mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 11:13:28 +01:00
f4af38fa5f
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 llvm-svn: 309886
50 lines
1.8 KiB
LLVM
50 lines
1.8 KiB
LLVM
; RUN: opt < %s -S -loop-unroll -unroll-runtime=true -unroll-count=16 | FileCheck --check-prefix=UNROLL-16 %s
|
|
; RUN: opt < %s -S -loop-unroll -unroll-runtime=true -unroll-count=4 | FileCheck --check-prefix=UNROLL-4 %s
|
|
|
|
; RUN: opt < %s -S -passes='require<opt-remark-emit>,unroll' -unroll-runtime=true -unroll-count=16 | FileCheck --check-prefix=UNROLL-16 %s
|
|
; RUN: opt < %s -S -passes='require<opt-remark-emit>,unroll' -unroll-runtime=true -unroll-count=4 | FileCheck --check-prefix=UNROLL-4 %s
|
|
|
|
; Given that the trip-count of this loop is a 3-bit value, we cannot
|
|
; safely unroll it with a count of anything more than 8.
|
|
|
|
define i3 @test(i3* %a, i3 %n) {
|
|
; UNROLL-16-LABEL: @test(
|
|
; UNROLL-4-LABEL: @test(
|
|
entry:
|
|
%cmp1 = icmp eq i3 %n, 0
|
|
br i1 %cmp1, label %for.end, label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
; UNROLL-16-LABEL: for.body:
|
|
; UNROLL-4-LABEL: for.body:
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
|
|
%sum.02 = phi i3 [ %add, %for.body ], [ 0, %entry ]
|
|
%arrayidx = getelementptr inbounds i3, i3* %a, i64 %indvars.iv
|
|
|
|
; UNROLL-16-LABEL: for.body
|
|
; UNROLL-16-LABEL: getelementptr
|
|
; UNROLL-16-LABEL-NOT: getelementptr
|
|
|
|
; UNROLL-4-LABEL: getelementptr
|
|
; UNROLL-4-LABEL: getelementptr
|
|
; UNROLL-4-LABEL: getelementptr
|
|
; UNROLL-4-LABEL: getelementptr
|
|
|
|
%0 = load i3, i3* %arrayidx
|
|
%add = add nsw i3 %0, %sum.02
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i3
|
|
%exitcond = icmp eq i3 %lftr.wideiv, %n
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
; UNROLL-16-LABEL: for.end
|
|
; UNROLL-4-LABEL: for.end
|
|
|
|
; UNROLL-16-NOT: for.body.epil:
|
|
; UNROLL-4: for.body.epil:
|
|
|
|
for.end: ; preds = %for.body, %entry
|
|
%sum.0.lcssa = phi i3 [ 0, %entry ], [ %add, %for.body ]
|
|
ret i3 %sum.0.lcssa
|
|
}
|