Clean up float16 a.k.a. Eigen::half support in Eigen. Move the definition of half to Core/arch/Default and move arch-specific packet ops to their respective sub-directories.

1 files changed, 51 insertions, 0 deletions

diff --git a/Eigen/src/Core/arch/SSE/TypeCasting.h b/Eigen/src/Core/arch/SSE/TypeCasting.h
index f607366f0..1b8e9a550 100644
--- a/Eigen/src/Core/arch/SSE/TypeCasting.h
+++ b/Eigen/src/Core/arch/SSE/TypeCasting.h
@@ -77,6 +77,57 @@ template<> EIGEN_STRONG_INLINE Packet4f preinterpret<Packet4f,Packet4i>(const Pa
   return _mm_castsi128_ps(a);
 }
 
+
+// Disable the following code since it's broken on too many platforms / compilers.
+//#elif defined(EIGEN_VECTORIZE_SSE) && (!EIGEN_ARCH_x86_64) && (!EIGEN_COMP_MSVC)
+#if 0
+
+template <>
+struct type_casting_traits<Eigen::half, float> {
+  enum {
+    VectorizedCast = 1,
+    SrcCoeffRatio = 1,
+    TgtCoeffRatio = 1
+  };
+};
+
+template<> EIGEN_STRONG_INLINE Packet4f pcast<Packet4h, Packet4f>(const Packet4h& a) {
+  __int64_t a64 = _mm_cvtm64_si64(a.x);
+  Eigen::half h = raw_uint16_to_half(static_cast<unsigned short>(a64));
+  float f1 = static_cast<float>(h);
+  h = raw_uint16_to_half(static_cast<unsigned short>(a64 >> 16));
+  float f2 = static_cast<float>(h);
+  h = raw_uint16_to_half(static_cast<unsigned short>(a64 >> 32));
+  float f3 = static_cast<float>(h);
+  h = raw_uint16_to_half(static_cast<unsigned short>(a64 >> 48));
+  float f4 = static_cast<float>(h);
+  return _mm_set_ps(f4, f3, f2, f1);
+}
+
+template <>
+struct type_casting_traits<float, Eigen::half> {
+  enum {
+    VectorizedCast = 1,
+    SrcCoeffRatio = 1,
+    TgtCoeffRatio = 1
+  };
+};
+
+template<> EIGEN_STRONG_INLINE Packet4h pcast<Packet4f, Packet4h>(const Packet4f& a) {
+  EIGEN_ALIGN16 float aux[4];
+  pstore(aux, a);
+  Eigen::half h0(aux[0]);
+  Eigen::half h1(aux[1]);
+  Eigen::half h2(aux[2]);
+  Eigen::half h3(aux[3]);
+
+  Packet4h result;
+  result.x = _mm_set_pi16(h3.x, h2.x, h1.x, h0.x);
+  return result;
+}
+
+#endif
+
 } // end namespace internal
 
 } // end namespace Eigen