[LV] PreferPredicateOverEpilog respecting option

Follow-up of cb47b8783: don't query TTI->preferPredicateOverEpilogue when
option -prefer-predicate-over-epilog is set to false, i.e. when we prefer not
to predicate the loop.

Differential Revision: https://reviews.llvm.org/D70382
This commit is contained in:
Sjoerd Meijer 2019-11-21 14:03:28 +00:00
parent 8cf8ec40a1
commit 901cd3b3f6
2 changed files with 23 additions and 1 deletions

View File

@ -7429,6 +7429,9 @@ getScalarEpilogueLowering(Function *F, Loop *L, LoopVectorizeHints &Hints,
ScalarEvolution *SE, DominatorTree *DT,
const LoopAccessInfo *LAI) {
ScalarEpilogueLowering SEL = CM_ScalarEpilogueAllowed;
bool PredicateOptDisabled = PreferPredicateOverEpilog.getNumOccurrences() &&
!PreferPredicateOverEpilog;
if (Hints.getForce() != LoopVectorizeHints::FK_Enabled &&
(F->hasOptSize() ||
llvm::shouldOptimizeForSize(L->getHeader(), PSI, BFI)))
@ -7436,7 +7439,8 @@ getScalarEpilogueLowering(Function *F, Loop *L, LoopVectorizeHints &Hints,
else if (PreferPredicateOverEpilog ||
Hints.getPredicate() == LoopVectorizeHints::FK_Enabled ||
(TTI->preferPredicateOverEpilogue(L, LI, *SE, *AC, TLI, DT, LAI) &&
Hints.getPredicate() != LoopVectorizeHints::FK_Disabled))
Hints.getPredicate() != LoopVectorizeHints::FK_Disabled &&
!PredicateOptDisabled))
SEL = CM_ScalarEpilogueNotNeededUsePredicate;
return SEL;

View File

@ -30,6 +30,18 @@
; RUN: -enable-arm-maskedldst=true -S < %s | \
; RUN: FileCheck %s -check-prefixes=CHECK,PREFER-FOLDING
; RUN: opt -mtriple=thumbv8.1m.main-arm-eabihf -mattr=+mve.fp \
; RUN: -prefer-predicate-over-epilog=false \
; RUN: -disable-mve-tail-predication=false -loop-vectorize \
; RUN: -enable-arm-maskedldst=true -S < %s | \
; RUN: FileCheck %s -check-prefixes=CHECK,NO-FOLDING
; RUN: opt -mtriple=thumbv8.1m.main-arm-eabihf -mattr=+mve.fp \
; RUN: -prefer-predicate-over-epilog=true \
; RUN: -disable-mve-tail-predication=false -loop-vectorize \
; RUN: -enable-arm-maskedldst=true -S < %s | \
; RUN: FileCheck %s -check-prefixes=CHECK,FOLDING-OPT
define void @prefer_folding(i32* noalias nocapture %A, i32* noalias nocapture readonly %B, i32* noalias nocapture readonly %C) #0 {
; CHECK-LABEL: prefer_folding(
; PREFER-FOLDING: vector.body:
@ -186,6 +198,12 @@ define void @narrowing_load_not_allowed(i8* noalias nocapture %A, i8* noalias no
; PREFER-FOLDING-NOT: llvm.masked.load
; PREFER-FOLDING-NOT: llvm.masked.store
; PREFER-FOLDING: br i1 %{{.*}}, label %{{.*}}, label %vector.body
; FOLDING-OPT: vector.body:
; FOLDING-OPT call <8 x i16> @llvm.masked.load.v8i16.p0v8i16
; FOLDING-OPT call <8 x i8> @llvm.masked.load.v8i8.p0v8i8
; FOLDING-OPT call void @llvm.masked.store.v8i8.p0v8i8
; FOLDING-OPT: br i1 %{{.*}}, label %{{.*}}, label %vector.body
entry:
br label %for.body