Slashdot Mirror

← Back to Stories (view on slashdot.org)

Ars Technica Interviews 970 Designers

Posted by Hemos on from the talking-wtih-the-man dept.

11223 writes "John "Hannibal" Stokes has interviewed Pete Sandon, the PowerPC 970's main designer, and David Edelsohn, a compiler writer from IBM, and clarified several points about the 970 regarding group formation, vector issue queues and performance, and more. The interview is a very interesting read for anyone who has been following his earlier articles on the processor that Apple calls the G5."

46 of 225 comments (clear)

  1. Anybody else by Pxtl · · Score: 5, Funny

    misenterpret this to mean "ars interviews nine-hundred and seventy different people"?

    1. Re:Anybody else by Just3Ws · · Score: 2, Funny

      Yep, I was wondering if any of the nine hundred and seventy designers would have had anything to say about the /. gamers section?

    2. Re:Anybody else by cK-Gunslinger · · Score: 4, Funny

      I did. I just thought Ars was trying to 1-up Anantech on their 13- Motherboard CEOs interview.

  2. Whats with this? by Anonymous Coward · · Score: 3, Funny

    I don't want to start a holy war here, but what is the deal with you cat fanatics? I've been sitting here on my sofa in front of a cat (a sealpoint siamese) for about 20 minutes now while attempting to get it's attention away from a bug on the floor. 20 minutes. At home, with my labrador cross, which by all standards should be a lot dumber than this cat, the same operation would take about 2 minutes. If that.

    In addition, during this attention seeking attempt, my children's attention is also held by the cat. And everything else has ground to a halt. Even trying to get the remote from my partner fails.

    I won't bore you with the laundry list of other problems that I've encountered while dealing with other cats, but suffice it to say there have been many, not the least of which is I've never seen a cat that fetches as much as it's canine counterpart, despite the cat's faster ambulatory system. My terrier with one ingrown toenail runs consistently faster than this siamese at times, as the cat is often completely asleep. From a productivity standpoint, I don't get how people can claim that the cat is a superior animal.

    Cat addicts, flame me if you'd like, but I'd rather hear some intelligent reasons why anyone would choose to use a cat over other faster, cheaper, more affectionate animals.

    1. Re:Whats with this? by Thud457 · · Score: 2, Funny
      Yeah, but most of the time, it's fetching half dead small furry / feathered / slimy things which flail around getting blood on your carpet and drapes until you catch it.

      You should really be less pitiful as a hunter. You're emberassing your cat.

      --

      the preceding comment is my own and in no way reflects the opinion of the Joint Chiefs of Staff

  3. 970 designers! by HardcoreGamer · · Score: 3, Funny

    Ars Technica Interviews 970 Designers

    970 designers! Holy nerd-fest Batman! That's where Gotham's entire supply of throat lozenges disppeared to!

  4. Altivec execution by BWJones · · Score: 3, Interesting

    I was interested to find out find out they used the older Altivec instruction unit rather than the one from the G4e. Is there anyone that can comment of differences between the two Altivec units?

    --
    Visit Jonesblog and say hello.
    1. Re:Altivec execution by Jon+Abbott · · Score: 5, Informative

      The following was snipped from this message:

      "The AltiVec subunits are more independant than in the 7400, i.e. there isn't just a single vector ALU, instead the vector FPU, vector simple IU, and the vector complex IU can now accept AltiVec instructions concurrently (up to two vector instructions per clock); this means technically, the G4e does have 4 AltiVec units, while the MPC7400 has only two, but in practice the G4e merely relaxes some instruction scheduling restrictions that the 7400 has to adhere to."

      --
      Slashdot's first reaction to VMware
  5. IBM in the apple.slashdot.org section ? by peterprior · · Score: 3, Funny

    1) I never thought I'd see the day.
    2) That logo clashes like hell with the sexy aqua theme 8|

    1. Re:IBM in the apple.slashdot.org section ? by Raster+Burn · · Score: 3, Funny

      Strange... the eight bar logo lines up with the aqua-style bars perfectly.

      conspiracy!

    2. Re:IBM in the apple.slashdot.org section ? by Drakonian · · Score: 2, Informative
      1) That day was a long time ago.

      I'm assuming it was even longer than that. IBM has made the G3 for Apple for ages.

      --
      Random is the New Order.
    3. Re:IBM in the apple.slashdot.org section ? by peterprior · · Score: 3, Funny

      Don't normally reply to myself, by I just thought about it further and realised that the IBM equivalent of the Imac girl would be Optimus Prime

      ..Scary stuff :|

    4. Re:IBM in the apple.slashdot.org section ? by valkraider · · Score: 4, Interesting

      Why is Apple+IBM such a new thing?

      How about October, 1991?

      More info about the PowerPC alliance.

      Apple never said that IBMs *technology* was no good. They said that IBM made boring corporate Personal Computers that didn't foster individuality and creativity amongst it's users. I would say that is still correct.

    5. Re:IBM in the apple.slashdot.org section ? by clarkcox3 · · Score: 2, Informative

      IBM makes the G3's that Apple currently uses (i.e. in the iBooks), Motorola makes the G4's.

      --
      There are no tiger attacks in my area and it's all because this rock I'm holding keeps the tigers away.
  6. The Reality Distortion Field by Jon+Abbott · · Score: 4, Funny

    One of the best quotes from the interview was from David Edelsohn: "IBM is not gonna try to compete with Apple's reality distortion field :)"

    --
    Slashdot's first reaction to VMware
  7. Windows based 970? by Bill,+Shooter+of+Bul · · Score: 5, Interesting

    I think if you read the end of the article where they are talking about the possibility of straight non apple boxes with 970 inside, you'll notice that they can not reply. Why not? It would be obvious to have linux based servers on top of the platform, so to have no responce to that makes me wonder if they aren't talking to soemone else about something nonobvious. What is the most non obvious step that would really get it in trouble with apple? Another deal with Microsoft. Heck the NT Kernel is portable and is currently being ported to itanium2 and amd64 why not ppc 970? I don't know how closely apple has tied panther to Their chipset, but if it isn't too tight this could mean cheap apple clones( they wouldn't ship with osx, but it could be installed). Now that would kill apple, and as a guy who had advance knowledge of it, I would simply say "No Comment" when asked about non apple based ppc 970 platforms.

    --
    Well.. maybe. Or Maybe not. But Definitely not sort of.
    1. Re:Windows based 970? by pv2b · · Score: 4, Interesting

      Not legally.

      You still need a licence to run Mac OS X, and I think it would be trivial for Apple to add a clause (if it's not already there) that would forbid installing the software on non-apple hardware.

      There is also a port of Mac OS X for Intel processors being maintained in parallell, mainly because it CAN be done very easilly with minimal effort. Covering all bases...

      Remember, Apple is a hardware company, and will protect their core business, which currently is and always has been hardware.

    2. Re:Windows based 970? by binaryDigit · · Score: 4, Insightful

      Another deal with Microsoft. Heck the NT Kernel is portable and is currently being ported to itanium2 and amd64 why not ppc 970?

      It is already ported to PPC (maybe not 970, but PPC) and has been since 3.51. Even with that, I _highly_ doubt that Microsoft will venture down that road again. Back in the late 80's/early 90's when RISC was the "NEXT BIG THING", M$ was hedging their bets by making sure that NT was available for all manner of RISC flavours. Now that RISC is "NOT THE NEXT BIG THING", I really don't think M$ cares anymore, to them it's just another platform they'd have to support and probably wouldn't make any money off of.

      Now having it run Linux is a no brainer. IBM is obviously in Linux in a big way, so having some 970 based boxen are obvious. Now having "generic" white box 970's designed to run Linux is a different story. I don't know if this would make sense from a market perspective. Perhaps cheaper commodity based servers? Perhaps giving Dell a run for their money in the Linux market for higher end workstations? Hard to say, esp the latter since IBM is notorious for not wanting to cannibalize their higher end sales by having lower end box's with better price/performance ratios.

      BTW, you can kiss off the Apple clone notion. Makes absolutely no sense for Apple unless they can assure themselves of at least doubling Mac market share by such a move. Anything less would mean a repeat of their previous foray, which Stever would never allow to happen.

    3. Re:Windows based 970? by pv2b · · Score: 4, Insightful

      Apple doesn't want you to buy OS X, they want you to buy a Mac.

      I repeat, Apple is a hardware company.

    4. Re:Windows based 970? by Bill,+Shooter+of+Bul · · Score: 4, Interesting

      Yeah, thats what I'm saying. What would stop people from doing it ( if its technically possible some people will do it regardless of leagality)? Here's a riddle for everyone to think about: If apple's a hardware company what unique piece of hardware does it actually make? The motherboard?
      I think apple is really a software company that has managed to force people to buy hardware from it( at high margins) so their software can be run. As obvious as that statement is, I think many people forget it.

      --
      Well.. maybe. Or Maybe not. But Definitely not sort of.
    5. Re:Windows based 970? by cant_get_a_good_nick · · Score: 4, Informative

      Windows NT 3.51 and 4.0 supported PowerPC. Was dropped because of bad sales. Solaris had a PowerPC port too if you can believe it. This ws all when PowerPC was shiny and new and PowerPC was going to take over the world, giving a consistent platform free of all that x86 cruft. Problem was NT in that day wasn't compatible yet with loads of software, and Windows 3.1 and 95 were very much x86 only, so the software market never followed to PowerPC. Intel threw enough silicon at the problem to make x86 performance acceptable, and the RISC world withered.

      The most interesting thing for me with all this "cheap PowerPC" stuff is it seems to be the rebirth of CHRP, which Apple kind of scotched becasue they were fearful of clones back then. Maybe they realize they need to kill some of the "hardware premium price" and get costs more in line with Intel boxes.

    6. Re:Windows based 970? by pv2b · · Score: 5, Insightful

      People hacking OS X to run on their non-apple machines is not a real threat to Apples.

      COMPANIES selling non-Apple machines running OS X are a real threat to Apple.

      The legal issues won't stop the first crowd (but then again, Apple won't have lost a great deal), but the people who actually buy computers and work with them as well as Joe home user will not go to any lengths to save a few bucks just to run OS X on a non-Apple box.

      That's where Apple gets its money -- and it's pretty well protected.

      Apple does make the entire computer, which is much more than a sum of its parts.

      I'm not sure how many of the components that go into a car (I'm not a car nut) are actually made by the car company themselves, but let's for the sake of argument say that the car company doesn't make any of the components in the car. But the design of the car and putting the car together is still something the car company does, and that is the value they add.

      This is basically what Apple does, to make a product you don't neccecarilly have to make your components yourself.

    7. Re:Windows based 970? by bnenning · · Score: 2, Informative
      You still need a licence to run Mac OS X


      You don't need a license to run software that you buy. See 17 USC 117.

      --
      How to solve most of our problems: 1.Lots of nuclear plants. 2.Cure aging.
    8. Re:Windows based 970? by Johnny+Mnemonic · · Score: 2, Interesting


      Now having "generic" white box 970's designed to run Linux is a different story.

      Hmm...or IBM branded, consumer or corp grade desktops, with 970s, running Red Hat, Yellow Dog Linux, or IBMnix? I think the big advantages would be IBM QA and warranty on the hardware, and a linux optimized for the 970. Commodity parts, no M$ tax, the processor at cost since it's being sold by the fabber=cheap cheap and powerful. Say, $4-500 for a very competent office/workstation machine.

      I can see these on a lot of desktops moving from Windows to Linux...I wonder if IBM knows any?

      --

      --
      $tar -xvf .sig.tar
    9. Re:Windows based 970? by shotfeel · · Score: 2, Informative

      "The motherboard?"

      Well, the chip set for the motherboard. See the second page of the article, under Miscellany, the second question "I also asked at one point about the Apple-designed chipset..."

      I was really hoping we'd find out more about the chip set used in the 970 blades. Oh well.

    10. Re:Windows based 970? by pv2b · · Score: 3, Insightful

      A computer is hardware. Hardware is made by hardware companies. Apple makes computers. Ergo, Apple is a hardware company!

      A computer is more than the sum of its parts. You wouldn't say a car company wasn't a car company merely because it used commodity parts?

      This is redundant of course, since I posted the exact same argument in this thread in this post.

    11. Re:Windows based 970? by shotfeel · · Score: 2, Insightful

      Does that mean Dell isn't a hardware company either?

    12. Re:Windows based 970? by shotfeel · · Score: 2, Insightful

      Ignore my previous post, I didn't grok the "hardware marketing company" vs. "hardware company" difference you were making, though I don't agree with that distinction either.

      One thing to note is that Apple has always designed their own motherboards, including the chip sets. They still do. That would seem to make them a hardware company even as you've defined it.

      Also consider that the PPC architecture is designed by the AIM (Apple-IBM-Motorola) alliance. Thus Apple has had some input in the CPU design as well (how much, I don't know).

    13. Re:Windows based 970? by frankie · · Score: 4, Informative
      What hardware do they make? Last I checked they have gone the commodity PC hardware route

      User-serviceable parts (RAM, HD, AGP, etc) are commodity, but the hard stuff is designed in Cupertino.

    14. Re:Windows based 970? by WNight · · Score: 4, Informative

      What reason is there to expect that EULAs are valid?

      They're post-sale contracts. This sort of thing has never been legit.

      When they show you the license in the store, and you must overtly agree to it to buy the product, then they may be legal. Until then they're lies.

      But, they'll have to be a lot simpler. Judges are already invalidating long small-print contracts for regular consumers. If it takes a law degree to understand, you can't possibly enter into it knowingly. Thus, the company should reasonably know that nobody reads (and hence, nobody agree to) their contracts.

      Further, the concept of post-sale restrictions was decided in the early 1900s, with the First-Sale doctrine. Books were being sold with 'contracts' inside the cover limiting resale rights. It didn't work then, it won't work now, even if the many issues keeping EULAs from being valid contracts were fixed.

      (Such as, they disclaim consumer rights they aren't allowed to disclaim under the Magnuson-Moss warranty act. Many EULAs disclaim all responsibility even if the product doesn't function at all, etc. Not allowed, and in fact, likely criminal to claim.)

      You do everyone a disservice by saying that EULAs might be valid. It's misleading and can be very damaging.

    15. Re:Windows based 970? by TheNetAvenger · · Score: 2, Interesting

      The NT kernel WAS portable. It has been said by MS kernel engineers that with Windows 2000, the changes made to the kernel made it very non-portable.

      I'd like to see this quote, since the majority of the Win2k development cycle (including up to beta 2) supported the Alpha CPU.

      So if Microsoft made NT (Win2k) non-portable did they do it in the Release Client a month or two before release just to screw with people or maybe in a mysterious service pack? Give me a break.

      Win2k WAS designed for FULL Alpha support, and since the ALPHA development was cancelled LATE in the Beta, I seriously doubt they went back to the drawing board and rewrote the NT kernel after 10 years of portable design just to lock it into the x86 platform.

      Besides, do you NOT get that the Itanium support in WindowsXP is not BASED upon x86, but a NATIVE NT Kernel running on the Itanium CPU, which has been available for almost two years now? Additionally the Windows 2003 Server support for the Itanium is a FULL 64 bit OS with a 64bit NATIVE kernel sitting on the Itanium processor. Geesh.

      From the developers we worked with at Microsoft in the past year, even Windows 2003 server (which would include Win2k and XP) still have the basic HAL underpinning design and the lower NT kernel itself is STILL written in portable C.

      According to the 'official' NT kernel development team, NT has been portable, stands by a portable design, and STILL is fully portable even TODAY.

      So if you have some magical information that even the NT designers don't have, please share...

  8. ahh, but by cliveholloway · · Score: 2, Funny
    What I want to know is, what are the other 499 server errors that happen when they get slashdotted?

    cLive ;-)

    --
    -- Trinity in high heels carrying a whip: The donimatrix - there is no spoonerism
  9. Improvements to GCC? by Realistic_Dragon · · Score: 5, Interesting

    At one point in the interview it looks like IBM and Apple are working together on GCC improvements and donating the code back to the FSF.

    This is a fairly big deal as people have pointed out before that GCC on PPC isn't as hot as it should be, but with that kind of muscle and money behind it it should go forwards by leaps and bounds.

    With the new GCC improvements it looks like Linux on those new, remarkably cheap, P970 IBM boxes is going to be a real winner. And AFAIK Gentoo already runs on PPC fine - no one is going to be bitching about compile times with 4 1gig+ CPUs crunching away at it!

    --
    Beep beep.
    1. Re:Improvements to GCC? by Jon+Abbott · · Score: 3, Informative
      This is a fairly big deal as people have pointed out before that GCC on PPC isn't as hot as it should be, but with that kind of muscle and money behind it it should go forwards by leaps and bounds.
      There are some issues with the FSF accepting patches from IBM though, for a number of reasons... This message on the ArsTechnica discussion list explains all of these reasons well, so I won't repeat them here...
      --
      Slashdot's first reaction to VMware
    2. Re:Improvements to GCC? by __past__ · · Score: 2, Interesting
      "Donating" the code back to the FSF? They pretty much have to release it under a GPL-compatible license anyway, if they don't plan to keep their improvements inhouse.

      Apple (or probably rather NeXT, but who cares nowadays) already tried once to improve GCC without releasing their changes, esp. the Objective C support. Turned out not to be such a good idea.

      --
      Programming can be fun again. Film at 11.
    3. Re:Improvements to GCC? by cactopus · · Score: 4, Interesting

      This box -- i.e. even future inexpensive ones are really designed to be Itanium and Xeon killers in addition to Sparc killers. They're basically going to be priced in the 3G-10G range for quite a lot of 64 bit computing muscle and the ability to run AIX. When you outgrow them you can move to POWER4+ on pSeries quite smoothly. A trusted and proven architecture.

      These are basically this generation's Alphas... but with a better market positioning and without Digital/Compaq/HP at the helm. (we all know their pilot is dead at the wheel)

    4. Re:Improvements to GCC? by WatertonMan · · Score: 2, Interesting
      The issue isn't whether they'd release changes to the FSF. The issue is what to do with changes that the FSF doesn't want.

      It may well be that the changes that IBM and Apple want to do to gcc are such that it would violate the basic model and methadology that gcc is following. At that point IBM can simply stick with Visual Age, accept a flawed compiler, or go with a fork. Apple's in a bit more of a pickle due to not owning Visual Age. There are rumors floating around about a port of Visual Age for OSX. However the problem of obj-C and so forth makes me think that this wouldn't help Apple as much as many think. Also it is in IBM's Linux plans to have a good gcc to make porting easier. So I think both want gcc to be as good as possible.

      Even if they make a fork, I think everyone using PPC chips would use the Apple/IBM fork. So, outside of some likely contention with FSF, I don't think this would really cause that many problems. And the benefits definitely outweight the costs. (Assuming FSF doesn't get too pissed)

    5. Re:Improvements to GCC? by Big+Jason · · Score: 2, Interesting

      As a Sun fanatic, I must admit that the POWER architecture is pretty nice. AIX OTOH is a steaming piece of garbage, and I'd rather be a Wintel admin than have to deal with it again. Hell, HP-UX 9.0 would be a step up.

      I really wish Sun would ditch the ailing SPARC line and adopt the POWER/PPC line.

    6. Re:Improvements to GCC? by Duncan3 · · Score: 4, Interesting

      Yes, it is great. Unfortunately in the next couple questions he goes on to say that the underlying engine GCC uses is completely unable to deal with the complexities of the 970 and other deep and wide architectures.

      So either GCC needs a serious reworking on a fundamental level, or more likely since it already exists, they will just release a separate compiler that doesn't suck.

      I just hope they release the proprietary compiler for OS X sometime before the G5 hits. The 2-3x performance hit of GCC is really starting to hurt Apple, and piss off all the developers. If IBM only releases the good compiler for their OSs and Linux, they are effectively telling people that OS X is not welcome on the 970.

      Noone seriously considers using gcc on x86 now that the Intel compiler is free (root beer). And frankly that alone makes AMD chips totally unattractive for a computation farm (that and the nuclear plant you need to power the things).

      IBM needs to step up and do the same.

      --
      - Adam L. Beberg - The Cosm Project - http://www.mithral.com/
    7. Re:Improvements to GCC? by Realistic_Dragon · · Score: 4, Insightful

      Yes, it is great. Unfortunately in the next couple questions he goes on to say that the underlying engine GCC uses is completely unable to deal with the complexities of the 970 and other deep and wide architectures.

      It has been stated that GCC is attempting to be a 'good' solution for all architectres rather than the 'best' for any one. It's not incapable of adapting to be the best for the P970, but that would require a permanent fork from the general GCC code.

      So either GCC needs a serious reworking on a fundamental level, or more likely since it already exists, they will just release a separate compiler that doesn't suck.

      The advantage of using GCC is that developers can write with reasonable confidence for any platform with GCC available. I have done some heavy porting work between code written for TC/TCC and code written for GCC and it's no fun at all. By comparison code for GCC for PPC and x86 isn't that bad to chop and change.

      Given the nature of Apple (who seem to like being able to use open source apps written for GCC) and IBM (who want Linux - developed for GCC - to compile on their boxes) I think they will prefer to optimise GCC as far as possible for the P970.

      Given the competence of IBM and Apple programmers (especially the former) I suspect that they will do a pretty good job.

      --
      Beep beep.
    8. Re:Improvements to GCC? by Halo1 · · Score: 3, Informative

      Apple already has a fork. The gcc that comes with Mac OS X has some 30+ optimizations (both PPC-specific and generic) which aren't in FSF gcc, because FSF refused the patches. Apple does try to keep that kind of stuff at a minimum though, since it means more maintenance work for them as they have to merge those patches with every new gcc version and update them if necessary.

      --
      Donate free food here
    9. Re:Improvements to GCC? by Carewolf · · Score: 2, Informative

      Actually the intel compiler is an excellent compiler for AMD chips, so in that area it makes no difference. Also because of the number of x86 developers, gcc is a really good compiler on i386 (within 5-10% of icc), most people just dont know the right buttons to push.

      The biggest problem for gcc is the confusing switches (I've still not seen a single benchmark use the aggresive optimization of gcc correctly) and the fact that it not really got onto the RISC movement and is basically still a CISC compiler at heart (trying to use as few registers as possible).

  10. Intel by gilesjuk · · Score: 3, Interesting

    Wonder how long it will be until Intel headhunt these guys?

    Wouldn't be the first time

    Link to story

  11. Re:I can't wait.. by SuperBanana · · Score: 3, Funny
    Windows Longhorn woth its cool 3D UI

    Lost you there. Oh, oh, MacOS X. Gotcha, sorry.

    I bet Visual Basic code runs reel fast on this baby

    Visual Basic, fast? Oh god, please...someone mod the parent up as funny, he/she deserves it :-)

    --
    Please help metamoderate.
  12. Re:I can't wait.. by Mononoke · · Score: 4, Funny
    ...to see what this thing will be like running Windows Longhorn woth its cool 3D UI.
    You already can, because their R&D dept already released it. It's called Mac OSX.

    --
    NetInfo connection failed for server 127.0.0.1/local
  13. GCC by eadint · · Score: 2, Interesting

    So whats the deal.
    1) would it be possible to fork GCC so that it is completely optimized for the 970, if this is possible than GCC will be a good compiler.
    2) from personal experience GCC sucks, its inefficient and wastes cycles, borland or Solarises compilers beat the crap out of GCC on their respective platforms. so when is apple going to have a highly optimized 970 based compiler that will make x86 whine in the corner after being raped, and made to look like the bad market whore that it is.
    3) if a GCC970 can be separated, optimized and made into a special compiler, than well have something t talk about.