Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Politics : Formerly About Advanced Micro Devices -- Ignore unavailable to you. Want to Upgrade?

To: wily who wrote (88977)	1/22/2000 3:11:00 PM
From: wily	Respond to of 1572600

Hannibal at ars technica did up a nice piece on the Crusoe. Here's the last little segment (the piece is pretty long): arstechnica.com ------------------------------------------------------------ The Competition Now for my favorite part of the article, where I get take a step back from the tech to look at the Big Picture and tell you what I think Transmeta is up to and what they're capable of. First off, I haven't yet mentioned that the Code Morphing software can be modified to support architectures other than x86. In fact, something like Alpha or PPC would probably be a better fit to Crusoe's core, and provide better performance. So I'm sure they'll be announcing something like that before long. Also, since all of the translation is done in software, I wouldn't be surprised if at some point you could run code intended for more than one ISA on the same chip at the same time. That, however, is pure speculation on my part. Next, I've seen some misguided speculation here and there where people have claimed that Transmeta, in going mobile, is not really competing with Intel. Wrong. The embedded/mobile market has repeatedly been touted as the biggest potential growth market for semiconductors in the next 10-20 years. If you're making chips, then you're eyeing the embedded market--and this includes Intel. Furthermore, both Intel and Transmeta will be competing directly in the x86 laptop space, a point that Transmeta made clear when they repeatedly compared their product to the Pentium line throughout their presentation. That Transmeta is competing with Intel in the mobile and laptop markets should be obvious. What's perhaps not so obvious is that could very soon be competing with Intel, AMD, Compaq, and Sun in the high-end server and workstation markets. If you listened to Linus' speech at COMDEX, then you know that he has a vision of Linux as an infinitely scalable OS that can run on everything from a cell phone to a database server. Linux is about a kernel that can run on anything, with functionality added to it as is needed. Well, it's no coincidence that Linus is working with Transmeta, because I believe that they share this vision for their product line. A few quotes in Transmeta's tech doc bear this out. Let me give you two of them. First, on p.3: For the initial Transmeta products, models TM3120 and TM5400, the hardware designers opted for minimal space and power. By eliminating roughly three quarters of the logic transistors that would be required for an all-hardware design of similar performance, the designers have likewise reduced power requirements and die size. However, future hardware designs can emphasize different factors and accordingly use different implementation techniques. Check out that last line, and think about the first part of this article: different questions mean different answers. Not if, but when Transmeta shows us their answer to the performance question (and I'm sure their designers are already asking it), it will be very interesting to see what happens. Now let's check out that other quote, from p. 8: For its initial products, Transmeta has drawn the line between hardware and software so that software handles the complex task of decoding x86 instructions and generating explicitly parallel molecules, which the hardware executes using a very simple, high-speed VLIW engine....The hardware-software line might be drawn differently for another kind of product, for instance, a high-end server processor. So you see, they made the Code Morphing software extremely modular. They can implement whatever parts of it they like in hardware to get whatever degree of performance gain they want. Crusoe should be viewed more as a proof of concept than as the ultimate outcome of 5 years of work. Crusoe represents one extreme of a spectrum that stretches from "implement the bare minimum in hardware" to "implement everything in hardware." Now that Transmeta has a technology that's proven to work in the most difficult case (where 2/3 of the transistor logic has been moved into software), they can go back in the other (easier) direction and start putting stuff in silicon. Furthermore, since there's a software layer between the ISA of the binary and the machine's native ISA, Transmeta is free to beef up the execution engine (or any other part of the core) however they like, because the only thing that will require a recompile is the Code Morphing software. A case in point is the two chips in its product line. Each has a slightly different core (the Windows chip has special instructions in it that help speed up Windows), but they both are fully x86 compatible. There's nothing to keep them from stuffing new functions and features (SIMD anyone?) into the silicon, to help scale the product has high up as they want to go with it. I'd say that it's only a matter of time before we hear an announcement of another product line from Transmeta. It won't be named Crusoe, because it won't be aimed at the mobile and embedded markets. It'll be a workstation and server class x86 CPU that runs Linux like a fiend, and it'll compete directly with Intel's IA-64. I can't wait.