On Tuesday Nvidia announced its plans to provide the source code for the new CUDA low level virtual machine (LLVM) based compiler. This will be available for academic researchers and software tool vendors so they can easily add GPU support for more programming languages and support CUDA applications on alternative processor architectures. The actual compiler itself resides in the latest release of the publicly available CUDA Toolkit (v4.1), and is enhanced to support Nvidia’s parallel GPUs.

“Opening up the CUDA platform is a significant step,” said Sudhakar Yalamanchili, professor at Georgia Institute of Technology and lead of the Ocelot project, which maps software written in CUDA C to different processor architectures. ”The future of computing is heterogeneous, and the CUDA programming model provides a powerful way to maximize performance on many different types of processors, including AMD GPUs and Intel x86 CPUs.”

LLVM is an open source compiler infrastructure with a modular design that makes it easy to add support for new programming languages and processor architectures. It is used for a range of programming requirements by many leading companies, including Adobe, Apple, Cray, Electronic Arts, and others.

Nvidia believes that releasing the source code to the LLVM-based CUDA compiler will enable alternate approaches to programming and thus accelerate the development of exascale computing. Researchers will have more flexibility in mapping the CUDA programming model to other architectures. It will also further the overall development of next-generation higher performance computing platforms.

Early access to the CUDA compiler source code is available for qualified academic researchers and software tools developers by registering here: http://developer.nvidia.com/cuda-source. To learn more about the Nvidia CUDA programming environment, visit the CUDA web site.

SOURCE via Nvidia

We’ve already seen quite a few companies lower their forecasts in the wake of the Thailand floods and subsequent hard drive shortage, and it unsurprisingly looks like Intel is no exception. The company issued a press release today advising that its fourth quarter revenue is now expected to come in at $13.7 billion, plus or minus $300 million, and not $14.7 billion (plus or minus $500 million) as previously expected. If you do the math, that means the company is taking around a $1 billion hit in revenue, due largely to a reduction in the worldwide PC supply chain that’s led to a drop in processor purchases. According to Intel, thing should begin to turn around in the fourth quarter, when it expects computer sales to be “up sequentially,” although it notes that hard drive shortages are expected to continue into the first quarter, with a recovery anticipated to take place over the first half of 2012.

The market firm estimates that the industry will ship 3.8 million fewer PC than previously predicted as hard drives just are not as easy to come by. As a result, IHS now believes that the PC industry will not grow by 9.5 percent, but only by about 6.8 percent, which equates to 84.2 million units. PC shipments typically drop by about 6 percent from Q4 to Q1, but the limited hard drive supply will cause the decline to reach 11.6 percent, iSuppli said.

IHS predicts that worldwide PC shipments in the first quarter of 2012 will amount to 84.2 million units, compared to the earlier forecast of 88 million. The new first-quarter forecast foresees an 11.6 percent sequential decline from 95.3 million units in the fourth quarter of 2011. While PC shipments typically decrease in the first quarter compared to the peak holiday-selling season in the fourth quarter, the drop in 2012 will be far sharper than the 6 percent historical average decline.

“The PC supply chain says it has sufficient HDD inventory for the fourth quarter of 2011. However, those stockpiles will run out in the first quarter of 2012, impacting PC production during that period,” said Matthew Wilkins, senior principal analyst, compute platforms for IHS. Wilkins expects the supply situation to improve during the first quarter. and a rebound of shipments could take place in the second half of the year. In fact, the market research firm said that there is a chance of hard drive excess supply in the market by the end of 2012 as the industry returns to full production in Thailand.

For the entire year, it appears that the PC industry will miss its 400 million goal once again. IHS believes that only 376 million PCs will ship, “partly due to the HDD shortage, along with weakening demand due to other factors.” IHS says that “the bulk in reduction in shipments will be in the notebook space, which is the area impacted by the HDD shortage.” The market firm also noted that PCs will continue to be impacted by the demand for notebooks and are likely to face strong headwind.

An announcement from Nvidia made at the most recent SC11 conference apparently got lost in a wave of supercomputing announcements. However, it’s a pretty significant change in Nvidia’s strategy on how to approach multi-core computing in the future and worth a note.

Together with Cray, PGI and CAPS, Nvidia announced a new parallel programming standard called OpenACC. OpenACC has been published as API that includes a range of compiler directives which describe code additions for C, C++ and Fortran to take advantage of accelerators to speed up code processing in highly data parallel environments. OpenACC is designed to apply to general parallel processors and can be used on GPUs as well as CPUs.

Cray, PGI and CAPS are planning to deliver initial compiler support for OpenACC Q1 2012. There was no information when Nvidia would provide a dedicated OpenACC compiler, but the company said that its CUDA architecture is “fully compatible and interoperable” with OpenACC. Nvidia did not indicate that it would drop CUDA anytime soon, but its participation in this group of companies suggests that Nvidia may be planning for a time beyond CUDA.

While CUDA code also runs on multi-core processors, the underlying architecture is proprietary technology. The advantage of OpenACC is a much broader range of devices support. Initially, there is no indication that OpenACC will have a huge impact in consumer applications as the group of OpenACC supporters is especially hoping for interest from developers in supercomputing applications fields in industry and academia covering topics such as chemistry, biology, physics, data analytics, weather and climate, intelligence, and many other fields.

SOURCE via Nvidia

Recently leaked slides suggest Korean computer outfit Zalman will soon jump into the ever-expanding graphics card market, initially partnering with AMD on its Radeon series. Known best for its quiet computing technologies, the company’s move to infuse GPUs with cooling solutions could enhance the performance of the cards, making overclocking a lesson in simplicity. The slides only show the AMD 6870, 6850, and 6770, but it’s feasible more models will appear when official news is released. Given AMD’s many board partners, differentiation is important to remain competitive and on their payroll — graphics cards and their overheating habits is Zalman’s cup of tea. Hopefully this brings more innovative products in the coming future, perhaps as early as CES. Check past the break to view the specifications breakdown for the aforementioned cards.

SOURCE via Anandtech

Two laptops touting the AMD’s as-yet-unreleased HD7000 series graphics of chips have been listed in sales brochures and driver download sites, according to German website PC Games Hardware.

According to the site, the chips have been listed as part of the specification in the forthcoming ASUS’ X53TK and a new 17inch HP Envy. The ASUS features an HD7670M to supplement its Fusion processor, while the HP has the higher performing Mobility Radeon HD 7690M on board.

Neither company, nor AMD, have commented on the story, and the parts remain officially unannounced. Drivers are available for download from HP’s site, though.

The important thing is that while there’s not a lot to choose between AMD and NVIDIA graphics on the desktop at the moment, when it comes to laptops mid-range Mobility Radeon cards have been performing far better for the price recently – even though they’ve been strangely difficult to find on sale. The X53TX

Sadly, as far as we know, this is unlikely to be the first outing for AMD’s forthcoming GPU architecture that it’s calling Graphics Core Next (GCN – also known as Southern Islands). GCN has a completely new internal design to the one which AMD has used (with modifications) since the launch of DirectX 10. While the entire HD7000 series of GPUs was originally planned to be based on GCN, recently leaked slides suggest that only the top end HD7900s will use it, leaving most of the range as a die shrink to 28nm of the existing designs.

Or could it? There’re plenty of rumours flying around about GCN and its ilk – as well as suggestion of a prelaunch event sometime this week.

SOURCE via Thinq

AMD released its A-Series APUs almost six months ago, and since then it’s seen Intel update the A-Series’ Sandy Bridge counterparts. So, it’s about time for the Llano laptop lineup to do the same, and the refresh has come in the form of seven spiffy new APUs. At the high end, there’s the quad-core A8-3550MX clocked at 2.0 GHz with Radeon HD 6620G graphics to supplant the older A8-3530MX chip. On the low end, the 1.9GHz dual core A4-3305M with Radeon HD 6480G graphics joins AMD’s A4-3300M. It’s a minor update all around, with most models seeing a 100MHz boost in turbo frequency over existing A-Series APUs.

SOURCE via AMD

When the certifications come in, you wipe a tear from your eye and ponder how proud you are. On Thursday, the Video Electronics Standards Association announced that AMD’s Radeon HD 6000 series graphics cards, including the high-end Radeon HD 6990, are the first to receive DisplayPort Version 1.2 certification. That means the cards are rated to support DisplayPort’s 5.4Gbps HBR2 data link speed and also feature increased display resolution, color depths and refresh rates, plus improved support for Full HD 3D stereoscopic displays. For the multiple monitor die-hards, there’s also better support for multiple monitors connected to a single DisplayPort receptacle to make your lives easier. Ah, it’s good to see a capable card series grow up a bit / become a man.

Super Talent has released a new range of “enthusiast” level MLC NAND Flash SSDs that offer the sort of face-melting speed that only comes when someone else is paying. The SATA Rev. 3.0 drives come with a SandForce 2200 processor (with a firmware tweaked for performance) in a 2.5-inch form factor that offers the usual 6Gb/s pipeline in: 64GB (540 Read / 490 Write), 120GB (540 / 510), 240GB (540 / 520) and 480GB (540/480) flavors. The drives begin shipping “today” and will set you back $109 / 60GB, $179 / 120GB, $365 / 240GB and $920 for the 480GB whopper.

SOURCE via Slashgear

Intel has notified its partners to prepare for a significant change in desktop processor supply in 2012, which clears the company’s product portfolio to accommodate the Sandy Bridge-E processors as well as the upcoming 22 nm product generation.

Intel is set to phase out the Core i7-860, Core i7-860, i7-930, i7-950, i7-960, i7-980 and i7-990X on the LGA 1366 platform to its end-of-life cycle. The LGA 1366 platform was first introduced in November of 2008. It represented Intel’s high-end desktop platform. To this day, this platform continues to hold its own in performance against to today’s top processors (Bulldozer, Sandy Bridge and Sandy Bridge-E). The LGA 1366 was replaced by the LGA 2011 (Sandy Bridge-E) on November 14, 2011.

Intel is set to send the Core i3-540, i5-650, i5-660, i5-670, i5-680, i7-860 and i7-870, along with the Pentium G6950 and G6960 on the LGA 1156 platform to its end-of-life cycle. LGA 1156 was first introduced in September of 2009. It represented Intel’s mainstream desktop platform. The LGA 1156 platform was short-lived with its replacement by the LGA 1155 (Sandy Bridge) in January of 2011.

The LGA 1366 and LGA 1156 boxed parts will be available for order until June 29, 2012. Tray SKUs will be available until December 7, 2012 or until supplies are depleted.

Along with the processor discontinuance, Intel also announced the phasing out of its H55, P55 and H57 chipsets.

SOURCE via Intel