The Core Truth

June 4th, 2008

AMD announces Puma laptop platform, Mobile Radeon 3800 GPU

Posted by John Morris @ 9:43 am

Categories: Intel, AMD, Power conservation, multicore processors, notebooks, dual-core processors, PC gaming, PC graphics

Tags: Mobile, Advanced Micro Devices Inc., Laptop Computer, Radeon, GPU, Puma, Radeon 3200, Puma Platform, ATI XGP, Chipsets

Located in the PC component capital of the world, Computex has become the tradeshow for chipsets, so it’s no surprise AMD chose to announce its new mobile platform here in Taiwan today. (You can watch the press conference here.) Known by its code-name Puma, the platform itself doesn’t have a brand name, but it consists of four parts:

• AMD Turion X2 Ultra dual-core processors
  Mobile 7-series chipset: AMD M780G and AMD SB700 with Radeon HD 3200 integrated graphics
• Mobile Radeon HD 3800 series GPUs
• 802.11n controllers from Atheros, Broadcom, and Ralink

Designed for mainstream laptops for both consumers and small- and medium-size businesses (SMB), Puma includes more sophisticated power management features, better 3D graphics and HD video performance, and hybrid graphics–a feature AMD was the first to introduce with the 780 desktop chipset back in March (Nvidia’s new nForce780a desktop chipset also support what it calls Hybrid SLI with GeForce 8800 series GPUs).

On a broader scale, AMD says Puma is a big step toward its vision of an APU that combine the CPU and GPU on a single piece of silicon, a project that would first come to full fruition with a processor code-named Shrike sometime in 2010. It would also validate AMD’s acquisition of ATI.

“There’s only two companies that can generate high-performance, leading-edge microprocessors in volume. And there are only two companies in the industry that can generate leading-edge GPUs in volume,” AMD President and COO Dirk Meyer said. “And we happen to be the only company that can do both.” Read the rest of this entry »

May 29th, 2008

Via finally releases new Nano processor

Posted by John Morris @ 9:55 am

Categories: Intel, Power conservation, notebooks, semiconductors, Nvidia, UMPC, VIA Technologies, Energy efficiency

Tags: VIA Technologies Inc., Watt, Nano, C7, Ultramobile PCs (UMPCs), Processors, Tablets, Hardware, Notebooks & Tablets, Emerging Technologies

Early this morning Via Technologies finally announced is new Nano processor, better-known by its code name, Isaiah. The Nano will deliver two to three times the performance of the current C7 with roughly the same power requirements, according to the company.

Via has spent years working on Nano, which represents a major leap forward from the C7. By now, the technical details are well known. Specifically, Nano has many of the microarchitectural features–64-bit x86 instruction set, superscalar pipeline, speculative and out-of-order execution of program instructions–found in advanced Intel or AMD chips.

Manufactured by Fujitsu using 65nm process technology, Nano has 94 million transistors–roughly twice as many as the C7–and measures 63.3 square millimeters. That translates to about 1,000 chips on a single, 300mm silicon wafer. Nano is significantly larger than both the C7-M (30 square millimeters) and Intel’s Atom (25 square millimeters), which both have a much simpler microarchitecture. Nano is pin-compatible with C7, which means OEMs that already sell small form-factor desktops, ultraportables or UMPCs with Via processors should be able to easily upgrade.

Because Nano offers significantly better performance than the C7, Via is going after a broader market. The L version (for Low Voltage) is designed for mainstream desktops and notebooks, and it will compete directly with Intel’s low-end mobile processors such as Celeron-M and Core 2 Solo. The U version (Ultra Low Voltage) version is designed for mini-notebooks and UMPCs, and it will compete with Intel’s new Atom, aka Silverthorne. All Nano processors have 1MB of L2 cache.

All of the current Nano processors are single-core, though Via has hinted that a dual-core version would be a logical next step. There has also been some speculation that Via will switch to foundry TSMC’s advanced 45nm process technology for the next version of Nano.

Via’s competitive advantage has been in power efficiency, and the specs for Nano look impressive. The high-end processors consume a maximum of 17 to 25 watts, and the ultra low-voltage versions top out at 5 to 8 watts, depending on the clock speed. When the chip is idle, it consumes anywhere from 0.1 watts for the 1.0GHz U2300 to 0.5 watts for the fastest 1.8GHz L2800. For comparison, here are the specs for the initial Intel Atom processors, announced last month.

How the Nano will actually perform against the Core 2 Solo and Atom is still unclear. Via published a white paper that shows some performance numbers, but they mainly focus on improvements over C7 on synthetic benchmarks. Via told me to expect performance that comes close to the Core 2 Solo with much lower power requirements. Perhaps we’ll get a better idea at Computex next week.

Via says it has already shipped Nano processors to OEMs, and they will start to show up in systems sometime in the third quarter. The pricing hasn’t been announced, though it will almost certainly be very aggressive, as Via is promising the lowest-priced systems capable of handling Blu-ray high-definition movies. Also, watch for some news from Nvidia on its work to develop GPUs, and eventually chipsets, for Nano that should result in some of the lowest-cost DirectX 10-capable systems. There are many mini-notebook and UMPC design based on the C7–including Via’s own OpenBook and the HP 2133 Mini-note–so it’s no surprise that Via also plans to keep it around for a while.

May 21st, 2008

Report: Nvidia GTX 200 series will be one big GPU

Posted by John Morris @ 3:47 am

Categories: AMD, PC gaming, Nvidia, PC graphics

Tags: NVidia Corp., Series, Chip, GPU, Semiconductors, Network Technology, Hardware, Networking, John Morris

More details on Nvidia’s new GTX 200 series GPUs, which are set to launch sometime next month, courtesy of the site TGDaily.

The new chip will reportedly be massive, measuring 576 square millimeters, due to the increased number of processing units and a 512-bit memory controller. All told it will have around 1 billion transistors. By comparison the current G92 (the basis of several GeForce 8800 and 9800 series GPUs) measures 330 square millimeters. Both are manufactured on a 65nm processs by TSMC, the world’s largest foundry.

AMD’s Radeon HD 3800 series (aka the RV670) is significantly smaller, measuring 192 square millimeters with 666 million transistors. It is also manufactured by TSMC, but using a more advanced 55nm process.

The size of the chip determines the manufacturing cost–the smaller the chip, the more you can squeeze onto a single silicon wafer. TGDaily estimates that 100 GTX 280 or GTX 260 GPUs will fit on a single wafer (which has a diameter of 300mm). By my calculations, the actual number would be closer to 94 assuming a perfect yield, so the real figure would be even lower.

In other words, if these specs are accurate, the GTX 280 and GTX 260 will make for some very pricey, albeit powerful, graphics cards. Within the next few weeks, we should get all the details, and find out how it will stack up against the AMD Radeon 4800 series.

May 19th, 2008

AMD announces new PC gaming push

Posted by John Morris @ 4:00 am

Categories: AMD, Desktops, Alienware, PC gaming, Nvidia, PC graphics

Tags: PC, Advanced Micro Devices Inc., AMD Game Ultra, Games, Personal Technology, John Morris

AMD announced today a new program designed to boost sales of mainstream PCs for gaming. The AMD Game logos will appear on AMD-based desktops and notebooks that meet the system requirements to run nearly all of the latest games.

Of the 263 million PC gamers worldwide, only 13 million are the hard-core gamers, according to the PC Gaming Alliance. These are the users AMD and Nvidia battle over. Another 197 million are casual gamers (think Solitaire) who can use any old PC. But there’s about 50 million somewhere in the middle who like to play more demanding PC games. The goal of AMD Game is to make the experience as easy as it is on a console or, as Godfrey Cheng, AMD’s Director of Marketing, Platform Technologies, puts it, “We want to be sure that when ‘Joe Six-Pack’ walks into Wal-Mart and picks up a copy of Deer Hunter Tournament, it’ll play on his PC.”

There are two levels: AMD Game includes systems with an Athlon X2 5600+ processor, 2GB of memory, Radeon HD 3650 graphics, and an AMD 770 or Nvidia nForce 500 series chipset or better. AMD Game Ultra requires a minimum of a Phenom X4 9650, 2GB of memory, a Radeon HD 3870, and an AMD 770 chipset.

AMD says many systems costing $1,000 to $2,000 will meet these requirements and be capable of playing a list of top-selling games in four different genres at 30 frames per second (see the slide below) or better. You can configure an Alienware Aurora desktop that meets the Game Ultra requirements for about $1,350. The complete list of tested configurations is here. AMD has also tested many other system components, including motherboards, power supplies and input devices, to ensure that they will support AMD Game systems and are compatible with the most popular games.

AMD doesn’t currently offer a CPU that can match the fastest Intel chips (or arguably a single GPU that can match the Nvidia GeForce 9800 GTX), which is one of the reasons it has been preaching a “balanced platform” approach. AMD’s CPU-GPU platform does offer a lot of performance for the price, and AMD’s Game initiative is a logical extension of the balanced platform push. But whether it will succeed in getting the word out to a group that is difficult to market to–or meet the fate of logo programs such as AMD Live and Intel Viiv–remains to be seen.

May 16th, 2008

Fight card: AMD Radeon 4800 vs. Nvidia GTX 200

Posted by John Morris @ 8:44 am

Categories: AMD, PC gaming, Nvidia

Tags: Card, NVidia Corp., Advanced Micro Devices Inc., Graphics, Radeon, GPU, John Morris

The high-end graphics card market isn’t the straightforward, mano-a-mano battle it used to be. Graphics cards with dual GPUs, systems with multiple cards in CrossFire or SLI implementations, and most recently hybrid graphics have all muddied the picture. Meanwhile, Intel has improved its integrated graphics and has long-term plans in Larrabee to challenge AMD and Nvidia in discrete graphics.

But next month we should get a good, old-fashioned GPU showdown when AMD and Nvidia release entirely new, high-end GPUs. Details of these GPUs, AMD’s RV770 and Nvidia’s G200, and the graphics cards based on them, are trickling out.

The RV770, or ATI Radeon 4800 series, will launch on June 16, according to several sites. Graphics cards based on the first GPU in the series, the Radeon 4850 with 512MB GDDR3 memory, will be available immediately for $230. This GPU is the follow-up to the current Radeon 3850. Higher-end cards based on the Radeon 4870 with 512MB GDDR5 and the dual-GPU Radeon 4870 X2 with 1,024MB GDDR5–a first–will be announced on June 23. The Radeon 4870 cards won’t ship immediately because of the lack of availability of GDDR5 memory, but when they do show up prices should be around $350. The Radeon 4870 X2 cards won’t show up until early 4Q and will cost about $550.

One of the more intriguing specs of the Radeon 4800, according to the site TGDaily which has many details on the 4800 series, is “physics processing capabilities.” Physics is used to define how objects in a game move and interact. It can deliver a more realistic, compelling experience, but few games are designed to take advantage of physics.

There are really only two players here: Havok, which makes software for game developers and movie editors, and Ageia, a competitor best known for pioneering the PhysX Accelerator boards for gamers. Intel purchased Havok in September 2007, and Nvidia completed the acquisition of Ageia in February and plans to integrate the PhysX Accelerator into its GPUs. ATI previously worked with Havok on physics (and AMD reportedly considered buying Ageia late last year), but it is unclear where AMD is getting the physics technology now. (There have been some reports that AMD borrowed a programming language developed at Stanford University for the GPUs that power the Folding@home research project and extended it to support game physics.)

Nvidia’s G200 will reportedly launch on June 18 (some sites put it in early July). This GPU family was previously known at the GeForce 9900 series, but several sites are now reporting that Nvidia will switch to a new naming scheme: the GTX 200 series. Initially this should consist of two products, the GTX 280 and GTX 260, but otherwise there are few details aside from the fact that G200s supposedly contain more than 1 billion transistors (not including memory), use GDDR3 memory with a 512-bit interface, have an updated Unified Shader architecture, and will be in cards that cost $450 or more.

With the massive Computex tradeshow in Taipei coming the first week of June, I suspect we will know a lot more about these new GPUs before the rumored announce dates.

May 6th, 2008

After a slow start, quad-core is catching on

Posted by John Morris @ 7:08 am

Categories: Intel, AMD, Desktops, Dell, multicore processors, Hewlett-Packard, semiconductors, Gateway, quad-core processors

Tags: Desktop, Hard Drive, Quad-core, Memory, Advanced Micro Devices Inc., Intel Corp., Chip, Processors, Semiconductors, Hardware

This week AMD is expected to announce that it has sold more than 1 million quad-core processors, according to the site TGDaily. That sounds about right since the company previously said it had shipped 500,000 in the first quarter, and 400,000 in the fourth quarter last year. AMD announced its Barcelona quad-core Opterons in September, followed by Phenom desktop chips in November.

Meanwhile Intel has shipped more than 10 million quad-core processors, according to a recent report by Mercury Research. Intel introduced its first quad-core processors, the Xeon 5300 series server and Core 2 Extreme QX6700 desktop chips, in late 2006.

Those sound like big numbers, but in that period the industry shipped roughly 360 million CPUs so quad-cores represent only about 3% of the market by units. And the vast majority of those are Xeon server processors, not desktop chips. “I don’t think anyone had imagined how popular the low-cost quad core server parts were going to be at the time,” said Dean McCarron, Founder and Principal, Mercury Research.

Quad-core desktops have been slow to catch on because of the price, and because there are still very few PC applications that really take advantage of multiple cores. That is why the processor and graphics companies keep throwing money at universities to research parallel computing.

Despite the lack of real-world applications, an increasing number of consumers are buying quad-cores for “future-proofing” as prices start to come down. Intel recently cut the price of the 2.4GHz Q6600 to $224 and introduced a 45nm Penryn quad-core, the 2.5GHz Q9300, at $266. AMD prices the 2.2GHz Phenom 9550 at less than $200.

Those cuts are reflected in the latest system prices. The HP Pavilion a6460t with the 2.5GHz Intel Core 2 Quad Q9300 (2GB of memory and 500GB hard drive) is $830. The Dell Inspiron 530 with the older Core 2 Quad Q6600 (1GB of memory and 500GB hard drive) is now $750 with a 19-inch flat-panel display. Gateway is selling a retail desktop, the GT5674, with a 2.2GHz AMD Phenom 9500 (3GB of memory and 500GB hard drive) for $650. All of these have integrated graphics and Windows Vista Home Premium. Gateway also sells retail models with Intel quad-core chips. The GT5678 with the Q6600 (4GB of memory, 750GB hard drive, and ATI Radeon HD 2400XT graphics) is $850.

The cheapest quad-core, however, is an AMD triple-core, which is technically the same chip with one core disabled. The HP Pavilion a6450z with the 2.1GHz Phenom 8400 (1GB of memory and a 500GB hard drive) sells for $600. Gateway offers a model, the GT5670, with the same Phenom chip, and 3GB of memory and a 320GB hard drive, for $550. But you’ll pay the price in terms of performance.