mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-02-01 05:01:59 +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
38 lines
1.9 KiB
LLVM
38 lines
1.9 KiB
LLVM
; RUN: opt < %s -S -unroll-partial-threshold=20 -unroll-threshold=20 -loop-unroll -unroll-allow-partial -unroll-runtime -unroll-allow-remainder -unroll-max-percent-threshold-boost=100 | FileCheck %s
|
|
; RUN: opt < %s -S -passes='require<opt-remark-emit>,unroll' -unroll-partial-threshold=20 -unroll-threshold=20 -unroll-allow-partial -unroll-runtime -unroll-allow-remainder -unroll-max-percent-threshold-boost=100 | FileCheck %s
|
|
;
|
|
; Also check that the simple unroller doesn't allow the partial unrolling.
|
|
; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll-full)' -unroll-partial-threshold=20 -unroll-threshold=20 -unroll-allow-partial -unroll-runtime -unroll-allow-remainder -unroll-max-percent-threshold-boost=100 | FileCheck %s --check-prefix=CHECK-NO-UNROLL
|
|
|
|
; The Loop TripCount is 9. However unroll factors 3 or 9 exceed given threshold.
|
|
; The test checks that we choose a smaller, power-of-two, unroll count and do not give up on unrolling.
|
|
|
|
; CHECK: for.body:
|
|
; CHECK: store
|
|
; CHECK: for.body.1:
|
|
; CHECK: store
|
|
|
|
; CHECK-NO-UNROLL: for.body:
|
|
; CHECK-NO-UNROLL: store
|
|
; CHECK-NO-UNROLL-NOT: store
|
|
|
|
define void @foo(i32* nocapture %a, i32* nocapture readonly %b) nounwind uwtable {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 1, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
|
|
%ld = load i32, i32* %arrayidx, align 4
|
|
%idxprom1 = sext i32 %ld to i64
|
|
%arrayidx2 = getelementptr inbounds i32, i32* %a, i64 %idxprom1
|
|
%st = trunc i64 %indvars.iv to i32
|
|
store i32 %st, i32* %arrayidx2, align 4
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp eq i64 %indvars.iv.next, 20
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|