maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[LV] Mark first-order recurrences as allowed exits 

First-order recurrences require special treatment when they are live-out;
such treatment is provided by fixFirstOrderRecurrence(), so they should be
included in AllowedExit set.

(Should probably have been included originally in D16197.)

Fixes PR45526: AllowedExit set is used by prepareToFoldTailByMasking() to
check whether the treatment for live-outs also holds when folding the tail,
which is not (yet) the case for first-order recurrences.

Differential Revision: https://reviews.llvm.org/D78210
This commit is contained in:
Ayal Zaks 2020-04-15 17:04:01 +03:00
parent 7fde990694
commit 8e0c5f7200
2 changed files with 34 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
View File

@ -668,6 +668,7 @@ bool LoopVectorizationLegality::canVectorizeInstrs() {
if (RecurrenceDescriptor::isFirstOrderRecurrence(Phi, TheLoop,
SinkAfter, DT)) {
AllowedExit.insert(Phi);
FirstOrderRecurrences.insert(Phi);
continue;
}

33
llvm/test/Transforms/LoopVectorize/optsize.ll
View File

@ -121,6 +121,39 @@ for.body29:
br i1 %cmp26, label %for.body29, label %for.cond.cleanup28
}
; PR45526: don't vectorize with fold-tail if first-order-recurrence is live-out.
;
define i32 @pr45526() optsize {
;
; CHECK-LABEL: @pr45526
; CHECK-NEXT: entry:
; CHECK-NEXT: br label %loop
; CHECK-EMPTY:
; CHECK-NEXT: loop:
; CHECK-NEXT: %piv = phi i32 [ 0, %entry ], [ %pivPlus1, %loop ]
; CHECK-NEXT: %for = phi i32 [ 5, %entry ], [ %pivPlus1, %loop ]
; CHECK-NEXT: %pivPlus1 = add nuw nsw i32 %piv, 1
; CHECK-NEXT: %cond = icmp ult i32 %piv, 510
; CHECK-NEXT: br i1 %cond, label %loop, label %exit
; CHECK-EMPTY:
; CHECK-NEXT: exit:
; CHECK-NEXT: %for.lcssa = phi i32 [ %for, %loop ]
; CHECK-NEXT: ret i32 %for.lcssa
;
entry:
br label %loop
loop:
%piv = phi i32 [ 0, %entry ], [ %pivPlus1, %loop ]
%for = phi i32 [ 5, %entry ], [ %pivPlus1, %loop ]
%pivPlus1 = add nuw nsw i32 %piv, 1
%cond = icmp ult i32 %piv, 510
br i1 %cond, label %loop, label %exit
exit:
ret i32 %for
}
!llvm.module.flags = !{!0}
!0 = !{i32 1, !"ProfileSummary", !1}
!1 = !{!2, !3, !4, !5, !6, !7, !8, !9}