Patches to support ARM NEON with Clang 3.0 and LLVM-GCC

2 files changed, 38 insertions, 24 deletions

diff --git a/Eigen/src/Core/arch/NEON/Complex.h b/Eigen/src/Core/arch/NEON/Complex.h
index 8e55548c9..212887184 100644
--- a/Eigen/src/Core/arch/NEON/Complex.h
+++ b/Eigen/src/Core/arch/NEON/Complex.h
@@ -27,8 +27,8 @@
 
 namespace internal {
 
-static uint32x4_t p4ui_CONJ_XOR = { 0x00000000, 0x80000000, 0x00000000, 0x80000000 };
-static uint32x2_t p2ui_CONJ_XOR = { 0x00000000, 0x80000000 };
+static uint32x4_t p4ui_CONJ_XOR = EIGEN_INIT_NEON_PACKET4(0x00000000, 0x80000000, 0x00000000, 0x80000000);
+static uint32x2_t p2ui_CONJ_XOR = EIGEN_INIT_NEON_PACKET2(0x00000000, 0x80000000);
 
 //---------- float ----------
 struct Packet2cf
diff --git a/Eigen/src/Core/arch/NEON/PacketMath.h b/Eigen/src/Core/arch/NEON/PacketMath.h
index 478ef8038..6c7cd1590 100644
--- a/Eigen/src/Core/arch/NEON/PacketMath.h
+++ b/Eigen/src/Core/arch/NEON/PacketMath.h
@@ -52,6 +52,16 @@ typedef uint32x4_t  Packet4ui;
 #define _EIGEN_DECLARE_CONST_Packet4i(NAME,X) \
   const Packet4i p4i_##NAME = pset1<Packet4i>(X)
 
+#if defined(__llvm__) && !defined(__clang__)
+  //Special treatment for Apple's llvm-gcc, its NEON packet types are unions
+  #define EIGEN_INIT_NEON_PACKET2(X, Y)       {{X, Y}}
+  #define EIGEN_INIT_NEON_PACKET4(X, Y, Z, W) {{X, Y, Z, W}}
+#else
+  //Default initializer for packets
+  #define EIGEN_INIT_NEON_PACKET2(X, Y)       {X, Y}
+  #define EIGEN_INIT_NEON_PACKET4(X, Y, Z, W) {X, Y, Z, W}
+#endif
+    
 #ifndef __pld
 #define __pld(x) asm volatile ( "   pld [%[addr]]\n" :: [addr] "r" (x) : "cc" );
 #endif
@@ -84,7 +94,7 @@ template<> struct packet_traits<int>    : default_packet_traits
   };
 };
 
-#if EIGEN_GNUC_AT_MOST(4,4)
+#if EIGEN_GNUC_AT_MOST(4,4) && !defined(__llvm__)
 // workaround gcc 4.2, 4.3 and 4.4 compilatin issue
 EIGEN_STRONG_INLINE float32x4_t vld1q_f32(const float* x) { return ::vld1q_f32((const float32_t*)x); }
 EIGEN_STRONG_INLINE float32x2_t vld1_f32 (const float* x) { return ::vld1_f32 ((const float32_t*)x); }
@@ -100,12 +110,12 @@ template<> EIGEN_STRONG_INLINE Packet4i pset1<Packet4i>(const int&    from)   {
 
 template<> EIGEN_STRONG_INLINE Packet4f plset<float>(const float& a)
 {
-  Packet4f countdown = { 0, 1, 2, 3 };
+  Packet4f countdown = EIGEN_INIT_NEON_PACKET4(0, 1, 2, 3);
   return vaddq_f32(pset1<Packet4f>(a), countdown);
 }
 template<> EIGEN_STRONG_INLINE Packet4i plset<int>(const int& a)
 {
-  Packet4i countdown = { 0, 1, 2, 3 };
+  Packet4i countdown = EIGEN_INIT_NEON_PACKET4(0, 1, 2, 3);
   return vaddq_s32(pset1<Packet4i>(a), countdown);
 }
 
@@ -395,25 +405,29 @@ template<> EIGEN_STRONG_INLINE int predux_max<Packet4i>(const Packet4i& a)
   return s[0];
 }
 
-template<int Offset>
-struct palign_impl<Offset,Packet4f>
-{
-  EIGEN_STRONG_INLINE static void run(Packet4f& first, const Packet4f& second)
-  {
-    if (Offset!=0)
-      first = vextq_f32(first, second, Offset);
-  }
-};
-
-template<int Offset>
-struct palign_impl<Offset,Packet4i>
-{
-  EIGEN_STRONG_INLINE static void run(Packet4i& first, const Packet4i& second)
-  {
-    if (Offset!=0)
-      first = vextq_s32(first, second, Offset);
-  }
-};
+// this PALIGN_NEON business is to work around a bug in LLVM Clang 3.0 causing incorrect compilation errors,
+// see bug 347 and this LLVM bug: http://llvm.org/bugs/show_bug.cgi?id=11074
+#define PALIGN_NEON(Offset,Type,Command) \
+template<>\
+struct palign_impl<Offset,Type>\
+{\
+    EIGEN_STRONG_INLINE static void run(Type& first, const Type& second)\
+    {\
+        if (Offset!=0)\
+            first = Command(first, second, Offset);\
+    }\
+};\
+
+PALIGN_NEON(0,Packet4f,vextq_f32)
+PALIGN_NEON(1,Packet4f,vextq_f32)
+PALIGN_NEON(2,Packet4f,vextq_f32)
+PALIGN_NEON(3,Packet4f,vextq_f32)
+PALIGN_NEON(0,Packet4i,vextq_s32)
+PALIGN_NEON(1,Packet4i,vextq_s32)
+PALIGN_NEON(2,Packet4i,vextq_s32)
+PALIGN_NEON(3,Packet4i,vextq_s32)
+    
+#undef PALIGN_NEON
 
 } // end namespace internal