mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-08-21 18:29:46 +00:00
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
20 lines
794 B
LLVM
20 lines
794 B
LLVM
; RUN: llvm-as < %s | llc -march=arm -mattr=+neon > %t
|
|
; RUN: grep {vrsqrts\\.f32} %t | count 2
|
|
|
|
define <2 x float> @vrsqrtsf32(<2 x float>* %A, <2 x float>* %B) nounwind {
|
|
%tmp1 = load <2 x float>* %A
|
|
%tmp2 = load <2 x float>* %B
|
|
%tmp3 = call <2 x float> @llvm.arm.neon.vrsqrts.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
|
ret <2 x float> %tmp3
|
|
}
|
|
|
|
define <4 x float> @vrsqrtsQf32(<4 x float>* %A, <4 x float>* %B) nounwind {
|
|
%tmp1 = load <4 x float>* %A
|
|
%tmp2 = load <4 x float>* %B
|
|
%tmp3 = call <4 x float> @llvm.arm.neon.vrsqrts.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
|
|
ret <4 x float> %tmp3
|
|
}
|
|
|
|
declare <2 x float> @llvm.arm.neon.vrsqrts.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
|
declare <4 x float> @llvm.arm.neon.vrsqrts.v4f32(<4 x float>, <4 x float>) nounwind readnone
|