efa99eccfc
…d loops Add a count of the number of partitions LoopDist made when distributing a loop in meta data, then check for loops which are already distributed to prevent reprocessing. We see this happen on some spec apps, LD is on by default at SiFive.
131 lines
6.5 KiB
LLVM
131 lines
6.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: opt -aa-pipeline=basic-aa -passes=loop-distribute -enable-loop-distribute -verify-loop-info -verify-dom-info -debug-only=loop-distribute --disable-output -S < %s 2>&1 | FileCheck %s
|
|
; REQUIRES: asserts
|
|
|
|
; Test if a loop already distributed will not reprocess because of metadata
|
|
; information marking it as processed.
|
|
|
|
; CHECK: LDist: Distributed loop guarded for reprocessing
|
|
; CHECK: LDist: Skipping;
|
|
|
|
define dso_local void @_Z13distribution3PiS_S_S_i(ptr noundef captures(none) %a, ptr noundef readonly captures(none) %b, ptr noundef captures(none) %c, ptr noundef writeonly captures(none) %d, i64 noundef signext %len) {
|
|
entry:
|
|
%cmp = icmp sgt i64 %len, 0
|
|
br i1 %cmp, label %end, label %for.body.lver.check
|
|
|
|
for.body.lver.check: ; preds = %entry
|
|
%0 = shl i64 %len, 2
|
|
%scevgep = getelementptr i8, ptr %a, i64 %0
|
|
%scevgep1 = getelementptr i8, ptr %c, i64 -4
|
|
%scevgep2 = getelementptr i8, ptr %c, i64 %0
|
|
%scevgep3 = getelementptr i8, ptr %d, i64 %0
|
|
%scevgep4 = getelementptr i8, ptr %b, i64 %0
|
|
%bound0 = icmp ult ptr %a, %scevgep2
|
|
%bound1 = icmp ult ptr %scevgep1, %scevgep
|
|
%found.conflict = and i1 %bound0, %bound1
|
|
%bound05 = icmp ult ptr %a, %scevgep3
|
|
%bound16 = icmp ult ptr %d, %scevgep
|
|
%found.conflict7 = and i1 %bound05, %bound16
|
|
%conflict.rdx = or i1 %found.conflict, %found.conflict7
|
|
%bound08 = icmp ult ptr %a, %scevgep4
|
|
%bound19 = icmp ult ptr %b, %scevgep
|
|
%found.conflict10 = and i1 %bound08, %bound19
|
|
%conflict.rdx11 = or i1 %conflict.rdx, %found.conflict10
|
|
%bound012 = icmp ult ptr %scevgep1, %scevgep3
|
|
%bound113 = icmp ult ptr %d, %scevgep2
|
|
%found.conflict14 = and i1 %bound012, %bound113
|
|
%conflict.rdx15 = or i1 %conflict.rdx11, %found.conflict14
|
|
%bound016 = icmp ult ptr %d, %scevgep4
|
|
%bound117 = icmp ult ptr %b, %scevgep3
|
|
%found.conflict18 = and i1 %bound016, %bound117
|
|
%conflict.rdx19 = or i1 %conflict.rdx15, %found.conflict18
|
|
br i1 %conflict.rdx19, label %for.body.ph.lver.orig, label %for.body.ph.ldist1
|
|
|
|
for.body.ph.lver.orig: ; preds = %for.body.lver.check
|
|
br label %for.body.lver.orig
|
|
|
|
for.body.lver.orig: ; preds = %for.body.lver.orig, %for.body.ph.lver.orig
|
|
%indvars.iv.lver.orig = phi i64 [ 0, %for.body.ph.lver.orig ], [ %indvars.iv.next.lver.orig, %for.body.lver.orig ]
|
|
%arrayidx.lver.orig = getelementptr inbounds i32, ptr %b, i64 %indvars.iv.lver.orig
|
|
%i2.lver.orig = load i32, ptr %arrayidx.lver.orig, align 4, !tbaa !0
|
|
%add4.lver.orig = add nsw i32 %i2.lver.orig, 1
|
|
%arrayidx8.lver.orig = getelementptr inbounds i32, ptr %a, i64 %indvars.iv.lver.orig
|
|
store i32 %add4.lver.orig, ptr %arrayidx8.lver.orig, align 4, !tbaa !0
|
|
%i3.lver.orig = getelementptr i32, ptr %c, i64 %indvars.iv.lver.orig
|
|
%arrayidx17.lver.orig = getelementptr i8, ptr %i3.lver.orig, i64 -4
|
|
%i4.lver.orig = load i32, ptr %arrayidx17.lver.orig, align 4, !tbaa !0
|
|
%sub18.lver.orig = sub nsw i32 %add4.lver.orig, %i4.lver.orig
|
|
store i32 %sub18.lver.orig, ptr %i3.lver.orig, align 4, !tbaa !0
|
|
%i5.lver.orig = load i32, ptr %arrayidx8.lver.orig, align 4, !tbaa !0
|
|
%add27.lver.orig = add nsw i32 %i5.lver.orig, 2
|
|
%arrayidx31.lver.orig = getelementptr inbounds i32, ptr %d, i64 %indvars.iv.lver.orig
|
|
store i32 %add27.lver.orig, ptr %arrayidx31.lver.orig, align 4, !tbaa !0
|
|
%indvars.iv.next.lver.orig = add i64 %indvars.iv.lver.orig, 1
|
|
%cmp1.not.lver.orig = icmp eq i64 %indvars.iv.next.lver.orig, %len
|
|
br i1 %cmp1.not.lver.orig, label %end.loopexit.loopexit, label %for.body.lver.orig, !llvm.loop !4
|
|
|
|
for.body.ph.ldist1: ; preds = %for.body.lver.check
|
|
br label %for.body.ldist1
|
|
|
|
for.body.ldist1: ; preds = %for.body.ldist1, %for.body.ph.ldist1
|
|
%indvars.iv.ldist1 = phi i64 [ 0, %for.body.ph.ldist1 ], [ %indvars.iv.next.ldist1, %for.body.ldist1 ]
|
|
%arrayidx.ldist1 = getelementptr inbounds i32, ptr %b, i64 %indvars.iv.ldist1
|
|
%i2.ldist1 = load i32, ptr %arrayidx.ldist1, align 4, !tbaa !0, !alias.scope !7
|
|
%add4.ldist1 = add nsw i32 %i2.ldist1, 1
|
|
%arrayidx8.ldist1 = getelementptr inbounds i32, ptr %a, i64 %indvars.iv.ldist1
|
|
store i32 %add4.ldist1, ptr %arrayidx8.ldist1, align 4, !tbaa !0, !alias.scope !10, !noalias !12
|
|
%i3.ldist1 = getelementptr i32, ptr %c, i64 %indvars.iv.ldist1
|
|
%arrayidx17.ldist1 = getelementptr i8, ptr %i3.ldist1, i64 -4
|
|
%i4.ldist1 = load i32, ptr %arrayidx17.ldist1, align 4, !tbaa !0, !alias.scope !15, !noalias !16
|
|
%sub18.ldist1 = sub nsw i32 %add4.ldist1, %i4.ldist1
|
|
store i32 %sub18.ldist1, ptr %i3.ldist1, align 4, !tbaa !0, !alias.scope !15, !noalias !16
|
|
%indvars.iv.next.ldist1 = add i64 %indvars.iv.ldist1, 1
|
|
%cmp1.not.ldist1 = icmp eq i64 %indvars.iv.next.ldist1, %len
|
|
br i1 %cmp1.not.ldist1, label %for.body.ph, label %for.body.ldist1, !llvm.loop !17
|
|
|
|
for.body.ph: ; preds = %for.body.ldist1
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %for.body.ph
|
|
%indvars.iv = phi i64 [ 0, %for.body.ph ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx8 = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
|
|
%i5 = load i32, ptr %arrayidx8, align 4, !tbaa !0, !alias.scope !10, !noalias !12
|
|
%add27 = add nsw i32 %i5, 2
|
|
%arrayidx31 = getelementptr inbounds i32, ptr %d, i64 %indvars.iv
|
|
store i32 %add27, ptr %arrayidx31, align 4, !tbaa !0, !alias.scope !16, !noalias !7
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%cmp1.not = icmp eq i64 %indvars.iv.next, %len
|
|
br i1 %cmp1.not, label %end.loopexit.loopexit20, label %for.body, !llvm.loop !17
|
|
|
|
end.loopexit.loopexit: ; preds = %for.body.lver.orig
|
|
br label %end.loopexit
|
|
|
|
end.loopexit.loopexit20: ; preds = %for.body
|
|
br label %end.loopexit
|
|
|
|
end.loopexit: ; preds = %end.loopexit.loopexit20, %end.loopexit.loopexit
|
|
br label %end
|
|
|
|
end: ; preds = %end.loopexit, %entry
|
|
ret void
|
|
}
|
|
|
|
!0 = !{!1, !1, i64 0}
|
|
!1 = !{!"int", !2, i64 0}
|
|
!2 = !{!"omnipotent char", !3, i64 0}
|
|
!3 = !{!"Simple C++ TBAA"}
|
|
!4 = distinct !{!4, !5, !6}
|
|
!5 = !{!"llvm.loop.mustprogress"}
|
|
!6 = !{!"llvm.loop.isdistributed", i32 1}
|
|
!7 = !{!8}
|
|
!8 = distinct !{!8, !9}
|
|
!9 = distinct !{!9, !"LVerDomain"}
|
|
!10 = !{!11}
|
|
!11 = distinct !{!11, !9}
|
|
!12 = !{!13, !14, !8}
|
|
!13 = distinct !{!13, !9}
|
|
!14 = distinct !{!14, !9}
|
|
!15 = !{!13}
|
|
!16 = !{!14}
|
|
!17 = distinct !{!17, !5}
|