by Anton Shilov, XbitLabs
Manju Hegde, the former founder and chief executive of Ageia and the former manager of Nvidia Corp.’s CUDA and PhysX initiatives, has joined Advanced Micro Devices as corporate vice president of Fusion Experience Program, under which he will work with software developers to promote AMD’s heterogeneous multi-core processors known as accelerated processing [...]

[Read more →]

NVIDIA announced today that ACUSIM Software, a leading provider of computational fluid dynamics (CFD) solutions widely used by engineers and scientists involved in product design, has integrated support for NVIDIA® Tesla™ 20-series GPUs into the company’s latest AcuSolve 1.8 release.
Performance tests of the general-purpose finite-element-based CFD flow solver have demonstrated up to a 2x boost [...]

[Read more →]

by Arthur Cole
It seemed like for a while the graphics processing unit (GPU) was on the verge of swarming into everyday enterprise infrastructures. The more companies like Nvidia, Intel and AMD pushed the platform’s capabilities, the more it appeared that we would soon see GPUs pushing alphanumerical data for standard business applications.
That drive took a [...]

[Read more →]

XMOS has released the XMOS Timing Analyzer (XTA) that accelerates the design of embedded applications using its family of XCore processor arrays.
According to David May, chief technology officer of XMOS, together with the deterministic nature of XMOS XCore processors, XTA makes it simple to develop software that meets timing deadlines – every time it executes. [...]

[Read more →]

by Agam Shah, IDG News
Intel won’t ship its Larrabee graphics processor, but elements of the chip will be used in future server and laptop processors, a company spokesman said on Wednesday.
The company on late Tuesday said it wouldn’t bring its first discrete graphics processor to market, ending speculation about the chip’s fate after the company [...]

[Read more →]

In a blog post, Intel spokesman Bill Kircos said the chip giant will not release a discrete graphics chip anytime soon, putting an end to its “Larrabee” project. However, Kircos said Intel will continue enhancing the graphics capabilities integrated into its CPUs, and said Intel officials at the ISC 2010 show will outline an HPC [...]

[Read more →]

by Marcus Yam
Last month Intel announced that it was shipping systems with its experimental 48-core processor. Now we get to see what a system with the radical chip looks like.
X-bit labs caught the supercomputer on chip (SCC) system on demonstration in Europe, which runs on an experimental “Copper Ridge” motherboard with integrated I/O and graphics [...]

[Read more →]

By Thomas Antony in Tech News
For the last three years we have been hearing about how Intel is all set to shake up the GPU market with their LarraBee discrete GPU. But it was later downsized into a “software platform” last year and now Intel has finally decided to shelve the project completely. According [...]

[Read more →]

by Michael Feldman, HPCwire Editor
Supercomputer maker Cray did a pre-launch of sorts for its upcoming “Baker” supercomputer on Tuesday, giving the machine its official product designation: the XE6. Although the company won’t be shipping the hardware until later this year, there’s already a backlog of orders for the petascale machines, and Cray is setting the [...]

[Read more →]

By Katherine Bourzac, MIT Review
Anticipating the ever-increasing computing demands of tomorrow’s mobile devices, chip makers are rolling out compact designs for processors that boost performance while drawing less battery power.
Designing processors for mobile devices requires more than simply reproducing desktop computer architecture in a smaller device. The tinier transistors get, the more electricity they leak, [...]

[Read more →]

At the Research@Intel, Europe event in Brussels Intel Labs Europe showed a new technology that could dramatically improve performance of microprocessors when running older software. The technology called “Anaphase” has been developed at Intel Labs Barcelona.
Current processor designs have shifted towards multi-core. Nevertheless single thread performance remains very important as many applications have limited thread-level [...]

[Read more →]

When Intel ran into a performance wall with CPUs about a decade ago, it was the end of the single-core era of chips. As the thinking went, if chipmakers couldn’t get processors to 4GHz, 5GHz and beyond, then they would get performance by dividing up the work among multiple CPU cores.
That’s great for apps that [...]

[Read more →]

Google I/O Google’s back-end infrastructure is now running applications built with its new-age Go programming language.
“We’re already using Go internally at Google for some production stuff,” Robert Pike, one of Go’s developers and a former member of the Unix team at Bell Labs, said today during a question and answer session at the company’s annual [...]

[Read more →]

By Michael D. McCool
Parallel programming is challenging for a number of reasons. In addition to all the challenges of serial computation, parallel programs can also suffer from race conditions and deadlock, and even if correct may be non-deterministic, which complicates testing. Achieving high performance with a parallel program also requires minimization of contention for limited [...]

[Read more →]

By TED NEEDLEMAN
It used to be easy to figure out how much computing horsepower your PC has — computers had one processor with a single core, which ran at a given clock speed.
Thanks to the rise of multicore processors such as Intel’s recently released i7-980X, today’s computer processors have as many as six processors packed [...]

[Read more →]

by David Bell and Greg Wood
As application complexity continues to grow we have reached a limit on increasing performance by merely scaling clock speed. To meet the ever-increasing processing demand, modern System-On-Chip solutions contain multiple processing cores. The dilemma is how to map applications to multicore devices. In this paper, the authors present a programming [...]

[Read more →]

by Michael Feldman, HPCwire Editor
Microsoft’s ambitions have always been big. A quarter of a century ago, the company’s primary mission was to put a consumer-friendly computer on every desktop. At least in the industrialized world, they can consider that mission accomplished. Now they want to do nothing less than model the world.
Actually, what they’re envisioning [...]

[Read more →]

Dell Inc. is set to test multicore ARM processors from Marvell Technology Group for possible use in low-power servers for large data centers. The company has already shipped a few thousand low-power servers based on x86 processors from Taiwan’s Via Technologies Inc.
Separately, an executive from IBM Corp. said Big Blue backs the trend toward new [...]

[Read more →]

Advantech, a global manufacturer of telecom computing blades and multicore network platforms, announced today the expansion of its AdvancedMC product range with the introduction of the AMC-4201, based on Freescale Semiconductor’s QorIQ™ P4080 multicore processor. Aimed at further increasing Advantech’s presence in Tier-1 OEM equipment, the AMC-4201 is targeted at new infrastructure designs in [...]

[Read more →]

By Kurt Keutzer and Tim Mattson
The trend has been well established — parallel processors will dominate most, if not every, niche of computing. Ideally, this transition would be driven by the needs of software. Scalable software would demand scalable hardware and that would drive CPUs to add cores. But software demands are not driving parallelism. [...]

[Read more →]