6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-02-08 21:32:39 +00:00
Code Issues Projects Releases Wiki Activity

Add correct NEON encodings for vqdmlal.

Browse Source 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@117134 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Owen Anderson 2010-10-22 19:35:48 +00:00
parent 385e136dce
commit 9b26497273
2 changed files with 28 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
lib/Target/ARM/ARMInstrNEON.td
View File

@ -1495,10 +1495,10 @@ class N3VLInt3<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
InstrItinClass itin, string OpcodeStr, string Dt,
ValueType TyQ, ValueType TyD, Intrinsic IntOp>
: N3V<op24, op23, op21_20, op11_8, 0, op4,
(outs QPR:$dst), (ins QPR:$src1, DPR:$src2, DPR:$src3), N3RegFrm, itin,
OpcodeStr, Dt, "$dst, $src2, $src3", "$src1 = $dst",
[(set QPR:$dst,
(TyQ (IntOp (TyQ QPR:$src1), (TyD DPR:$src2), (TyD DPR:$src3))))]>;
(outs QPR:$Vd), (ins QPR:$src1, DPR:$Vn, DPR:$Vm), N3RegFrm, itin,
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "$src1 = $Vd",
[(set QPR:$Vd,
(TyQ (IntOp (TyQ QPR:$src1), (TyD DPR:$Vn), (TyD DPR:$Vm))))]>;
class N3VLInt3SL<bit op24, bits<2> op21_20, bits<4> op11_8, InstrItinClass itin,
string OpcodeStr, string Dt,
ValueType ResTy, ValueType OpTy, Intrinsic IntOp>

24
test/MC/ARM/neon-mul-accum-encoding.ll
View File

@ -165,3 +165,27 @@ define <2 x i64> @vmlalu_2xi32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) noun
%tmp7 = add <2 x i64> %tmp1, %tmp6
ret <2 x i64> %tmp7
}
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
; CHECK: vqdmlal_4xi16
define <4 x i32> @vqdmlal_4xi16(<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
; CHECK: vqdmlal.s16 q8, d19, d18 @ encoding: [0xa2,0x09,0xd3,0xf2
%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
}
; CHECK: vqdmlal_2xi32
define <2 x i64> @vqdmlal_2xi32(<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
; CHECK: vqdmlal.s32 q8, d19, d18 @ encoding: [0xa2,0x09,0xe3,0xf2]
%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
}