mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 04:02:41 +01:00
4f0b3bb42b
Patch by Brendon Cahoon! This extends the existing LoopUnroll and LoopUnrollPass. Brendon measured no regressions in the llvm test suite with -unroll-runtime enabled. This implementation works by using the existing loop unrolling code to unroll the loop by a power-of-two (default 8). It generates an if-then-else sequence of code prior to the loop to execute the extra iterations before entering the unrolled loop. llvm-svn: 146245
32 lines
1.3 KiB
LLVM
32 lines
1.3 KiB
LLVM
; RUN: opt < %s -S -loop-unroll -unroll-threshold=50 -unroll-runtime -unroll-count=8 | FileCheck %s
|
|
|
|
; Choose a smaller, power-of-two, unroll count if the loop is too large.
|
|
; This test makes sure we're not unrolling 'odd' counts
|
|
|
|
; CHECK: unr.cmp:
|
|
; CHECK: for.body.unr:
|
|
; CHECK: for.body:
|
|
; CHECK: br i1 %exitcond.3, label %for.end.loopexit{{.*}}, 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
|
|
}
|