Optimize away nop CONCAT_VECTOR nodes.

Optimize CONCAT_VECTOR nodes that merge EXTRACT_SUBVECTOR values that extract from the same vector.

rdar://13402653
PR15866

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180871 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 310da09edf5fab422500e0d2af71b05f50ecee72..85f5df911dbc7d59f53182498511d15a04a9e0ad 100644 (file)
--- a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -9122,6 +9122,45 @@ SDValue DAGCombiner::visitCONCAT_VECTORS(SDNode *N) {
   if (ISD::allOperandsUndef(N))
     return DAG.getUNDEF(N->getValueType(0));
 
+  // 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
+  // place the incoming vectors at the exact same location.
+  SDValue SingleSource = SDValue();
+  unsigned PartNumElem = N->getOperand(0).getValueType().getVectorNumElements();
+
+  for (unsigned i = 0, e = N->getNumOperands(); i != e; ++i) {
+    SDValue Op = N->getOperand(i);
+
+    if (Op.getOpcode() == ISD::UNDEF)
+      continue;
+
+    // Check if this is the identity extract:
+    if (Op.getOpcode() != ISD::EXTRACT_SUBVECTOR)
+      return SDValue();
+
+    // Find the single incoming vector for the extract_subvector.
+    if (SingleSource.getNode()) {
+      if (Op.getOperand(0) != SingleSource)
+        return SDValue();
+    } else {
+      SingleSource = Op.getOperand(0);
+    }
+
+    unsigned IdentityIndex = i * PartNumElem;
+    ConstantSDNode *CS = dyn_cast<ConstantSDNode>(Op.getOperand(1));
+    // The extract index must be constant.
+    if (!CS)
+      return SDValue();
+    
+    // Check that we are reading from the identity index.
+    if (CS->getZExtValue() != IdentityIndex)
+      return SDValue();
+  }
+
+  if (SingleSource.getNode())
+    return SingleSource;
+  
   return SDValue();
 }
 

diff --git a/test/CodeGen/ARM/nop_concat_vectors.ll b/test/CodeGen/ARM/nop_concat_vectors.ll
new file mode 100644 (file)
index 0000000..c810900
--- /dev/null
+++ b/test/CodeGen/ARM/nop_concat_vectors.ll
@@ -0,0 +1,13 @@
+; RUN: llc < %s -mtriple=armv7-apple-darwin | FileCheck %s
+
+;CHECK: _foo
+;CHECK-NOT: vld1.32
+;CHECK-NOT: vst1.32
+;CHECK: bx
+define void @foo(<16 x i8>* %J) {
+  %A = load <16 x i8>* %J
+  %T1 = shufflevector <16 x i8> %A, <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+  %T2 = shufflevector <8 x i8>  %T1, <8 x i8> undef, <16 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  store <16 x i8> %T2, <16 x i8>* %J
+  ret void
+}