* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler. * Change dynamic loading of CUDA driver API functions to load 32-bit or 64-bit versions of depending on the the host architecture. * Add ability to generate PTX kernels to be launched both on 32-bit and 64-bit hosts. * Use Unified Virtual Memory APIs to perform array argument marshalling. * PTX array storage test runs on the device and returns correct results. * More integer test failures on GPU fixed.

Gilles Duboscq (gdub)
Peter Hofer
Christian Haeubl (chaeubl)
Christian Humer (chumer)
Roland Schatz
Doug Simon (dnsimon)
Lukas Stadler (lstadler)
Alexander Stipsits
Katrin Strassl
Christian Wimmer (cwimmer)
Andreas Woess (aw)
Thomas Wuerthinger (thomaswue)