GPU tagged news

NVIDIA and its ecosystem partners will deliver, over the next few months, the industry’s broadest set of software releases to developers using GPU Computing in their work. These updates feature major releases across a broad spectrum of GPU Computing development languages, tools and libraries. NVIDIA is releasing its R195 driver which includes new extensions to its OpenCL 1.0 conformant driver and toolkit. The new extensions include support for double precision, OpenGL interoperability and the new OpenCL Installable Client Device (ICD).

The Khronos™ Group today announced strong industry support and a wide range of shipping products utilizing OpenCL™ at SC09 (an international conference for high-performance computing). A number of demonstrations and tutorials from Khronos Group members highlighting the power and scalability of OpenCL will also be a major part of SC09. Khronos released a conformance suite for the OpenCL 1.0 specification in May 2009 that exhaustively tests both the functionality and numerical accuracy of OpenCL implementations before they are licensed to use the OpenCL trademark. A number of shipping products from working group members have successfully passed OpenCL conformance including products from AMD, Apple and NVIDIA. The current list of conformant products can be found on the Khronos website.

The Khronos Group will be demoing OpenCL at their booth at SC09 in Portland Oregon. This year, the Khronos Group is pleased to hand out a free, nicely-laminated OpenCL Quick Reference card to SC09 booth visitors. This comprehensive 6 page quick reference covers all important aspects of the OpenCL API. A complete schedule of Khronos events at SC09 is located on the Khronos Group SC09 event page, along with a signup form for guests. Space is limited, so please signup early to reserve your spot.

Top500.org will announce the new list of world’s most powerful supercomputers during this month during Supercomputing 09 conference held in Portland, Oregon between November 14-20. Among those announcements, the Chinese National University of Defense Technology is hoping to have their new system listed in the top ten, running in practice at 563.1 TFLOPS and theoretically at 1.206 PFLOPS using GPUs running Linpack, SOPEoptimized code. Their supercomputer is using 5120 AMD RV770 GPUs.

S3 Graphics announced the OpenCL 1.0 capable Chrome 5400E GPGPU processor. The 5400E features native support of OpenCL, the industry’s best GFLOPS per watt rating including, a OpenGL 3.1 / DirectX® 10.1 graphics engine, ChromotionHD video core for HD video decode including Blu-ray, H.264, and VC-1, a video encode engine, and an OpenVG 1.1 engine. The 5400E is the most versatile GPU for embedded applications requiring longevity, customization, performance, features, and low power. Complete details are available on the S3 Graphics website.

ARM announced the launch of the ARM® Mali Developer Center. The Developer Center offers a comprehensive suite of resources for graphics and embedded applications developers working with the Khronos OpenGL ES 1.1 and 2.0, OpenVG 1.0 and 1.1, as well as other APIs. Accessing these resources as members of the Mali ecosystem will enable developers targeting Mali graphics processing unit (GPU) platforms to bring best-in-class content to market.

NVIDIA is hosting two more seminars over the next few days which cover ‘Best Practices for OpenCL Programming’, and ‘An Introduction to GPU Computing and OpenCL’. The series will cover many topics including C for CUDA, programming to the OpenCL™ API , using DirectCompute and performance optimization techniques. The Webinars are presented by NVIDIA Developer Technology Engineering team and have NVIDIA staff online to answer Questions.

ExtremeTech discusses GPGPU computing on Windows 7. “Both Nvidia and ATI are committed to supporting DirectX 11 on their newest boards; and both now have early OpenCL drivers out as well. In particular, I expect both of their Windows 7 drivers will support OpenCL.” says Michael Miller.

MacResearch has posted part 6 in their series of OpenCL tutorials. In this episode, a real-world code that has been parallelized by porting to the GPU. The use of shared memory to improve performance is covered as well as a discussion of synchronization points for coordinated work within a work-group. Source code is provided.

Vivante Corporation today announced that Arkmicro Technologies, Inc. has licensed Vivante GPU IP for its newest mobile navigation and entertainment system-on-chip (SoC) designs. “The stunning visual effects offered by OpenGL ES 2.0 and OpenVG 1.1 are driving a wide range of location based applications in markets around the globe,” said Wei-Jin Dai, President and CEO of Vivante Corporation. Peter Shi, CEO of Arkmicro Technologies, added, “Vivante GPUs give us the outstanding visual graphics quality and performance we need to extend our leading media SoC family of solutions.”

A new project on Google code offers up Java/Scala bindings for OpenCL. OpenCL4Java is a library that provides three levels of Java bindings for OpenCL: C-style wrappings auto-JNAerated by JNAerator; Thin Object-Oriented wrappings that hide away the complexity of the C-style wrappings; ScalaCL, which is a kind of “parallel expressions for dummies” in Scala. A thread on the OpenCL message boards is available for feedback.