forked from OSchip/llvm-project
70 lines
2.5 KiB
LLVM
70 lines
2.5 KiB
LLVM
; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
|
|
|
|
define <8 x i16> @vmlals8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
|
|
;CHECK: vmlals8:
|
|
;CHECK: vmlal.s8
|
|
%tmp1 = load <8 x i16>* %A
|
|
%tmp2 = load <8 x i8>* %B
|
|
%tmp3 = load <8 x i8>* %C
|
|
%tmp4 = call <8 x i16> @llvm.arm.neon.vmlals.v8i16(<8 x i16> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3)
|
|
ret <8 x i16> %tmp4
|
|
}
|
|
|
|
define <4 x i32> @vmlals16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
|
|
;CHECK: vmlals16:
|
|
;CHECK: vmlal.s16
|
|
%tmp1 = load <4 x i32>* %A
|
|
%tmp2 = load <4 x i16>* %B
|
|
%tmp3 = load <4 x i16>* %C
|
|
%tmp4 = call <4 x i32> @llvm.arm.neon.vmlals.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3)
|
|
ret <4 x i32> %tmp4
|
|
}
|
|
|
|
define <2 x i64> @vmlals32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
|
|
;CHECK: vmlals32:
|
|
;CHECK: vmlal.s32
|
|
%tmp1 = load <2 x i64>* %A
|
|
%tmp2 = load <2 x i32>* %B
|
|
%tmp3 = load <2 x i32>* %C
|
|
%tmp4 = call <2 x i64> @llvm.arm.neon.vmlals.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3)
|
|
ret <2 x i64> %tmp4
|
|
}
|
|
|
|
define <8 x i16> @vmlalu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
|
|
;CHECK: vmlalu8:
|
|
;CHECK: vmlal.u8
|
|
%tmp1 = load <8 x i16>* %A
|
|
%tmp2 = load <8 x i8>* %B
|
|
%tmp3 = load <8 x i8>* %C
|
|
%tmp4 = call <8 x i16> @llvm.arm.neon.vmlalu.v8i16(<8 x i16> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3)
|
|
ret <8 x i16> %tmp4
|
|
}
|
|
|
|
define <4 x i32> @vmlalu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
|
|
;CHECK: vmlalu16:
|
|
;CHECK: vmlal.u16
|
|
%tmp1 = load <4 x i32>* %A
|
|
%tmp2 = load <4 x i16>* %B
|
|
%tmp3 = load <4 x i16>* %C
|
|
%tmp4 = call <4 x i32> @llvm.arm.neon.vmlalu.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3)
|
|
ret <4 x i32> %tmp4
|
|
}
|
|
|
|
define <2 x i64> @vmlalu32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
|
|
;CHECK: vmlalu32:
|
|
;CHECK: vmlal.u32
|
|
%tmp1 = load <2 x i64>* %A
|
|
%tmp2 = load <2 x i32>* %B
|
|
%tmp3 = load <2 x i32>* %C
|
|
%tmp4 = call <2 x i64> @llvm.arm.neon.vmlalu.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3)
|
|
ret <2 x i64> %tmp4
|
|
}
|
|
|
|
declare <8 x i16> @llvm.arm.neon.vmlals.v8i16(<8 x i16>, <8 x i8>, <8 x i8>) nounwind readnone
|
|
declare <4 x i32> @llvm.arm.neon.vmlals.v4i32(<4 x i32>, <4 x i16>, <4 x i16>) nounwind readnone
|
|
declare <2 x i64> @llvm.arm.neon.vmlals.v2i64(<2 x i64>, <2 x i32>, <2 x i32>) nounwind readnone
|
|
|
|
declare <8 x i16> @llvm.arm.neon.vmlalu.v8i16(<8 x i16>, <8 x i8>, <8 x i8>) nounwind readnone
|
|
declare <4 x i32> @llvm.arm.neon.vmlalu.v4i32(<4 x i32>, <4 x i16>, <4 x i16>) nounwind readnone
|
|
declare <2 x i64> @llvm.arm.neon.vmlalu.v2i64(<2 x i64>, <2 x i32>, <2 x i32>) nounwind readnone
|