mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-30 02:32:08 +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
121 lines
4.2 KiB
LLVM
121 lines
4.2 KiB
LLVM
; RUN: opt < %s -S -loop-unroll -unroll-runtime=true | FileCheck %s
|
|
|
|
; Tests for unrolling loops with run-time trip counts
|
|
|
|
; CHECK: %xtraiter = and i32 %n
|
|
; CHECK: %lcmp.mod = icmp ne i32 %xtraiter, 0
|
|
; CHECK: %lcmp.overflow = icmp eq i32 %n, 0
|
|
; CHECK: %lcmp.or = or i1 %lcmp.overflow, %lcmp.mod
|
|
; CHECK: br i1 %lcmp.or, label %for.body.prol, label %for.body.preheader.split
|
|
|
|
; CHECK: for.body.prol:
|
|
; CHECK: %indvars.iv.prol = phi i64 [ %indvars.iv.next.prol, %for.body.prol ], [ 0, %for.body.preheader ]
|
|
; CHECK: %prol.iter.sub = sub i32 %prol.iter, 1
|
|
; CHECK: %prol.iter.cmp = icmp ne i32 %prol.iter.sub, 0
|
|
; CHECK: br i1 %prol.iter.cmp, label %for.body.prol, label %for.body.preheader.split, !llvm.loop !0
|
|
|
|
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
|
|
}
|
|
|
|
|
|
; Still try to completely unroll loops with compile-time trip counts
|
|
; even if the -unroll-runtime is specified
|
|
|
|
; CHECK: for.body:
|
|
; CHECK-NOT: for.body.prol:
|
|
|
|
define i32 @test1(i32* nocapture %a) nounwind uwtable readonly {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%sum.01 = phi i32 [ 0, %entry ], [ %add, %for.body ]
|
|
%arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
|
|
%0 = load i32* %arrayidx, align 4
|
|
%add = add nsw i32 %0, %sum.01
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 5
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret i32 %add
|
|
}
|
|
|
|
; This is test 2007-05-09-UnknownTripCount.ll which can be unrolled now
|
|
; if the -unroll-runtime option is turned on
|
|
|
|
; CHECK: bb72.2:
|
|
|
|
define void @foo(i32 %trips) {
|
|
entry:
|
|
br label %cond_true.outer
|
|
|
|
cond_true.outer:
|
|
%indvar1.ph = phi i32 [ 0, %entry ], [ %indvar.next2, %bb72 ]
|
|
br label %bb72
|
|
|
|
bb72:
|
|
%indvar.next2 = add i32 %indvar1.ph, 1
|
|
%exitcond3 = icmp eq i32 %indvar.next2, %trips
|
|
br i1 %exitcond3, label %cond_true138, label %cond_true.outer
|
|
|
|
cond_true138:
|
|
ret void
|
|
}
|
|
|
|
|
|
; Test run-time unrolling for a loop that counts down by -2.
|
|
|
|
; CHECK: for.body.prol:
|
|
; CHECK: br i1 %prol.iter.cmp, label %for.body.prol, label %for.body.preheader.split
|
|
|
|
define zeroext i16 @down(i16* nocapture %p, i32 %len) nounwind uwtable readonly {
|
|
entry:
|
|
%cmp2 = icmp eq i32 %len, 0
|
|
br i1 %cmp2, label %for.end, label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%p.addr.05 = phi i16* [ %incdec.ptr, %for.body ], [ %p, %entry ]
|
|
%len.addr.04 = phi i32 [ %sub, %for.body ], [ %len, %entry ]
|
|
%res.03 = phi i32 [ %add, %for.body ], [ 0, %entry ]
|
|
%incdec.ptr = getelementptr inbounds i16* %p.addr.05, i64 1
|
|
%0 = load i16* %p.addr.05, align 2
|
|
%conv = zext i16 %0 to i32
|
|
%add = add i32 %conv, %res.03
|
|
%sub = add nsw i32 %len.addr.04, -2
|
|
%cmp = icmp eq i32 %sub, 0
|
|
br i1 %cmp, label %for.cond.for.end_crit_edge, label %for.body
|
|
|
|
for.cond.for.end_crit_edge: ; preds = %for.body
|
|
%phitmp = trunc i32 %add to i16
|
|
br label %for.end
|
|
|
|
for.end: ; preds = %for.cond.for.end_crit_edge, %entry
|
|
%res.0.lcssa = phi i16 [ %phitmp, %for.cond.for.end_crit_edge ], [ 0, %entry ]
|
|
ret i16 %res.0.lcssa
|
|
}
|
|
|
|
; CHECK: !0 = metadata !{metadata !0, metadata !1}
|
|
; CHECK: !1 = metadata !{metadata !"llvm.loop.unroll.disable"}
|
|
|