mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-07-20 10:30:03 +00:00
5bafff36c7
This is still a work in progress but most of the NEON instruction set is supported. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@73919 91177308-0d34-0410-b5e6-96231b3b80d8
64 lines
2.6 KiB
LLVM
64 lines
2.6 KiB
LLVM
; RUN: llvm-as < %s | llc -march=arm -mattr=+neon > %t
|
|
; RUN: grep {vmlal\\.s8} %t | count 1
|
|
; RUN: grep {vmlal\\.s16} %t | count 1
|
|
; RUN: grep {vmlal\\.s32} %t | count 1
|
|
; RUN: grep {vmlal\\.u8} %t | count 1
|
|
; RUN: grep {vmlal\\.u16} %t | count 1
|
|
; RUN: grep {vmlal\\.u32} %t | count 1
|
|
|
|
define <8 x i16> @vmlals8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
|
|
%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 {
|
|
%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 {
|
|
%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 {
|
|
%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 {
|
|
%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 {
|
|
%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
|