Q&A with Greg Kurtzer from the GPU Technology Conference
Rags Srinivas talks to Greg Kurtzer, a serial Open Source contributor at the GPU Tech Conference.
Apple Plans to Develop a Fully Custom GPU Architecture
Apple will develop its own custom graphics architecture to power the GPUs for its future devices, according to UK-based firm Imagination Technologies, Apple’s current GPU provider. The new GPUs should be ready in 15 months to two years' time and will be the first Apple-made GPUs that will bear no resemblance to Imagination Technologies’.
Apple Proposes a New 3D Graphics Standard Called WebGPU
Apple has proposed a new GPU API for the browser, called WebGPU. Google has another solution called NXT in the development.
Nvidia Introduces cuDNN, a CUDA-based library for Deep Neural Networks
Nvidia earlier this month released cuDNN, a set of optimized low-level primitives to boost the processing speed of deep neural networks (DNN) on CUDA compatible GPUs. The company intends to help developers harness the power of graphics processing units for deep learning applications.
Hadoop Jobs on GPU with ParallelX
The MapReduce paradigm is not always ideal when dealing with large computationally intensive algorithms. A small team of entrepreneurs is building a product called ParallelX to solve that bottleneck by harnessing the power of GPUs to give Hadoop jobs a significant boost.
Amazon re:invent roundup
Amazon announced a number of new services at the recent re:invent conference in Las Vegas: Amazon WorkSpaces - Desktop Computing in the Cloud, Identity and Access Management using SAML, Amazon AppStream - Delivering Streaming Applications from the Cloud, Amazon Kinesis - Streaming Big Data, CloudTrail - Capturing AWS API Activity, Postgres support in RDS and new EC2 instance types
Harlan with Support for Rich Data Structures, Trees, Ragged Arrays and Higher Order Procedures
Harlan programming language developed by Eric Holk, a doctoral student at Indiana University provides support for rich data structures, trees and ragged arrays in addition to higher order procedures.
GPU.NET 2.0 Brings HPC to Linux and Mac
GPU.NET 2.0 supports Mono, enabling building and deploying computational intensive applications for Linux and Mac OS X along the already supported Windows.
WebCL Brings Parallelism to the Browser
WebCL brings parallelism support to the browser, enabling JavaScript developers to write data intensive web applications. Nokia has a prototype for Firefox while Samsung has one for WebKit browsers.
Moonlight Playbacks Video Directly on GPU
Moonlight has been enhanced to support GPU-accelerated video playback. Silverlight 5 will do the same, but with extra features.
Moonlight 4.0 Preview 1 Has Been Released
Moonlight 4.0 Preview 1 includes all the Silverlight 3.0 API and a part of Silverlight 4.0 API. New features include: Out-of-Browser, GPU-accelerated graphics, 3D transformation, shaders, V4L2 video capture, H.264 and AAC, and better smooth streaming.
Targeting the GPU with GPU.NET
GPU.NET is a managed solution integrated with Visual Studio 2010 for .NET developers and aimed at creating calculation intensive applications for GPU.
Amazon Offers Cluster GPU Instances
Amazon has announced the availability of Cluster GPU instances for high performance applications starting with an instance of 2 NVidia Tesla GPUs and going up to a cluster of 128 or more instances, appealing to financial analysis, imaging, biology, simulation, and other domains.
Moonlight Leaps Ahead of Silverlight with Hardware Accelerated Pixel Shaders
Recently David Reveman added significant amounts of hardware rendering to Novel’s Moonlight. This puts it in the lead over Silverlight, offers only a limited amount of hardware rendering support.
Aparapi: New, “Pure Java” API for Executing Arbitrary Compute Tasks on GPUs Unveiled at JavaOne
InfoQ catches up with Gary Frost from AMD who unveiled an alpha release of Aparapi, an API that allows programmers to write logic in Java to be executed on a GPU. GPUs are the massively parallel hardware acceleration chips originally installed in PCs to boost graphics rendering performance but that are now pushed to other kinds of compute-intensive tasks that have nothing to do with graphics.
