Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 



Forgot your password?
typodupeerror
Check out the new SourceForge HTML5 internet speed test! No Flash necessary and runs on all devices. ×
Transmeta

A Transmeta Couplet 79

Godfather writes: "According to the heise-people the 600-MHz-TM5600 performs somewhere in between a Pentium III-400 and a Pentium III-600. It seems to be amazingly fast in memory access. The article is in German so you have to try the fish." A better translation would be appreciated, too, since Babelfish still leaves certain things murky. And if you've heard enough about the upcoming Picturebook, Timothy Brown writes: "Fujitsu is releasing (in early November) the Loox-T laptop, with a 500Mhz Crusoe chip. It's only available in Japan, but Dynamism, a company which sells Japan stuff to purchasers in the U.S., is accepting preorders." Here's that link.
This discussion has been archived. No new comments can be posted.

A Transmeta Couplet

Comments Filter:
  • To wit:

    The machine is not fur gefingerpoken and mittengrabben. Easy snatches if that is branching factory, blowenfusen and corkenpoppen with sharpen-deactivate. Is not fur trades by the dummkopfen. The rubbernecken sightseeren keepen hands in pockets. Relaxen and vatch blinkenlights!!!

    I still don't get it, though...

    t_t_b
    --
    I think not; therefore I ain't®

  • I'm still annoyed that there's no serial port on Sony's recent laptops...


    OpenVerse Visual Chat: http://openverse.org [openverse.org]
  • This is pretty old. It's a sign people sometimes put on their console when they are away from their desk. It's a humorous pseudo-German warning not to touch the machine.
  • Calvin was one of the major guys to write in a non-Latin language.

    Actually, I believe that his Institutes of the Christian Religion was published in Latin. Of course, it was also published in French and I don't know which one he originally wrote it in--but there you are. Whoa, this is really getting offtopic!

  • Here's what I get on our Rebel.com Crusoe TM5400 (533 MHz) based NetWinder that is in development.

    # uname -a
    Linux redhat62 2.4.0-test8 #29 Mon Oct 16 12:40:09 EDT 2000 i586 unknown

    # cat /proc/cpuinfo
    processor : 0
    vendor_id : GenuineTMx86
    cpu family : 5
    model : 4
    model name : Transmeta(tm) Crusoe(tm) Processor TM5400
    stepping : 3
    cpu MHz : 531.482082
    cache size : 256 KB
    fdiv_bug : no
    hlt_bug : no
    sep_bug : no
    f00f_bug : no
    coma_bug : no
    fpu : yes
    fpu_exception : yes
    cpuid level : 1
    wp : yes
    flags : fpu vme de pse tsc msr cx8 cmov mmx
    bogomips : 1035.47

    # dnetc -bench # abbreviated
    Benchmark for RC5 core #2 (RG class 6)
    1,398,112.00 keys/sec
    Benchmark for OGR core #0 (GARSP 5.13)
    2,425,544.844 nodes/sec

    --
    Andrew E. Mileski - Software Engineer
    Rebel.com http://www.rebel.com/
  • : ... I thought this was going to be a story about Transmeta poetry.

    : Help! Help! I'm being repressed!

    Nah. The poetry comes after they have their IPO, right? :-)

    Seriously, I wish someone would address some details (like XF86Config settings, etc.) to help all the geeks out here who would like to run Linux on it.

  • thats entirely untrue. as a matter of fact, the vatican employs one man whos single job is to invent new latin words to keep up with the world. although much of latin could be considered dead, it is in fact a thriving language in certain parts of the world.

  • From the one guy's translation, I think the ID number is more like an identifier for the microcode translator inside the CPU, a kind of a version number that isn't unique across 2 identical TM-equipped Vaios. ICBW, of course.

  • by sfid ( 33738 )
    Yeah, it's nice and all hearing about the new prosessors from Transmeta, but what ever happened to the russian E2k processor [slashdot.org] from the Moscow company Elbrus?
  • That built in camera really is tempting, y'know ...

    Other than that, you're right about the G3 powerbooks ... they're amazing for the battery life, and esp. the 400Mhz variety is a huge bargain in its stock config vs. a comparably equipped Intel type laptop.

    However, the thing about a picturebook (even discounting the sexy camera) is that is is *so small and light*. Powerbooks, again, are a bargain in the weight department as well vs. similar laptops, but they aren't 2.2 lb. cuties.

    This raises the question ... WHY NOT?! :)

    I would love a powerbook running OS X the size of a picturebook, with a little bulge for the internal airport card!!! Please, Apple? Smaller hard drive (as in 6 or more GB) -- Fine! external drives / docking? Fine! No camera integrated? Fine! But make it small, battery efficient, and with a workable keyboard (the picturebook isn't as bad as I'd feared) and I am so sold ...

    (sigh)

    timothy

  • Luther wrote in Latin as did most of the Catholic church. Given the fact that most of the educated people of the time were in the clergy, the educated people DID use Latin. Calvin was one of the major guys to write in a non-Latin language. I believe that some of Newtons stuff was written in Latin too (don't quote me on that!)
  • So what kernel options do I use to compile for a chip which can emulate just about anything? Would it be possible to turn on MMX and SSE, as well as 3DNow! ?
  • One more time, for the idiots:

    Simply making the CPU more power-efficient WILL NOT increase the total battery-life very much at all for a notebook computer. There are other things using up that battery too, you know. Mostly the backlight for the LCD.

    Transmeta is full of marketing-type shit with their battery-life claims.
  • Latin was never the language of choice for educated people, even in the times of the Roman Empire. I believe that was Greek (?).

    Go read your history and quit sounding like an asshole.
  • Have to admit... haven't tried W2K on this laptop... have NT4 and RH6.2 dual-booting.

    Two things:
    o W2K may be all wonderful and shiny, but Linux knocks the socks off it for some things, like text processing, some scientific apps and instant stats generation. That's my use for it.
    o A lot of the talk about web-pads and other mini-computer-thingies have centred on their using Linux... I haven't heard of any moving towards WinME or CE or any of their other stuff... so caging linux as a "server OS" doesn't swing. Linus publicly played Quake on it... I haven't seen many servers running Quake.

    BTW, ESR is getting wadloads without "sucking down the bucks" from a company that doesn't use him... I could name many more.
    --
    We may be human, but we're still animals.
  • ...who cares. The only serious laptop OS is windows 2000 (don't comment unless you've tried it to see what I mean). Given the volume of windows on laptop's and the (at least initial) target of this chip is low power consumption laptops - who cares how it runs server OSes...

    Linus? Input? He's sucking down the bucks from the only place that'll pay him. I question how much he did to earn it.
  • This puppy has a unique serial number exposed that can be used to track you...

    Where is the same outrage we heard when Intel (profitable company) did what Transmuta (won't make a dime company) is doing?

    Ahhh yes, I forgot, Linus is involved...
  • I must tell you that NT4 is horrible for laptop users - you simply must upgrade to w2k for your laptop. you will be simply amazed at how much improved your battery life and overall performance will be.

    I'm curious - what types of scientific apps and instant stants generation for RH (nothing comparable under win32?)

    Quake runs on any windows machine (so long as the video card has opengl support), server or otherwise.
  • Ummm, remember this is a third party selling hardware that is NOT being supplied by the manufacturer in this country... Thus there is a fairly large mark-up... Hell, look at the Libretto on the same site.. if I recall it's a pentium 266 and is going for like $2700....

    Now look at the Sony Picturebook being provided by the manufacturer in this country.. $2299... Oh, and I wouldn't hold my breath for the LOOX to be sold in this country... but that's just MHO...

    .technomancer

  • what i want to know is where we can get pIII 400's :)

    B1ood

  • I'd like to see some notebooks in the Vaio 505 line be shipped with Crusoe processors. Since they are still quite small and light, but with a larger screen and some have lower price tags than the PictureBook. Has Sony decided to phase out the 505's with the new SR (5 & 7) line?
    An SR with a Transmeta processor could work too, haven't seen one in person yet.

    --
  • Okis, next time stfu!
    Person who speaks more than one language: Bilingual
    Person who speaks one language: American
    Whenether it's karma whoring or not, it still helps other persons to understand the text :p
  • the 600-MHz-TM5600 performs somewhere in between a Pentium III-400 and a Pentium III-600

    Like a Pentium III-500 you mean?
  • Though what thats about i know not.....

    s'ok everybody else does
    thanks for a laugh

    .oO0Oo.
  • Well, if CPU identification goes into the next Mozilla build as planned... then, I'd say, "a piece of software .. to target ads more effectively." The problem is that AOL is demanding that CPUID functionality be built in so they can better target AOL shopping ads and identify who is currently an AOL subscriber so they don't waste their time and money sending banners about AOL service to them. No doubt, AOL will be involved in some dirty, under-the-table deals with doubleclick in the near future. This should get interesting.
    ---
  • would it be possible to use the transmeta cpu for emulating a k8 sledgehammer oder a itanum cpu ? wow the crusoe goes 64 bit , YEAH ;-) this looks mor sencefull to me than spent 384 megs of ram :-)
  • They were talking about speed. They also said that they will have a complete test next week. I am not sure if they will publish all the details on their website, though. You will probably have to buy the C`t nagazine to get the full results. They are in the publishing business after all. Marcus
  • I remember reading an article many months ago concerning the speed of the Crusoe processor(No clue where at, anyone know?). In the article it talked of how when designing the chip, the people at Transmeta, being of mostly non-windows backgrounds, didn't take into account all the intricacies that Microsoft puts in their OS, and thus when they finally tested it on Windows, to bombed, vs. great performance on other OS's. They then went back and did some redesigning to bring the performance up, however, it still acts slower than it is under windows. This was quite a while ago, so hopefully someone can point to a newer source of news on this. -_-CarpeDiem_-_
  • Who care's if it is "per-cpu identifiable"? Your computer already has expoitable serial numbers all over from software to hardware MAC addresses. Ever try to run quake3 twice on the same LAN, or photoshop or any other heavily pirated program? I do wonder how useful these numbers are however. No browser or software I know of sends local hardware serial numbers to a remote host. And even if they started, it would be relatively simple to remove or forge that infomation at before it left you computer or the network.

    Does anyone know how this CPUID command works on SMP machines? I would assume it return the ID of the CPU in slot 1.
  • I have seen a Transmeta Crusoe TM5400 running at 533 MHz posting a BogoMIP score of 992. This compared to a StrongARM SA110 at 275 MHz posting 233 BogoMIPs. Say what you will - I was impressed! Seems the system was one of the new NetWinders ...
  • About what Linus does over at transmeta..and I saw a coupla other posts wondering the same thing...So, I looked it up, and he is not a top executive or anything, just a simple soul coding software so that transmeta processors can communicate with normal software/hardware...I was under the impression that he was in charge...but..I was wrong.


  • everything you say is pretty much on the mark, IMHO. Light weight, big disk, and battery life are everything. PictureBooks and Vaio505's are great machines, and I'm speaking from direct experience. Above 4 pounds is too heavy for me to take seriously as portable.
  • Correct on the backlight. What would be nice is a backlight with a dimmer switch. Maybe even a translucent back to the display to allow use of ambient light, so you can turn off the backlight altogether. As for RAM, I don't think it consumes very much power. My computer has an open case and whenever I reach in and feel my DIMMs they are hardly even warm. The more power flowing through a device, the warmer it runs (as a general rule).
  • Das machine is nicht fur gefingerpoken und
    mittengrabben. Ist easy schnappen der
    springenwerk, blowenfusen und corkenpoppen mit
    spitzensparken. Ist nicht fur gewerken by das
    dummkopfen. Das rubbernecken sightseeren keepen
    hands in das pockets. Relaxen und vatch das
    blinkenlights!!!
  • Huh? I heard my name.
    ---
  • A well-designed notebook doesn't have a fan, it uses the case as a giant heatsink.
  • Except that pnambic translated "durchaus ordentlich" with "impressive", which is wrong. "pretty good" or "decent" are much better translations.

    Too bad this short review didn't include anything about battery life. The claims Transmeta makes are somewhat ridiculous in this regard, sometimes claiming double the battery life even though the processor accounts only for around 20 percent of power usage in a modern notebook.

  • No, the article says that the CPU ID is generated *by* the codemorphing software. IMO that means it's a software construct (which could potentially be removed, changed, faked, etc) but it's still there. I'm not sure why they say that CPUID gives a serial number, but that the "true" Athlon-compatible CPUID instruction does not do this. Does an x86 processor have two different instructions for getting the CPU ID?
  • massively increased (ie 2x or 3x) battery life

    Don't count on it. Most of the power in a notebook is consumed by the backlight and RAM. The CPU accounts for a relatively small percentage. They couldn't even get that kind of battery life if the CPU used *no* power.

  • "Transmeta announces more blah, blah, blah. Their chip is fast, blah, blah, blah. Pentium killer, blah, blah, blah."

    Transmeta is a science project, not a market reality. No mention of high volume production, razor thin profit margins, intense market competition.

  • s'ok everybody else does
    thanks for a laugh
    Arww explain the joke DrThingymawatsit
    &#9786
  • I thinks this is a good developement, if the crusoe chip can get out in volume, and offer massively increased (ie 2x or 3x) battery life, then the venture should become profitiable very quickly. The main point of this, to me anyway, is that I think low power chips should be very useful on the desktop, finally realising the dream of a silent-running PC. This isnt going to happen (in the intel world anyway) until low-power chips are selling in the volumes necassary to begin to compete on price

    One thought that occurs to me, is that, for those of us outside the Windows world, there are presumably some alreay existant low-power CPU designs out there (the last generation of StrongARMs spring to mind, there must be others). Does anybody know if any company is making low-powered linux/BSD portables now?

    Also [inadvertantly starting a flame war?] how do the various OSes stack up in their use of notebook features, in power-management, in the execution of 'sleep' modes, etc etc
    {as you might have guessed, im buying my first notebook soon &#9786}

  • My germans pretty awful, but it basically means:

    The machine is not for poking or holding [grabbing?]. It easily breaks or stops working, blowsfuses or explodes spitting sparks. It is nor for use [operation?] by stupid-heads [idiots]. The rubbernecked sightseers should keep there hands in their pockets, Relax and watch the lights blink!!

    Though what thats about i know not.....
  • is it legally binding?
    can i sue?

  • an ~500MHz i386 chip could be a little of an overkill, even for those fancy, all singing graphical calcs, surely an low end ARM, or something by TI would be sufficient

    .....opps just noticed you were an AC, have I been trolled?

  • lmmfao &#9786
  • This is true,
    Its also made me realise that i've never really thought about calculators having OSes before.
    So kiddies, sharpen your tongues, and prepare your FUD attacks because.................
    ..............its time for the calc-OS FLAMEWARS

  • Does anyone have an idea how people plan to benchmark this processor?

    One feature of the Crusoe processor's emulation is that it gets faster with repetition.

    How is this going to work if a benchmark was to be run 3 times?
  • It depends on which version of code morphing software you have.

    I know that as of now it doesn't support MMX, because it generated too much heat.

    I've looked all over the crusoe web site and their .pdf files. There is no mention as to exactly what it morphs.
  • Yeah, but if it gives off less heat, it needs less fan and less shielding and we don't get the Laptop From Heck or How I Learned To Use My Laptop To Melt Ice Off My Windshield.

    Or maybe that's a bad thing.

  • Oh. Too bad I can't change my username.
  • No. Just have to post double as much then, because each post earns -1 instead of -2 Karma.
  • Which used to be the language of choice for educated people. But, oh wait, there's no educated people anymore.
  • And a slow one, on top of it. pnambic beat him by 10 minutes.
  • Slashdot is the right place for you.
  • Who said I was talking about the times of the Roman Empire? In the Middle Ages, it was. Dumbass.
  • to make it slower than today.
  • Didn't -100 use to be the threshold where you start posting at -1? That should make it somewhat difficult to go much below that.
  • ...check this out:

    http://www.spec.org/osg/web99/results/res2000q2/ [spec.org]

    Vendor: Dell
    Model: PowerEdge 6400/700
    Processor: 700MHz Pentium III Xeon
    # Processors: 4
    Memory: 8 GB
    Disk Subsystem: 7 9GB 10KRPM drives
    Operating System: Windows 2000 Advanced Server
    File System: NTFS
    HTTP Software
    Vendor: Microsoft
    HTTP Software: Internet Information Server 5.0
    Conforming Simultaneous Connections (Median): 1598

    Vendor: Dell
    Model: PowerEdge 6400/700
    Processor: 700MHz Pentium III Xeon
    # Processors: 4
    Memory: 8 GB
    Disk Subsystem: 5 9GB 10KRPM drives
    Operating System: Red Hat Linux 6.2 Threaded Web Server Add-On
    File System: ext2
    HTTP Software
    Vendor: Red Hat
    HTTP Software: TUX 1.0
    Conforming Simultaneous Connections (Median): 4200

    Of course, it all means nothing, I'm sure...

    ...just mere numbers.

    Right?

    t_t_b
    --
    I think not; therefore I ain't®

  • THE CPUID INSTRUCTION DOES NOT VIOLATE PRIVACY.

    repeat until you understand. most cpu's do provide cpuids. it's used mainly for licensing - and there are ways around that. obviously if a company can't depend on a cpuid for locally running apps, they'd be foolish to depend on one for non-local apps.

    i am not an intel fan. but the cpuid fiasco was a tempest in a teapot. a marketing person at intel made a stupid comment - stupid for techincal as well as non-technical reasons. but marketing people are *supposed* to be stupid in any company! but the complete and utter stupidity of harping on it by "privacy activists" makes that marketing droid look downright brilliant in comparison.

    so enough already with the cpuids. sun has had them since the 80's. macs have them (or they should). aix boxes have them, hp/ux, etc. big deal. it's not an issue. this windmill has been tilted at enough, go find something real to work on.
  • Don't count on it. Most of the power in a notebook is consumed by the backlight and RAM. The CPU accounts for a relatively small percentage. They couldn't even get that kind of battery life if the CPU used *no* power.

    True. Of course, the TM5400 also swallows part of the PCI bridge, and eliminates some of the other legacy devices that are normally out in the chipset by emulating them in software at the Code Morphing level. Both of these steps also help save power (fewer bus transactions, fewer off-chip peripherals) that wasn't being counted towards the CPU to begin with. (Incidentally, having part of the PCI bridge onchip may account for those impressive memcpy/memset scores.)

    Still, this isn't quite the same as integrating the backlight onchip. ;-)

    --Joe
    --
  • When I saw the headline, I thought /. had sunk to a new low--I thought this was going to be a story about Transmeta poetry.
  • A bloody three-hour battery life.

    That alone takes it out of the running.

    The Psion 5mx gets a *FULL MONTH* off two AA batteries. And runs Office-compatible software.

    Now to be sure, there are some deficiencies when looking at the Psion: relatively low-res, grey-scale LCD, and limited software selection. But it satisfies for about 90% of typical laptop use: wordprocessing, daytimer, calculator, web browser.

    I'd like to see something that strikes in the middle: about a week on a full charge and a high resolution grey-scale screen, and more apps.

    That'd make for a really great laptop.

    --
  • Good luck getting a week's battery life with a hard drive, colour TFT screen, and 500+ MHz Intel-compatible processor. Oh, the Psion doesn't have any of those, does it... Not surprising it has a completely different level of power usage, then.

    Try comparing apples to apples - it sounds like you would be better off using a WinCE notebook-format device, maybe with Linux on it since this is slashdot :)
  • still, double is over the top.
  • The CPUID instruction looks at a "function" number in a register. (EAX, if I recall). If it's one value, it returns what processor type it is. If it's another value, it returns a bitflag of known capabilities. If it's other values, it returns the range of legal values for this function index. New functions can be added by different processors.

    In the Piii, CPUID supported a function to return a unique per-chip number. They later recanted, returning identical garbage or zeros on all Piiis.

    To be compatible, Athlons followed suit: they made a damaged CPUID function akin to Pentiums.

    The article SEEMS to be saying that the Transmeta emulates the Athlon's implementation, but that a NEW function is available to get unique per-cpu numbers.

  • That note was created in the 1940's by US computer scientists working with the imported Nazi scientists. The US scientists decided to have a little fun one day... and the rest, as they say, is history!
    ---
  • The difference between post #15 and #28 on Slashdot, in time, is nearly non-existent. I'm quite sure post #15 wasn't there when Ashran began his translation.

    Also, I found the translation in post #28 much easier to read due to better formatting and more natural-sounding English (sounded less like a literal translation than #15).

    So maybe you could shut up? Thanks.

  • Latin is great for talking about religion, and Caesar's conquests in Gaul, but since it is a dead language, it would be kind of hard to use it to discuss the latest in laptop technology.
  • Crusoe T-Labor transforming tM5600 of Transmeta (in Sony Vaio) must at this moment prove-lhea T-Labor. First Benchmarkergebnisse of the movement 600-MHz-TM5600 in the sector enters Pentium III-400 (approximately it it t-Apfelmaennchen with badly 15 million iterations to as) and Pentium III-600. The operation of the memory is total clean for the small notebook, MByte/s starts above approximately stops of MemCopy with the 60 and hangelt with of the blow hidden in the translations of intermediary of the storage of the transforming one in 170 MByte/s. The letter in the memory (for Memset) cría the transforming one with the 280 MByte/v. good with the matching, Pentium III 500 with of the Chipsatz iI is delayed distant in this only disciplines with the 70 respectively 150 MBYTE. Pentium-III-Coppermine-800 in the board i815 is approximately immediately with 190 and 255 MByte/s. It is so interesting as crusoe of the one of hashing gives a number of CPUID work (not to abschaltbar with Vaio). This number of the work of logical software that morphing CMS () only produced not obstante obvious. Commando " the truth ", (in a compatible way in Athlon aMD) does not announce the number of the work for the transforming one. In the other hand, Transmeta did not define to exist commando $$MPXCHG8 that a transforming one of the Pentium of the classroom worked perfectly with " " the official features, since that Windows NT comes beyond with exception to a stool, if (this capacity offers to the families - identification 5). T the following week will publish other values of consumición electric the power and the test test standard (as/c ' T)
  • by Splat ( 9175 ) on Sunday October 08, 2000 @06:23AM (#722807)
    Boycott this translation! Babelfish is closed source! You should be using GPLTrans [sourceforge.net] instead! We cannot let the corporate hegemony of Slashdot dictate our translation ways! [recommended moderation: funny] But eh seriously... why doesn't GPLTrans ever get mentioned? I find in most of the cases with these non-english articles, it produces much more readable text than MangleFish.
  • by Pengo ( 28814 ) on Sunday October 08, 2000 @05:29AM (#722808) Journal

    Has anyone actually used one of those things? I currently am using a Sony Viao F409. It has a 650mhz PIII w/15" display. Very nice, and with 2 batteries I get almost 4 hours out of the thing (Its floppy drive swaps out for an optional second battery).

    Pro's of a big laptop: It's nice when it's actually on your desk, cables all undone, plugged in, re-set my network connection settings.. (I don't use DHCP in the office or at home lan). Booted the machine, plugged in my external mouse and keyboard. (No docking station for me!)

    The Picturebook seems nice, with exception that you don't have the large screen. (Only a half-hight ??). This might be ok if you are plugging into a monitor at the home/office .. as 90% of my work w/my laptop is somewhere where I have an external monitor to plug into the thing.

    I have upgraded my machine to 256 megs of ram which is really nice, and I have RedHat 6.2 working nicely with my USB mouse. The main problem is getting my External monitor to work correctly in XWindows, but maybe that is probably more due to my ignorance in XWin configuration than the laptop.

    I guess, the whole point of my babeling.. I have purchased and invested in what I thought would be the 'Dream' laptop. It's fast and nice with a great display that runs linux very nice... As now I spend really no time programming and all my time doing network diagrams, technical specifications and network administration on it.

    But despite all the great hardware on this laptop, the reality is ... It's a pain in the ass to lugg around. It takes a while for the thing to boot up and shut down, etc. and I feel that I am dragging around a TON of cables everywhere I go. It costed me over £300 for memory and battery to try and increase the battery life over the pathetic 2 hours it does normally. I can't really work w/it in bed because the thing gets so damn hot sitting on my lap..

    Anyway, this is from someone that has invested a very large amount of memory into a laptop. Frankly I am a bit disapointed and am considering a picturebook to replace it.

    Has anyone got any real practical experience using a picturebook? It sounds to me that the battery life/size and ease of porting it around. (Just toss it in my rook-sack and take it, battery lasts the whole working day and bring it home and charge it!) No cables.. etc.

    Anyway, don't want to run down a fools paradise.

    ;-)


    --------------------
  • by Nailer ( 69468 ) on Sunday October 08, 2000 @11:19AM (#722809)
    > The "real" CPUID command, (compatible to the AMD-Athlon) returns no Serial-Number back.

    Interesting - I thought the AMD Athlon has no CPUID `feature' - there was old recent issues with Red Hat 6.2 and Athlons, where the kernel would detect a PIII compatible chip pthis was before Red Hat started doing Athlon Kernerls] and attempt to disable the CPUID feature. Following finding a PIII, thre kernel would try to turn of CPUID [yay kernel people!] and die horrible, because AMD Athlons apparently didn't have one.

    Or do they?
  • So we have a study of performance on NT, ONE study. As anyone who has been following benchmarking issues (c.f. recent IIS vs. Apache on Dell) will know, we can't really guess anything from this test.

    What would be VERY nice is if some enterprising lab got together (ArsTechnica, overclockers.com etc.?), played with this beasty with a number of configs, a number of OSs (NT, Linux, BeOS, BSD, etc), and ripped out a few stats.

    Hey, even a comparitive IIS vs. Apache on THIS machine would be fun. How would PHP work with all of this code-morphing cache stuff?

    Still, I have to wonder how much input Linus has in all - the focus at the press release time was VERY much on NT, except for the embarrassing Quake moment. Anyone know of a publicly available set of Linux tests on one of these?

    Can't wait 'til the webpads though. That'll sort out the "debian on iPaq" trolls...
    --
    We may be human, but we're still animals.
  • by Speare ( 84249 ) on Sunday October 08, 2000 @05:31AM (#722811) Homepage Journal

    Another interesting fact is that the Crusoe processor supplies a serial number via CPUID... The "true" CPUID command (compatible with the AMD Athlon) does not yield a serial number.

    I don't get it. They want to appear "privacy friendly" by not implementing the Intel Pentium III CPUID serial number code, but they are still per-cpu identifiable.

    Which will come first, the big Linux-world outcry that Linus Torvalds works for a privacy sellout, or a piece of software that sniffs the Crusoe's cpuid-stained butt to target ads more effectively?

  • by istartedi ( 132515 ) on Sunday October 08, 2000 @01:52PM (#722812) Journal

    OK, I triedGPLTrans [translator.cx] just now:

    This is a test of GPLTrans. I wonder if it's better than Babelfish. Mary had a little lamb, it's fleece was white as snow. Everywhere that mary went, the lamb was shure to grok.

    Dieses ist eines Test über gPLTrans. I Wunder wenn it's besser als babelfish. Mary hatte eines wenig Lamm, it's fleece wurde weiß wie schneien. überall dies mary gingen, die Lamm wurde shure zu grok.

    When I tried to translate this back to English, I got an internal server error.

    It seems to handle nonsense words and proper names by passing them through (what else could it do). Contractions don't appear to work well, unless ``it's'' is valid German.

    I'm not sanguine about the GPL either, but as long as there is more than one option, I think we should know about it. Is anybody aware of any other on-line translation services?

  • by Ashran ( 107876 ) on Sunday October 08, 2000 @05:24AM (#722813) Homepage
    Well, my english is not perfect, so please bear with me =).
    I hope this translation is better than what the fish blurps.

    <Translation>
    The TM5600-Processor of Transmeta (used in the Sony Vaio) has to prove itself in the c't-Test-Facality right now.
    First Benchmark results show that the performance of 600-MHz-TM5600 is between the
    performance of a PIII 400 (while using the Appleman-testprogram, with about 15 Million iterations / sec)
    and a PIII 600.

    The Memory performance is pretty good for such a small Notebook,
    it starts with 60 MByte/s (MemCopy) , and goes up with Cache-Hits in the Translation buffer (to 170 MByte/s).
    Writing to the Memory (using Memset) is at about 280 MByte/s.
    To compare:
    Pentium III 500 (Via-Apollo-II-Chipsatz) writes with 70 Mbyte/s and 150 Mbyte/s.
    Pentium-III-Coppermine-800 (Solano-i815-Board) is about as good, with 190 MByte/s and 255 MByte/s.

    An interesting thing is, that the Crusoe-Processor responds to the CPUID command. (Cannot be disabled in the Vaio.
    But the Serial-Number seems to be calculated by the Code-Morphing-Software.
    The "real" CPUID command, (compatible to the AMD-Athlon) returns no Serial-Number back.

    There is no correct working CMPXCH8 command in the official specs,
    because Windows NT depends on the wierd behavior of a non correct CMPXCH8 if it detects a Pentium-Family CPU (Family -ID 5)
    (my note: AFAIK Intel first implemented a non RCF CMPXCH8 command)
    </Translation>

  • by pnambic ( 3298 ) on Sunday October 08, 2000 @05:14AM (#722814)
    Crusoe in the c't labs

    Transmeta's TM5600 processor (built into a Sony Vaio) is currently undergoing c't labs' scrutiny. The first benchmark results put it into the range between a Pentium III-400 (e.g. the c't Mandelbrot fractal at about 15 million iterations per second) and a Pentium III-600. Memory performance is impressive for a small notebook, starting with about 60MB/s for MemCopy and increasing to about 170MB/s for cache hits within the processor's translation buffer. Write performance (measured via Memset) peaks at about 280MB/s. In comparison, a Pentium III-500 with Via-Apollo-II chipset won't reach more than 70MB/s and 150MB/s, respectively. A Pentium III-Coppermine-800 on a Solano i815 board comes in close at 190 and 255MB/s.

    Another interesting fact is that the Crusoe processor supplies a serial number via CPUID, which cannot be disabled, at least in the Vaio configuration. This serial number seems however to be generated exclusively by the code-morphing software. The "true" CPUID command (compatible with the AMD Athlon) does not yield a serial number. Additionally, Transmeta declared the otherwise flawlessly functional CMPXCHG8 command as not available in the list of official features, since Windows NT can't cope with a Pentium-class processor (family ID 5) supplying this feature.

    Further benchmarks and power consumption measures will be published by c't during the next week.

There's no sense in being precise when you don't even know what you're talking about. -- John von Neumann

Working...