mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-15 04:30:12 +00:00
dbaeb6e7cb
Runtime unrolling will create a prologue to execute the extra
iterations which is can't divided by the unroll factor. It
generates an if-then-else sequence to jump into a factor -1
times unrolled loop body, like
extraiters = tripcount % loopfactor
if (extraiters == 0) jump Loop:
if (extraiters == loopfactor) jump L1
if (extraiters == loopfactor-1) jump L2
...
L1: LoopBody;
L2: LoopBody;
...
if tripcount < loopfactor jump End
Loop:
...
End:
It means if the unroll factor is 4, the loop body will be 7
times unrolled, 3 are in loop prologue, and 4 are in the loop.
This commit is to use a loop to execute the extra iterations
in prologue, like
extraiters = tripcount % loopfactor
if (extraiters == 0) jump Loop:
else jump Prol
Prol: LoopBody;
extraiters -= 1 // Omitted if unroll factor is 2.
if (extraiters != 0) jump Prol: // Omitted if unroll factor is 2.
if (tripcount < loopfactor) jump End
Loop:
...
End:
Then when unroll factor is 4, the loop body will be copied by
only 5 times, 1 in the prologue loop, 4 in the original loop.
And if the unroll factor is 2, new loop won't be created, just
as the original solution.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218604 91177308-0d34-0410-b5e6-96231b3b80d8
31 lines
1.2 KiB
LLVM
31 lines
1.2 KiB
LLVM
; RUN: opt < %s -S -loop-unroll -unroll-runtime -unroll-count=2 | FileCheck %s
|
|
|
|
; This tests that setting the unroll count works
|
|
|
|
; CHECK: for.body.prol:
|
|
; CHECK: br label %for.body.preheader.split
|
|
; CHECK: for.body:
|
|
; CHECK: br i1 %exitcond.1, label %for.end.loopexit.unr-lcssa, label %for.body
|
|
; CHECK-NOT: br i1 %exitcond.4, label %for.end.loopexit{{.*}}, label %for.body
|
|
|
|
define i32 @test(i32* nocapture %a, i32 %n) nounwind uwtable readonly {
|
|
entry:
|
|
%cmp1 = icmp eq i32 %n, 0
|
|
br i1 %cmp1, label %for.end, label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
|
|
%sum.02 = phi i32 [ %add, %for.body ], [ 0, %entry ]
|
|
%arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
|
|
%0 = load i32* %arrayidx, align 4
|
|
%add = add nsw i32 %0, %sum.02
|
|
%indvars.iv.next = add 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
|
|
%sum.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
|
|
ret i32 %sum.0.lcssa
|
|
}
|