[llvm] [RISCV] Handle zvfhmin and zvfbfmin promotion to f32 in half arith costs (PR #108361)
Luke Lau via llvm-commits
llvm-commits at lists.llvm.org
Tue Sep 24 01:31:35 PDT 2024
https://github.com/lukel97 updated https://github.com/llvm/llvm-project/pull/108361
>From 8e883a4ac72aedc81ca6cb0af123f63c3a25b528 Mon Sep 17 00:00:00 2001
From: Luke Lau <luke at igalia.com>
Date: Thu, 12 Sep 2024 18:46:02 +0800
Subject: [PATCH 1/3] [RISCV] Handle zvfhmin/zvfbfmin promotion to f32 in half
arith costs
Arithmetic half or bfloat ops on zvfhmin and zvfbfmin respectively will be promoted and carried out in f32, so this updates getArithmeticInstrCost to check for this.
---
.../Target/RISCV/RISCVTargetTransformInfo.cpp | 11 +-
.../test/Analysis/CostModel/RISCV/arith-fp.ll | 208 ++++++++++++------
2 files changed, 144 insertions(+), 75 deletions(-)
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 768df71715fa63..b527c35c7eb9e0 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -1908,6 +1908,13 @@ InstructionCost RISCVTTIImpl::getArithmeticInstrCost(
return BaseT::getArithmeticInstrCost(Opcode, Ty, CostKind, Op1Info, Op2Info,
Args, CxtI);
+ // On zvfhmin, f16 vectors may be promoted to f32.
+ // FIXME: nxv32f16 will be custom lowered and split.
+ unsigned ISDOpcode = TLI->InstructionOpcodeToISD(Opcode);
+ if (TLI->getOperationAction(ISDOpcode, LT.second) ==
+ TargetLoweringBase::LegalizeAction::Promote)
+ LT.second = TLI->getTypeToPromoteTo(ISDOpcode, LT.second);
+
auto getConstantMatCost =
[&](unsigned Operand, TTI::OperandValueInfo OpInfo) -> InstructionCost {
if (OpInfo.isUniform() && TLI->canSplatOperand(Opcode, Operand))
@@ -1929,7 +1936,7 @@ InstructionCost RISCVTTIImpl::getArithmeticInstrCost(
ConstantMatCost += getConstantMatCost(1, Op2Info);
unsigned Op;
- switch (TLI->InstructionOpcodeToISD(Opcode)) {
+ switch (ISDOpcode) {
case ISD::ADD:
case ISD::SUB:
Op = RISCV::VADD_VV;
@@ -1959,11 +1966,9 @@ InstructionCost RISCVTTIImpl::getArithmeticInstrCost(
break;
case ISD::FADD:
case ISD::FSUB:
- // TODO: Address FP16 with VFHMIN
Op = RISCV::VFADD_VV;
break;
case ISD::FMUL:
- // TODO: Address FP16 with VFHMIN
Op = RISCV::VFMUL_VV;
break;
case ISD::FDIV:
diff --git a/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll b/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
index b96fdb0109829b..ead69e9b9dc710 100644
--- a/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
@@ -16,9 +16,9 @@ define void @fadd() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16BF16 = fadd <16 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1BF16 = fadd <vscale x 1 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2BF16 = fadd <vscale x 2 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4BF16 = fadd <vscale x 4 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8BF16 = fadd <vscale x 8 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16BF16 = fadd <vscale x 16 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4BF16 = fadd <vscale x 4 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8BF16 = fadd <vscale x 8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16BF16 = fadd <vscale x 16 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = fadd <1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fadd <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fadd <4 x float> undef, undef
@@ -81,21 +81,37 @@ define void @fadd() {
}
define void @fadd_f16() {
-; CHECK-LABEL: 'fadd_f16'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fadd half undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16 = fadd <1 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fadd <2 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fadd <4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fadd <8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fadd <16 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32F16 = fadd <32 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16 = fadd <vscale x 1 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16 = fadd <vscale x 2 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4F16 = fadd <vscale x 4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16 = fadd <vscale x 8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16 = fadd <vscale x 16 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fadd <vscale x 32 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; ZVFH-LABEL: 'fadd_f16'
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fadd half undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16 = fadd <1 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fadd <2 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fadd <4 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fadd <8 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fadd <16 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32F16 = fadd <32 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16 = fadd <vscale x 1 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16 = fadd <vscale x 2 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4F16 = fadd <vscale x 4 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16 = fadd <vscale x 8 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16 = fadd <vscale x 16 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fadd <vscale x 32 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; ZVFHMIN-LABEL: 'fadd_f16'
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fadd half undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16 = fadd <1 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fadd <2 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fadd <4 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F16 = fadd <8 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F16 = fadd <16 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32F16 = fadd <32 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16 = fadd <vscale x 1 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16 = fadd <vscale x 2 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4F16 = fadd <vscale x 4 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8F16 = fadd <vscale x 8 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16F16 = fadd <vscale x 16 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fadd <vscale x 32 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%F16 = fadd half undef, undef
@@ -128,9 +144,9 @@ define void @fsub() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16BF16 = fsub <16 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1BF16 = fsub <vscale x 1 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2BF16 = fsub <vscale x 2 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4BF16 = fsub <vscale x 4 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8BF16 = fsub <vscale x 8 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16BF16 = fsub <vscale x 16 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4BF16 = fsub <vscale x 4 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8BF16 = fsub <vscale x 8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16BF16 = fsub <vscale x 16 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = fsub <1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fsub <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fsub <4 x float> undef, undef
@@ -193,21 +209,37 @@ define void @fsub() {
}
define void @fsub_f16() {
-; CHECK-LABEL: 'fsub_f16'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fsub half undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16 = fsub <1 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fsub <2 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fsub <4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fsub <8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fsub <16 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32F16 = fsub <32 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16 = fsub <vscale x 1 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16 = fsub <vscale x 2 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4F16 = fsub <vscale x 4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16 = fsub <vscale x 8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16 = fsub <vscale x 16 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fsub <vscale x 32 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; ZVFH-LABEL: 'fsub_f16'
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fsub half undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16 = fsub <1 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fsub <2 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fsub <4 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fsub <8 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fsub <16 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32F16 = fsub <32 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16 = fsub <vscale x 1 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16 = fsub <vscale x 2 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4F16 = fsub <vscale x 4 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16 = fsub <vscale x 8 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16 = fsub <vscale x 16 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fsub <vscale x 32 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; ZVFHMIN-LABEL: 'fsub_f16'
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fsub half undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16 = fsub <1 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fsub <2 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fsub <4 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F16 = fsub <8 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F16 = fsub <16 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32F16 = fsub <32 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16 = fsub <vscale x 1 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16 = fsub <vscale x 2 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4F16 = fsub <vscale x 4 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8F16 = fsub <vscale x 8 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16F16 = fsub <vscale x 16 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fsub <vscale x 32 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%F16 = fsub half undef, undef
@@ -240,9 +272,9 @@ define void @fmul() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16BF16 = fmul <16 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1BF16 = fmul <vscale x 1 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2BF16 = fmul <vscale x 2 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4BF16 = fmul <vscale x 4 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8BF16 = fmul <vscale x 8 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16BF16 = fmul <vscale x 16 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4BF16 = fmul <vscale x 4 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8BF16 = fmul <vscale x 8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16BF16 = fmul <vscale x 16 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = fmul <1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fmul <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fmul <4 x float> undef, undef
@@ -305,21 +337,37 @@ define void @fmul() {
}
define void @fmul_f16() {
-; CHECK-LABEL: 'fmul_f16'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fmul half undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16 = fmul <1 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fmul <2 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fmul <4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fmul <8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fmul <16 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32F16 = fmul <32 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16 = fmul <vscale x 1 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16 = fmul <vscale x 2 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4F16 = fmul <vscale x 4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16 = fmul <vscale x 8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16 = fmul <vscale x 16 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fmul <vscale x 32 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; ZVFH-LABEL: 'fmul_f16'
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fmul half undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16 = fmul <1 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fmul <2 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fmul <4 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fmul <8 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fmul <16 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32F16 = fmul <32 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16 = fmul <vscale x 1 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16 = fmul <vscale x 2 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4F16 = fmul <vscale x 4 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16 = fmul <vscale x 8 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16 = fmul <vscale x 16 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fmul <vscale x 32 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; ZVFHMIN-LABEL: 'fmul_f16'
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fmul half undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16 = fmul <1 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fmul <2 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fmul <4 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F16 = fmul <8 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F16 = fmul <16 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32F16 = fmul <32 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16 = fmul <vscale x 1 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16 = fmul <vscale x 2 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4F16 = fmul <vscale x 4 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8F16 = fmul <vscale x 8 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16F16 = fmul <vscale x 16 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fmul <vscale x 32 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%F16 = fmul half undef, undef
@@ -352,9 +400,9 @@ define void @fdiv() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16BF16 = fdiv <16 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1BF16 = fdiv <vscale x 1 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2BF16 = fdiv <vscale x 2 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4BF16 = fdiv <vscale x 4 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8BF16 = fdiv <vscale x 8 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16BF16 = fdiv <vscale x 16 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4BF16 = fdiv <vscale x 4 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8BF16 = fdiv <vscale x 8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16BF16 = fdiv <vscale x 16 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = fdiv <1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fdiv <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fdiv <4 x float> undef, undef
@@ -417,21 +465,37 @@ define void @fdiv() {
}
define void @fdiv_f16() {
-; CHECK-LABEL: 'fdiv_f16'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fdiv half undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16 = fdiv <1 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fdiv <2 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fdiv <4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fdiv <8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fdiv <16 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32F16 = fdiv <32 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16 = fdiv <vscale x 1 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16 = fdiv <vscale x 2 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4F16 = fdiv <vscale x 4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16 = fdiv <vscale x 8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16 = fdiv <vscale x 16 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fdiv <vscale x 32 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+; ZVFH-LABEL: 'fdiv_f16'
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fdiv half undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16 = fdiv <1 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fdiv <2 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fdiv <4 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fdiv <8 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fdiv <16 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V32F16 = fdiv <32 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16 = fdiv <vscale x 1 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16 = fdiv <vscale x 2 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4F16 = fdiv <vscale x 4 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8F16 = fdiv <vscale x 8 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16F16 = fdiv <vscale x 16 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fdiv <vscale x 32 x half> undef, undef
+; ZVFH-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; ZVFHMIN-LABEL: 'fdiv_f16'
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fdiv half undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16 = fdiv <1 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fdiv <2 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fdiv <4 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F16 = fdiv <8 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F16 = fdiv <16 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32F16 = fdiv <32 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16 = fdiv <vscale x 1 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16 = fdiv <vscale x 2 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4F16 = fdiv <vscale x 4 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8F16 = fdiv <vscale x 8 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16F16 = fdiv <vscale x 16 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fdiv <vscale x 32 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%F16 = fdiv half undef, undef
>From 05f889e29bb1cf86df8c342a3913f01eb4d49a93 Mon Sep 17 00:00:00 2001
From: Luke Lau <luke at igalia.com>
Date: Mon, 23 Sep 2024 23:32:03 +0800
Subject: [PATCH 2/3] Update comment
---
llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index b527c35c7eb9e0..33d36af4832f45 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -1908,8 +1908,8 @@ InstructionCost RISCVTTIImpl::getArithmeticInstrCost(
return BaseT::getArithmeticInstrCost(Opcode, Ty, CostKind, Op1Info, Op2Info,
Args, CxtI);
- // On zvfhmin, f16 vectors may be promoted to f32.
- // FIXME: nxv32f16 will be custom lowered and split.
+ // f16 with zvfhmin and bf16 will be promoted to f32.
+ // FIXME: nxv32[b]f16 will be custom lowered and split.
unsigned ISDOpcode = TLI->InstructionOpcodeToISD(Opcode);
if (TLI->getOperationAction(ISDOpcode, LT.second) ==
TargetLoweringBase::LegalizeAction::Promote)
>From 909dd47e3107f4885bb27b3533b3152302f251fa Mon Sep 17 00:00:00 2001
From: Luke Lau <luke at igalia.com>
Date: Tue, 24 Sep 2024 16:31:03 +0800
Subject: [PATCH 3/3] Add cost of extending and truncating
---
.../Target/RISCV/RISCVTargetTransformInfo.cpp | 30 +++-
.../test/Analysis/CostModel/RISCV/arith-fp.ll | 128 +++++++++---------
2 files changed, 87 insertions(+), 71 deletions(-)
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 33d36af4832f45..3bef01da0a4454 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -1911,9 +1911,25 @@ InstructionCost RISCVTTIImpl::getArithmeticInstrCost(
// f16 with zvfhmin and bf16 will be promoted to f32.
// FIXME: nxv32[b]f16 will be custom lowered and split.
unsigned ISDOpcode = TLI->InstructionOpcodeToISD(Opcode);
- if (TLI->getOperationAction(ISDOpcode, LT.second) ==
- TargetLoweringBase::LegalizeAction::Promote)
- LT.second = TLI->getTypeToPromoteTo(ISDOpcode, LT.second);
+ InstructionCost CastCost = 0;
+ if ((LT.second.getVectorElementType() == MVT::f16 ||
+ LT.second.getVectorElementType() == MVT::bf16) &&
+ TLI->getOperationAction(ISDOpcode, LT.second) ==
+ TargetLoweringBase::LegalizeAction::Promote) {
+ MVT PromotedVT = TLI->getTypeToPromoteTo(ISDOpcode, LT.second);
+ Type *PromotedTy = EVT(PromotedVT).getTypeForEVT(Ty->getContext());
+ Type *LegalTy = EVT(LT.second).getTypeForEVT(Ty->getContext());
+ // Add cost of extending arguments
+ CastCost += LT.first * Args.size() *
+ getCastInstrCost(Instruction::FPExt, PromotedTy, LegalTy,
+ TTI::CastContextHint::None, CostKind);
+ // Add cost of truncating result
+ CastCost +=
+ LT.first * getCastInstrCost(Instruction::FPTrunc, LegalTy, PromotedTy,
+ TTI::CastContextHint::None, CostKind);
+ // Compute cost of op in promoted type
+ LT.second = PromotedVT;
+ }
auto getConstantMatCost =
[&](unsigned Operand, TTI::OperandValueInfo OpInfo) -> InstructionCost {
@@ -1980,9 +1996,9 @@ InstructionCost RISCVTTIImpl::getArithmeticInstrCost(
default:
// Assuming all other instructions have the same cost until a need arises to
// differentiate them.
- return ConstantMatCost + BaseT::getArithmeticInstrCost(Opcode, Ty, CostKind,
- Op1Info, Op2Info,
- Args, CxtI);
+ return CastCost + ConstantMatCost +
+ BaseT::getArithmeticInstrCost(Opcode, Ty, CostKind, Op1Info, Op2Info,
+ Args, CxtI);
}
InstructionCost InstrCost = getRISCVInstructionCost(Op, LT.second, CostKind);
@@ -1991,7 +2007,7 @@ InstructionCost RISCVTTIImpl::getArithmeticInstrCost(
// scalar floating point ops aren't cheaper than their vector equivalents.
if (Ty->isFPOrFPVectorTy())
InstrCost *= 2;
- return ConstantMatCost + LT.first * InstrCost;
+ return CastCost + ConstantMatCost + LT.first * InstrCost;
}
// TODO: Deduplicate from TargetTransformInfoImplCRTPBase.
diff --git a/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll b/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
index ead69e9b9dc710..b3e66ccc705f8f 100644
--- a/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
@@ -14,11 +14,11 @@ define void @fadd() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4BF16 = fadd <4 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8BF16 = fadd <8 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16BF16 = fadd <16 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1BF16 = fadd <vscale x 1 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2BF16 = fadd <vscale x 2 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4BF16 = fadd <vscale x 4 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8BF16 = fadd <vscale x 8 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16BF16 = fadd <vscale x 16 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV1BF16 = fadd <vscale x 1 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV2BF16 = fadd <vscale x 2 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %NXV4BF16 = fadd <vscale x 4 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8BF16 = fadd <vscale x 8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16BF16 = fadd <vscale x 16 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = fadd <1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fadd <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fadd <4 x float> undef, undef
@@ -99,17 +99,17 @@ define void @fadd_f16() {
;
; ZVFHMIN-LABEL: 'fadd_f16'
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fadd half undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16 = fadd <1 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fadd <2 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fadd <4 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F16 = fadd <8 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F16 = fadd <16 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32F16 = fadd <32 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16 = fadd <vscale x 1 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16 = fadd <vscale x 2 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4F16 = fadd <vscale x 4 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8F16 = fadd <vscale x 8 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16F16 = fadd <vscale x 16 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V1F16 = fadd <1 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2F16 = fadd <2 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4F16 = fadd <4 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8F16 = fadd <8 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16F16 = fadd <16 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V32F16 = fadd <32 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV1F16 = fadd <vscale x 1 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV2F16 = fadd <vscale x 2 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %NXV4F16 = fadd <vscale x 4 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8F16 = fadd <vscale x 8 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16F16 = fadd <vscale x 16 x half> undef, undef
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fadd <vscale x 32 x half> undef, undef
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
@@ -142,11 +142,11 @@ define void @fsub() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4BF16 = fsub <4 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8BF16 = fsub <8 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16BF16 = fsub <16 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1BF16 = fsub <vscale x 1 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2BF16 = fsub <vscale x 2 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4BF16 = fsub <vscale x 4 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8BF16 = fsub <vscale x 8 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16BF16 = fsub <vscale x 16 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV1BF16 = fsub <vscale x 1 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV2BF16 = fsub <vscale x 2 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %NXV4BF16 = fsub <vscale x 4 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8BF16 = fsub <vscale x 8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16BF16 = fsub <vscale x 16 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = fsub <1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fsub <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fsub <4 x float> undef, undef
@@ -227,17 +227,17 @@ define void @fsub_f16() {
;
; ZVFHMIN-LABEL: 'fsub_f16'
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fsub half undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16 = fsub <1 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fsub <2 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fsub <4 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F16 = fsub <8 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F16 = fsub <16 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32F16 = fsub <32 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16 = fsub <vscale x 1 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16 = fsub <vscale x 2 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4F16 = fsub <vscale x 4 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8F16 = fsub <vscale x 8 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16F16 = fsub <vscale x 16 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V1F16 = fsub <1 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2F16 = fsub <2 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4F16 = fsub <4 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8F16 = fsub <8 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16F16 = fsub <16 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V32F16 = fsub <32 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV1F16 = fsub <vscale x 1 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV2F16 = fsub <vscale x 2 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %NXV4F16 = fsub <vscale x 4 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8F16 = fsub <vscale x 8 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16F16 = fsub <vscale x 16 x half> undef, undef
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fsub <vscale x 32 x half> undef, undef
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
@@ -270,11 +270,11 @@ define void @fmul() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4BF16 = fmul <4 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8BF16 = fmul <8 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16BF16 = fmul <16 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1BF16 = fmul <vscale x 1 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2BF16 = fmul <vscale x 2 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4BF16 = fmul <vscale x 4 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8BF16 = fmul <vscale x 8 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16BF16 = fmul <vscale x 16 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV1BF16 = fmul <vscale x 1 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV2BF16 = fmul <vscale x 2 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %NXV4BF16 = fmul <vscale x 4 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8BF16 = fmul <vscale x 8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16BF16 = fmul <vscale x 16 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = fmul <1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fmul <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fmul <4 x float> undef, undef
@@ -355,17 +355,17 @@ define void @fmul_f16() {
;
; ZVFHMIN-LABEL: 'fmul_f16'
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fmul half undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16 = fmul <1 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fmul <2 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fmul <4 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F16 = fmul <8 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F16 = fmul <16 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32F16 = fmul <32 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16 = fmul <vscale x 1 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16 = fmul <vscale x 2 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4F16 = fmul <vscale x 4 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8F16 = fmul <vscale x 8 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16F16 = fmul <vscale x 16 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V1F16 = fmul <1 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2F16 = fmul <2 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4F16 = fmul <4 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8F16 = fmul <8 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16F16 = fmul <16 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V32F16 = fmul <32 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV1F16 = fmul <vscale x 1 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV2F16 = fmul <vscale x 2 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %NXV4F16 = fmul <vscale x 4 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8F16 = fmul <vscale x 8 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16F16 = fmul <vscale x 16 x half> undef, undef
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fmul <vscale x 32 x half> undef, undef
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
@@ -398,11 +398,11 @@ define void @fdiv() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4BF16 = fdiv <4 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8BF16 = fdiv <8 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16BF16 = fdiv <16 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1BF16 = fdiv <vscale x 1 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2BF16 = fdiv <vscale x 2 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4BF16 = fdiv <vscale x 4 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8BF16 = fdiv <vscale x 8 x bfloat> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16BF16 = fdiv <vscale x 16 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV1BF16 = fdiv <vscale x 1 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV2BF16 = fdiv <vscale x 2 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %NXV4BF16 = fdiv <vscale x 4 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8BF16 = fdiv <vscale x 8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16BF16 = fdiv <vscale x 16 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = fdiv <1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fdiv <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fdiv <4 x float> undef, undef
@@ -483,17 +483,17 @@ define void @fdiv_f16() {
;
; ZVFHMIN-LABEL: 'fdiv_f16'
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fdiv half undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F16 = fdiv <1 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fdiv <2 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fdiv <4 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F16 = fdiv <8 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16F16 = fdiv <16 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V32F16 = fdiv <32 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16 = fdiv <vscale x 1 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16 = fdiv <vscale x 2 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV4F16 = fdiv <vscale x 4 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV8F16 = fdiv <vscale x 8 x half> undef, undef
-; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV16F16 = fdiv <vscale x 16 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V1F16 = fdiv <1 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V2F16 = fdiv <2 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4F16 = fdiv <4 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8F16 = fdiv <8 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16F16 = fdiv <16 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V32F16 = fdiv <32 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV1F16 = fdiv <vscale x 1 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %NXV2F16 = fdiv <vscale x 2 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %NXV4F16 = fdiv <vscale x 4 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %NXV8F16 = fdiv <vscale x 8 x half> undef, undef
+; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %NXV16F16 = fdiv <vscale x 16 x half> undef, undef
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV32F16 = fdiv <vscale x 32 x half> undef, undef
; ZVFHMIN-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
More information about the llvm-commits
mailing list