Index: llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -11499,6 +11499,62 @@
   return SDValue();
 }
 
+static SDValue combineConcatVectorOfScalars(SDNode *N, SelectionDAG &DAG) {
+  const TargetLowering &TLI = DAG.getTargetLoweringInfo();
+  EVT OpVT = N->getOperand(0).getValueType();
+
+  // If the operands are legal vectors, leave them alone.
+  if (TLI.isTypeLegal(OpVT))
+    return SDValue();
+
+  SDLoc DL(N);
+  EVT VT = N->getValueType(0);
+  SmallVector<SDValue, 8> Ops;
+
+  EVT SVT = EVT::getIntegerVT(*DAG.getContext(), OpVT.getSizeInBits());
+  SDValue ScalarUndef = DAG.getNode(ISD::UNDEF, DL, SVT);
+
+  // Keep track of what we encounter.
+  bool AnyInteger = false;
+  bool AnyFP = false;
+  for (const SDValue &Op : N->ops()) {
+    if (ISD::BITCAST == Op.getOpcode() &&
+        !Op.getOperand(0).getValueType().isVector())
+      Ops.push_back(Op.getOperand(0));
+    else if (ISD::UNDEF == Op.getOpcode())
+      Ops.push_back(ScalarUndef);
+    else
+      return SDValue();
+
+    if (Ops.back().getValueType().isFloatingPoint())
+      AnyFP = true;
+    else
+      AnyInteger = true;
+  }
+
+  // If any of the operands is a floating point scalar bitcast to a vector,
+  // use floating point types throughout, and bitcast everything.  
+  // Replace UNDEFs by another scalar UNDEF node, of the final desired type.
+  if (AnyFP) {
+    SVT = EVT::getFloatingPointVT(OpVT.getSizeInBits());
+    ScalarUndef = DAG.getNode(ISD::UNDEF, DL, SVT);
+    if (AnyInteger) {
+      for (SDValue &Op : Ops) {
+        if (Op.getValueType() != SVT) {
+          Op = DAG.getNode(ISD::BITCAST, DL, SVT, Op);
+          if (Op.getOpcode() == ISD::UNDEF)
+            Op = ScalarUndef;
+        }
+      }
+    }
+  }
+
+  EVT VecVT = EVT::getVectorVT(*DAG.getContext(), SVT,
+                               VT.getSizeInBits() / SVT.getSizeInBits());
+  return DAG.getNode(ISD::BITCAST, DL, VT,
+                     DAG.getNode(ISD::BUILD_VECTOR, DL, VecVT, Ops));
+}
+
 SDValue DAGCombiner::visitCONCAT_VECTORS(SDNode *N) {
   // TODO: Check to see if this is a CONCAT_VECTORS of a bunch of
   // EXTRACT_SUBVECTOR operations.  If so, and if the EXTRACT_SUBVECTOR vector
@@ -11601,6 +11657,10 @@
     return DAG.getNode(ISD::BUILD_VECTOR, SDLoc(N), VT, Opnds);
   }
 
+  // Fold CONCAT_VECTORS of only bitcast scalars (or undef) to BUILD_VECTOR.
+  if (SDValue V = combineConcatVectorOfScalars(N, DAG))
+    return V;
+
   // Type legalization of vectors and DAG canonicalization of SHUFFLE_VECTOR
   // nodes often generate nop CONCAT_VECTOR nodes.
   // Scan the CONCAT_VECTOR operands and look for a CONCAT operations that
Index: llvm/trunk/test/CodeGen/AArch64/concat_vector-scalar-combine.ll
===================================================================
--- llvm/trunk/test/CodeGen/AArch64/concat_vector-scalar-combine.ll
+++ llvm/trunk/test/CodeGen/AArch64/concat_vector-scalar-combine.ll
@@ -0,0 +1,125 @@
+; RUN: llc < %s -mtriple aarch64-unknown-unknown -aarch64-neon-syntax=apple -asm-verbose=false | FileCheck %s
+
+target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
+
+; Test the (concat_vectors (bitcast (scalar)), ..) pattern.
+
+define <8 x i8> @test_concat_scalar_v2i8_to_v8i8_dup(i32 %x) #0 {
+entry:
+; CHECK-LABEL: test_concat_scalar_v2i8_to_v8i8_dup:
+; CHECK-NEXT: dup.4h v0, w0
+; CHECK-NEXT: ret
+  %t = trunc i32 %x to i16
+  %0 = bitcast i16 %t to <2 x i8>
+  %1 = shufflevector <2 x i8> %0, <2 x i8> undef, <8 x i32> <i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1>
+  ret <8 x i8> %1
+}
+
+define <8 x i8> @test_concat_scalar_v4i8_to_v8i8_dup(i32 %x) #0 {
+entry:
+; CHECK-LABEL: test_concat_scalar_v4i8_to_v8i8_dup:
+; CHECK-NEXT: dup.2s v0, w0
+; CHECK-NEXT: ret
+  %0 = bitcast i32 %x to <4 x i8>
+  %1 = shufflevector <4 x i8> %0, <4 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
+  ret <8 x i8> %1
+}
+
+define <8 x i16> @test_concat_scalar_v2i16_to_v8i16_dup(i32 %x) #0 {
+entry:
+; CHECK-LABEL: test_concat_scalar_v2i16_to_v8i16_dup:
+; CHECK-NEXT: dup.4s v0, w0
+; CHECK-NEXT: ret
+  %0 = bitcast i32 %x to <2 x i16>
+  %1 = shufflevector <2 x i16> %0, <2 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 2, i32 0, i32 1, i32 0, i32 1>
+  ret <8 x i16> %1
+}
+
+define <8 x i8> @test_concat_scalars_2x_v2i8_to_v8i8(i32 %x, i32 %y) #0 {
+entry:
+; CHECK-LABEL: test_concat_scalars_2x_v2i8_to_v8i8:
+; CHECK-NEXT: ins.h v0[0], w0
+; CHECK-NEXT: ins.h v0[1], w1
+; CHECK-NEXT: ins.h v0[3], w1
+; CHECK-NEXT: ret
+  %tx = trunc i32 %x to i16
+  %ty = trunc i32 %y to i16
+  %bx = bitcast i16 %tx to <2 x i8>
+  %by = bitcast i16 %ty to <2 x i8>
+  %r = shufflevector <2 x i8> %bx, <2 x i8> %by, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 2, i32 3>
+  ret <8 x i8> %r
+}
+
+define <8 x i8> @test_concat_scalars_2x_v4i8_to_v8i8_dup(i32 %x, i32 %y) #0 {
+entry:
+; CHECK-LABEL: test_concat_scalars_2x_v4i8_to_v8i8_dup:
+; CHECK-NEXT: fmov s0, w1
+; CHECK-NEXT: ins.s v0[1], w0
+; CHECK-NEXT: ret
+  %bx = bitcast i32 %x to <4 x i8>
+  %by = bitcast i32 %y to <4 x i8>
+  %r = shufflevector <4 x i8> %bx, <4 x i8> %by, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+  ret <8 x i8> %r
+}
+
+define <8 x i16> @test_concat_scalars_2x_v2i16_to_v8i16_dup(i32 %x, i32 %y) #0 {
+entry:
+; CHECK-LABEL: test_concat_scalars_2x_v2i16_to_v8i16_dup:
+; CHECK-NEXT: fmov s0, w0
+; CHECK-NEXT: ins.s v0[1], w1
+; CHECK-NEXT: ins.s v0[2], w1
+; CHECK-NEXT: ins.s v0[3], w0
+; CHECK-NEXT: ret
+  %bx = bitcast i32 %x to <2 x i16>
+  %by = bitcast i32 %y to <2 x i16>
+  %r = shufflevector <2 x i16> %bx, <2 x i16> %by, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 2, i32 3, i32 0, i32 1>
+  ret <8 x i16> %r
+}
+
+; Also make sure we minimize bitcasts.
+
+; This is a pretty artificial testcase: make sure we bitcast to floating-point
+; if any of the scalars is floating-point.
+define <8 x i8> @test_concat_scalars_mixed_2x_v2i8_to_v8i8(float %dummy, i32 %x, half %y) #0 {
+entry:
+; CHECK-LABEL: test_concat_scalars_mixed_2x_v2i8_to_v8i8:
+; CHECK-NEXT: fmov s[[X:[0-9]+]], w0
+; CHECK-NEXT: ins.h v0[0], v[[X]][0]
+; CHECK-NEXT: ins.h v0[1], v1[0]
+; CHECK-NEXT: ins.h v0[2], v[[X]][0]
+; CHECK-NEXT: ins.h v0[3], v1[0]
+; CHECK-NEXT: ret
+  %t = trunc i32 %x to i16
+  %0 = bitcast i16 %t to <2 x i8>
+  %y0 = bitcast half %y to <2 x i8>
+  %1 = shufflevector <2 x i8> %0, <2 x i8> %y0, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
+  ret <8 x i8> %1
+}
+
+define <2 x float> @test_concat_scalars_fp_2x_v2i8_to_v8i8(float %dummy, half %x, half %y) #0 {
+entry:
+; CHECK-LABEL: test_concat_scalars_fp_2x_v2i8_to_v8i8:
+; CHECK-NEXT: ins.h v0[0], v1[0]
+; CHECK-NEXT: ins.h v0[1], v2[0]
+; CHECK-NEXT: ins.h v0[2], v1[0]
+; CHECK-NEXT: ins.h v0[3], v2[0]
+; CHECK-NEXT: ret
+  %0 = bitcast half %x to <2 x i8>
+  %y0 = bitcast half %y to <2 x i8>
+  %1 = shufflevector <2 x i8> %0, <2 x i8> %y0, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
+  %2 = bitcast <8 x i8> %1 to <2 x float>
+  ret <2 x float> %2
+}
+
+define <4 x float> @test_concat_scalar_fp_v2i16_to_v16i8_dup(float %x) #0 {
+entry:
+; CHECK-LABEL: test_concat_scalar_fp_v2i16_to_v16i8_dup:
+; CHECK-NEXT: dup.4s v0, v0[0]
+; CHECK-NEXT: ret
+  %0 = bitcast float %x to <2 x i16>
+  %1 = shufflevector <2 x i16> %0, <2 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 2, i32 0, i32 1, i32 0, i32 1>
+  %2 = bitcast <8 x i16> %1 to <4 x float>
+  ret <4 x float> %2
+}
+
+attributes #0 = { nounwind }