Slashdot Mirror
Ars Technica Interviews 970 Designers
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."
misenterpret this to mean "ars interviews nine-hundred and seventy different people"?
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.
Ars Technica Interviews 970 Designers
970 designers! Holy nerd-fest Batman! That's where Gotham's entire supply of throat lozenges disppeared to!
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) I never thought I'd see the day.
2) That logo clashes like hell with the sexy aqua theme 8|
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
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.
cLive ;-)
-- Trinity in high heels carrying a whip: The donimatrix - there is no spoonerism
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.
Wonder how long it will be until Intel headhunt these guys?
Wouldn't be the first time
Link to story
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.
I can't _wait_ to see MS port anything to the PPC970! :)
That's a lot of designers! Are they planning on making the site look a little better?
I found the meaning of life the other day, but I had write-only access.
NetInfo connection failed for server 127.0.0.1/local
It has been there for a while. It is mentioned on the mac-on-linux pages.
how they managed a team of that size! It seemed like an awful lot of designers for one chip.
"There is more worth loving than we have strength to love." - Brian Jay Stanley
> 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
Indeed... MS finally admits future technology will contain cheese....this certainly would be a quantum leap in computing...I can't wait till I can run SETI@Home on a block of cheddar or colby...then of course we'd have to come up with a cooling system because that would be really nasty on a hot day.
Humor was lost on this moderator.
Haha, I agree... Dude - that OP image kicks butt... ;) Thanks for the link!
Ars Technica Interviews 970 Designers, creating a new guinness world record.
What a pain in the Ars.
Ahh, but then people would try to make wisecracks about 70's designers, and/or complain about writing 970's instead of 1970's or just 70's...
:)
Damned if you do, damned if you don't
ClutterMe.com - easiest site creation on the Net. Just click and type.
.. the Apple Network Server which ran AIX (!).
___
Cogito cogito, ergo cogito sum.
The interviewer in question, Charlie White, is an asshole. BOXX is a small manufacturer of Opteron systems and its unlikely that many people have heard of them. If you were talking about a larger company, like HP, Dell, Gateway, hell even Acer, it probably would have been a different story. The best part though, is that the BOXX computers are marketed as graphical workstations, not desktops.
From Digit Media Online
DMN: Now, you're saying it's the first 64-bit desktop machine. But isn't there an Opteron dual-processor machine? It shipped on June 4th. BOXX Technologies shipped it. It has an Opteron 244 in it.
Rubinstein: Uh...
Akrout: It's not a desktop.
DMN: That's a desktop unit.
Akrout: It depends on what you call a desktop, now. These... From a full desktop per se, this is the first one. I don't know how you really distinguish the other one as a desktop.
DMN: Well, it's a dual processor desktop machine, just like that one.
Akrout: It's not 64, then.
DMN: Yes, it's a 64-bit machine with two Opteron chips in it. It started shipping June 4th.
Akrout: That we'll double check, but in my mind, it wasn't.
Whenever the offence inspires less horror than the punishment, the rigour of penal law is obliged to give way...
Wow. Maybe this is why you never get any respect from the troll crowd.
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.
You are *so* wrong.
1) There is no relationship of the "bitness" of an OS to the MHz of the processor. Clearly, you are an informed dickhead who thinks that MHz is a speedometer, not a tachometer.
2) Jaguar *can* be installed on a G2. I have a machine right here under my desk...in fact, it's an old Mac clone built by PowerComputing. The thing that prevents Jaguar from installing on G2's is the boot rom -- and there are ways around it.
3) There is no real difference between the 60x instruction set and the G3/G4 instruction set. They did not "delete" that stuff. They added new code that takes advantage of the Altivec in the G4.
4) There is no "nigh-universal ranting" about "skewed" benchmarks -- there's a lot of support for them, and a lot of concern over them, but it's not universal.
In other words, STFU until you get a clue.
3) There is no real difference between the 60x instruction set and the G3/G4 instruction set. They did not "delete" that stuff. They added new code that takes advantage of the Altivec in the G4.
From the source itself:
Aside from the nigh-universal ranting about skewed benchmarks that has been circulating recently, there's another aspect the Power Mac G5 not many have touched upon.
benchmarking is an art where you can twist anything that you can get the tresults you want. OSnews recently had an article comparing powerpc and x86 architecture. he also made a few remarks about the dispute about this benchmark dispute: he seems to think that apple's figures are more realistic as far as a normal user is concerned (not having looked at either benchmark, i can't offer an opinion, but from the reasons he gave, it's at least credible).
Mac OS X is a 32-bit operating system, and since the PowerPC 970 is a 64-bit chip, Mac OS X will effectively be running at 800, 900, and 1,000MHz in the new Power Macs. Not 1.6, 1.8, and 2.0GHz as Apple claims. Let's stick to the specs and stats and look a little deeper into this problem.
this is absolute nonsense. the hardware still is 64 bits and runs at the stated speed. it's only that most programs will perform integer operatins on 32 bit date, not really a big deal in most cases.
One just can't scale an operating system to 64-bit mode on a whim
i suspect what apple is planning is to gradually move the system to 64 bits. the first step will be to enable applicatoions running in 64 bit mode, and you should be able to see that very soon (if it isn't there yet)
In two months we have the G5 systems shipping to consumers, with an operating system that will half the clock since it can't use half the bits of the chip it will run on!
no offense, but this is absolute crap. please tell us what you are smoking. it must be pretty potent stuff. alternatively, you might consider getting a clue before postin
Sir.
Please post instructions on how to install Jaguar on G2 Macintosh systems.
Thank you.
You cocksucking faggot.
It's installer that tells you that you can't install Jag on that hardware - at first It's incompatibility with default initialisation of HD controller on 8500-8600 like machines AFAIK Both causes are resolvable. First I can and did by myself, second-like was done by time of G3 upgrades
Sir.
Please post instructions on how to install Jaguar on G2 Macintosh systems.
Thank you.
Sir.
Please post instructions on how to install Jaguar on G2 Macintosh systems.
Thank you.
Unrefuted testimony is presumed fact. I ao declare, the person you are responding to is in-fact denying that Windows and Lunix and BDS are using *RECYCLED* electrons to store data!
This was proven by the ol' Old Testament biblical concept of unrefuted testimony presumed fact:
Planet Earth was proven to be flat. You can't prove otherwise until astronaughts go into space and take a picture while on the pancake-shaped moon. That is why the lunar landing missions to the moon are all fake! Fake! The moon is flat, same with planet Earth! You can't trust pictures taken from space probes looking at planet Earth, because we know freely-available technology is availble to manipulate and doctor-up space evidence! Doo-doo-Im-not-listening-doo-doo.
I get sick and tired of non-enlightened computer users knocking a modern (Alpha) architecture just because the company selling them didn't price them low enough for use in the present.
The Alpha's problem was shitty marketing. When the marketers couldn't think of somthing better to market than "It is the Windows NT dream workstation", there was a problem... People didn't buy it because it was too expensive, and in-turn the numerous companies (Samsung, API Networks, IBM, Penguin Computing, DEC) selling the hardware would only raise the price to make-up for low sales (2% market share). The result: an architecture 3 years more advanced than anything Intel and Sun could put out, combined, stuck in a prison of Federal Reserve Notes. Alpha burned. It's followers were the IT technologists that held onto them when their companies upgraded to even better Alphas. You know a Good Thing(TM) when it is tossed in the dumpster for an upgrade, and performs 2x faster than the latest Pentium3 out-of-box-trashcan.
To make a short story shorter, there is a growing intelect repository on the Alpha architecture. Some people want to purchase the patents from Intel and AMD, in order to open-source the Alpha architecture in favor of a 100% open-source computing platform. This will work wonders; 64bit clean architecture, consistent instruction set, wonderfuly optimized native C compiler for Linux.
As of note, someone on LinuxGames or HappyPenguin was talking about a homebrew dual Alpha (ev5/6/7?) based PDA. Would'nt that rock? Open-source arch, PDA-sized modules, SMP, portable; what more can you ask other than some good power managment support? Well, I dunno about low-power; the purpose of the project is portability and small-size super-computing on a 100% free and 100% documented architecture. Remember, a mere 400MHz Alpha ev6 out-performs a Pentium4 at 2000MHz as well as a mere old-school Alpha ev5 out-powerforms a Pentium3 1000MHz; and Alpha ev5 and ev6 are still ontop of a 100MHz BUS!
Alpha rocks!
But then that would sound too much like 1970's designers.
Hey hey hey. Anyone see my design of the Warp Pipe yet?
Yesiree, we've been beta-testin' it as wee speeeek. *hic --Excellent smoke retention.
I get sick and tired of non-enlightened computer users knocking a modern (Alpha) architecture just because the company selling them didn't price them low enough for use in the present.
The Alpha's problem was shitty marketing. When the marketers couldn't think of somthing better to market than "It is the Windows NT dream workstation", there was a problem... People didn't buy it because it was too expensive, and in-turn the numerous companies (Samsung, API Networks, IBM, Penguin Computing, DEC) selling the hardware would only raise the price to make-up for low sales (2% market share). The result: an architecture 3 years more advanced than anything Intel and Sun could put out, combined, stuck in a prison of Federal Reserve Notes. Alpha burned. It's followers were the IT technologists that held onto them when their companies upgraded to even better Alphas. You know a Good Thing(TM) when it is tossed in the dumpster for an upgrade, and performs 2x faster than the latest Pentium3 out-of-box-trashcan.
To make a short story shorter, there is a growing intelect repository on the Alpha architecture. Some people want to purchase the patents from Intel and AMD, in order to open-source the Alpha architecture in favor of a 100% open-source computing platform. This will work wonders; 64bit clean architecture, consistent instruction set, wonderfuly optimized native C compiler for Linux.
As of note, someone on LinuxGames or HappyPenguin was talking about a homebrew dual Alpha (ev5/6/7?) based PDA. Would'nt that rock? Open-source arch, PDA-sized modules, SMP, portable; what more can you ask other than some good power managment support? Well, I dunno about low-power; the purpose of the project is portability and small-size super-computing on a 100% free and 100% documented architecture. Remember, a mere 400MHz Alpha ev6 out-performs a Pentium4 at 2000MHz as well as a mere old-school Alpha ev5 out-powerforms a Pentium3 1000MHz; and Alpha ev5 and ev6 are still ontop of a 100MHz BUS!
Alpha rocks!
No way
1. While I'm doing it for my own interest on my own Mac - it's ok. When I'll redistribute this to public - I can be sued in many ways.
2. in 9.2 times when full installer does not work, individual installers still works on same Mac
3. Did Jag, pre-installed on compatible Mac, worked on target Mac?
4. Do you know what Resourcerer/ResEdit, The Fragmalyzer and Carbon Copy Cloner is?
5. If what I said already is not enough for you - you can't do it by yourself.
2. Yes, familiar with this.
3. What!?
4. Yes.
5. ???
6. PROFIT!!!
Sir.
Please email me the instructions.
Thank you.
To clean-up p.3:
;)
Install 10.2 on ANY compatible with it Mac.
Get that HD and set it to target "incompatible with 10.2" Mac.
Take off ALL unnecessary cards and periferia. All HD, mouse, modem/network, scsi, video (use onboard), etc.
Will it boot in some way? Normal, shifted, single-user?
What it says if no? On which stage?
Have you possibilities to remote debug that?
Have you possibilities to try to use alternate kernel loader?
Alternate debugger?
Have you looked into source of stuff that hunged booting?
Have you looked into source of same stuff (inits of memory/pci) from Motorola docs?
on p.5: I did it on one partial Mac. I almost sure that my way will not work for you (or anybody else). In addition, it was not some kind of algorithm - more like shamaning-voodooing. Sorry, but I just can't show here step by step solution (for Anonymous Coward on Thursday July 24, @12:52PM (#6523034)).
Instead I tried to point places where you can find the way to do that - and I not recommend to do that - it will work WERY slow on that Macs, in will be inexpectedly, inpredictably buggy, and I don't know will it still work after software update session.
I personally can't see any practical reason to do that, I did it coase I had time and interest. I looked once and saw that old system is far more practical on old Mac. OS X on old machines is plain unusable.
So, I will not do it again. For other partial config of Mac with other partial config of PCI cards etc., which I even not own.
And so, you have to do that by yourself on your Mac.
And "If what I said already is not enough for you - you can't do it by yourself"
to p.6 - honour is mine
P.S. Keep in mind - english is my 3-rd lang, so may be I'm not as clean as I wish and may be I can't strictly understand you
Install 10.2 on ANY compatible with it Mac.
Get that HD and set it to target "incompatible with 10.2" Mac.
Take off ALL unnecessary cards and periferia. All HD, mouse, modem/network, scsi, video (use onboard), etc.
Will it boot in some way? Normal, shifted, single-user?
What it says if no? On which stage?
Have you possibilities to remote debug that?
Have you possibilities to try to use alternate kernel loader?
Alternate debugger?
Have you looked into source of stuff that hunged booting?
Have you looked into source of same stuff (inits of memory/pci controller of your old Mac, 99.5% sure if it will not boot as single user) from Motorola docs?
Into source of same stuff from Linux build that that works on your Mac?
Do you really think that anybody will do it with your Mac remotely?
Only you, by your own brain and hands.
Go there:o /macosx/ 11168
http://www.versiontracker.com/dyn/moreinf
utility name is XPostFacto