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

[AArch64 NEON] Fix a bug when lowering BUILD_VECTOR. 

DAG.getVectorShuffle() doesn't always return a vector_shuffle node.
If mask is the exact sequence of it's operand(For example, operand_0
is v8i8, and  the mask is 0, 1, 2, 3, 4, 5, 6, 7), it will directly
return that operand. So a check is added here.

llvm-svn: 197967
This commit is contained in:
Kevin Qin 2013-12-24 08:16:06 +00:00
parent cd5f3153f5
commit 82bd84aadf
2 changed files with 27 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
View File

@ -3957,6 +3957,9 @@ bool AArch64TargetLowering::isKnownShuffleVector(SDValue Op, SelectionDAG &DAG,
if (V1.getNode() && NumElts == V0NumElts && if (V1.getNode() && NumElts == V0NumElts &&
V0NumElts == V1.getValueType().getVectorNumElements()) { V0NumElts == V1.getValueType().getVectorNumElements()) {
SDValue Shuffle = DAG.getVectorShuffle(VT, DL, V0, V1, Mask); SDValue Shuffle = DAG.getVectorShuffle(VT, DL, V0, V1, Mask);
if(Shuffle.getOpcode() != ISD::VECTOR_SHUFFLE)
Res = Shuffle;
else
Res = LowerVECTOR_SHUFFLE(Shuffle, DAG); Res = LowerVECTOR_SHUFFLE(Shuffle, DAG);
return true; return true;
} else } else

22
llvm/test/CodeGen/AArch64/neon-copy.ll
View File

@ -704,3 +704,25 @@ define <4 x i32> @testDUP.v1i32(<1 x i32> %a) {
%f = insertelement <4 x i32> %e, i32 %b, i32 3 %f = insertelement <4 x i32> %e, i32 %b, i32 3
ret <4 x i32> %f ret <4 x i32> %f
} }
define <8 x i8> @getl(<16 x i8> %x) #0 {
; CHECK-LABEL: getl:
; CHECK: ret
%vecext = extractelement <16 x i8> %x, i32 0
%vecinit = insertelement <8 x i8> undef, i8 %vecext, i32 0
%vecext1 = extractelement <16 x i8> %x, i32 1
%vecinit2 = insertelement <8 x i8> %vecinit, i8 %vecext1, i32 1
%vecext3 = extractelement <16 x i8> %x, i32 2
%vecinit4 = insertelement <8 x i8> %vecinit2, i8 %vecext3, i32 2
%vecext5 = extractelement <16 x i8> %x, i32 3
%vecinit6 = insertelement <8 x i8> %vecinit4, i8 %vecext5, i32 3
%vecext7 = extractelement <16 x i8> %x, i32 4
%vecinit8 = insertelement <8 x i8> %vecinit6, i8 %vecext7, i32 4
%vecext9 = extractelement <16 x i8> %x, i32 5
%vecinit10 = insertelement <8 x i8> %vecinit8, i8 %vecext9, i32 5
%vecext11 = extractelement <16 x i8> %x, i32 6
%vecinit12 = insertelement <8 x i8> %vecinit10, i8 %vecext11, i32 6
%vecext13 = extractelement <16 x i8> %x, i32 7
%vecinit14 = insertelement <8 x i8> %vecinit12, i8 %vecext13, i32 7
ret <8 x i8> %vecinit14
}