2009-09-09 02:09:15 +02:00
|
|
|
; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
|
2009-06-23 01:27:02 +02:00
|
|
|
|
|
|
|
define <8 x i8> @vabas8(<8 x i8>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
|
2009-08-04 23:33:22 +02:00
|
|
|
;CHECK: vabas8:
|
|
|
|
;CHECK: vaba.s8
|
2009-06-23 01:27:02 +02:00
|
|
|
%tmp1 = load <8 x i8>* %A
|
|
|
|
%tmp2 = load <8 x i8>* %B
|
|
|
|
%tmp3 = load <8 x i8>* %C
|
2010-09-03 03:35:08 +02:00
|
|
|
%tmp4 = call <8 x i8> @llvm.arm.neon.vabds.v8i8(<8 x i8> %tmp2, <8 x i8> %tmp3)
|
|
|
|
%tmp5 = add <8 x i8> %tmp1, %tmp4
|
|
|
|
ret <8 x i8> %tmp5
|
2009-06-23 01:27:02 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
define <4 x i16> @vabas16(<4 x i16>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
|
2009-08-04 23:33:22 +02:00
|
|
|
;CHECK: vabas16:
|
|
|
|
;CHECK: vaba.s16
|
2009-06-23 01:27:02 +02:00
|
|
|
%tmp1 = load <4 x i16>* %A
|
|
|
|
%tmp2 = load <4 x i16>* %B
|
|
|
|
%tmp3 = load <4 x i16>* %C
|
2010-09-03 03:35:08 +02:00
|
|
|
%tmp4 = call <4 x i16> @llvm.arm.neon.vabds.v4i16(<4 x i16> %tmp2, <4 x i16> %tmp3)
|
|
|
|
%tmp5 = add <4 x i16> %tmp1, %tmp4
|
|
|
|
ret <4 x i16> %tmp5
|
2009-06-23 01:27:02 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
define <2 x i32> @vabas32(<2 x i32>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
|
2009-08-04 23:33:22 +02:00
|
|
|
;CHECK: vabas32:
|
|
|
|
;CHECK: vaba.s32
|
2009-06-23 01:27:02 +02:00
|
|
|
%tmp1 = load <2 x i32>* %A
|
|
|
|
%tmp2 = load <2 x i32>* %B
|
|
|
|
%tmp3 = load <2 x i32>* %C
|
2010-09-03 03:35:08 +02:00
|
|
|
%tmp4 = call <2 x i32> @llvm.arm.neon.vabds.v2i32(<2 x i32> %tmp2, <2 x i32> %tmp3)
|
|
|
|
%tmp5 = add <2 x i32> %tmp1, %tmp4
|
|
|
|
ret <2 x i32> %tmp5
|
2009-06-23 01:27:02 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
define <8 x i8> @vabau8(<8 x i8>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
|
2009-08-04 23:33:22 +02:00
|
|
|
;CHECK: vabau8:
|
|
|
|
;CHECK: vaba.u8
|
2009-06-23 01:27:02 +02:00
|
|
|
%tmp1 = load <8 x i8>* %A
|
|
|
|
%tmp2 = load <8 x i8>* %B
|
|
|
|
%tmp3 = load <8 x i8>* %C
|
2010-09-03 03:35:08 +02:00
|
|
|
%tmp4 = call <8 x i8> @llvm.arm.neon.vabdu.v8i8(<8 x i8> %tmp2, <8 x i8> %tmp3)
|
|
|
|
%tmp5 = add <8 x i8> %tmp1, %tmp4
|
|
|
|
ret <8 x i8> %tmp5
|
2009-06-23 01:27:02 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
define <4 x i16> @vabau16(<4 x i16>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
|
2009-08-04 23:33:22 +02:00
|
|
|
;CHECK: vabau16:
|
|
|
|
;CHECK: vaba.u16
|
2009-06-23 01:27:02 +02:00
|
|
|
%tmp1 = load <4 x i16>* %A
|
|
|
|
%tmp2 = load <4 x i16>* %B
|
|
|
|
%tmp3 = load <4 x i16>* %C
|
2010-09-03 03:35:08 +02:00
|
|
|
%tmp4 = call <4 x i16> @llvm.arm.neon.vabdu.v4i16(<4 x i16> %tmp2, <4 x i16> %tmp3)
|
|
|
|
%tmp5 = add <4 x i16> %tmp1, %tmp4
|
|
|
|
ret <4 x i16> %tmp5
|
2009-06-23 01:27:02 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
define <2 x i32> @vabau32(<2 x i32>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
|
2009-08-04 23:33:22 +02:00
|
|
|
;CHECK: vabau32:
|
|
|
|
;CHECK: vaba.u32
|
2009-06-23 01:27:02 +02:00
|
|
|
%tmp1 = load <2 x i32>* %A
|
|
|
|
%tmp2 = load <2 x i32>* %B
|
|
|
|
%tmp3 = load <2 x i32>* %C
|
2010-09-03 03:35:08 +02:00
|
|
|
%tmp4 = call <2 x i32> @llvm.arm.neon.vabdu.v2i32(<2 x i32> %tmp2, <2 x i32> %tmp3)
|
|
|
|
%tmp5 = add <2 x i32> %tmp1, %tmp4
|
|
|
|
ret <2 x i32> %tmp5
|
2009-06-23 01:27:02 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
define <16 x i8> @vabaQs8(<16 x i8>* %A, <16 x i8>* %B, <16 x i8>* %C) nounwind {
|
2009-08-04 23:33:22 +02:00
|
|
|
;CHECK: vabaQs8:
|
|
|
|
;CHECK: vaba.s8
|
2009-06-23 01:27:02 +02:00
|
|
|
%tmp1 = load <16 x i8>* %A
|
|
|
|
%tmp2 = load <16 x i8>* %B
|
|
|
|
%tmp3 = load <16 x i8>* %C
|
2010-09-03 03:35:08 +02:00
|
|
|
%tmp4 = call <16 x i8> @llvm.arm.neon.vabds.v16i8(<16 x i8> %tmp2, <16 x i8> %tmp3)
|
|
|
|
%tmp5 = add <16 x i8> %tmp1, %tmp4
|
|
|
|
ret <16 x i8> %tmp5
|
2009-06-23 01:27:02 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
define <8 x i16> @vabaQs16(<8 x i16>* %A, <8 x i16>* %B, <8 x i16>* %C) nounwind {
|
2009-08-04 23:33:22 +02:00
|
|
|
;CHECK: vabaQs16:
|
|
|
|
;CHECK: vaba.s16
|
2009-06-23 01:27:02 +02:00
|
|
|
%tmp1 = load <8 x i16>* %A
|
|
|
|
%tmp2 = load <8 x i16>* %B
|
|
|
|
%tmp3 = load <8 x i16>* %C
|
2010-09-03 03:35:08 +02:00
|
|
|
%tmp4 = call <8 x i16> @llvm.arm.neon.vabds.v8i16(<8 x i16> %tmp2, <8 x i16> %tmp3)
|
|
|
|
%tmp5 = add <8 x i16> %tmp1, %tmp4
|
|
|
|
ret <8 x i16> %tmp5
|
2009-06-23 01:27:02 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
define <4 x i32> @vabaQs32(<4 x i32>* %A, <4 x i32>* %B, <4 x i32>* %C) nounwind {
|
2009-08-04 23:33:22 +02:00
|
|
|
;CHECK: vabaQs32:
|
|
|
|
;CHECK: vaba.s32
|
2009-06-23 01:27:02 +02:00
|
|
|
%tmp1 = load <4 x i32>* %A
|
|
|
|
%tmp2 = load <4 x i32>* %B
|
|
|
|
%tmp3 = load <4 x i32>* %C
|
2010-09-03 03:35:08 +02:00
|
|
|
%tmp4 = call <4 x i32> @llvm.arm.neon.vabds.v4i32(<4 x i32> %tmp2, <4 x i32> %tmp3)
|
|
|
|
%tmp5 = add <4 x i32> %tmp1, %tmp4
|
|
|
|
ret <4 x i32> %tmp5
|
2009-06-23 01:27:02 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
define <16 x i8> @vabaQu8(<16 x i8>* %A, <16 x i8>* %B, <16 x i8>* %C) nounwind {
|
2009-08-04 23:33:22 +02:00
|
|
|
;CHECK: vabaQu8:
|
|
|
|
;CHECK: vaba.u8
|
2009-06-23 01:27:02 +02:00
|
|
|
%tmp1 = load <16 x i8>* %A
|
|
|
|
%tmp2 = load <16 x i8>* %B
|
|
|
|
%tmp3 = load <16 x i8>* %C
|
2010-09-03 03:35:08 +02:00
|
|
|
%tmp4 = call <16 x i8> @llvm.arm.neon.vabdu.v16i8(<16 x i8> %tmp2, <16 x i8> %tmp3)
|
|
|
|
%tmp5 = add <16 x i8> %tmp1, %tmp4
|
|
|
|
ret <16 x i8> %tmp5
|
2009-06-23 01:27:02 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
define <8 x i16> @vabaQu16(<8 x i16>* %A, <8 x i16>* %B, <8 x i16>* %C) nounwind {
|
2009-08-04 23:33:22 +02:00
|
|
|
;CHECK: vabaQu16:
|
|
|
|
;CHECK: vaba.u16
|
2009-06-23 01:27:02 +02:00
|
|
|
%tmp1 = load <8 x i16>* %A
|
|
|
|
%tmp2 = load <8 x i16>* %B
|
|
|
|
%tmp3 = load <8 x i16>* %C
|
2010-09-03 03:35:08 +02:00
|
|
|
%tmp4 = call <8 x i16> @llvm.arm.neon.vabdu.v8i16(<8 x i16> %tmp2, <8 x i16> %tmp3)
|
|
|
|
%tmp5 = add <8 x i16> %tmp1, %tmp4
|
|
|
|
ret <8 x i16> %tmp5
|
2009-06-23 01:27:02 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
define <4 x i32> @vabaQu32(<4 x i32>* %A, <4 x i32>* %B, <4 x i32>* %C) nounwind {
|
2009-08-04 23:33:22 +02:00
|
|
|
;CHECK: vabaQu32:
|
|
|
|
;CHECK: vaba.u32
|
2009-06-23 01:27:02 +02:00
|
|
|
%tmp1 = load <4 x i32>* %A
|
|
|
|
%tmp2 = load <4 x i32>* %B
|
|
|
|
%tmp3 = load <4 x i32>* %C
|
2010-09-03 03:35:08 +02:00
|
|
|
%tmp4 = call <4 x i32> @llvm.arm.neon.vabdu.v4i32(<4 x i32> %tmp2, <4 x i32> %tmp3)
|
|
|
|
%tmp5 = add <4 x i32> %tmp1, %tmp4
|
|
|
|
ret <4 x i32> %tmp5
|
2009-06-23 01:27:02 +02:00
|
|
|
}
|
|
|
|
|
2010-09-03 03:35:08 +02:00
|
|
|
declare <8 x i8> @llvm.arm.neon.vabds.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
|
|
|
|
declare <4 x i16> @llvm.arm.neon.vabds.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
|
|
|
|
declare <2 x i32> @llvm.arm.neon.vabds.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
|
2009-06-23 01:27:02 +02:00
|
|
|
|
2010-09-03 03:35:08 +02:00
|
|
|
declare <8 x i8> @llvm.arm.neon.vabdu.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
|
|
|
|
declare <4 x i16> @llvm.arm.neon.vabdu.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
|
|
|
|
declare <2 x i32> @llvm.arm.neon.vabdu.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
|
2009-06-23 01:27:02 +02:00
|
|
|
|
2010-09-03 03:35:08 +02:00
|
|
|
declare <16 x i8> @llvm.arm.neon.vabds.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
|
|
|
|
declare <8 x i16> @llvm.arm.neon.vabds.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
|
|
|
|
declare <4 x i32> @llvm.arm.neon.vabds.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
|
2009-06-23 01:27:02 +02:00
|
|
|
|
2010-09-03 03:35:08 +02:00
|
|
|
declare <16 x i8> @llvm.arm.neon.vabdu.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
|
|
|
|
declare <8 x i16> @llvm.arm.neon.vabdu.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
|
|
|
|
declare <4 x i32> @llvm.arm.neon.vabdu.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
|
2009-10-09 22:20:54 +02:00
|
|
|
|
|
|
|
define <8 x i16> @vabals8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
|
|
|
|
;CHECK: vabals8:
|
|
|
|
;CHECK: vabal.s8
|
|
|
|
%tmp1 = load <8 x i16>* %A
|
|
|
|
%tmp2 = load <8 x i8>* %B
|
|
|
|
%tmp3 = load <8 x i8>* %C
|
2010-09-03 03:35:08 +02:00
|
|
|
%tmp4 = call <8 x i8> @llvm.arm.neon.vabds.v8i8(<8 x i8> %tmp2, <8 x i8> %tmp3)
|
|
|
|
%tmp5 = zext <8 x i8> %tmp4 to <8 x i16>
|
|
|
|
%tmp6 = add <8 x i16> %tmp1, %tmp5
|
|
|
|
ret <8 x i16> %tmp6
|
2009-10-09 22:20:54 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
define <4 x i32> @vabals16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
|
|
|
|
;CHECK: vabals16:
|
|
|
|
;CHECK: vabal.s16
|
|
|
|
%tmp1 = load <4 x i32>* %A
|
|
|
|
%tmp2 = load <4 x i16>* %B
|
|
|
|
%tmp3 = load <4 x i16>* %C
|
2010-09-03 03:35:08 +02:00
|
|
|
%tmp4 = call <4 x i16> @llvm.arm.neon.vabds.v4i16(<4 x i16> %tmp2, <4 x i16> %tmp3)
|
|
|
|
%tmp5 = zext <4 x i16> %tmp4 to <4 x i32>
|
|
|
|
%tmp6 = add <4 x i32> %tmp1, %tmp5
|
|
|
|
ret <4 x i32> %tmp6
|
2009-10-09 22:20:54 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
define <2 x i64> @vabals32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
|
|
|
|
;CHECK: vabals32:
|
|
|
|
;CHECK: vabal.s32
|
|
|
|
%tmp1 = load <2 x i64>* %A
|
|
|
|
%tmp2 = load <2 x i32>* %B
|
|
|
|
%tmp3 = load <2 x i32>* %C
|
2010-09-03 03:35:08 +02:00
|
|
|
%tmp4 = call <2 x i32> @llvm.arm.neon.vabds.v2i32(<2 x i32> %tmp2, <2 x i32> %tmp3)
|
|
|
|
%tmp5 = zext <2 x i32> %tmp4 to <2 x i64>
|
|
|
|
%tmp6 = add <2 x i64> %tmp1, %tmp5
|
|
|
|
ret <2 x i64> %tmp6
|
2009-10-09 22:20:54 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
define <8 x i16> @vabalu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
|
|
|
|
;CHECK: vabalu8:
|
|
|
|
;CHECK: vabal.u8
|
|
|
|
%tmp1 = load <8 x i16>* %A
|
|
|
|
%tmp2 = load <8 x i8>* %B
|
|
|
|
%tmp3 = load <8 x i8>* %C
|
2010-09-03 03:35:08 +02:00
|
|
|
%tmp4 = call <8 x i8> @llvm.arm.neon.vabdu.v8i8(<8 x i8> %tmp2, <8 x i8> %tmp3)
|
|
|
|
%tmp5 = zext <8 x i8> %tmp4 to <8 x i16>
|
|
|
|
%tmp6 = add <8 x i16> %tmp1, %tmp5
|
|
|
|
ret <8 x i16> %tmp6
|
2009-10-09 22:20:54 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
define <4 x i32> @vabalu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
|
|
|
|
;CHECK: vabalu16:
|
|
|
|
;CHECK: vabal.u16
|
|
|
|
%tmp1 = load <4 x i32>* %A
|
|
|
|
%tmp2 = load <4 x i16>* %B
|
|
|
|
%tmp3 = load <4 x i16>* %C
|
2010-09-03 03:35:08 +02:00
|
|
|
%tmp4 = call <4 x i16> @llvm.arm.neon.vabdu.v4i16(<4 x i16> %tmp2, <4 x i16> %tmp3)
|
|
|
|
%tmp5 = zext <4 x i16> %tmp4 to <4 x i32>
|
|
|
|
%tmp6 = add <4 x i32> %tmp1, %tmp5
|
|
|
|
ret <4 x i32> %tmp6
|
2009-10-09 22:20:54 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
define <2 x i64> @vabalu32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
|
|
|
|
;CHECK: vabalu32:
|
|
|
|
;CHECK: vabal.u32
|
|
|
|
%tmp1 = load <2 x i64>* %A
|
|
|
|
%tmp2 = load <2 x i32>* %B
|
|
|
|
%tmp3 = load <2 x i32>* %C
|
2010-09-03 03:35:08 +02:00
|
|
|
%tmp4 = call <2 x i32> @llvm.arm.neon.vabdu.v2i32(<2 x i32> %tmp2, <2 x i32> %tmp3)
|
|
|
|
%tmp5 = zext <2 x i32> %tmp4 to <2 x i64>
|
|
|
|
%tmp6 = add <2 x i64> %tmp1, %tmp5
|
|
|
|
ret <2 x i64> %tmp6
|
2010-08-04 02:12:08 +02:00
|
|
|
}
|