Slashdot Mirror

MIPS released the R10000 core in 1995 which was their second superscalar design, and all subsequent MIPS designs have been based upon the R10000 core. Also, the M4K core that Microchip uses on the PIC32 has a 16 bit instruction word length mode (MIPS16e): http://www.mips.com/products/architectures/mips16e/ ARM's floating point is an extension to the architecture- the Cortex-A8 has a cut-down version that requires (according to the Wikipedia article) 10x more clock cycles per float operation. The utility of floating point for an embedded processor is somewhat questionable- It requires an awful lot of silicon for something that doesn't get used all that often (in embedded apps). The MIPS architecture does have floating point registers, though as I understand it, the floating point opcodes are more like macros.

Oh, but MIPS are still being used commonly. http://www.mips.com/

No way to 'stomp' on it - embedded is bigger than PC and has been for a couple of years. So if Intel wants to fight ARM, they need to one or more of the following: 1. Make a 'synthesizable', power efficient Atom. I don't think they can do much about the power unless they completely recraft it, and then who knows what happens to x86 legacy apps. 2. Buy ARM, if they can afford it. 3. Buy MIPS, like I've been hearing for a while now. 4. Build up the sexiness of Atom with things like enhanced security (that's become kind of a hot button for us.) This might be the Europe outfit that's rumored to have the goods - called Iunika, in Madrid (wow! How cool is that?): http://www.mips.com/news-events/newsroom/newsindex/index.dot?id=27937 Maybe this Iunika bunch is using MIPS for an MCU to run encryption for laptops? That wraps it all up - Intel needs a real embedded play and buys MIPS, and makes its embedded more appealing with the iunika security code.

Or Android, which runs on ARM and x86, and there's probably a MIPS port as well. The apps are Dalvik VM / Hybrid Java/Touch/Google things.

http://www.mips.com/android/ yup

...and MIPS are both dead and gone...

I highly recommend knowing a bit about the subject matter before making asinine comments.

Sse http://www.mips.com/ for more information.

Typically, it's MIPS32 R4000 architecture.

To be entirely pedantic, it's usually a MIPS32 4k core, which is derived from the old R4000 chip.

The MIPS architecture is a popular one with people who implement their own cores. In fact, it is rather common for computer science/engineering students to implement their own using FPGAs, based on the commonly used Computer Architecture by Hennessy and Patterson. The architecture is extremely simple, straightforward, and easy to implement.

I believe you can implemented a near complete MIPS R3000 core with only minor differences and avoid any patent issues (as long as you don't call it a MIPS). Some of the ops on the newer cores are still encumbered and cannot be implemented without paying money to MIPS Technologies. I've worked with a couple of MIPS clones, some by American companies, and there is nothing illegal about them. In fact, it would be far more surprising if the Chinese companies wasted the time creating their own architecture instead of basing it on a proven one.

Well, I'll ignore the racist tone of your comment (Wang Chung, Chung King, etc) - but MIPS is hardly a product of a defunct chip designer. I know, I work for them as a product engineer.

In fact, MIPS is the #1 architecture in several market segments, including:
Cable STB 76%
Satellite STB 30%
DVD Recorders 70%
Cable Modems 95%
Internet Backbone 40%
DSL 52%
WLAN 55%
VoIP 72%

See http://www.mips.com/ for more information on that.

-Bruce Chin

SGI did something similar when they brought out 64-bit MIPS chips and a 64-bit version of IRIX. They also doubled the number of registers.

MIPS IV has 64 GPRs? MIPSco disagrees with you:

• Fully MIPS IV(TM) and MIPS V(TM) ISA compatible
  ...
• 32 general purpose 64-bit registers (GPRs)

(No, MIPS I through III didn't have 16 GPRs.)

MIPS was spun off years ago. It's mostly used in embedded hardware (although fighting with ARM based systems there).

Its very good for low power consumption chips for applications that can't have a fan.

Although, I still can't figure out all those damn ABI's even after playing with it for a couple of years.

For my job I support a number of processors made by various vendors. Whenever somebody asks me a question about a Broadcom CPU I don't have docs for already I'm forced to answer: "I don't know, and there's no easy way to look at the docs to find the answer." (The Broadcom process to get docs is they fax you and NDA, which you sign and fax back. Then you get a .pdf with on each page stamped "Confidential for XYZ" and it's got a password to boot.) I love http://www.mips.com/ for its excellent and readily available documentation.

upgrade from your SGI workstation to a tablet today!

upgrade from your SGI workstation to a tablet today!

GC is certainly 32-bit . The 970 (Power4/G5) is the first widely released 64-bit processor in the PowerPC family aside from the defunct PowerPC 620 (circa 1994). I believe the 620 didn't yeild the kind of results IBM was hoping for so they canned it.

And the PS2 does use a 128-bit MIPS-based processor designed by Sony and Toshiba. MIPS-"based" means that they bought a 64-bit MIPS architecture license from MIPS (about the only thing they sell) and adapted it to their application. Now, I'm not an expert on that architecture and and there is some argument as to what truly makes an n-bit processor (its data bus or address bus). I'm going to have to say that it is at minimum 64-bit data bus with a 128-bit address bus or 128-bit data bus with a 64-bit address bus, but it could just as well be fully 128-bit.

Not that ANY of that matters, like you say. The PS2 CPU isn't what's interesting about it at all. It's the VPUs , which have caused oh-so-much pain for game developers around the world.

does anybody know the names of ARM's competitors?

MIPS, for one, although their list of products using MIPS-architecture processors doesn't say anything about mobile phones other than a satellite phone.

does anybody know the names of ARM's competitors?

MIPS, for one, although their list of products using MIPS-architecture processors doesn't say anything about mobile phones other than a satellite phone.

I've been researching chipsets for digital TV. Here are my links to current hardware products:

STMicroelectronics System on Chip (2) Get Linux here
ATI Xilleon 220 (Products)
Sigma Designs Digital Media Processors (Products)
IBM PowerPC405 STBxx (Zarlink [2], Araneo)
Texas Instruments DM642 DSP (i3 Mood Box , X-Designs Flikit + Softier MediaLinux)
NEC EMMArchitecture2 (Galaxis + LinuxTV , PRISMIQ + Linux)
Equator Technologies BSP-15 boards
Via CN400 (Mini-ITX Board), PM800 and PM880 (w/ HDTV for Pentium 4) , ShowShifter HMN, Soyo Multimedia Ready Motherboard (with TV Tuner, $129.99)
Toshiba TX System RISC (MontaVista Linux)
Windows chipsets:
Intel 815 VisionPlus terrestrial box (Korean OEM)
AMD Geode (CoCom)
ARM (Samsung, etc.)
Digeo X-Stream (Paul Allen company)

MHz != million instructions per second, it means simply "cycles per second".

If the poster did mean the latter then I was saying that he probably meant to say MHz. The reason being is that most people without a clue but with money focus on MHz as a determination of whether a machine is fast enough rather on other factors, such as running benchmarks as you suggest. These same clueless people most likely wouldn't know what MIPS is in either of the two forms I mentioned.

So if all that is true, then I agree with what I thought the poster was trying to say: The sooner people realize that MHz isn't that relevant the better. There are a lot of other variables in making a decision on whether you have the best machine for the job.

intel processors are PROPRIETARY. They are not a published, open standard, like SPARC and MIPS. You can license the SPARC for $99 IIRC. You can not do this with intel. You must pay much more money to license their instruction set, under much more restrictive terms.

intel processors (x86) are COMMODITY processors. They are a "de-facto" standard, in the same way that Microsoft Windows is a de-facto standard operating system. It is in no way Open. It is proprietary.

Gcc is also most heavily optimized for the intel platform.

This bit is at least correct. That's because most people have PeeCees with intel (or compatible) processors in them, and most development, by default, has been done in this architecture. Optimisations on this architecture therefore benefit most people.

...at least by modern standards. The PD61130 MPEG2 Decoder, as NEC calls it, provides 200 Dhrystone MIPS at 167 MHz / 160 MIPS at 133 MHz using an "Integrated high-performance CPU: NEC MIPS(R)-based VR4120A(TM) core". Note that these are MIPS, or Meaningless Indicators of Processor Speed. Meaningless why? They're produced by benchmarks! Anyway, it only supports up to 64MB of SDRAM... Thinkgeek's "specifications" says the processor is a "NEC uPD61130 32-bit MIPS microprocessor with integrated MPEG decoder", but they don't bother to mention that it's an MPEG2 decoder, not MPEG2+4.

They say the device plays DivX, but since it doesn't have an MPEG4 decoder, it all has to be done in software, and I'm skeptical about the device's ability to play high-bitrate MPEG4 (DivX, XVid, others) streams. And while they say that the device will be easily extensible to support future formats, if they are anything like MPEG4, then it certainly won't be fast enough to play them.

MIPS is kind enough to provide a newsletter which comes up in a search for "4210A" which contains the following interesting paragraph:

EMMArchitecture2 is designed for mid/high-end STB/ DTV applications such as Personal Video Recorders (PVR) and wireless IP STBs. It uses the NEC-designed MIPS CPU 4120A, plus NEC's original audio DSP, versatile stream processing engine and ATA I/F, together with a PCI bus. This unique architecture allows not only a single-chip, mid-range PVR configuration, which is controlled by an on-chip 200-mips 4120A CPU, but also a high-end, multi-chip STB configuration, which utilizes a PCI to connect an external high-performance CPU such as NEC's 500-mips, MIPS-based(TM) VR5500A CPU, together with a PCI bus bridge.

But, as the specifications for the PrismIQ show, they are not in fact including a VR5500A, just the VR4120A-based PD61130. I assume this plays the majority of MPEG4 content today, or else they wouldn't be selling it, but as bitrates rise, I believe that they will be in trouble.

Note that I have never seen let alone tested one of these, so I am just wanking in the dark here, but it doesn't seem likely to really provide the necessary longetivity. We all know that amazing things can be done with a 200MHz MIPS chip, go ait down at an SGI Indy sometime if you don't believe me, but I think the lack of an MPEG4 decoder will hurt them in the long run. There are numerous MPEG4 hardware solutions available today, and unfortunately, they did not see fit to use any of them.

...at least by modern standards. The PD61130 MPEG2 Decoder, as NEC calls it, provides 200 Dhrystone MIPS at 167 MHz / 160 MIPS at 133 MHz using an "Integrated high-performance CPU: NEC MIPS(R)-based VR4120A(TM) core". Note that these are MIPS, or Meaningless Indicators of Processor Speed. Meaningless why? They're produced by benchmarks! Anyway, it only supports up to 64MB of SDRAM... Thinkgeek's "specifications" says the processor is a "NEC uPD61130 32-bit MIPS microprocessor with integrated MPEG decoder", but they don't bother to mention that it's an MPEG2 decoder, not MPEG2+4.

They say the device plays DivX, but since it doesn't have an MPEG4 decoder, it all has to be done in software, and I'm skeptical about the device's ability to play high-bitrate MPEG4 (DivX, XVid, others) streams. And while they say that the device will be easily extensible to support future formats, if they are anything like MPEG4, then it certainly won't be fast enough to play them.

MIPS is kind enough to provide a newsletter which comes up in a search for "4210A" which contains the following interesting paragraph:

EMMArchitecture2 is designed for mid/high-end STB/ DTV applications such as Personal Video Recorders (PVR) and wireless IP STBs. It uses the NEC-designed MIPS CPU 4120A, plus NEC's original audio DSP, versatile stream processing engine and ATA I/F, together with a PCI bus. This unique architecture allows not only a single-chip, mid-range PVR configuration, which is controlled by an on-chip 200-mips 4120A CPU, but also a high-end, multi-chip STB configuration, which utilizes a PCI to connect an external high-performance CPU such as NEC's 500-mips, MIPS-based(TM) VR5500A CPU, together with a PCI bus bridge.

But, as the specifications for the PrismIQ show, they are not in fact including a VR5500A, just the VR4120A-based PD61130. I assume this plays the majority of MPEG4 content today, or else they wouldn't be selling it, but as bitrates rise, I believe that they will be in trouble.

Note that I have never seen let alone tested one of these, so I am just wanking in the dark here, but it doesn't seem likely to really provide the necessary longetivity. We all know that amazing things can be done with a 200MHz MIPS chip, go ait down at an SGI Indy sometime if you don't believe me, but I think the lack of an MPEG4 decoder will hurt them in the long run. There are numerous MPEG4 hardware solutions available today, and unfortunately, they did not see fit to use any of them.

China's 64bit Homegrown CPU
Posted by
michael
in The Mysterious Future!

from the enter-the-dragon dept.
An anonymous reader writes: "EE Times is reporting on China's BLX IC Design Corp nearing the completion of their first 64-bit CPU. Based on the MIPS instruction set the 500-MHz Godson-2 microprocessor is aimed toward distributed grid computing. To avoid MIPS patent issues, several instructions (unaligned loads and storeds in the 32 bit version) have not been implemented but with the support of over 60 software providers such as Red Flag Linux and the ability to tweak compilers to not use these instructions this should not be a problem. The Godson-1 processor (also patent free) was announced last year and was aimed at the embedded market." The Godson processor line has generally been called Dragon by the Western press.

Also, 64 bit chips are not ready for the mainstream market yet. They need more testing, analyzation, and intrepration with an unbiased group of persons as the sample, to make reliable predictions.

Yeah, no one makes 64 bit chips that are ready to use.

They do, go here

Motorola makes a couple of PowerPC based microcontrollers. These come with a number of usefull peripherals (USB endpoints, ethernet interfaces, serial ports, parallel I/O ports, etc.), some RAM and some EPROM all on a single chip. In decades past, Steve Ciarcia built a small publishing empire on the practice of building homebrew personal computers on similar microcontrollers (Z80 variants, in his case). The same approach could be used today. If you don't want to use a PowerPC, there are similar beasts available based on other popular architectures.

What is most impressive about this to me is that they did it using Linux over IRIX. Why? Because this has provent to be Linux's weakest point: scalability.

This new system is news, but it's hardly groundbreaking news. Back in '99, SGI spun off MIPS and announced they would do commodity systems -- including supercomputers with commodity processors. At that they had a choice: port IRIX to the Itanium, or teach Linux to scale so they could use it on their supercomputers. It's been no secret that they chose the latter. Or why: it was less expensive, and catered to an established user community.

Note that Itanium/Linux systems are not meant to replace MIPS/Irix systems. Unless they've changed their strategy since I worked there, SGI plans to keep developing Irix systems for another 10 years, at least. Of course, that depends on maintaining loyalty to Irix solutions, and the buzz is that they're having trouble with that.

see

sony and MIPS

multicore

see

sony and MIPS

multicore

Well, I guess that's a good reason to obsolete the architecture ;)

Seriously though, MIPS (I believe) ported Unix to their processors, and called it RiscOS, independent of the RISCOS guys.

Where the Itanium (and, I'm assuming, the Opteron/64-bit Athlon) really matter is in in large database and high-end workstation solutions. Basically, anything that needs more than 4GB of RAM. In these uses, it's not actually the processor speed that is needed, it's the RAM.

I would like to see one of these give a specFp result

I bet that it could cane IA64 in the specInt but the real test would be floating point and to do IEEE754 properly you need 64 bit otherwise you end up emulating it

now we have of the true 64 bit microproessor's

Sun Microsystems - Processors which are a Sparc

PA-risc which is MIPS like

and MIPS64 which I like alot

of the ports linux to 64bit for linux HPPA and the oldie but goodie linux Alpha and linux sprac64 of course not forgeting linux for IA64 but unfortunately the linux for MIPS is not 64bit so if ever their was a challenge as linux is mostly 64bit clean its to do a MIPS64 port

oh and intel wont like to say linux for hammer which is not real 64bit just has some 64bit registers tacked on (but hey you can do fp right ;-)

To my knowledge, SGI was the only major company to use them... and as far as I know, that tradition is over. SGI is either using sparc or powerpc processors. Further, I seem to recall thinking that the reason this was going was because the MIPS processors were no longer available.

MIPS is a company.

I believe MIPS has had 64bits since the R4000 in 1991. See micropressor history.

Well it depends on what kind of embedded device you're designing, but in many cases the MIPS processor fits the bill better than ARM. MIPS processors are designed by many different vendors, and each has their own target market. The MIPS architecture has seen a massive growth in the embedded market in the last few years and there are some impressive processors out there from the low end to the extremely high-end.

StrongARM is well positioned for handheld devcies, but I'd say the MIPS architecture is the most promising in the embedded space over all.

- j

Compaq also produce some MIPS systems in the Compaq NonStop Himalaya series.

Perhaps SGI designed the processor itself, but I believe the intellectual property does actually belong to MIPS. Just as LSI, QED (now PMC Sierra), IDT, etc. design MIPS based processors with MIPS IP. (MIPS does not, of course, actually manufacture any processors; it's an IP only company.)

I did find this page of "MIPS-Based(TM) Products" at MIPS, which lists SGI's machines. That page states "Design efforts utilizing MIPS® intellectual property are continuing for the system and server markets by Silicon Graphics."

Also notice that SGI's R10000 processor page includes the following at the bottom: "R10000, ANDES, and Avalanche are trademarks of MIPS Technologies, Inc."

To me it looks like SGI behaves like any of MIPS licensees; they use intellectual property that (now) belongs to MIPS Technologies Inc., and design their processors using that. Perhaps there is an agreement between MIPS and SGI, but I couldn't find details of it. I'd be very appreciative (really) if you can show evidence to the contrary. I'm not trying to be argumentative; I would actually like to know how this is set up.

Silicon Graphics still develops IRIX and MIPS processors.

Actually, Silicon Graphics has nothing to do with MIPS anymnore, other than perhaps being one of MIPS' best customers. Around a year ago SGI got rid of its remaining stake in MIPS Technologies Inc..

Indeed, on some processors the assembler does even more including expanding one assembly instruction into multiple machine instructions. On a MIPS for example there's even a register reserved for the assembler ( at - assembler temporary) to use when expanding instructions.

The advantage of the ARM platform is that it's a decent, high performance and low power embedded system. For example, if you wanted to build an in-dash MP3 player you might want to use a StrongARM processor.

At one point I was planning a StrongARM based embedded device and looked at these boards as a way to get the software guys up and running before my hardware was ready. I later settled on a MIPS processor before the project was scrapped.

Bottom line - you can't beat an off-the-shelf PC motherboard and processor for price/performance. There's no way anything else can compete because of the volumes that PC stuff is made in.

I won't argue with you, using an x86 for a console, is a MAJOR flaw. However what do you mean that consoles usually have specially developed CPUs? Consoles usually use an existing chip (or some slightly modified variation) because it's cheaper than developing a new one, testing it, and then having it manufactured. Nintendo and Sega don't have the resources to do that and maintain their central business. The Dreamcast's SuperH4 chip is just a standard component you can get from hitachi as far as I know. Other console's CPUs (OTTOMH) are: Master System/Game Gear -- Z80, NES -- 6502, Genesis -- 68000, SNES -- 65c816, Saturn -- SH2 (two of them), and Playstation and N64 both have MIPS processors (R3000 and R4300 respectively?)...

mips

I don't think you can judge exactly how this layoff will affect them, at least not without knowing who they layed off.

I'm still trying to figure out the MIPS deal, so I guess there is no way I can understand this one. First, they spin off MIPS to outside development. Then they move to some Intel based hardware, blah blah blah Merced, blah blah, look at our new Xeon box.

Meanwhile MIPS makes inroads in the PDA, portable and gaming markets, shoots up in stock price, but over the last few weeks has been on a decline too (along with SGI). But wait, it's not that simple (of course not). MIPS (the mips.com people) announce that they will focus on the older MIPS designs in newer markets... Yet, at the same time, SGI pulls out thier "time-line/road-map" and confuses the heck out of everyone talking about thier plains for MIPS boxes for several years to come. So, how does that happen? Inovations in MIPS have to come from SGI?

SGI's hardware timeline uses MIPS well past the projected Merced introduction (which is good, can't put all your eggs in one basket, and MIPS is one of the best things SGI has going for it). But, now MIPS is MIPS and not part of SGI, so, who do you count on?

So, more layoffs.... Well, are they laying off factory workers who put together boxes because they are not selling enough? Or are they laying of designers of systems and software developers? It's all a blur they are spinning so fast. I use to be convinced they were driveing themselfs into the ground, now I just don't know, with all the RADICAL moves, maybe they could make an upswing?

For one, they CAN'T dump MIPS in favor of Intel, that would seal there fate and burry them deep in the ground.... That puts them as a small player in the world of Dell, Compaq, Gateway, etc... Bad move. Not to mention VA has that nitch as far as Linux/Intel goes already. And SGI's pricing and maintainance/support price structure is very weird for a modern market anyhow, when IBM, SUN, and all the "big boys" are moving to openly posting product prices on the net, you have to make tons of phone calls and wait days for an SGI price quote, only to have your jaw drop open and go "WHAT? your Joking, Right?"

But if they dump MIPS developers, and the MIPS guys go over to MIPS (proper, the MIPS company) that might be good, because it means development continues, just under diffrent roofs.

Dump the IRIX guys I say. IRIX is plagued with problems for SGI's market. If they can retain enought IRIX guys to get all of IRIX to be replaced with Linux, that would really reduce development costs, and possably (with a lot of work) benifit thier OS usability and also gain support of the Linux community.

Counting thier assets that set them apart in the computing market, they have 1) Name Recogintion 2) Cool Hardware (read MIPS) 3) Loyal Client base (which they better bust thier butts to keep, because some are waking up to lower cost alternitives now).

Counting thier downs, they have 1) Horriable support at an outragous price (Read, unless you have an SGI box made in the last 2 years, support costs more than your hardware is worth, but without support which includes new OS releases, the hardware is worthless anyhow, you can only get the newest IRIX with the support contract, and old IRIX doesn't play friendly with new IRIX for networked SGI boxes without MAJOR tweaking). 2) A trend to move into the more highly competitive and less profitable Intel market. 3) Lack of "corporate stability" 4) Loss of a lot of good technical staff.

I say, SGI -and- MIPS are probably good stock buys... Why? MIPS has a rocking future, it's thier ties with SGI that are driveing thier price down, they will rise, CPU alternitives are a good thing. SGI sucks, if they kill themselfs, they will get bought out by someone driving thier price up in the end ;-)

My suggestions to the SGI CEOs (who won't listen) are: 1) integrate all of IRIX, and all of your software into Linux, get Linux on MIPS really working. Then your legacy hardware will retain it's value because people can still use it, you keep clients happy. They also lower development costs of software, and can work on getting a "support" department that really works (yea, I know some of the people there are still OK, but they have a lot of Bozo's too.) 2) CLING TO MIPS, it's the awsome hardware that has always set SGI apart, and made them rise. Intel is a nice "supplement" for low end stuff, and maybe even consider a Strong Arm X-Terminal? But don't loose MIPS... But, since they won't listen to me, maybe someone else will ... so, HAY VA... IPO and buy out SGI, and add MIPS to your product line ;-)

Well basically Cobalt sells standalone server appliances and rackmount systems, a niche area eminently suited for Linux due to hands-off maintenance and need for long-term stability. Rather intrigingly, they use MIPS-based chips (is similar to SGI) which, despite corporate x86 fixation, is a very cost-effective and efficient processor. If one ignores benchmark pissing contests, MIPS chips actually produce very good real-world application performance per dollar. Some generic reviews can be found by searching zdnet for their products. While I have no clue as to their success in the wider market, I note that several ISPs offer bulk CPU/storage/network based on amortised capital cost + (storage+bandwidth) operational charges. This may be a good choice for companies looking for a place to park their corporate data without worrying about the fine details.

The interesting question for /.ers is should Cobalt be viewed as a company that supports the OpenSource philosophy? Despite porting Linux to use MIPS, as far as I'm aware, they have not contributed their port back into mainstream (correct me if I'm mistaken). Despite distribution hiccips and angst, RedHat have recognised the value of the Linux community by releasing a portion of its IPO shares to the hacker community but then their success is directly tied to the availability of high quality source. Cobalt is not exactly the same situation being more a vertical integrator rather than Linux distributor/support.

I suspose the point of all this musing is to think and explore the relationship between traditional businesses and the OpenSource "gift economy" as detailed by ESR. Would insisting on a gift (of shares) be considered boorish? A "gift" which is automatically expected suddenly shifts from a voluntary exchange of appreciation to a compulsary tithe on the future goodwill (ie thou must give away x servers or else!) which could shatter the easy-going nature of the OpenSource community. While individuals can be expected to keep social balances in their heads (e.g. cousin x gave y last Xmas so I'll give z in return where y~=z), corporations are run on tough balance sheets principles under recognised accounting rules with the sole objective aim of increasing "value" to "shareholders". This creates an unresolved issue in dicussing how corporations can both support and benefit from OpenSource without being seen as overly exploitive (which could potentially lead to loss of goodwill). What do people think?

LL

Um, MIPS itself tried this some years ago; it was called "ARC" - the notion was to put together a standard for a commodity hardware platform that was not based on Intel's badly designed CPUs and outdated instruction set. Alas, the effort failed to garner enough momentum from the industry or interest from consumers, and so it died.

If you really want an alternative to Intel, keep pushing on Linux, NetBSD, FreeBSD, et. al. to port cleanly to as many different kinds of computers as possible. If we get the OS sufficiently independent of the hardware that you don't have to care what it is, you will be able to buy hardware with the best price/performance available, and the hardware guys will be freed from the tyranny of the "Intel Standard" to go and design better architectures.

A little steep for an intel based machine.
Regardless of no. of processors or speed,
it's no SGI. I called SGI and for a basic
SGI ONYX^2 Base Reality 2x 195Mhz RS10k .. yada
system its only $70,000. The basic setup
for this 8 xeon proc box is $100,000.

-Z