mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-09-01 19:29:22 +00:00
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@83667 91177308-0d34-0410-b5e6-96231b3b80d8
133 lines
3.8 KiB
LLVM
133 lines
3.8 KiB
LLVM
; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
|
|
|
|
define <8 x i8> @vcnt8(<8 x i8>* %A) nounwind {
|
|
;CHECK: vcnt8:
|
|
;CHECK: vcnt.8
|
|
%tmp1 = load <8 x i8>* %A
|
|
%tmp2 = call <8 x i8> @llvm.arm.neon.vcnt.v8i8(<8 x i8> %tmp1)
|
|
ret <8 x i8> %tmp2
|
|
}
|
|
|
|
define <16 x i8> @vcntQ8(<16 x i8>* %A) nounwind {
|
|
;CHECK: vcntQ8:
|
|
;CHECK: vcnt.8
|
|
%tmp1 = load <16 x i8>* %A
|
|
%tmp2 = call <16 x i8> @llvm.arm.neon.vcnt.v16i8(<16 x i8> %tmp1)
|
|
ret <16 x i8> %tmp2
|
|
}
|
|
|
|
declare <8 x i8> @llvm.arm.neon.vcnt.v8i8(<8 x i8>) nounwind readnone
|
|
declare <16 x i8> @llvm.arm.neon.vcnt.v16i8(<16 x i8>) nounwind readnone
|
|
|
|
define <8 x i8> @vclz8(<8 x i8>* %A) nounwind {
|
|
;CHECK: vclz8:
|
|
;CHECK: vclz.i8
|
|
%tmp1 = load <8 x i8>* %A
|
|
%tmp2 = call <8 x i8> @llvm.arm.neon.vclz.v8i8(<8 x i8> %tmp1)
|
|
ret <8 x i8> %tmp2
|
|
}
|
|
|
|
define <4 x i16> @vclz16(<4 x i16>* %A) nounwind {
|
|
;CHECK: vclz16:
|
|
;CHECK: vclz.i16
|
|
%tmp1 = load <4 x i16>* %A
|
|
%tmp2 = call <4 x i16> @llvm.arm.neon.vclz.v4i16(<4 x i16> %tmp1)
|
|
ret <4 x i16> %tmp2
|
|
}
|
|
|
|
define <2 x i32> @vclz32(<2 x i32>* %A) nounwind {
|
|
;CHECK: vclz32:
|
|
;CHECK: vclz.i32
|
|
%tmp1 = load <2 x i32>* %A
|
|
%tmp2 = call <2 x i32> @llvm.arm.neon.vclz.v2i32(<2 x i32> %tmp1)
|
|
ret <2 x i32> %tmp2
|
|
}
|
|
|
|
define <16 x i8> @vclzQ8(<16 x i8>* %A) nounwind {
|
|
;CHECK: vclzQ8:
|
|
;CHECK: vclz.i8
|
|
%tmp1 = load <16 x i8>* %A
|
|
%tmp2 = call <16 x i8> @llvm.arm.neon.vclz.v16i8(<16 x i8> %tmp1)
|
|
ret <16 x i8> %tmp2
|
|
}
|
|
|
|
define <8 x i16> @vclzQ16(<8 x i16>* %A) nounwind {
|
|
;CHECK: vclzQ16:
|
|
;CHECK: vclz.i16
|
|
%tmp1 = load <8 x i16>* %A
|
|
%tmp2 = call <8 x i16> @llvm.arm.neon.vclz.v8i16(<8 x i16> %tmp1)
|
|
ret <8 x i16> %tmp2
|
|
}
|
|
|
|
define <4 x i32> @vclzQ32(<4 x i32>* %A) nounwind {
|
|
;CHECK: vclzQ32:
|
|
;CHECK: vclz.i32
|
|
%tmp1 = load <4 x i32>* %A
|
|
%tmp2 = call <4 x i32> @llvm.arm.neon.vclz.v4i32(<4 x i32> %tmp1)
|
|
ret <4 x i32> %tmp2
|
|
}
|
|
|
|
declare <8 x i8> @llvm.arm.neon.vclz.v8i8(<8 x i8>) nounwind readnone
|
|
declare <4 x i16> @llvm.arm.neon.vclz.v4i16(<4 x i16>) nounwind readnone
|
|
declare <2 x i32> @llvm.arm.neon.vclz.v2i32(<2 x i32>) nounwind readnone
|
|
|
|
declare <16 x i8> @llvm.arm.neon.vclz.v16i8(<16 x i8>) nounwind readnone
|
|
declare <8 x i16> @llvm.arm.neon.vclz.v8i16(<8 x i16>) nounwind readnone
|
|
declare <4 x i32> @llvm.arm.neon.vclz.v4i32(<4 x i32>) nounwind readnone
|
|
|
|
define <8 x i8> @vclss8(<8 x i8>* %A) nounwind {
|
|
;CHECK: vclss8:
|
|
;CHECK: vcls.s8
|
|
%tmp1 = load <8 x i8>* %A
|
|
%tmp2 = call <8 x i8> @llvm.arm.neon.vcls.v8i8(<8 x i8> %tmp1)
|
|
ret <8 x i8> %tmp2
|
|
}
|
|
|
|
define <4 x i16> @vclss16(<4 x i16>* %A) nounwind {
|
|
;CHECK: vclss16:
|
|
;CHECK: vcls.s16
|
|
%tmp1 = load <4 x i16>* %A
|
|
%tmp2 = call <4 x i16> @llvm.arm.neon.vcls.v4i16(<4 x i16> %tmp1)
|
|
ret <4 x i16> %tmp2
|
|
}
|
|
|
|
define <2 x i32> @vclss32(<2 x i32>* %A) nounwind {
|
|
;CHECK: vclss32:
|
|
;CHECK: vcls.s32
|
|
%tmp1 = load <2 x i32>* %A
|
|
%tmp2 = call <2 x i32> @llvm.arm.neon.vcls.v2i32(<2 x i32> %tmp1)
|
|
ret <2 x i32> %tmp2
|
|
}
|
|
|
|
define <16 x i8> @vclsQs8(<16 x i8>* %A) nounwind {
|
|
;CHECK: vclsQs8:
|
|
;CHECK: vcls.s8
|
|
%tmp1 = load <16 x i8>* %A
|
|
%tmp2 = call <16 x i8> @llvm.arm.neon.vcls.v16i8(<16 x i8> %tmp1)
|
|
ret <16 x i8> %tmp2
|
|
}
|
|
|
|
define <8 x i16> @vclsQs16(<8 x i16>* %A) nounwind {
|
|
;CHECK: vclsQs16:
|
|
;CHECK: vcls.s16
|
|
%tmp1 = load <8 x i16>* %A
|
|
%tmp2 = call <8 x i16> @llvm.arm.neon.vcls.v8i16(<8 x i16> %tmp1)
|
|
ret <8 x i16> %tmp2
|
|
}
|
|
|
|
define <4 x i32> @vclsQs32(<4 x i32>* %A) nounwind {
|
|
;CHECK: vclsQs32:
|
|
;CHECK: vcls.s32
|
|
%tmp1 = load <4 x i32>* %A
|
|
%tmp2 = call <4 x i32> @llvm.arm.neon.vcls.v4i32(<4 x i32> %tmp1)
|
|
ret <4 x i32> %tmp2
|
|
}
|
|
|
|
declare <8 x i8> @llvm.arm.neon.vcls.v8i8(<8 x i8>) nounwind readnone
|
|
declare <4 x i16> @llvm.arm.neon.vcls.v4i16(<4 x i16>) nounwind readnone
|
|
declare <2 x i32> @llvm.arm.neon.vcls.v2i32(<2 x i32>) nounwind readnone
|
|
|
|
declare <16 x i8> @llvm.arm.neon.vcls.v16i8(<16 x i8>) nounwind readnone
|
|
declare <8 x i16> @llvm.arm.neon.vcls.v8i16(<8 x i16>) nounwind readnone
|
|
declare <4 x i32> @llvm.arm.neon.vcls.v4i32(<4 x i32>) nounwind readnone
|