Intel cancels Larrabee GPGPU-chip

Intel has spent several years developing the Larrabee GPGPU-chip that was initially set for release in 2008. The multifunctional chip based on the x86 instruction set was to serve both as a parallel computing processor as well as a graphics card. Earlier this year, it already became known that the performance of the chip as GPU are to be compared to nVidia's GTX 285 card. During the last IDF, two demonstrations of the Larrabee chip were also given.

The last launch date of the chip was officially planned for the first quarter of 2010, but several rumors already mentioned the permanent cancellation of the Larrabee chip. Intel has since officially confirmed this. Though the graphics card is cancelled, the Larrabee project will remain in existence. It will continue the development of software and the SDK package.


Though the exact reason for cancellation remains unknown, it's likely that Intel was falling behind schedule with the development of the chip and matching software. If Intel were to continue the launch of the Larrabee, the card was to compete with nVidia's Fermi GTX 300 and AMD's Radeon HD5000 series, both significantly faster than the GTX 285 that the Larrabee was to be on par with.

The disappointing performance of the chip is not just caused by the delay of the chip itself, but also by the problematic development of the matching software. Though Intel has a lot of experience when it comes to developing x86 software to program the chip, the company isn't very used to graphics drivers. The multifunctional chip was also to retain backwards-compatibility with older drivers such as DirectX 9.0, while also being prepared for the future DirectX 12 version, making drivers difficult to program.

Intel initially planned to release the Larrabee as one of the fastest graphics cards at launch that could also be used for GPGPU applications. Since this won't be achieved in 2010, the graphics card was cancelled altogether. Though the first Larrabee chip will not see the daylight, the project will still continue, making it possible that Intel will release a more powreful Larrabee graphics card at a later point in time

Intel's 32nm Core i3/i5 in pre-order

Over a month before Intel will officially launch its new Core i3/5 dualcore processors, a German webshop has already added the new models as pre-orders. The online catalog shows two Core i3 models, the 530 and 540. These two models feature a clock frequency of respectively 2,93 and 3,06 GHz, which is locked due to the absence of Turbo boost. The CPUs do support Hyperthreading, allowing an operating system to work with four virtual cores. The integrated DirectX 10 GPU in these Core i3 chips is clocked at 733 MHz.

At the moment, these entry-level 32nm dualcores with integrated videochip cost 103,90 and 120,90 for respectively the i3 530 and i3 540. In the Core i5 series, the existing i5 750 quadcore will be joined by four 32nm dualcore 'Clarkdale' chips. These new models are branded Core i5 650, 660, 661 and 670, clocked at 3,2 GHz for the cheapest and 3,46 GHz for the most expensive model. Apart from these higher clock frequencies, the Core i5 models of Intel's new 32nm dualcores also support TUrbo Boost, allowing the frequencies to be increased when adequate cooling is present.

A remarkable processor is the Core i5 661: it is the only chip in the entire Clarkdale family to feature a higher GPU clock frequency, 900 MHz rather than the conventional 733 MHz. This does affect the TDP, which rises to 83 Watt. All other chips have an estimated TDP of 73 Watt. The pricetags of the Core i5 6xx models range from 160,90 for the 3,2 GHz model to 252,90 for the 3,46 GHz chip. The Core i5 660 and 661 can both be pre-ordered at a price of 175,90.

HD5950 to be released in early 2010?

HKEPC reports that AMD is working on a second dual-GPU graphics card in its DirectX 11 line-up. This new model is to be positioned below the HD5970 and will also be equipped with two Cypress chips. The difference is that each core will not feature 1600 but only 1440 active shader units, making it look more like a double HD5850 solution. The clock frequencies of this HD5950 card will be lower than those of the HD5970, otherwise the performance gap between the two would be too small.

Heat production can also be an issue when the original HD5850 clock frequencies are retained; the high-end HD5970 already uses specially selected GPUs which will run at a lower voltage. The Radeon HD5950 is to be equipped with two times 1GB of GDDR5 memory. It's still unclear how fast the HD5950 will be in comparison to an HD5970 or Crossfire HD5850 configuration, given the uncertainties in regards to the final clock frequencies.

Because AMD is already troubled by the huge demand, it seems unlikely that a second dual-GPU card will be released soon. HKEPC expects that the new model will new be introduced until early 2010.

Intel demonstrates processor with 48 cores

Chip manufacter Intel has recently demonstrated a new processor consisting of 48 seperate cores. Intel calls this chip the Single-chip Cloud Computer (SCC). This processor is derived from the Tera design, which was introduced in 2006. Initially, processors based on the Tera architecture were to feature 80 cores, though these have never been produced for industrial applications. The Tera design was a so-called 'proof-of-concept' design. This resulted in the creation of the Single-chip Cloud Computer, codenamed Bangalore.

While the Tera architecture consisted of 80 'simple' floating point processors, the SCC features 48 x86 chips, created using a 45nm process. The surface is specified at 567 mm². The 48 cores are divided in 24 ' tiles'. Intel calls these dual-core tiles. Each of these tiles is capable of running at a different clock frequency to limit power consumption. These tiles communicate with one another by means of a 6x4 2D mesh network, featuring a total bandwidth of 256 GB/s.

The design also integrates four DDR3 memory controllers, capable of adressing up to 64 GB of memory. Despite the specifications, the chip uses no more power than a modern quad-core processor. The usage of this SCC ranges from 25 to 125W, dependant on the required performance.

The name Single-chip Cloud Computing can be explained because the design of the Bangalore is similar to the method datacenters are used for cloud computping. Everything is connected to eachother to gather more computing power. Intel claims that the new chip will also reduce the space required for servers, as well as significantly drop their power consumption.

It's still unclear when Intel will release its new SCC processor. The company does report that it won't take much longer, given the fact presentations have already been given. An SCC chip already rendered a JavaScript-based 3D model. The motherboard used in combination with this chip is branded Copper Ridge and sports an LGA 1248 socket.

USB 3.0 to Deliver a Tenfold Speed Increase

Fasten your seat belts — data transfer is going into overdrive.

The ubiquitous Universal Serial Bus, better known as USB, is on track to make its first major upgrade in eight years — a tenfold speed increase over the current USB 2.0 standard. That means we’ll be able to rip music, video, photos from the vast array of peripherals we connect to our computers much more quickly, and it makes such up-and-coming devices as HD video cameras that much more practical.

USB 3.0 will also deliver greater power efficiency and the ability to recharge a wider variety of gadgets — and it will most likely mean the death of the competing standard known as FireWire.

To get a sense of the speed increase, consider this: Under USB 2.0 it takes about 10 minutes to transfer a high-def video from a Blu-ray disc. With USB 3.0, it will take just about a minute.

"What the user will see is really a much faster response time, less waiting, more productivity," says Patrick Moorhead, vice president of advanced marketing at AMD, one of the supporters of the USB 3.0
standard.

But none of this will happen tomorrow. The first USB 3.0 devices probably won’t show up until the end of
2009 or early 2010, say analysts. Users can get a glimpse into future devices sporting SuperSpeed USB as early as the annual Consumer
Electronics Show in January, and Wired.com will be there.

"The first places that you will see this show up is where you get the biggest benefits — HD video cameras and hard drives," says Moorhead.

The USB Implementers Forum, a nonprofit group founded by companies to promote the standard, will announce Monday the final set of specs that will clear the way for the adoption of USB 3.0 by device and component manufacturers.

"USB 3.0 will take USB 2.0 to the next level and take away performance as an issue for data transfer in many devices," says Brian O’Rourke, an analyst with research firm In-Stat. "USB 3.0 will make it even more pervasive across devices than it is today."

Since the USB specification was first introduced in 1996, it has changed the way we interact with our computers. USB has allowed everything from keyboards, mouse, PDAs, printers, digital cameras and personal media players — pretty much the entire spectrum of consumer electronics — to be connected to a host PC using a single standardized socket.

It has also made the process truly plug-and-play. Devices can be connected and disconnected without having to reboot the host computer and the technology offered perks such as allowing for many devices to be charged using the USB socket with no need for individual device drivers to be installed first.

Not surprisingly, USB’s ease of use and capabilities has meant it has become nearly ubiquitous. More than 2.6 billion USB-enabled devices were shipped in 2007, estimates research firm In-Stat.

And USB’s star will continue to rise, says the firm. Nearly four billion USB-enabled devices are expected to ship by 2012. Its ubiquity has meant that some manufacturers use USB ports and plugs for recharging devices such as Bluetooth headsets and phones without utilizing its data-transfer capabilities.

But USB 2.0 is getting a bit long in the tooth, with its slow speed, inefficient power usage and relatively small wattage. The new standard takes aim at all of those shortcomings.

Pour on the Speed

At a glance:USB 3.0
Faster: 10 times faster than USB 2.0 and six times faster than FireWire 800

Greater power efficiency: New interrupt driven protocol optimizes power management.

Better Power Output: Power output bump to 900 milliamps from 100 milliamps allows more devices to be charged faster via USB.

Backward Compatible: New connectors and cables will work with work with devices running the older USB 2.0
The new spec will support data transfers at 4.8 gigabits per second, or Gbps, nearly 10 times faster than the current standard’s 480 megabits per second and six times faster than FireWire 800. It’s also 400 times faster than the 12 Mbps offered by the original spec, USB 1.0.

USB 2.0 is also known as "Hi-Speed USB," while USB 3.0 will have the confusingly similar moniker "SuperSpeed USB."

The new USB 3.0 connectors and devices will be compatible with older USB ports (on devices using USB 2.0 and 1.0) but they will be limited to the older ports’ slower speeds.

Power and Efficiency

USB 2.0 uses a polling-based architecture, which means the host computer has to constantly check the bus to see if any devices are attached and if so, whether they are doing anything. As a result, that keeps the host computer busy, drawing power even when it’s not needed.

"It’s a problem when you attach a USB device to a laptop running on battery," says Steve Kleynhans, vice president, client computing for research firm Gartner.

USB 3.0 offers better specifications for power management. "We will move to an interrupt-driven architecture where your PC can ignore the connected device till the latter actually does something," says Kleynhans. "That can really lower the power consumption."

It also has better power output, 900 milliamps compared to 100 milliamps with USB 2.0. That means up to four devices can be charged from a single USB port and charged faster.


Standardizing the specifications for USB 3.0 hasn’t been easy. Two months ago, Intel released part of the draft specifications for USB 3.0
to developers resolving a dispute between itself, Nvidia and AMD over it.

Nvidia and AMD claimed that Intel was not sharing the specifications that potentially compete with it. Intel denied it.

"There was some debate between us," says Moorhead, "but we have buried the hatchet and we are all in the same boat now."

USB Implementers Forum chairman Jeff Ravencraft declined to be available for comment.

While
USB 3.0 devices are coming soon, consumers won’t immediately see all the benefits. "You can get the USB 3.0 speeds only when one 3.0 device connects to another," says Gartner’s Kleynhans. So the latest SuperSpeed USB-enabled devices connecting to older PCs running USB 2.0 or lower will experience data transfer rates that are much slower.

Killing FireWire

USB 3.0 is likely to signal the death of FireWire/IEEE 1394, a competing interface standard also known as i.Link and Lynx. Today, the industry is bifurcated between IEEE 1394 and USB 2.0. Many devices support both, though a single standard would be optimal.

"If we are all aligned, we are saving money and development time for the industry," says Moorhead.

With
Apple seemingly taking step away from FireWire, it seems like USB could gain the upper hand. Apple’s newly introduced MacBook computers lack a
FireWire port and instead has USB. MacBook Pro still sports FireWire
800.

That leaves Sony as one of the few remaining proponents of the standard.

"FireWire stably declining in most markets and USB 3.0 will continue that trend,"
says O’Rourke. "We could see USB emerge as the standardization of a high-speed interconnect."

Monday’s first USB 3.0 developer conference will be a big step towards that, say experts. "It’s for everyone in the USB value chain, from chipmakers to software makers to learn the new USB standard and get on it," says O’Rourke.

Wired.com

Micron places 16 GB DDR3 on a single module

Micron recently announced that the company has developed a new technology which allows them to place 16 gigabyte of DDR3-memory on a single module. It should also become possible to equip a server with up to nine of these modules, accounting for a total of 144 GB of memory. The so called load-reduced dual-inline memory modules (LRDIMM's) use Micron's 50 nm DDR3-memory chips with a capacity of 2 gigabit a piece. These chips operate at 1,35 V.

Micron reports that the term 'load reduced' means that the server memory will not stress the memory bus as much, allowing for higher data frequencies and capacities. This decreased load is achieved by using an Inphi iMB chip, or isolation memory buffer chip. Compared to the current registered DIMM's, Micron claims a stress-decrease of 50% for dual-rank LRDIMM's and even 75%^for quad-rank modules. Micron also mentions than an LRDIMM has 57% more bandwidth than an RDIMM.

At the moment, Micron is shipping samples of 8 GB LRDIMM-memory to its partners. It's expected that the mass production of 16 GB modules will start in 2010.

Overclocking AMD PhenomTM II Processors to the Limit

Overclocking AMD PhenomTM II Processors to the Limit

PC speed-freaks from across Europe will be pushing their processors to the limit in a series of extreme overclocking trials over the next month. The trials, which have been organised by AMD (NYSE:AMD), will see forum users from 19 leading technology forums from across the continent compete in a series of pedal-to-the-metal contests where they will attempt to push AMD platform technology, codenamed “Dragon,” to the fastest speed possible. During the trials, the contestants will try to clock up the highest scores in categories such as 3D Mark performance, calculation speed and highest CPU clock speed.(i)

The first of these events was held in London on Thursday 23rd April 2009, where sparks flew, literally! In this special event,eight teams of daredevil journalists went head to head in an attempt to break through the sonic wall in 3D Mark05 and CPU clock speeds. Things got so fast and so furious that sparks actually flew from one of the team’s “Dragon” rigs!(i)

It was a closely fought battle, but two winners emerged victorious. Clive Webster from Custom PC won the 3D Mark05 competition with a score of 24,689, while Tim Smally & Rich Swinburne from Bit-Tech won the CPU clock frequency competition with a speed of 4,211MHz. For this special opening event, both winning teams won a prize of $1000 each. The Custom PC donated their winnings to the Phyllis Tuckwell Hospice and the Bit-Tech team gave their winnings to the Myton Hamlet Hospice.
Video to the overclocking event in London