forked from OSchip/llvm-project
[SVE] Fix the FP arithmetic instruction costs for SVE
Several FP instructions (fadd, fsub, etc.) were incorrectly assigned a higher cost for SVE because they have custom lowering, however we know they are legal. This patch explicitly assigns a cost of 2 to these opcodes. Tests added here: Analysis/CostModel/AArch64/arith-fp-sve.ll Differential Revision: https://reviews.llvm.org/D108993
This commit is contained in:
David Sherwood
parent
dfb7518df1
commit
d581d94385
|
|
@ -1393,9 +1393,13 @@ InstructionCost AArch64TTIImpl::getArithmeticInstrCost(
|
|||
return (Cost + 1) * LT.first;
|
||||
|
||||
case ISD::FADD:
|
||||
case ISD::FSUB:
|
||||
case ISD::FMUL:
|
||||
case ISD::FDIV:
|
||||
case ISD::FNEG:
|
||||
// These nodes are marked as 'custom' just to lower them to SVE.
|
||||
// We know said lowering will incur no additional cost.
|
||||
if (isa<FixedVectorType>(Ty) && !Ty->getScalarType()->isFP128Ty())
|
||||
if (!Ty->getScalarType()->isFP128Ty())
|
||||
return (Cost + 2) * LT.first;
|
||||
|
||||
return Cost + BaseT::getArithmeticInstrCost(Opcode, Ty, CostKind, Opd1Info,
|
||||
|
|
|
|||
|
|
@ -0,0 +1,134 @@
|
|||
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
|
||||
; RUN: opt < %s -enable-no-nans-fp-math -cost-model -analyze -mtriple=aarch64 -mattr=+fullfp16 -mattr=+sve | FileCheck %s
|
||||
|
||||
define void @fadd() {
|
||||
; CHECK-LABEL: 'fadd'
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fadd <vscale x 4 x half> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fadd <vscale x 8 x half> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fadd <vscale x 16 x half> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fadd <vscale x 2 x float> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fadd <vscale x 4 x float> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fadd <vscale x 8 x float> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fadd <vscale x 2 x double> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fadd <vscale x 4 x double> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
%V4F16 = fadd <vscale x 4 x half> undef, undef
|
||||
%V8F16 = fadd <vscale x 8 x half> undef, undef
|
||||
%V16F16 = fadd <vscale x 16 x half> undef, undef
|
||||
|
||||
%V2F32 = fadd <vscale x 2 x float> undef, undef
|
||||
%V4F32 = fadd <vscale x 4 x float> undef, undef
|
||||
%V8F32 = fadd <vscale x 8 x float> undef, undef
|
||||
|
||||
%V2F64 = fadd <vscale x 2 x double> undef, undef
|
||||
%V4F64 = fadd <vscale x 4 x double> undef, undef
|
||||
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @fsub() {
|
||||
; CHECK-LABEL: 'fsub'
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fsub <vscale x 4 x half> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fsub <vscale x 8 x half> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fsub <vscale x 16 x half> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fsub <vscale x 2 x float> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fsub <vscale x 4 x float> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fsub <vscale x 8 x float> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fsub <vscale x 2 x double> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fsub <vscale x 4 x double> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
%V4F16 = fsub <vscale x 4 x half> undef, undef
|
||||
%V8F16 = fsub <vscale x 8 x half> undef, undef
|
||||
%V16F16 = fsub <vscale x 16 x half> undef, undef
|
||||
|
||||
%V2F32 = fsub <vscale x 2 x float> undef, undef
|
||||
%V4F32 = fsub <vscale x 4 x float> undef, undef
|
||||
%V8F32 = fsub <vscale x 8 x float> undef, undef
|
||||
|
||||
%V2F64 = fsub <vscale x 2 x double> undef, undef
|
||||
%V4F64 = fsub <vscale x 4 x double> undef, undef
|
||||
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @fneg() {
|
||||
; CHECK-LABEL: 'fneg'
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F16 = fneg <vscale x 2 x half> undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fneg <vscale x 4 x half> undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fneg <vscale x 8 x half> undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fneg <vscale x 16 x half> undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fneg <vscale x 2 x float> undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fneg <vscale x 4 x float> undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fneg <vscale x 8 x float> undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fneg <vscale x 2 x double> undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fneg <vscale x 4 x double> undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
%V2F16 = fneg <vscale x 2 x half> undef
|
||||
%V4F16 = fneg <vscale x 4 x half> undef
|
||||
%V8F16 = fneg <vscale x 8 x half> undef
|
||||
%V16F16 = fneg <vscale x 16 x half> undef
|
||||
|
||||
%V2F32 = fneg <vscale x 2 x float> undef
|
||||
%V4F32 = fneg <vscale x 4 x float> undef
|
||||
%V8F32 = fneg <vscale x 8 x float> undef
|
||||
|
||||
%V2F64 = fneg <vscale x 2 x double> undef
|
||||
%V4F64 = fneg <vscale x 4 x double> undef
|
||||
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @fmul() {
|
||||
; CHECK-LABEL: 'fmul'
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fmul <vscale x 4 x half> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fmul <vscale x 8 x half> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fmul <vscale x 16 x half> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fmul <vscale x 2 x float> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fmul <vscale x 4 x float> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fmul <vscale x 8 x float> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fmul <vscale x 2 x double> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fmul <vscale x 4 x double> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
%V4F16 = fmul <vscale x 4 x half> undef, undef
|
||||
%V8F16 = fmul <vscale x 8 x half> undef, undef
|
||||
%V16F16 = fmul <vscale x 16 x half> undef, undef
|
||||
|
||||
%V2F32 = fmul <vscale x 2 x float> undef, undef
|
||||
%V4F32 = fmul <vscale x 4 x float> undef, undef
|
||||
%V8F32 = fmul <vscale x 8 x float> undef, undef
|
||||
|
||||
%V2F64 = fmul <vscale x 2 x double> undef, undef
|
||||
%V4F64 = fmul <vscale x 4 x double> undef, undef
|
||||
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @fdiv() {
|
||||
; CHECK-LABEL: 'fdiv'
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F16 = fdiv <vscale x 4 x half> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8F16 = fdiv <vscale x 8 x half> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fdiv <vscale x 16 x half> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fdiv <vscale x 2 x float> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fdiv <vscale x 4 x float> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fdiv <vscale x 8 x float> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = fdiv <vscale x 2 x double> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fdiv <vscale x 4 x double> undef, undef
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
%V4F16 = fdiv <vscale x 4 x half> undef, undef
|
||||
%V8F16 = fdiv <vscale x 8 x half> undef, undef
|
||||
%V16F16 = fdiv <vscale x 16 x half> undef, undef
|
||||
|
||||
%V2F32 = fdiv <vscale x 2 x float> undef, undef
|
||||
%V4F32 = fdiv <vscale x 4 x float> undef, undef
|
||||
%V8F32 = fdiv <vscale x 8 x float> undef, undef
|
||||
|
||||
%V2F64 = fdiv <vscale x 2 x double> undef, undef
|
||||
%V4F64 = fdiv <vscale x 4 x double> undef, undef
|
||||
|
||||
ret void
|
||||
}
|
||||
|
|
@ -42,7 +42,7 @@ define void @reductions(<vscale x 4 x i32> %v0, <vscale x 4 x i64> %v1, <vscale
|
|||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %smax_nxv4i32 = call i32 @llvm.vector.reduce.smax.nxv4i32(<vscale x 4 x i32> %v0)
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1)
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %fadd_nxv4f32 = call fast float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v2)
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v3)
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v3)
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %fmin_nxv4f32 = call fast float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> %v2)
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %fmin_nxv4f64 = call fast double @llvm.vector.reduce.fmin.nxv4f64(<vscale x 4 x double> %v3)
|
||||
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %fmax_nxv4f32 = call fast float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float> %v2)
|
||||
|
|
|
|||
|
|
@ -8,7 +8,7 @@ declare <vscale x 2 x double> @llvm.sqrt.v2f64(<vscale x 2 x double>)
|
|||
|
||||
define <vscale x 2 x double> @fadd_v2f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b) {
|
||||
; THRU-LABEL: 'fadd_v2f64'
|
||||
; THRU-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = fadd <vscale x 2 x double> %a, %b
|
||||
; THRU-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = fadd <vscale x 2 x double> %a, %b
|
||||
; THRU-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <vscale x 2 x double> %r
|
||||
;
|
||||
; LATE-LABEL: 'fadd_v2f64'
|
||||
|
|
|
|||
Loading…
Reference in New Issue