OpenCL 2.0 brings new graphics-chip power to software

The Khronos Group announced OpenCL 2.0 on Monday, an update designed to give graphics chips more independence and therefore power when running general-purpose software.

OpenCL provides a standard mechanism for software to tap into the computational power of graphics chips, and the Khronos Group standardizes it. It announced a provisional 2.0 specification the Siggraph 2013 conference this week, planning to make it final after a six-month feedback period.

Graphics processing units (GPUs) are geared for graphics chores, of course, but they're also becoming steadily more capable of handling jobs ordinarily assigned to the general-purpose central processing unit (… Read more

Intel not joining graphics chip alliance

Intel will not join a chip-related alliance aimed at making it easier for software developers to take advantage of the compute power locked up in graphics silicon.

Advanced Micro Devices, ARM, Imagination Technologies, MediaTek Inc., and Texas Instruments announced the Heterogeneous System Architecture (HSA) Foundation on Tuesday.

Here's how Lisa Su, an AMD senior vice president, described it in a phone interview with CNET.

"The point is, even if you put a really powerful CPU next to a really powerful GPU, if these [chips] don't interact and the applications don't know when it's better to … Read more

Will this tantalizing tech make it into the new MacBook?

What's in the next spin of the MacBook Pro? 0ne answer is obvious, others are guesswork.

The obvious? Intel's newest Ivy Bridge chip. The guesswork? A thinner MBP made possible by ripping out the optical drive, a la the MacBook Air. And here's some more wishful thinking:

Retina display: A Pro (or maybe a new Air at some point?) with a 2,560x1,600 resolution display? That's the resolution that Intel's Kirk Skaugen mentioned this week at an Intel conference in Beijing in connection with the upcoming Ivy Bridge chip. And he specifically used the … Read more

OpenCL adapts for control-freak programming

The Khronos Group announced version 1.2 of OpenCL today, an update that gives programmers tighter control over how they run software on graphics chips.

OpenCL is a standard interface that makes it easier for programmers to tap into the "GPGPU" idea--general-purpose graphical processing unit, which runs software such as game physics engines on a computing device's graphics hardware rather than on its central processing unit (CPU). With OpenCL, or with another technology such as Microsoft's rival DirectCompute, a programmer can use a GPGPU approach without having to worry about the particulars of individual graphics chips. … Read more

Apple issues MacBook Pro black-screen fix for Snow Leopard

One ongoing problem that has been affecting users of the 15-inch mid-2010 MacBook Pro is a black-screen bug that appears regularly when the computer is performing tasks like waking from sleep and manipulating graphics. While this problem became more prominent once OS X Lion arrived, a number of people have reported encountering this in Snow Leopard as well.

The issue was acknowledged by Apple and users were assured a fix was in the works. Shortly thereafter Apple released a MacBook Pro video update that included new video drivers and an update to the OpenCL framework in OS X. This update … Read more

'Sandy Bridge' driver update boosts Windows game performance

Intel has released a graphics driver update for its Sandy Bridge processors that boosts performance up to 37 percent for games on Windows 7 and Vista.

"This major graphics driver update for 2nd generation Intel Core processors with Intel HD graphics improves game performance by up to 37% on ULV platforms," Intel said in a statement.

ULV--or Ultra Low Voltage--processors are Intel's most power efficient and are typically used in thin and/or compact laptops such as Hewlett-Packard's updated Pavilion dm1 and Samsung Series 9.

ULV-based systems will see the biggest performance improvement, Intel said. "It is where some of the biggest gains are seen on the driver," Intel spokesman Dave Salvator said. But the driver update applies to all systems with Sandy Bridge processors sporting HD graphics. … Read more

Intel next-gen chip to support key Apple tech

Intel's next-generation processor is expected to add support for a key OS X technology that accelerates gaming and financial applications. That potentially means a more powerful MacBook Air in the future.

Listed as a "core" OS X technology, OpenCL "dramatically accelerates" applications by tapping into the special processing power of the graphics processing unit (GPU), according to Apple. It taps into what an Apple developer page states as the "the amazing parallel computing power of the GPU."

GPU-centric acceleration can be used for financial modeling, accounting applications, analysis on large media files, games, and media applications. In general, the GPU is much better than the CPU (central processing unit) at certain types of computations--thus the necessity of GPUs in games. … Read more

Intel confirms special accelerators in Sandy Bridge

At a Wells Fargo Securities conference earlier this month, an Intel vice president confirmed that Sandy Bridge will have special media acceleration capabilities, in addition to the oft-touted boost in graphics performance.

The Sandy Bridge processor--to be announced January 5--will pack media acceleration circuitry, Stephen L. Smith, vice president and director of PC Client operations and enabling at Intel, confirmed at a Wells Fargo Technology, Media, and Telecom Conference held on November 9-10. CNET reported this capability earlier. Part of the conference--when Smith was speaking--was captured on an audio stream.

"The other cool thing is dedicated circuitry for media … Read more

New OpenGL 4.0 aims to match DirectX 11

Aiming to keep pace with Microsoft and advance the computing frontier, the group behind OpenGL has announced a new version of its interface designed to make advanced graphics easier for programmers to handle.

OpenGL 4.0 adds more support for using a graphics processing unit (GPU) for other computing chores and for tesselation, which subdivides a region on a graphics object into many smaller patches for more detailed imagery. The technology got its start as a graphics library at pioneering Silicon Graphics but has grown into a standard that works on many different computer systems and overseen by the Khronos … Read more

ATI and Nvidia face off--obliquely

Nvidia and Advanced Micro Devices' ATI division are taking different approaches to graphics processing in the next generations of their products. Both strategies have strengths and weaknesses, and I think it's too soon to pick the eventual winner in this long-running fight.

Before I get into my analysis, I should say that Nvidia paid me to write a white paper on the implications of its new GPU architecture (code-named Fermi) for high-performance computing applications. The white paper was released as part of the Fermi launch event at Nvidia's GPU Technology Conference last week.

Nvidia also paid for white papers from two other well-known microprocessor analysts, Nathan Brookwood of Insight64 and my friend and former colleague Tom Halfhill of Microprocessor Report. UC Berkeley professor David Patterson wrote a fourth white paper, and Nvidia wrote one of its own. All of these works take a different approach to the subject; all are worth reading if you need to understand what Fermi is all about.

In short, I think the Fermi architecture has been more thoroughly white-papered than any graphics chip design in history. All five of these documents are available on the Fermi home page on Nvidia's Web site, and just in case that page is moved or changed, you're welcome to take advantage of my own mirror of my white paper.

I've spent much of the last several days reading these documents plus David Kanter's excellent article on Fermi over on his Real World Technologies site. David managed to get some details on Fermi that Nvidia didn't give to the rest of us.

I've also had time to go through the coverage of ATI's recent launch of the RV870, which is what Nvidia's Fermi-based chips will be competing against. The first of Nvidia's chips bears the internal code name of GF100, and it's huge. Here's a life-size photo:… Read more