6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-03-21 18:31:36 +00:00
Code Issues Projects Releases Wiki Activity

LoopUnroll: If we're doing partial unrolling, use the PartialThreshold to limit unrolling.

Browse Source 
Otherwise we use the same threshold as for complete unrolling, which is
way too high. This made us unroll any loop smaller than 150 instructions
by 8 times, but only if someone specified -march=core2 or better,
which happens to be the default on darwin.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207940 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Benjamin Kramer 2014-05-04 19:12:38 +00:00
parent 28a739b4dc
commit 99b03e3401
2 changed files with 53 additions and 3 deletions
lib/Transforms/Scalar
LoopUnrollPass.cpp
test/Transforms/LoopUnroll/X86
partial.ll

9
lib/Transforms/Scalar/LoopUnrollPass.cpp

@ -238,9 +238,12 @@ bool LoopUnroll::runOnLoop(Loop *L, LPPassManager &LPM) {
return false;
}
uint64_t Size = (uint64_t)LoopSize*Count;
if (TripCount != 1 && Size > Threshold) {
DEBUG(dbgs() << " Too large to fully unroll with count: " << Count
<< " because size: " << Size << ">" << Threshold << "\n");
if (TripCount != 1 &&
(Size > Threshold || (Count != TripCount && Size > PartialThreshold))) {
if (Size > Threshold)
DEBUG(dbgs() << " Too large to fully unroll with count: " << Count
<< " because size: " << Size << ">" << Threshold << "\n");
bool AllowPartial = UserAllowPartial ? CurrentAllowPartial : UP.Partial;
if (!AllowPartial && !(Runtime && TripCount == 0)) {
DEBUG(dbgs() << " will not try to unroll partially because "

47
test/Transforms/LoopUnroll/X86/partial.ll

@ -76,5 +76,52 @@ for.end: ; preds = %vector.body
ret void
}
define zeroext i16 @test1(i16* nocapture readonly %arr, i32 %n) #0 {
entry:
%cmp25 = icmp eq i32 %n, 0
br i1 %cmp25, label %for.end, label %for.body
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%reduction.026 = phi i16 [ %add14, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i16* %arr, i64 %indvars.iv
%0 = load i16* %arrayidx, align 2
%add = add i16 %0, %reduction.026
%sext = mul i64 %indvars.iv, 12884901888
%idxprom3 = ashr exact i64 %sext, 32
%arrayidx4 = getelementptr inbounds i16* %arr, i64 %idxprom3
%1 = load i16* %arrayidx4, align 2
%add7 = add i16 %add, %1
%sext28 = mul i64 %indvars.iv, 21474836480
%idxprom10 = ashr exact i64 %sext28, 32
%arrayidx11 = getelementptr inbounds i16* %arr, i64 %idxprom10
%2 = load i16* %arrayidx11, align 2
%add14 = add i16 %add7, %2
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
%reduction.0.lcssa = phi i16 [ 0, %entry ], [ %add14, %for.body ]
ret i16 %reduction.0.lcssa
; This loop is too large to be partially unrolled (size=16)
; CHECK-LABEL: @test1
; CHECK: br
; CHECK: br
; CHECK: br
; CHECK: br
; CHECK-NOT: br
; CHECK-NOUNRL-LABEL: @test1
; CHECK-NOUNRL: br
; CHECK-NOUNRL: br
; CHECK-NOUNRL: br
; CHECK-NOUNRL: br
; CHECK-NOUNRL-NOT: br
}
attributes #0 = { nounwind uwtable }