Why can't I overlap asynchronous memcpy with kernel execution on fermi on win7 and CUDA 5.0?

[lucv]

I cannot even achieve overlapping memcpy and kernel execution with the simpleStreams example in the CUDA SDK, let alone in my own programs. These threads argue it is a problem with the WDDM driver in windows:

• http://stackoverflow.com/questions/12397798/why-it-is-not-possible-to-overlap-memhtod-with-gpu-kernel-with-gtx-590
• http://stackoverflow.com/questions/13568805/cuda-kernels-not-launching-before-cudadevicesynchronize/13570086#13570086

and suggest to:

• flush the WDDM queue with cudaEventQuery() or cudaEventQuery(). (Does not work).
• submit streams in breadth first manner. (Does not work).

This thread argues it is a bug in fermi:

• http://stackoverflow.com/questions/14456236/how-can-i-overlap-memory-transfers-and-kernel-execution-in-a-cuda-application

While this thread:

• http://blog.icare3d.org/2010/04/tesla-compute-drivers.html

proposes a solution to mitigate the problems with WDDM on windows. However, it only works for a Tesla card and it requires an additional video card to steer the display, since the proposed drivers are compute-only drivers.

However, none of these threads provide a real solution. I would appreciate it, if NVIDIA could comment on this problem and come up with a solution, since apparently a lot of people are experiencing this.