Forwarded message:
X-within-URL: http://techweb.cmp.com/eet/column1/wintel19.html
HOT X86 CHIPS FOR '98 AND BEYOND
[INLINE] Launching yet another x86 microprocessor into a field already crowded with clones isn't a good way to bet your company's future. But that's just what two startups and one CPU stalwart are doing, in a bid to beat Intel at its own game.
The new ventures--Centaur Technology Inc. (Austin, Texas) and Transmeta Corp. (Santa Clara, Calif.)--and long-time player Advanced Micro Devices Inc. (Sunnyvale, Calif.) each has its own twist on what it will take to survive in the cutthroat x86 world in 1998 and beyond. Let's take them one at a time.
Centaur, founded by renowned microprocessor architect Glenn Henry, is focusing on the low end of the market, where sub-$1,000 desktop machines and sub-$2,000 notebooks rule. Centaur's offering, launched only a few months ago, is called the IDT WinChip C6 ("IDT" stands for Integrated Device Technology Inc., which owns Centaur). It's a Pentium-class processor that supports the MMX multimedia instruction-set extensions, a Socket-7 interface, and comes in speed grades of 180-MHz and 200-MHz. Centaur is positioning the C6 as a direct alternative to Intel's Pentium with MMX, AMD's K6, and Cyrix's 6x86MX microprocessors.
From a design standpoint, what's interesting about the C6 is that Henry chose not to follow the reigning trends in chip architecture. Instead, he took a downsized approach, implementing just those features he needed to deliver decent performance in a high-volume, low-cost CPU.
"The biggest thing we did is throw out conventional thinking," Henry told me when we met recently. "We came to the conclusion that the added benefit of a lot of computer-science things wasn't worth the effort. We're not superscalar--we don't do out-of-order execution. Everyone else is designing 4-way superscalar processors, so we did a 6-way chip."
In designing the C6, Henry said his team found that, as CPU clock speeds approach 200-MHz, nearly half the time is spent waiting on the bus. So, Henry outfitted the C6 with a huge translation-look-aside buffer, as well as a second-level TLB, to reduce bus utilization and cut that wait-time to the bone.
Also notable is the fact that Centaur is a tiny outfit that began life a scant two years ago. "Intel would like the world to believe it takes tens of years and dozens of people to design a microprocessor," Henry said. Looking at the results rolling out of Centaur, it's obvious what a dedicated group of engineers can accomplish.
Over at AMD, a somewhat larger engineering team is already burning the midnight oil to design the K7 (code-named "Argon"), which will compete with Intel's upcoming 64-bit Merced CPU.
AMD has a project team hard at work on K7, but has leaked few details. Publicly, AMD wants to talk more about its new MMX-enhanced K6 processors. But K7 will be the key to AMD's long-term future, since a 64-bit chip is a must-have for any company that wants to remain a viable alternative to Intel.
The few details we do know emerged in October in a keynote speech at the Microprocessor Forum by AMD chairman Jerry Sanders. He said that the K7 will run at clock speeds in excess of 500-MHz and will come in a module that's mechanically--though not electrically--interchangeable with Intel's Slot 1 connector. Most interesting was the news that K7 will use the bus protocol developed by Digital Equipment Corp. for its Alpha EV-6 processor.
It's not clear how far along AMD is with the K7. Indeed, it will be a daunting task. But AMD has two things going for it in its quest. First, it is very strong in the simulation and verification department--an important factor in avoiding design flaws like the floating-point bug that struck Intel and its Pentium.
More important, AMD knows what it's like to wrestle with design delays, which struck its K5 project. Concerns on the K6 job were reportedly behind AMD's decision to purchase NexGen in January, 1996. Indeed, the NexGen team provided the Nx586 core, which became the basis for the K6.
The third, and potentially most interesting, effort involves Transmeta, a startup formed less than three years ago by former Sun Microsystems chip architect David Ditzel. Initial word had Transmeta at work on a PowerPC clone. Then, the buzz was that the company was designing a Java chip aimed at the nascent market for low-cost network computers. Now, it seems that Transmeta's effort is focused more on an x86 alternative that boasts either low-power, multimedia or network-computer capabilities. Or perhaps all three.
One interesting tidbit to emerge from Transmeta is the news that it has hired Linus Torvalds, the designer of the Linux operating system. Apart from Torvalds' considerable software skills, he's plugged into an influential community of Unix programmers, which could give Transmeta a big leg up in any effort to design a processor tuned to handle real-world networked applications.
Alexander Wolfe is EE Times' Managing Editor for computers and communications
____________________________________________________________________ | | | The most powerful passion in life is not love or hate, | | but the desire to edit somebody elses words. | | | | Sign in Ed Barsis' office | | | | _____ The Armadillo Group | | ,::////;::-. Austin, Tx. USA | | /:'///// ``::>/|/ http://www.ssz.com/ | | .', |||| `/( e\ | | -====~~mm-'`-```-mm --'- Jim Choate | | ravage@ssz.com | | 512-451-7087 | |____________________________________________________________________|