replaced _mm_prefetch in GeneralBlockPanelKernel.h, with ei_prefetch() inline function.

Implemented NEON and AltiVec versions, copied SSE version over from GeneralBlockPanelKernel.h.
Also in GCC case (or rather !_MSC_VER) it's implemented using __builtin_prefetch().
NEON managed to give a small but welcome boost, 0.88GFLOPS -> 0.91GFLOPS.
This commit is contained in:
oem
2010-04-24 00:44:14 +03:00
parent e3e34b5920
commit 6972c140f7
5 changed files with 36 additions and 26 deletions

View File

@@ -169,6 +169,14 @@ template<typename Scalar, typename Packet> inline void ei_pstore(Scalar* to, con
template<typename Scalar, typename Packet> inline void ei_pstoreu(Scalar* to, const Packet& from)
{ (*to) = from; }
/** \internal tries to do cache prefetching of \a addr */
template<typename Scalar> inline void ei_prefetch(const Scalar* addr)
{
#if !defined(_MSC_VER)
__builtin_prefetch(addr);
#endif
}
/** \internal \returns the first element of a packet */
template<typename Packet> inline typename ei_unpacket_traits<Packet>::type ei_pfirst(const Packet& a)
{ return a; }