forked from OSchip/llvm-project
64 lines
2.1 KiB
LLVM
64 lines
2.1 KiB
LLVM
; RUN: llvm-as < %s | llc -march=arm -mattr=+neon | FileCheck %s
|
|
|
|
define <8 x i16> @vabdls8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|
;CHECK: vabdls8:
|
|
;CHECK: vabdl.s8
|
|
%tmp1 = load <8 x i8>* %A
|
|
%tmp2 = load <8 x i8>* %B
|
|
%tmp3 = call <8 x i16> @llvm.arm.neon.vabdls.v8i16(<8 x i8> %tmp1, <8 x i8> %tmp2)
|
|
ret <8 x i16> %tmp3
|
|
}
|
|
|
|
define <4 x i32> @vabdls16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
|
|
;CHECK: vabdls16:
|
|
;CHECK: vabdl.s16
|
|
%tmp1 = load <4 x i16>* %A
|
|
%tmp2 = load <4 x i16>* %B
|
|
%tmp3 = call <4 x i32> @llvm.arm.neon.vabdls.v4i32(<4 x i16> %tmp1, <4 x i16> %tmp2)
|
|
ret <4 x i32> %tmp3
|
|
}
|
|
|
|
define <2 x i64> @vabdls32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
|
|
;CHECK: vabdls32:
|
|
;CHECK: vabdl.s32
|
|
%tmp1 = load <2 x i32>* %A
|
|
%tmp2 = load <2 x i32>* %B
|
|
%tmp3 = call <2 x i64> @llvm.arm.neon.vabdls.v2i64(<2 x i32> %tmp1, <2 x i32> %tmp2)
|
|
ret <2 x i64> %tmp3
|
|
}
|
|
|
|
define <8 x i16> @vabdlu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|
;CHECK: vabdlu8:
|
|
;CHECK: vabdl.u8
|
|
%tmp1 = load <8 x i8>* %A
|
|
%tmp2 = load <8 x i8>* %B
|
|
%tmp3 = call <8 x i16> @llvm.arm.neon.vabdlu.v8i16(<8 x i8> %tmp1, <8 x i8> %tmp2)
|
|
ret <8 x i16> %tmp3
|
|
}
|
|
|
|
define <4 x i32> @vabdlu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
|
|
;CHECK: vabdlu16:
|
|
;CHECK: vabdl.u16
|
|
%tmp1 = load <4 x i16>* %A
|
|
%tmp2 = load <4 x i16>* %B
|
|
%tmp3 = call <4 x i32> @llvm.arm.neon.vabdlu.v4i32(<4 x i16> %tmp1, <4 x i16> %tmp2)
|
|
ret <4 x i32> %tmp3
|
|
}
|
|
|
|
define <2 x i64> @vabdlu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
|
|
;CHECK: vabdlu32:
|
|
;CHECK: vabdl.u32
|
|
%tmp1 = load <2 x i32>* %A
|
|
%tmp2 = load <2 x i32>* %B
|
|
%tmp3 = call <2 x i64> @llvm.arm.neon.vabdlu.v2i64(<2 x i32> %tmp1, <2 x i32> %tmp2)
|
|
ret <2 x i64> %tmp3
|
|
}
|
|
|
|
declare <8 x i16> @llvm.arm.neon.vabdls.v8i16(<8 x i8>, <8 x i8>) nounwind readnone
|
|
declare <4 x i32> @llvm.arm.neon.vabdls.v4i32(<4 x i16>, <4 x i16>) nounwind readnone
|
|
declare <2 x i64> @llvm.arm.neon.vabdls.v2i64(<2 x i32>, <2 x i32>) nounwind readnone
|
|
|
|
declare <8 x i16> @llvm.arm.neon.vabdlu.v8i16(<8 x i8>, <8 x i8>) nounwind readnone
|
|
declare <4 x i32> @llvm.arm.neon.vabdlu.v4i32(<4 x i16>, <4 x i16>) nounwind readnone
|
|
declare <2 x i64> @llvm.arm.neon.vabdlu.v2i64(<2 x i32>, <2 x i32>) nounwind readnone
|