Use __builtin_shufflevector to implement vget_low and vget_high intrinsics.

This was suggested by Edmund Grimley Evans in pr8411.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123043 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/utils/TableGen/NeonEmitter.cpp b/utils/TableGen/NeonEmitter.cpp
index d019f1cada3b3a4dee92108a486eb823f6931322..64224d9e51d0b79e78944b5144dfc7050899ab38 100644 (file)
--- a/utils/TableGen/NeonEmitter.cpp
+++ b/utils/TableGen/NeonEmitter.cpp
@@ -576,9 +576,7 @@ static std::string GenOpString(OpKind op, const std::string &proto,
 
   std::string ts = TypeString(proto[0], typestr);
   std::string s;
-  if (op == OpHi || op == OpLo) {
-    s = "union { " + ts + " r; double d; } u; u.d = ";
-  } else if (!define) {
+  if (!define) {
     s = "return ";
   }
 
@@ -727,10 +725,12 @@ static std::string GenOpString(OpKind op, const std::string &proto,
     s += ", (int64x1_t)__b, 0, 1);";
     break;
   case OpHi:
-    s += "(((float64x2_t)__a)[1]);";
+    s += "(" + ts +
+      ")__builtin_shufflevector((int64x2_t)__a, (int64x2_t)__a, 1);";
     break;
   case OpLo:
-    s += "(((float64x2_t)__a)[0]);";
+    s += "(" + ts +
+      ")__builtin_shufflevector((int64x2_t)__a, (int64x2_t)__a, 0);";
     break;
   case OpDup:
     s += Duplicate(nElts, typestr, "__a") + ";";
@@ -804,11 +804,6 @@ static std::string GenOpString(OpKind op, const std::string &proto,
     throw "unknown OpKind!";
     break;
   }
-  if (op == OpHi || op == OpLo) {
-    if (!define)
-      s += " return";
-    s += " u.r;";
-  }
   return s;
 }
 
@@ -1135,11 +1130,6 @@ void NeonEmitter::run(raw_ostream &OS) {
     OS << " " << TypeString('d', TDTypeVec[i]) << ";\n";
   }
   OS << "\n";
-  OS << "typedef __attribute__((__vector_size__(8)))  "
-    "double float64x1_t;\n";
-  OS << "typedef __attribute__((__vector_size__(16))) "
-    "double float64x2_t;\n";
-  OS << "\n";
 
   // Emit struct typedefs.
   for (unsigned vi = 2; vi != 5; ++vi) {