719b26ba54
Before r268509, Clang would disable the loop unroll pass when optimizing for size. That commit enabled it to be able to support unroll pragmas in -Os builds. However, this regressed binary size in one of Chromium's DLLs with ~100 KB. This restores the original behaviour of no unrolling at -Os, but doing it in LLVM instead of Clang makes more sense, and also allows the pragmas to keep working. Differential revision: http://reviews.llvm.org/D20115 llvm-svn: 269124
35 lines
1.4 KiB
LLVM
35 lines
1.4 KiB
LLVM
; RUN: opt < %s -S -mtriple=powerpc64-unknown-linux-gnu -mcpu=a2 -loop-unroll | FileCheck %s -check-prefix=EPILOG
|
|
; RUN: opt < %s -S -mtriple=powerpc64-unknown-linux-gnu -mcpu=a2 -loop-unroll -unroll-runtime-epilog=false | FileCheck %s -check-prefix=PROLOG
|
|
|
|
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
|
|
}
|
|
|
|
; EPILOG-LABEL: @test
|
|
; EPILOG: for.body:
|
|
; EPILOG: br i1 %niter.ncmp.7, label %for.end.loopexit{{.*}}, label %for.body
|
|
; EPILOG: for.body.epil{{.*}}:
|
|
|
|
; PROLOG-LABEL: @test
|
|
; PROLOG: for.body.prol{{.*}}:
|
|
; PROLOG: for.body:
|
|
; PROLOG: br i1 %exitcond.7, label %for.end.loopexit{{.*}}, label %for.body
|
|
|