mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-08-31 12:30:06 +00:00
For inner one of nested loops, it is more likely to be a hot loop, and the runtime check can be promoted out from patch 0001, so the overhead is less, we can try a doubled threshold to unroll more loops. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@231632 91177308-0d34-0410-b5e6-96231b3b80d8
34 lines
1.2 KiB
LLVM
34 lines
1.2 KiB
LLVM
; RUN: opt < %s -S -loop-unroll -mtriple aarch64 -mcpu=cortex-a57 | 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: br i1 %lcmp.mod, label %for.body.prol, label %for.body.preheader.split
|
|
|
|
; CHECK: for.body.prol:
|
|
; CHECK: 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, i32* %a, i64 %indvars.iv
|
|
%0 = load i32, 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
|
|
}
|
|
|
|
|