Skip to main content


NVIDIA today announced availability of the production release of NVIDIA CUDA 6.5, the latest version of the world’s most pervasive parallel computing platform and programming model.

Available today as a free download at, version 6.5 of the CUDA Toolkit brings the power of GPU-accelerated computing for the first time to 64-bit ARM platforms. It enables a newly expanded range of efficient, high-performance computing options to accelerate compute-intensive high performance computing (HPC) and enterprise data center workloads.

CUDA 6.5 provides programmers with a robust, easy-to-use platform to develop advanced scientific, engineering, mobile and HPC applications on GPU-accelerated ARM and x86 CPU-based systems.

Additional performance and productivity features of the CUDA 6.5 platform include:

·         Support for Microsoft Visual Studio 2013 – Expands host compiler support to include Microsoft Visual Studio 2013 for Windows.

·         cuFFT callbacks capability – Delivers higher performance custom processing on input or output data by enabling programmers to specify callback functions that manipulate data in GPU memory before and during FFT processing.

·         Improved debugging for CUDA FORTRAN applications (preview) – Includes new debugging support for FORTRAN arrays (Linux only), improved source-to-assembly code correlation, and improved documentation.

·         Application Replay mode – Enables faster analysis of complex scenarios using multiple hardware counters.

·         Updated CUDA Occupancy Calculator API – Frees programmer from having to manually configure kernel launches for each GPU architecture.

·         New “nvprune” utility – New utility that prunes object files and libraries to only contain device code needed for the specified target architectures, reducing application size and improving load-time performance.

·         BSR sparse matrix format in cuSPARSE routines – Support for Block Sparse Row matrix format added to more sparse matrix operations.

For more details about new features and enhancements of the CUDA 6.5 platform, visit the Parallel Forall blog post.

Free CUDA Webinars

NVIDIA is hosting a series of webinars on the new features of the CUDA 6.5 Toolkit and parallel programming. Open to CUDA developers of all skill levels free of charge, the webinars will provide programming tips, best practices, and hands-on tutorials to help developers get the most out of programming GPU accelerators.

Upcoming webinars include:

·         CUDA 6.5 Overview and Features – Tuesday, Aug. 26 – 10 a.m. PT
Register here:

·         CUDA 6.5 Performance Overview – Wednesday, Sept. 17 – 10 a.m. PT
Register here:

To see the full list of webinars, visit the GTC Express Webinars website.


Read more about:


Media Partners