Skip to content

[RISCV][CostModel] Change select cost to 2 #75154

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 3 commits into from
Closed

[RISCV][CostModel] Change select cost to 2 #75154

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
aae3eef
[RISCV] Precommit test for changing select cost to 2
ShivaChen Dec 12, 2023
a2ca69b
[RISCV][CostModel] Change select cost to 2
ShivaChen Dec 12, 2023
7fe134c
Increase cost to 2 only when without Zicond
ShivaChen Dec 13, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1401,6 +1401,12 @@ InstructionCost RISCVTTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind,
I);

// Select might be expanded to move and branch without Zicond.
if (TLI->InstructionOpcodeToISD(Opcode) == ISD::SELECT &&
!ValTy->isVectorTy() && !ST->hasStdExtZicond() &&
!ST->hasVendorXVentanaCondOps())
return 2;

if (isa<FixedVectorType>(ValTy) && !ST->useRVVForFixedLengthVectors())
return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind,
I);
Expand Down
55 changes: 55 additions & 0 deletions llvm/test/Transforms/LoopVectorize/RISCV/slp-select-cost-2.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,55 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=slp-vectorizer -mtriple=riscv64 -mattr=+v -S | FileCheck %s

@s1 = dso_local local_unnamed_addr global [4 x double] zeroinitializer, align 32
@s2 = dso_local local_unnamed_addr global [4 x double] zeroinitializer, align 32
@s3 = dso_local local_unnamed_addr global [64 x double] zeroinitializer, align 32

define void @foo() {
; CHECK-LABEL: @foo(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = load <4 x double>, ptr @s1, align 8
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x double>, ptr @s2, align 8
; CHECK-NEXT: [[TMP2:%.*]] = fcmp fast ogt <4 x double> [[TMP0]], [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = select <4 x i1> [[TMP2]], <4 x double> <double -1.000000e+00, double -1.000000e+00, double -1.000000e+00, double -1.000000e+00>, <4 x double> zeroinitializer
; CHECK-NEXT: store <4 x double> [[TMP3]], ptr @s3, align 8
; CHECK-NEXT: [[TMP4:%.*]] = fcmp fast ule <4 x double> [[TMP0]], [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = select <4 x i1> [[TMP4]], <4 x double> <double -1.000000e+00, double -1.000000e+00, double -1.000000e+00, double -1.000000e+00>, <4 x double> zeroinitializer
; CHECK-NEXT: store <4 x double> [[TMP5]], ptr getelementptr inbounds ([64 x double], ptr @s3, i64 0, i64 4), align 8
; CHECK-NEXT: ret void
;
entry:
%0 = load double, ptr @s1, align 8
%1 = load double, ptr @s2, align 8
%cmp3 = fcmp fast ogt double %0, %1
%cond = select fast i1 %cmp3, double -1.000000e+00, double 0.000000e+00
store double %cond, ptr @s3, align 8
%2 = load double, ptr getelementptr inbounds ([4 x double], ptr @s1, i64 0, i64 1), align 8
%3 = load double, ptr getelementptr inbounds ([4 x double], ptr @s2, i64 0, i64 1), align 8
%cmp3.1 = fcmp fast ogt double %2, %3
%cond.1 = select fast i1 %cmp3.1, double -1.000000e+00, double 0.000000e+00
store double %cond.1, ptr getelementptr inbounds ([64 x double], ptr @s3, i64 0, i64 1), align 8
%4 = load double, ptr getelementptr inbounds ([4 x double], ptr @s1, i64 0, i64 2), align 8
%5 = load double, ptr getelementptr inbounds ([4 x double], ptr @s2, i64 0, i64 2), align 8
%cmp3.2 = fcmp fast ogt double %4, %5
%cond.2 = select fast i1 %cmp3.2, double -1.000000e+00, double 0.000000e+00
store double %cond.2, ptr getelementptr inbounds ([64 x double], ptr @s3, i64 0, i64 2), align 8
%6 = load double, ptr getelementptr inbounds ([4 x double], ptr @s1, i64 0, i64 3), align 8
%7 = load double, ptr getelementptr inbounds ([4 x double], ptr @s2, i64 0, i64 3), align 8
%cmp3.3 = fcmp fast ogt double %6, %7
%cond.3 = select fast i1 %cmp3.3, double -1.000000e+00, double 0.000000e+00
store double %cond.3, ptr getelementptr inbounds ([64 x double], ptr @s3, i64 0, i64 3), align 8
%cmp15 = fcmp fast ule double %0, %1
%cond16 = select fast i1 %cmp15, double -1.000000e+00, double 0.000000e+00
store double %cond16, ptr getelementptr inbounds ([64 x double], ptr @s3, i64 0, i64 4), align 8
%cmp15.1 = fcmp fast ule double %2, %3
%cond16.1 = select fast i1 %cmp15.1, double -1.000000e+00, double 0.000000e+00
store double %cond16.1, ptr getelementptr inbounds ([64 x double], ptr @s3, i64 0, i64 5), align 8
%cmp15.2 = fcmp fast ule double %4, %5
%cond16.2 = select fast i1 %cmp15.2, double -1.000000e+00, double 0.000000e+00
store double %cond16.2, ptr getelementptr inbounds ([64 x double], ptr @s3, i64 0, i64 6), align 8
%cmp15.3 = fcmp fast ule double %6, %7
%cond16.3 = select fast i1 %cmp15.3, double -1.000000e+00, double 0.000000e+00
store double %cond16.3, ptr getelementptr inbounds ([64 x double], ptr @s3, i64 0, i64 7), align 8
ret void
}