forked from OSchip/llvm-project
40 lines
1.5 KiB
LLVM
40 lines
1.5 KiB
LLVM
|
; 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.vpaddi.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.vpaddi.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.vpaddi.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.vpaddf.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
||
|
|
ret <2 x float> %tmp3
|
||
|
|
}
|
||
|
|
|
||
|
|
declare <8 x i8> @llvm.arm.neon.vpaddi.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
|
||
|
|
declare <4 x i16> @llvm.arm.neon.vpaddi.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
|
||
|
|
declare <2 x i32> @llvm.arm.neon.vpaddi.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
|
||
|
|
|
||
|
|
declare <2 x float> @llvm.arm.neon.vpaddf.v2f32(<2 x float>, <2 x float>) nounwind readnone
|