NEXT:  Cost Model: Invalid cost for instruction: %11 = call <vscale x 4 x bfloat> @llvm.fabs.nxv4bf16(<vscale x 4 x bfloat> undef)
-; ZVFH-NEXT:  Cost Model: Invalid cost for instruction: %12 = call <vscale x 8 x bfloat> @llvm.fabs.nxv8bf16(<vscale x 8 x bfloat> undef)
-; ZVFH-NEXT:  Cost Model: Invalid cost for instruction: %13 = call <vscale x 16 x bfloat> @llvm.fabs.nxv16bf16(<vscale x 16 x bfloat> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %16 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %17 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
-; ZVFH-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
-;
-; ZVFHMIN-LABEL: 'fabs_f16'
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call half @llvm.fabs.f16(half undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x bfloat> @llvm.fabs.v2bf16(<2 x bfloat> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x bfloat> @llvm.fabs.v4bf16(<4 x bfloat> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x bfloat> @llvm.fabs.v8bf16(<8 x bfloat> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x bfloat> @llvm.fabs.v16bf16(<16 x bfloat> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %9 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 2 x bfloat> @llvm.fabs.nxv2bf16(<vscale x 2 x bfloat> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call <vscale x 4 x bfloat> @llvm.fabs.nxv4bf16(<vscale x 4 x bfloat> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <vscale x 8 x bfloat> @llvm.fabs.nxv8bf16(<vscale x 8 x bfloat> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %13 = call <vscale x 16 x bfloat> @llvm.fabs.nxv16bf16(<vscale x 16 x bfloat> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %16 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %17 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
-; ZVFHMIN-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-LABEL: 'fabs_f16'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call half @llvm.fabs.f16(half undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = call <2 x bfloat> @llvm.fabs.v2bf16(<2 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x bfloat> @llvm.fabs.v4bf16(<4 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x bfloat> @llvm.fabs.v8bf16(<8 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x bfloat> @llvm.fabs.v16bf16(<16 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <2 x half> @llvm.fabs.v2f16(<2 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %9 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 2 x bfloat> @llvm.fabs.nxv2bf16(<vscale x 2 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call <vscale x 4 x bfloat> @llvm.fabs.nxv4bf16(<vscale x 4 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <vscale x 8 x bfloat> @llvm.fabs.nxv8bf16(<vscale x 8 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %13 = call <vscale x 16 x bfloat> @llvm.fabs.nxv16bf16(<vscale x 16 x bfloat> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %16 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %17 = call <vscale x 16 x half> @llvm.fabs.nxv16f16(<vscale x 16 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call half @llvm.fabs.f16(half undef)
   call <2 x bfloat> @llvm.fabs.v2f16(<2 x bfloat> undef)



More information about the llvm-commits mailing list