From 4905226c1c0a1324f4df38acee0ed6bc891ed2d1 Mon Sep 17 00:00:00 2001
From: Kevin Qin <Kevin.Qin@arm.com>
Date: Tue, 24 Dec 2013 08:16:06 +0000
Subject: [PATCH] [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.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@197967 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Target/AArch64/AArch64ISelLowering.cpp |  5 ++++-
 test/CodeGen/AArch64/neon-copy.ll          | 24 +++++++++++++++++++++-
 2 files changed, 27 insertions(+), 2 deletions(-)

diff --git a/lib/Target/AArch64/AArch64ISelLowering.cpp b/lib/Target/AArch64/AArch64ISelLowering.cpp
index f72dfe46de7..757eb0b248e 100644
--- a/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -3957,7 +3957,10 @@ bool AArch64TargetLowering::isKnownShuffleVector(SDValue Op, SelectionDAG &DAG,
   if (V1.getNode() && NumElts == V0NumElts &&
       V0NumElts == V1.getValueType().getVectorNumElements()) {
     SDValue Shuffle = DAG.getVectorShuffle(VT, DL, V0, V1, Mask);
-    Res = LowerVECTOR_SHUFFLE(Shuffle, DAG);
+    if(Shuffle.getOpcode() != ISD::VECTOR_SHUFFLE)
+      Res = Shuffle;
+    else
+      Res = LowerVECTOR_SHUFFLE(Shuffle, DAG);
     return true;
   } else
     return false;
diff --git a/test/CodeGen/AArch64/neon-copy.ll b/test/CodeGen/AArch64/neon-copy.ll
index c783c00c714..881a858bc19 100644
--- a/test/CodeGen/AArch64/neon-copy.ll
+++ b/test/CodeGen/AArch64/neon-copy.ll
@@ -703,4 +703,26 @@ define <4 x i32> @testDUP.v1i32(<1 x i32> %a) {
   %e = insertelement <4 x i32> %d, i32 %b, i32 2
   %f = insertelement <4 x i32> %e, i32 %b, i32 3
   ret <4 x i32> %f
-}
\ No newline at end of file
+}
+
+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
+}
-- 
2.34.1