News

NVIDIA today announced a new family of Tesla Kepler GPUs

NVIDIA today announced a new family of Tesla Kepler GPUs

Today NVIDIA today unveiled a new family of Tesla® GPUs based on the revolutionary NVIDIA® Kepler™ GPU computing architecture, which makes GPU-accelerated computing easier and more accessible for a broader range of high performance computing (HPC) scientific and technical applications. The new NVIDIA Tesla K10 and K20 GPUs are computing accelerators built to handle the…

OpenACC Gains Momentum with Growing Developer Tool Support

OpenACC Gains Momentum with Growing Developer Tool Support

The OpenACC standards group today announced growing support for OpenACC-supported development tools, and initial resultsfrom programmers who have been using the recently-released OpenACC compilers to accelerate research.

CUDA Compiler Goes Open Source

CUDA Compiler Goes Open Source

NVIDIA today announced that LLVM, one of the industry’s most popular open source compilers, now supports NVIDIA GPUs, dramatically expanding the range of researchers, independent software vendors (ISVs) and programming languages that can take advantage of the benefits of GPU acceleration.

Events & Training

Livestream GPU Technology Conference GTC 2012 Keynote Today

Livestream GPU Technology Conference GTC 2012 Keynote Today

Do not miss the opening keynote, featuring Jen-Hsun Huang, CEO and Co-Founder of NVIDIA. Hear about what’s next in computing and graphics, and preview disruptive technologies and exciting demonstrations from across industries. Jen-Hsun co-founded NVIDIA in 1993 and has served since its inception as president, chief executive officer and a member of the board of…

GTC Special Meetup: What You Always Wanted to Know About GPUs!

GTC Special Meetup: What You Always Wanted to Know About GPUs!

This is a special Meetup co-located with the GPU Technology Conference! Exchange ideas, meet experts, share code… all HPC & GPU, all practical, all cutting-edge.

NCSA to host FREE summer courses on heterogeneous programming

NCSA to host FREE summer courses on heterogeneous programming

NCSA will host two courses offered by the Virtual School of Computational Science and Engineering (VSCSE) this summer: Programming Heterogeneous Parallel Computing Systems and…

HPC

NVIDIA CEO, Leading Behavior and Space Scientists To Keynote At GTC 2012

NVIDIA CEO, Leading Behavior and Space Scientists To Keynote At GTC 2012

The greatest minds in the scientific, engineering, research and development communities from over 40 different countries will gather to discuss how GPUs are enabling breakthroughs across a range of scientific and commercial fields.

Call for Papers: Special Track on Rapid Development of Accelerators for the Biological Sciences

Call for Papers: Special Track on Rapid Development of Accelerators for the Biological Sciences

A special track has been added on the Rapid Development of Accelerators for the Biological Sciences. To design accelerators that have a significant impact on the biosciences, the computer science community must revolutionize the way accelerated applications and their underlying hardware are developed and deployed.

Registration open for XSEDE Extreme Scaling Workshop

Registration open for XSEDE Extreme Scaling Workshop

The National Center for Supercomputing Applications’ Blue Waters and the Extreme Science and Engineering Discovery Environment (XSEDE) projects are hosting the annual Extreme Scaling Workshop on July 15-16, 2012, in Chicago.

Publications

Realtime Computer Vision with OpenCV

Realtime Computer Vision with OpenCV

OpenCV have made it easier for application developers to use computer vision. They are well-documented and vibrant open source projects that keep growing, and they are being adapted to new computing technologies

Adaptive Subdivision Surface Reconstruction for Scattered Data in Reverse Engineering Based on GPU

Adaptive Subdivision Surface Reconstruction for Scattered Data in Reverse Engineering Based on GPU

In order to improve the efficiency of the algorithm, we implemented the reconstruction algorithm on GPU in parallel way and tested the program on several large scale data sets.

High-performance computing tools for the integrated assessment and modelling of social-ecological systems

High-performance computing tools for the integrated assessment and modelling of social-ecological systems

Integrated spatio-temporal assessment and modelling of complex social–ecological systems is required to address global environmental challenges.

Software

CUDA 5 Preview Release Now Available

CUDA 5 Preview Release Now Available

The CUDA 5 Preview release is now available to you via the CUDA Registered Developer program. CUDA 5 introduces several new tools and features that make it easier than ever to add GPU acceleration to your applications.

CUDA Compiler Goes Open Source

CUDA Compiler Goes Open Source

NVIDIA today announced that LLVM, one of the industry’s most popular open source compilers, now supports NVIDIA GPUs, dramatically expanding the range of researchers, independent software vendors (ISVs) and programming languages that can take advantage of the benefits of GPU acceleration.

Intel OpenCL SDK for OpenCL Applications 2012 with Ivy Bridge CPU and GPU Support

Intel OpenCL SDK for OpenCL Applications 2012 with Ivy Bridge CPU and GPU Support

Learn how the Intel® SDK for OpenCL* Applications 2012 now supports 3rd generation Intel® Core™ processors on both Intel® Processors and Intel® HD graphics 4000/2500. Join Suresh Rangarajulu, Marketing Manager for Intel® HD Graphics as he explains.

Code Example

Trip over threads to trap multicore bugs with Maze

Trip over threads to trap multicore bugs with Maze

What makes debugging of multiprocess and multithread applications so difficult? The first thing that comes to mind of every concurrent programmer is the lack of program execution reproducibility. The reason for such program behavior is the preemptive scheduling employed by real-time operating systems.

Whitepaper: The Xcelerit Software Development Kit

Whitepaper: The Xcelerit Software Development Kit

The paper presents the Xcelerit SDK, a parallel programming toolkit that leverages the dataflow programming model to efficiently use multi-core CPUs, graphics processors (GPUs), and combinations of these in a cluster (or grid) from a single high-level source code.

Hands-on tutorial: An introduction to OpenCL for HPC programmers

Hands-on tutorial: An introduction to OpenCL for HPC programmers

This is “programmer’s introduction” where we cover the ideas behind OpenCL but also show how these ideas are translated into source code. We will do this through a series of progressively more challenging examples

Also Recently

GPU Acceleration of Functional Neuroimaging

GPU Acceleration of Functional Neuroimaging

| 11 May, 2012 | 0 Comments

GPUs accelerate functional neuroimaging, by using three GPUs, 850 TB of data can be analyzed in 10 days, compared to 100 years with conventional software!

Continue Reading

Smoldyn on Graphics Processing Units: Massively Parallel Brownian Dynamics Simulations

Smoldyn on Graphics Processing Units: Massively Parallel Brownian Dynamics Simulations

| 9 May, 2012 | 0 Comments

In this paper, we analyze Smoldyn, a widely diffused algorithm for stochastic simulation of chemical reactions with spatial resolution and single molecule detail, and we propose an alternative, innovative implementation that exploits the parallelism of GPU

Continue Reading

Accelerating finite difference wavefield-continuation depth migration by GPU

Accelerating finite difference wavefield-continuation depth migration by GPU

| 8 May, 2012 | 0 Comments

We introduce a new hardware architecture, based on which the finite difference wavefield-continuation depth migration can be conducted using the GPU as a CPU coprocessor.

Continue Reading

A Parallel Front Propagation Method: Simulating geological folds on parallel architectures

A Parallel Front Propagation Method: Simulating geological folds on parallel architectures

| 4 May, 2012 | 0 Comments

In this thesis, a novel three-dimensional anisotropic front propagation algorithm for simulation of geological folds on parallel architecture is presented. The algorithm’s abundant parallelism is demonstrated on multi-core CPUs and GPU architectures.

Continue Reading

CUDA-MPI-FDTD implementation of Maxwell’s equations in general dispersive media

CUDA-MPI-FDTD implementation of Maxwell’s equations in general dispersive media

| 3 May, 2012 | 0 Comments

We present the first MPI-CUDA implementation of Finite-Difference Time-Domain (FDTD) discretization of Maxwell’s equations in dispersive media that uses the MPI API to assign each CPU node its share of the computational domain and GPUs to their corresponding CPU threads

Continue Reading