Accelerate Machine Learning with the cuDNN Deep Neural Network Library

Deep learning – training computers to teach themselves by sifting through massive amounts of data – is one of the fastest growing segments in machine learning. To make it easier for deep learning pros to advance their work, Nvidia has developed cuDNN – a CUDA-based library that helps developers quickly and easily harness the power of GPU acceleration. lesshttp://nvda.ly/Bg139

CfP: High Performance Computing Symposium 2015

The 2015 Spring Simulation Multi-conference will feature the 23rd High Performance Computing Symposium (HPC 2015), devoted to the impact of high performance computing and communications on computer simulations. Full information is available at the 23^rd High Performance Computing Symposium (HPC 2015)

Abstract submissions are due on September 12, 2014, but are not compulsory. Full paper submissions are due on November 22, 2014. Topics of interest include:

• High performance/large scale application case studies
• GPU for general purpose computations (GPGPU)
• Multicore and many-core computing
• Power aware computing
• Cloud, distributed, and grid computing
• Asynchronous numerical methods and programming
• Hybrid system modeling and simulation
• Large scale visualization and data management
• Tools and environments for coupling parallel codes
• Parallel algorithms and architectures
• High performance software tools
• Resilience at the simulation level
• Component technologies for high performance computing

Looking forward to your submission

NVIDIA Shows Off Mobile Variant of Kepler GPU

NVIDIA used a recent graphics conference to demonstrate Project Logan, the low-power version of the Kepler GPU that it’s developing for smartphones and tablets. The GPU maker says that, when it ships, Project Logan will enable graphics capabilities for mobile devices that are on par with the most powerful desktop- and console-based gaming systems.

View more

The Modern GPU: A Graphic History

What do the Atari 2600 and Tianhe-2 have in common? It may be difficult to imagine, but both systems are examples of the use of cutting-edge graphic processers for their times. This demonstrates the fascinating evolution of the GPU, which today is one of the most critical hardware components of supercomputer architectures.

View more