neon_div.ll
1.48 KB
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
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
; RUN: llc -mtriple arm-eabi -mattr=+neon -disable-post-ra -pre-RA-sched source %s -o - | FileCheck %s
; RUN: llc -mtriple thumbv7-windows-itanium -mattr=+neon -disable-post-ra -pre-RA-sched source %s -o - | FileCheck %s
define <8 x i8> @sdivi8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
%tmp1 = load <8 x i8>, <8 x i8>* %A
%tmp2 = load <8 x i8>, <8 x i8>* %B
%tmp3 = sdiv <8 x i8> %tmp1, %tmp2
ret <8 x i8> %tmp3
}
; CHECK-LABEL: sdivi8:
; CHECK: vrecpe.f32
; CHECK: vmovn.i32
; CHECK: vrecpe.f32
; CHECK: vmovn.i32
; CHECK: vmovn.i16
define <8 x i8> @udivi8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
%tmp1 = load <8 x i8>, <8 x i8>* %A
%tmp2 = load <8 x i8>, <8 x i8>* %B
%tmp3 = udiv <8 x i8> %tmp1, %tmp2
ret <8 x i8> %tmp3
}
; CHECK-LABEL: udivi8:
; CHECK: vrecpe.f32
; CHECK: vrecps.f32
; CHECK: vmovn.i32
; CHECK: vrecpe.f32
; CHECK: vrecps.f32
; CHECK: vmovn.i32
; CHECK: vqmovun.s16
define <4 x i16> @sdivi16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
%tmp1 = load <4 x i16>, <4 x i16>* %A
%tmp2 = load <4 x i16>, <4 x i16>* %B
%tmp3 = sdiv <4 x i16> %tmp1, %tmp2
ret <4 x i16> %tmp3
}
; CHECK-LABEL: sdivi16:
; CHECK: vrecpe.f32
; CHECK: vrecps.f32
; CHECK: vmovn.i32
define <4 x i16> @udivi16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
%tmp1 = load <4 x i16>, <4 x i16>* %A
%tmp2 = load <4 x i16>, <4 x i16>* %B
%tmp3 = udiv <4 x i16> %tmp1, %tmp2
ret <4 x i16> %tmp3
}
; CHECK-LABEL: udivi16:
; CHECK: vrecpe.f32
; CHECK: vrecps.f32
; CHECK: vrecps.f32
; CHECK: vmovn.i32