From 71224b02fbefe53f27cabc9b9aa56fa5dee7c983 Mon Sep 17 00:00:00 2001
From: Hao Liu <Hao.Liu@arm.com>
Date: Thu, 10 Jul 2014 03:41:50 +0000
Subject: [PATCH] [AArch64]Fix an assertion failure in DAG Combiner about
 concating 2 build_vector.

llvm-svn: 212677
---
 llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp   | 22 ++++++++++++++++++----
 llvm/test/CodeGen/AArch64/arm64-build-vector.ll | 16 +++++++++++++++-
 2 files changed, 33 insertions(+), 5 deletions(-)

diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index ab07954..1df041d 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -10390,10 +10390,24 @@ SDValue DAGCombiner::visitCONCAT_VECTORS(SDNode *N) {
     SmallVector<SDValue, 8> Opnds;
     unsigned BuildVecNumElts =  N0.getNumOperands();
 
-    for (unsigned i = 0; i != BuildVecNumElts; ++i)
-      Opnds.push_back(N0.getOperand(i));
-    for (unsigned i = 0; i != BuildVecNumElts; ++i)
-      Opnds.push_back(N1.getOperand(i));
+    EVT SclTy0 = N0.getOperand(0)->getValueType(0);
+    EVT SclTy1 = N1.getOperand(0)->getValueType(0);
+    if (SclTy0.isFloatingPoint()) {
+      for (unsigned i = 0; i != BuildVecNumElts; ++i)
+        Opnds.push_back(N0.getOperand(i));
+      for (unsigned i = 0; i != BuildVecNumElts; ++i)
+        Opnds.push_back(N1.getOperand(i));
+    } else {
+      // If BUILD_VECTOR are from built from integer, they may have different
+      // operand types. Get the smaller type and truncate all operands to it.
+      EVT MinTy = SclTy0.bitsLE(SclTy1) ? SclTy0 : SclTy1;
+      for (unsigned i = 0; i != BuildVecNumElts; ++i)
+        Opnds.push_back(DAG.getNode(ISD::TRUNCATE, SDLoc(N), MinTy,
+                        N0.getOperand(i)));
+      for (unsigned i = 0; i != BuildVecNumElts; ++i)
+        Opnds.push_back(DAG.getNode(ISD::TRUNCATE, SDLoc(N), MinTy,
+                        N1.getOperand(i)));
+    }
 
     return DAG.getNode(ISD::BUILD_VECTOR, SDLoc(N), VT, Opnds);
   }
diff --git a/llvm/test/CodeGen/AArch64/arm64-build-vector.ll b/llvm/test/CodeGen/AArch64/arm64-build-vector.ll
index 7a3c8ce..d0f6db0 100644
--- a/llvm/test/CodeGen/AArch64/arm64-build-vector.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-build-vector.ll
@@ -42,4 +42,18 @@ define <8 x i16> @build_all_zero(<8 x i16> %a) #1 {
   %b = add <8 x i16> %a, <i16 -32768, i16 undef, i16 undef, i16 undef, i16 undef, i16 undef, i16 undef, i16 undef>
   %c = mul <8 x i16> %b, <i16 -20864, i16 undef, i16 undef, i16 undef, i16 undef, i16 undef, i16 undef, i16 undef>
   ret <8 x i16> %c
-  }
+}
+
+; There is an optimization in DAG Combiner as following:
+;   fold (concat_vectors (BUILD_VECTOR A, B, ...), (BUILD_VECTOR C, D, ...))
+;        -> (BUILD_VECTOR A, B, ..., C, D, ...)
+; This case checks when A,B and C,D are different types, there should be no
+; assertion failure.
+define <8 x i16> @concat_2_build_vector(<4 x i16> %in0) {
+; CHECK-LABEL: concat_2_build_vector:
+; CHECK: movi
+  %vshl_n = shl <4 x i16> %in0, <i16 8, i16 8, i16 8, i16 8>
+  %vshl_n2 = shl <4 x i16> %vshl_n, <i16 9, i16 9, i16 9, i16 9>
+  %shuffle.i = shufflevector <4 x i16> %vshl_n2, <4 x i16> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  ret <8 x i16> %shuffle.i
+}
\ No newline at end of file
-- 
2.7.4