llvm/test/Transforms/LoopUnroll/runtime-loop3.ll
Teresa Johnson 99dd11f7e8 [PM] Split LoopUnrollPass and make partial unroller a function pass
Summary:
This is largely NFC*, in preparation for utilizing ProfileSummaryInfo
and BranchFrequencyInfo analyses. In this patch I am only doing the
splitting for the New PM, but I can do the same for the legacy PM as
a follow-on if this looks good.

*Not NFC since for partial unrolling we lose the updates done to the
loop traversal (adding new sibling and child loops) - according to
Chandler this is not very useful for partial unrolling, but it also
means that the debugging flag -unroll-revisit-child-loops no longer
works for partial unrolling.

Reviewers: chandlerc

Subscribers: mehdi_amini, mzolotukhin, eraman, llvm-commits

Differential Revision: https://reviews.llvm.org/D36157

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@309886 91177308-0d34-0410-b5e6-96231b3b80d8
2017-08-02 20:35:29 +00:00

47 lines
2.3 KiB
LLVM

; REQUIRES: asserts
; RUN: opt < %s -disable-output -stats -loop-unroll -unroll-runtime -unroll-partial-threshold=200 -unroll-threshold=400 -info-output-file - | FileCheck %s --check-prefix=STATS
; RUN: opt < %s -disable-output -stats -passes='require<opt-remark-emit>,unroll' -unroll-runtime -unroll-partial-threshold=200 -unroll-threshold=400 -info-output-file - | FileCheck %s --check-prefix=STATS
; Test that nested loops can be unrolled. We need to increase threshold to do it
; STATS: 2 loop-unroll - Number of loops unrolled (completely or otherwise)
define i32 @nested(i32* nocapture %a, i32 %n, i32 %m) nounwind uwtable readonly {
entry:
%cmp11 = icmp sgt i32 %n, 0
br i1 %cmp11, label %for.cond1.preheader.lr.ph, label %for.end7
for.cond1.preheader.lr.ph: ; preds = %entry
%cmp28 = icmp sgt i32 %m, 0
br label %for.cond1.preheader
for.cond1.preheader: ; preds = %for.inc5, %for.cond1.preheader.lr.ph
%indvars.iv16 = phi i64 [ 0, %for.cond1.preheader.lr.ph ], [ %indvars.iv.next17, %for.inc5 ]
%sum.012 = phi i32 [ 0, %for.cond1.preheader.lr.ph ], [ %sum.1.lcssa, %for.inc5 ]
br i1 %cmp28, label %for.body3, label %for.inc5
for.body3: ; preds = %for.cond1.preheader, %for.body3
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body3 ], [ 0, %for.cond1.preheader ]
%sum.19 = phi i32 [ %add4, %for.body3 ], [ %sum.012, %for.cond1.preheader ]
%0 = add nsw i64 %indvars.iv, %indvars.iv16
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %0
%1 = load i32, i32* %arrayidx, align 4
%add4 = add nsw i32 %1, %sum.19
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %m
br i1 %exitcond, label %for.inc5, label %for.body3
for.inc5: ; preds = %for.body3, %for.cond1.preheader
%sum.1.lcssa = phi i32 [ %sum.012, %for.cond1.preheader ], [ %add4, %for.body3 ]
%indvars.iv.next17 = add i64 %indvars.iv16, 1
%lftr.wideiv18 = trunc i64 %indvars.iv.next17 to i32
%exitcond19 = icmp eq i32 %lftr.wideiv18, %n
br i1 %exitcond19, label %for.end7, label %for.cond1.preheader
for.end7: ; preds = %for.inc5, %entry
%sum.0.lcssa = phi i32 [ 0, %entry ], [ %sum.1.lcssa, %for.inc5 ]
ret i32 %sum.0.lcssa
}