maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Add correct encodings for NEON vaddw.s* and vaddw.u*. 

llvm-svn: 117040
This commit is contained in:
Owen Anderson 2010-10-21 18:20:25 +00:00
parent 15c97706e8
commit 9561084188
2 changed files with 78 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
llvm/lib/Target/ARM/ARMInstrNEON.td
View File

@ -1668,11 +1668,25 @@ class N3VW<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
string OpcodeStr, string Dt, ValueType TyQ, ValueType TyD,
SDNode OpNode, SDNode ExtOp, bit Commutable>
: N3V<op24, op23, op21_20, op11_8, 0, op4,
(outs QPR:$dst), (ins QPR:$src1, DPR:$src2), N3RegFrm, IIC_VSUBiD,
OpcodeStr, Dt, "$dst, $src1, $src2", "",
[(set QPR:$dst, (OpNode (TyQ QPR:$src1),
(TyQ (ExtOp (TyD DPR:$src2)))))]> {
(outs QPR:$Qd), (ins QPR:$Qn, DPR:$Dm), N3RegFrm, IIC_VSUBiD,
OpcodeStr, Dt, "$Qd, $Qn, $Dm", "",
[(set QPR:$Qd, (OpNode (TyQ QPR:$Qn),
(TyQ (ExtOp (TyD DPR:$Dm)))))]> {
let isCommutable = Commutable;
// Instruction operands.
bits<4> Qd;
bits<4> Qn;
bits<5> Dm;
let Inst{15-13} = Qd{2-0};
let Inst{22} = Qd{3};
let Inst{12} = 0;
let Inst{19-17} = Qn{2-0};
let Inst{7} = Qn{3};
let Inst{16} = 0;
let Inst{3-0} = Dm{3-0};
let Inst{5} = Dm{4};
}
// Pairwise long 2-register intrinsics, both double- and quad-register.

60
llvm/test/MC/ARM/neon-fp-encoding.ll
View File

@ -119,3 +119,63 @@ define <2 x i64> @vaddlu_2xi32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
%tmp5 = add <2 x i64> %tmp3, %tmp4
ret <2 x i64> %tmp5
}
; CHECK: vaddws_8xi8
define <8 x i16> @vaddws_8xi8(<8 x i16>* %A, <8 x i8>* %B) nounwind {
%tmp1 = load <8 x i16>* %A
%tmp2 = load <8 x i8>* %B
%tmp3 = sext <8 x i8> %tmp2 to <8 x i16>
; CHECK: vaddw.s8 q8, q8, d18 @ encoding: [0xa2,0x01,0xc0,0xf2]
%tmp4 = add <8 x i16> %tmp1, %tmp3
ret <8 x i16> %tmp4
}
; CHECK: vaddws_4xi16
define <4 x i32> @vaddws_4xi16(<4 x i32>* %A, <4 x i16>* %B) nounwind {
%tmp1 = load <4 x i32>* %A
%tmp2 = load <4 x i16>* %B
%tmp3 = sext <4 x i16> %tmp2 to <4 x i32>
; CHECK: vaddw.s16 q8, q8, d18 @ encoding: [0xa2,0x01,0xd0,0xf2]
%tmp4 = add <4 x i32> %tmp1, %tmp3
ret <4 x i32> %tmp4
}
; CHECK: vaddws_2xi32
define <2 x i64> @vaddws_2xi32(<2 x i64>* %A, <2 x i32>* %B) nounwind {
%tmp1 = load <2 x i64>* %A
%tmp2 = load <2 x i32>* %B
%tmp3 = sext <2 x i32> %tmp2 to <2 x i64>
; CHECK: vaddw.s32 q8, q8, d18 @ encoding: [0xa2,0x01,0xe0,0xf2]
%tmp4 = add <2 x i64> %tmp1, %tmp3
ret <2 x i64> %tmp4
}
; CHECK: vaddwu_8xi8
define <8 x i16> @vaddwu_8xi8(<8 x i16>* %A, <8 x i8>* %B) nounwind {
%tmp1 = load <8 x i16>* %A
%tmp2 = load <8 x i8>* %B
%tmp3 = zext <8 x i8> %tmp2 to <8 x i16>
; CHECK: vaddw.u8 q8, q8, d18 @ encoding: [0xa2,0x01,0xc0,0xf3]
%tmp4 = add <8 x i16> %tmp1, %tmp3
ret <8 x i16> %tmp4
}
; CHECK: vaddwu_4xi16
define <4 x i32> @vaddwu_4xi16(<4 x i32>* %A, <4 x i16>* %B) nounwind {
%tmp1 = load <4 x i32>* %A
%tmp2 = load <4 x i16>* %B
%tmp3 = zext <4 x i16> %tmp2 to <4 x i32>
; CHECK: vaddw.u16 q8, q8, d18 @ encoding: [0xa2,0x01,0xd0,0xf3]
%tmp4 = add <4 x i32> %tmp1, %tmp3
ret <4 x i32> %tmp4
}
; CHECK: vaddwu_2xi32
define <2 x i64> @vaddwu_2xi32(<2 x i64>* %A, <2 x i32>* %B) nounwind {
%tmp1 = load <2 x i64>* %A
%tmp2 = load <2 x i32>* %B
%tmp3 = zext <2 x i32> %tmp2 to <2 x i64>
; CHECK: vaddw.u32 q8, q8, d18 @ encoding: [0xa2,0x01,0xe0,0xf3]
%tmp4 = add <2 x i64> %tmp1, %tmp3
ret <2 x i64> %tmp4
}