6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-07-25 13:24:46 +00:00
Code Issues Projects Releases Wiki Activity

LoopVectorizer: Add support for floating point reductions

Browse Source 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@171812 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Nadav Rotem
2013-01-07 23:13:00 +00:00
parent 59d152197d
commit 111e5fe7e0
2 changed files with 120 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
test/Transforms/LoopVectorize/float-reduction.ll Normal file
View File

@@ -0,0 +1,29 @@
; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.8.0"
;CHECK: @foo
;CHECK: fadd <4 x float>
;CHECK: ret
define float @foo(float* nocapture %A, i32* nocapture %n) nounwind uwtable readonly ssp {
entry:
br label %for.body
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%sum.04 = phi float [ 0.000000e+00, %entry ], [ %add, %for.body ]
%arrayidx = getelementptr inbounds float* %A, i64 %indvars.iv
%0 = load float* %arrayidx, align 4, !tbaa !0
%add = fadd fast float %sum.04, %0
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, 200
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret float %add
}
!0 = metadata !{metadata !"float", metadata !1}
!1 = metadata !{metadata !"omnipotent char", metadata !2}
!2 = metadata !{metadata !"Simple C/C++ TBAA"}