blob: b551fc0f6ab6dee74efff7010ed2df2aee629564 (
plain)
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
|
; RUN: llvm-as < %s | llc -march=arm -mattr=+neon > %t
; RUN: grep {vpadd\\.i8} %t | count 1
; RUN: grep {vpadd\\.i16} %t | count 1
; RUN: grep {vpadd\\.i32} %t | count 1
; RUN: grep {vpadd\\.f32} %t | count 1
define <8 x i8> @vpaddi8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
%tmp1 = load <8 x i8>* %A
%tmp2 = load <8 x i8>* %B
%tmp3 = call <8 x i8> @llvm.arm.neon.vpadd.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
ret <8 x i8> %tmp3
}
define <4 x i16> @vpaddi16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
%tmp1 = load <4 x i16>* %A
%tmp2 = load <4 x i16>* %B
%tmp3 = call <4 x i16> @llvm.arm.neon.vpadd.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
ret <4 x i16> %tmp3
}
define <2 x i32> @vpaddi32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
%tmp1 = load <2 x i32>* %A
%tmp2 = load <2 x i32>* %B
%tmp3 = call <2 x i32> @llvm.arm.neon.vpadd.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
ret <2 x i32> %tmp3
}
define <2 x float> @vpaddf32(<2 x float>* %A, <2 x float>* %B) nounwind {
%tmp1 = load <2 x float>* %A
%tmp2 = load <2 x float>* %B
%tmp3 = call <2 x float> @llvm.arm.neon.vpadd.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
ret <2 x float> %tmp3
}
declare <8 x i8> @llvm.arm.neon.vpadd.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
declare <4 x i16> @llvm.arm.neon.vpadd.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
declare <2 x i32> @llvm.arm.neon.vpadd.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
declare <2 x float> @llvm.arm.neon.vpadd.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
