1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
|
; RUN: opt < %s -passes=loop-vectorize -mtriple=aarch64-none-linux-gnu -mattr=+neon -S | FileCheck %s
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
; Function Attrs: nounwind
define ptr @array_add(ptr noalias nocapture readonly %a, ptr noalias nocapture readonly %b, ptr %c, i32 %size) {
;CHECK-LABEL: array_add
;CHECK: load <4 x i32>
;CHECK: load <4 x i32>
;CHECK: load <4 x i32>
;CHECK: load <4 x i32>
;CHECK: add nsw <4 x i32>
;CHECK: add nsw <4 x i32>
;CHECK: store <4 x i32>
;CHECK: store <4 x i32>
;CHECK: ret
entry:
%cmp10 = icmp sgt i32 %size, 0
br i1 %cmp10, label %for.body.preheader, label %for.end
for.body.preheader: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.preheader, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
%0 = load i32, ptr %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, ptr %b, i64 %indvars.iv
%1 = load i32, ptr %arrayidx2, align 4
%add = add nsw i32 %1, %0
%arrayidx4 = getelementptr inbounds i32, ptr %c, i64 %indvars.iv
store i32 %add, ptr %arrayidx4, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %size
br i1 %exitcond, label %for.end.loopexit, label %for.body
for.end.loopexit: ; preds = %for.body
br label %for.end
for.end: ; preds = %for.end.loopexit, %entry
ret ptr %c
}
|
