2013-09-12 05:20:40 +08:00
|
|
|
; RUN: opt < %s -S -mtriple=powerpc64-unknown-linux-gnu -mcpu=a2 -loop-unroll | FileCheck %s
|
|
|
|
define void @unroll_opt_for_size() nounwind optsize {
|
|
|
|
entry:
|
|
|
|
br label %loop
|
|
|
|
|
|
|
|
loop:
|
|
|
|
%iv = phi i32 [ 0, %entry ], [ %inc, %loop ]
|
|
|
|
%inc = add i32 %iv, 1
|
|
|
|
%exitcnd = icmp uge i32 %inc, 1024
|
|
|
|
br i1 %exitcnd, label %exit, label %loop
|
|
|
|
|
|
|
|
exit:
|
|
|
|
ret void
|
|
|
|
}
|
|
|
|
|
|
|
|
; CHECK-LABEL: @unroll_opt_for_size
|
|
|
|
; CHECK: add
|
|
|
|
; CHECK-NEXT: add
|
|
|
|
; CHECK-NEXT: add
|
|
|
|
; CHECK: icmp
|
|
|
|
|
|
|
|
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
|
|
|
|
}
|
|
|
|
|
|
|
|
; CHECK-LABEL: @test
|
Use a loop to simplify the runtime unrolling prologue.
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.
llvm-svn: 218604
2014-09-29 19:15:00 +08:00
|
|
|
; CHECK: for.body.prol{{.*}}:
|
2013-09-12 05:20:40 +08:00
|
|
|
; CHECK: for.body:
|
|
|
|
; CHECK: br i1 %exitcond.7, label %for.end.loopexit{{.*}}, label %for.body
|
|
|
|
|