mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 12:12:47 +01:00
6db76aaf10
This is still a work in progress but most of the NEON instruction set is supported. llvm-svn: 73919
23 lines
930 B
LLVM
23 lines
930 B
LLVM
; RUN: llvm-as < %s | llc -march=arm -mattr=+neon > %t
|
|
; RUN: grep {vqdmlal\\.s16} %t | count 1
|
|
; RUN: grep {vqdmlal\\.s32} %t | count 1
|
|
|
|
define <4 x i32> @vqdmlals16(<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.vqdmlal.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3)
|
|
ret <4 x i32> %tmp4
|
|
}
|
|
|
|
define <2 x i64> @vqdmlals32(<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.vqdmlal.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3)
|
|
ret <2 x i64> %tmp4
|
|
}
|
|
|
|
declare <4 x i32> @llvm.arm.neon.vqdmlal.v4i32(<4 x i32>, <4 x i16>, <4 x i16>) nounwind readnone
|
|
declare <2 x i64> @llvm.arm.neon.vqdmlal.v2i64(<2 x i64>, <2 x i32>, <2 x i32>) nounwind readnone
|