Friday, 14 February 2014

CUDA 6 Release Candidate (RC) is now available.

We’re excited to announce the CUDA 6 Release Candidate (RC) is now available. As a Registered Developer, you have access to the toolkit before it becomes available to the public.
Start programming with CUDA 6 RC today to start using:
  • Unified Memory: simplifies programming by enabling applications to access the CPU and GPU memory without the need to manually copy data.
  • Drop-in Libraries: automatically accelerate the linear algebra and FFTs in your applications by replacing CPU-only libraries with GPU-accelerated libraries.
  • Multi-GPU Scaling: the re-designed BLAS GPU library automatically scales performance across up to 8 GPUs in a single node.
Get a closer look at CUDA 6 at the GPU Technology Conference (GTC) and other learning opportunities:
  • Webinar: CUDA 6 – Overview of New Features, Presented by Mark Ebersole, CUDA Educator
    Wednesday, February 26, 2014 at 10 AM – 11 AM PST REGISTER
  • CUDACast videos covering CUDA 6 features such as Unified Memory and more.
    New weekly episodes start Wednesday, February 19, 2014. LEARN MORE
  • GTC Tutorial: Get CUDA Optimization Techniques, Presented by Dan Cyca, Acceleware
    Monday, March 24, 2:30 PM – 3:50 PM PST LEARN MORE
GTC is the world’s most important GPU developer conference delivering unmatched opportunities to learn how to harness the latest GPU technology. Taking place in the heart of Silicon Valley on March 24-27, 2014, it offers 500 sessions, hands-on labs and tutorials, and face-to-face interaction with industry luminaries and NVIDIA technologists. As a Registered Developer, you can take an extra 20% off using code GM20LME off of the discounted rate – Register now.

No comments:

Post a Comment