Posts Tagged ‘processors’

Android mini computer selling for just US$74

May 18th, 2012

Enthusiasts of embedded computing seem to be spoilt for choices nowadays.

A Chinese-made computer, that’s slightly larger than a typical thumbdrive, can now be bought online for just US$74. The fee includes free shipping to a number of Asian countries such as Japan, Malaysia and Singapore.

The MK802 is similar to the Cotton Candy computer-in-a-stick. Both are powered by ARM processors and support Android or other ARM-compatible Linux operating systems. It comes with a Mali 400 GPU that enables it to output 1080p videos through HDMI.

Despite its small size (it weighs just under 200g), the MK802 has a microSD card slot to add to its built-in 4GB flash storage, together with a full-sized USB port and a micro-USB version. Wi-Fi is also supported.

The more expensive US$199 Cotton Candy does have better hardware, including a dual-core ARM chip compared with the single-core version on the MK802. The Cotton Candy can also be plugged directly into a HDMI port–the MK802 requires an HDMI cable.

The low cost of ARM processors coupled with the popularity of Android appear to have led to more embedded computing solutions for hobbyists. The US$35 Raspberry Pi is another inexpensive mini computer that seems to be popular among enthusiasts for tasks like programming and video streaming. These devices could also serve as educational tools for children in less developed countries, especially when installed with the right applications.

Source:http://asia.cnet.com/android-mini-computer-selling-for-just-us74-62215414.htm

Nvidia Files Patent For Hierarchical Graphics Processors

May 1st, 2012

Filed earlier this year as an extension of the existing patent 7,634,637, Nvidia has applied for a patent that describes a hierarchical processor array. The idea is that there are two or three tiers of processing cores with dedicated functions that alleviates a problem in core design that results in increasingly wide and ineffective graphics rendering pipelines.

Those pipelines include various shaders, such as a vertex shader unit, a geometry shader, a pixel shader, among others, and each of these shaders are getting wider at every level of parallel execution hardware. Nvidia says that “each massively parallel stage in a stage-by-stage pipeline tends to provide little granularity of control of portions of each parallel stage”, each “massively parallel stage becomes unwieldy and prohibitively time-consuming to design”. Additionally, “the level of utilization may decrease, as the massively parallel stage struggles during operation to find sufficiently wide units of work to fully occupy the data path.”

To keep parallelization efficient, the company describes a processor with multiple levels of processing hierarchies with “multiple classes of graphics operations being associated with a different stage of graphics processing.” However, each level would also include at least one module that is capable of processing all graphics functions. There would also be one top-level component that is able to distribute certain classes of work to lower level classes of processors. The patent specifically mentions a third-level class in the processor hierarchy that would be reserved for general purpose computations, as well as “at least one” specialized graphics function module that “is capable of performing a class of graphics operations carried out based on frame buffer data for scan out to a display.”

According to the patent application, the resulting core design is “advantageously configured to execute a large number of threads in parallel, where the term ‘thread’ refers to an instance of a particular program executing on a particular set of input data.” For example, a thread would refer to the execution of a single vertex in the shader program or individual pixel being processed by the pixel shader.

Besides greater processing efficiency, the document states that a hierarchical structure of multithreaded core array also enables a faster design of “derivative chip designs.” Faster GPUs could be built simply by “adding additional components at one or more of the levels of the hierarchy”.

Source:http://www.tomshardware.com/news/nvidia-patent-gpu,15466.html

Intel offers support package for small businesses

April 11th, 2012

Intel on Tuesday announced a new suite called Small Business Advantage that takes advantage of specific features baked into the company’s Core processors to maintain and secure PCs.

The SBA tools are targeted at small businesses that cannot afford separate maintenance personnel, said an Intel spokeswoman. SBA uses hardware and software tools to perform backups, updates and maintenance tasks such as disk defragmentation, the company said. SBA can start PCs after work hours for maintenance and backup tasks.

SBA is a slimmed-down package of PC maintenance tools provided with Intel’s vPro platform, a hardware and software package targeted at larger businesses that makes it easier for system administrators to remotely manage and secure PCs. SBA takes advantage of features in Core i3, i5 and i7 processors based on the Sandy Bridge microarchitecture, much like the vPro platform.

All SBA software is packed into a single interface, which makes it easier for technically unsavvy small business owners to keep PCs secure and up to date, Intel said. One feature is Software Monitor, which tracks security software like antiviruses and issues alerts in case the software stops running. Software Monitor is similar to a feature called Agent Presence in vPro, and the application is stored below the operating system at the firmware level.

A feature called Local Maintenance Timer (LMT) allows a PC to power itself on from an off-state at a prescheduled time, after which it can carry out maintenance and backup tasks. Another feature called USB Blocker allows PCs to block access to USB devices such as flash drives or cameras. The settings can be configured to specify which USB devices are allowed access to the PC.

Intel will sell the package to computer makers, which can then plug the software into PCs.

Source:http://www.computerworld.com/s/article/9226074/Intel_offers_support_package_for_small_businesses

AMD Whips Up Two New FX Processors

March 22nd, 2012

While power users sit in patient anticipation of Intel’s Ivy Bridge platform, which seems like it’s taking forever to launch, AMD just keeps doing its thing. AMD’s “thing,” of course, is competing on the bang-for-buck front, and towards that end, the Sunnyvale chip maker is reportedly getting ready to launch a couple of new FX Series processors.

Turkish website Donanimhaber got its hands on a leaked roadmap of sorts and it shows AMD slotting in the FX-4130, a quad-core CPU clocked with a base frequency of 3.8GHz and a 3.9GHz Turbo clockspeed. It will feature 4MB of L2 cache and 4MB of L3 cache, a 125W TDP, and reside at the lower end of AMD’s FX lineup.

The other upcoming chip is a six-core FX-6130. This one has a base frequency of 3.6GHz, Turbo clockspeed of 3.9GHz, 8MB of L2 cache, 6MB of L3 cache, and a 125W TDP.

Pricing hasn’t been announced for either chip, though the FX-4130 sits below the FX-4100, which sells $115, and the FX-6130 falls in between the $145 FX-6100 and $165 FX-6200, so probably figure around $100 for the former and the $150ish for the latter. Both are scheduled to launch in the second quarter of 2012.

Source:http://hothardware.com/News/AMD-Whips-Up-Two-New-FX-Processors/

AMD Quietly Rolls Out a Pair of Athlon II X4 Processors

February 9th, 2012

AMD apparently isn’t finished attaching its Athlon II moniker to Llano parts, as evidenced by a couple of new Athlon II X4 processors the chip maker quietly introduced this week. Specifically, AMD added the Athlon II X4 638 and 641 to its official product price list. Both of these are based on AMD’s Llano architecture and ship without an integrated graphics core, but do slip into socket FM1 setups just like other Llano CPUs.

The Athlon II X4 638 is a quad-chip with four processing threads clocked at 2.7GHz. It has 4MB of L2 cache, a TDP of 65W, and is priced at $81.

Interestingly, the 641 is also priced at $81, but is 100MHz faster at 2.8GHz. It has a comparably high TDP at 100W, which is something to consider if you’re building a small form factor system or any type of setup that requires low power. Otherwise, the 641 boasts the same amount of L2 cache (4MB) along with identical core and thread counts.

Source:http://hothardware.com/News/AMD-Quietly-Rolls-Out-a-Pair-of-Athlon-II-X4-Processors/

Intel Donates Processors for Teaching, Research

January 28th, 2012

Intel, one of the world’s largest semiconductor chip makers, has donated a dozen computer processors to the Electrical and Computer Engineering (ECE) Department for use in research and teaching.

The donation, worth nearly $14,000, consists of six Intel Core i5-2500 and six Intel Xeon E7540 processors.

“These are powerful processors,” says Assoc. Prof. Yan Luo, who received the chips in behalf of the department. “They have multiple cores that can speed up computations of large-scale applications, which require a lot of CPU cycles.”

Luo says the chips will be used for scientific computations, modeling and simulations, machine-learning algorithms, high-performance network packet processing and virtualizations.

“We will also use them to teach undergraduate and graduate students how to write parallel programs,” he says.

Luo has had long-term involvement with Intel’s research labs and educational programs.

“In 2010, the company donated to the department two computer servers with powerful processors for use by our students in the lab,” he says.

The Cornell Cup Competition

Intel and Cornell University are hosting for the first time this year the Cornell Cup USA, a national competition that empowers undergraduate and graduate students in science and engineering to become inventors of the newest innovative applications of embedded-design technology.

UMass Lowell is one of 24 teams that have been selected to compete in the Cup’s finals, to be held in May at Walt Disney World in Florida. Other finalists include teams from UMass Amherst, MIT, Georgia Tech, Worcester Polytechnic Institute, UC Berkeley, Columbia, Penn State, Purdue and USC. The overall winner will receive a $10,000 prize.

UMass Lowell’s entry — called the “JouleCycle” — is a gaming system that helps people exercise regularly, achieve caloric balance and control obesity.

“Obesity is recognized as a serious public health problem that leads to many illnesses, such as diabetes and heart disease,” says Luo. “According to the Centers for Disease Control and Prevention, about a third of U.S. adults and 17 percent of children and adolescents aged 2 to 19 years are obese.”

The JouleCycle is built around a human-powered bicycle and an Intel Atom development board that uses no battery. The game player generates the electricity needed to run the Atom board and its customized hardware and software by pedaling.

“To make the game interesting and enjoyable, the power generated by the player determines the game’s themes and levels,” he says.

The JouleCycle Team consists of ECE seniors David Cote and John Foley, ECE sophomore Andrew Hajj and Mechanical Engineering master’s student Michael McGinley. Profs. Yan Luo of ECE and Hongwei Sun of Mechanical Engineering are the faculty advisers. The team received $2,500 in funding from Intel to build the system and help cover travel expenses to Florida.

Source:http://www.uml.edu/News/stories/2011-12/Intel-chip-donation.aspx

HP to use ARM processors in new line of servers

November 2nd, 2011

Breaking from its long-standing reliance on computer chips from Intel (INTC) and AMD, Hewlett-Packard (HPQ) on Tuesday unveiled a new line of servers using energy-efficient processors based on designs from an upstart company better known for technology used in mobile phones.

The new processors take up less space and consume only a tenth of the electricity needed to power conventional servers, according to the Texas startup Calxeda, which developed the new chips from designs it licensed from the British firm ARM Holdings.

That could provide huge savings on energy bills for companies that are rapidly expanding their data centers, especially Internet server farms that provide the back-end computing for a growing army of workers and consumers who use smartphones and other mobile devices to access information online, HP executive Paul Santeler said Tuesday.

Traditional server farms use large amounts of power to run the computers and the cooling systems needed to keep them from overheating. HP — which competes with IBM, Dell and other tech giants in the $100 billion market for data center hardware — is betting its new servers will appeal to customers

who want to lower their operating costs.

While showing off the new machines at HP’s Palo Alto headquarters, Santeler said they are the first of several HP models that will use power-sipping technology initially developed to let mobile phones and other gadgets run all day on a single battery charge.

HP also designed the servers with hardware and software that take advantage of the processors’ compact size and enable them to share other system components such as memory, switching gear and cooling equipment. That further reduces their space and power requirements.

It’s unclear how popular the new servers will be, since lower-power chips have not generally been used for extremely complex, high-speed computing in the past. HP said the first machines, code-named Redstone, will be available for a limited number of customers next year.

Initial users may include companies that operate social media sites and other Web-based services, which carry out a limited number of computing tasks on a huge scale, Santeler said. At least for now, he said, “it’s not for every type of application.”

But Forrester analyst Richard Fichera said he expects the technology will evolve and be adopted for wider uses, first in large commercial data centers and later in smaller computer operations.

That could be troubling for Intel and AMD, which have been HP’s biggest chip suppliers. Intel makes the processors used in the majority of servers sold by HP and other computer-makers today.

Chips that use ARM designs have already emerged as a threat to Intel in another major segment of its business, as smartphones and tablet computers that use ARM-based processors cut into sales of personal computers, which also mostly run on Intel or AMD chips. Intel has developed its own line of energy-efficient chips for mobile computing gadgets, but it has lagged in that market.

HP executives were careful to say they don’t plan to stop making traditional machines, often referred to as “x86″ servers because of the processor designs they use. “This is in addition to, not a replacement,” Santeler said.

HP also has plans to build new servers around Intel’s power-efficient Atom chip, he added. An Intel spokesman said his company has been working on so-called microserver designs for several years and noted that startup SeaMicro is already making servers that use Atom processors.

Intel sees the market as fairly small for now, added spokesman Radoslaw Walczyk, but he said: “People are always evaluating different approaches.”

Unlike Intel, ARM does not make chips but licenses its designs to several manufacturers. Calxeda is a startup funded in part by ARM Holdings and other investors.

Source:http://www.siliconvalley.com/news/ci_19240331

Get Adobe Flash playerPlugin by wpburn.com wordpress themes