NVIDIA Releases CUDA 6.5 As A Huge Update
NVIDIA put out version 6.5 of their Compute Unified Device Architecture today and it is a big step ahead, including better development tooling for CUDA Fortran.
Among the features for CUDA 6.5 is official support for 64-bit ARM, cuFFT device callback support, CUDA Fortran tools support, CUDA Occupancy Calculator APIs, double-precision performance improvements, static CUDA library versions on Linux, multi-process service performance improvements, and a variety of other changes.
Developers interested in learning more about CUDA 6.5 can read this NVIDIA blog post. CUDA 6.5 for all major platforms is available for download from NVIDIA's CUDA ZONE. The offered Linux binaries are for Fedora 20, openSUSE 13.1, RHEL/CentOS 6, RHEL/CentOS 5, SUSE Linux Enterprise Server 11 SP1, SteamOS 1.0 Beta, Ubuntu 12.04, and Ubuntu 14.04.
Among the features for CUDA 6.5 is official support for 64-bit ARM, cuFFT device callback support, CUDA Fortran tools support, CUDA Occupancy Calculator APIs, double-precision performance improvements, static CUDA library versions on Linux, multi-process service performance improvements, and a variety of other changes.
Developers interested in learning more about CUDA 6.5 can read this NVIDIA blog post. CUDA 6.5 for all major platforms is available for download from NVIDIA's CUDA ZONE. The offered Linux binaries are for Fedora 20, openSUSE 13.1, RHEL/CentOS 6, RHEL/CentOS 5, SUSE Linux Enterprise Server 11 SP1, SteamOS 1.0 Beta, Ubuntu 12.04, and Ubuntu 14.04.
10 Comments