The new version 4.0.1 of rCUDA is now available. Release highlights:

  • Fixed cudaHostRegister/cudaHostUnregister bugs.
  • Optimized asynchronous calls management.

The rCUDA team thanks Bright Computing, Inc its donation of an NVIDIA Tesla K20 GPU during the SuperComputing 2012 exhibition held in Salt Lake City (Utah) last November. This last generation GPU will be used to further improve the features and performance of the rCUDA middleware.

Tesla K20

We are happy to announce next rCUDA updates that will complete the rCUDA 4.0 version. The new features will complete the new rCUDA version, which includes binary compatibility, InfiniBand native support and enhanced data transfers.

In addition to the full binary compatibility feature recently released, the new features are going to be:

- rCUDA 4.0 release with CUDA 5.0 API support (excluding graphics interoperability).

- SLURM scheduler integration with rCUDA.

rCUDA 4.0 stable version finally released. This version includes full binary compatibility with CUDA applications, native InfiniBand support, enhanced data transfers and CUDA 5.0 API support (excluding graphics interoperability).

The upcoming rCUDA version, including full binary compatibility with CUDA applications, will be presented at SC12 at Mellanox' booth. If you are attending SC12, don't miss the opportunity of watching a live demonstration and chatting with the rCUDA developers!