RSS feed
MEVBench: A mobile computer vision benchmarking suite
Posted on 4-1-2012 by Zhenyu Ye Tags: application, vision, benchmark

MEVBench: A mobile computer vision benchmarking suite, is a paper published in IEEE International Symposium on Workload Characterization (IISWC) 2011. The source code of MEVBench is available on its website.

GPU cluster computing project results
Posted on 22-12-2011 by Cedric Nugteren Tags: GPU, CUDA, application, cluster

We have recently published the results of the GPU cluster computing project. In this project, 5 teams of post-master trainees each mapped an application on our 16-GPU cluster. On the special website you can find links to the results in the form of a 4-page paper and a website per project. The 5 applications are:

NVIDIA's LLVM-Based Compiler Becomes Open Source
Posted on 14-12-2011 by Zhenyu Ye Tags: GPU, CUDA, compiler

NVIDIA Opens Up CUDA Platform by Releasing Compiler Source Code, press release from NVIDIA. Early birds can register here to access the source code.

Vision - Hardware acceleration API for Computer Vision applications and libraries
Posted on 13-12-2011 by Zhenyu Ye Tags: programming, vision

Khronos planned to release the draft specification of the “Vision” API in Q4 2012. The “Vision” API is likely to become the counterpart of OpenGL for the vision domain. More info is available on the official website:

Embedded CUDA
Posted on 3-12-2011 by Cedric Nugteren Tags: GPU, CUDA

From the CUDA newsletter, there is interesting news on using CUDA for the Tegra 3 embedded platform. Is this the SoC for the Morpheus project?

Help Name the New ‘CUDA on ARM Dev Kit’
At SC11 we announced plans for an ARM-based GPU computing development kit to support the growing demand for energy-efficient HPC initiatives. The kit will feature a quad-core NVIDIA Tegra 3 ARM CPU accelerated by a discrete NVIDIA GPU. We are very excited about this technology and are looking for the perfect codename. Call up your creative juices and submit an idea. If your suggestion is chosen, you will receive a free DevKit when it launches next year!

Two Papers in Microarchitecture 2011 on GPU Architecture
Posted on 30-11-2011 by Zhenyu Ye Tags: GPU, architecture

The Micro-44 has two interesting papers on GPU architecture:

Low power Tegra 3 supercomputer at BSC
Posted on 16-11-2011 by Cedric Nugteren Tags: GPU, Tegra, supercomputing

On the website of the Barcelona Supercomputing Center there is information on the new Mont Blanc project. In summary, it is an energy efficient supercomputer build on top of NVIDIA Tegra 3 devices.

SEATTLE, WA — (Marketwire) — 11/14/2011 — SC11 — NVIDIA today announced that the Barcelona Supercomputing Center (BSC) is developing a new hybrid supercomputer that, for the first time, uses energy-efficient, low-power NVIDIA® Tegra™ ARM CPUs, together with high-performance NVIDIA® CUDA® GPUs.

BSC is planning to develop the first large scale system based on this technology, with a near term goal of demonstrating two to five times improvement in energy efficiency compared with today’s most efficient systems. BSC is showing the system design publicly for the first time at this week’s SC11 Conference, which runs Nov. 14-17 in Seattle, Wash., in exhibit booth #235.

IEEE Micro Special Issue: Hybrid CPU/GPU Computing
Posted on 25-10-2011 by Zhenyu Ye Tags: GPU, architecture, programming

IEEE Micro Sept.-Oct. 2011 is a special issue on hybrid CPU/GPU computing. Here are some highlights of the special issue: