a dozen cpu's on a chip

when N>4. N>> with the Chinese usage (ie big iron box didn't work and had service engineers tending it daily for about 6 months after delivery).

perform

don't fold

You seem to be assuming that one program will be run on multiple cores for performance. Yes, that's difficult. But it's unnecessary, since the average user doesn't do FFTs all day; he edits, browses, prints. If one cpu is allocated to each process, everything becomes simple, and we avoid context switching and, with a decent system design, a crash-proof OS can be easily designed.

It's not about performance; it's about escaping a programming methodology that's clearly broken.

John

It could go even further. You could have a situation where the "boss" integer only CPU does this:

Dear Mr Floating processor #1: Please go perform the code at the following address.

Hey Byte slinger processor #7: Go make this memory move.

Hey I/O processor #3: go do this work.

... etc ....

Early in the era of the 8086 there was an 8089 which was called a DMA processor even though it really was programmed I/O in its own instruction set. It could do I/O way faster than the 8086. If a CPU is intended to be part of a server, it could have parts like that in it for doing the things needed for fast disk operations.

Actually I can see multiple CPUs being the OS. When you have a lot of tasks to manage, it takes some processing power just to manage them. Future machines with thousands of CPUs may need tens of managers.

computation when N>4. N>>> with the Chinese usage (ie big iron box didn't work and had service engineers tending it daily for about 6 months after delivery).

NB Typo should be N You seem to be assuming that one program will be run on multiple cores

No. I was actually thinking of hardware problems related to shared common memory, bus arbitration, bandwidth and cache coherency.

All of which are easily done by timeslicing a single CPU.

Dream on. It isn't the context switching that is the problem it is bad or no design, sloppy programming languages and sloppy programmers.

OS/2 despite being designed by committee and reinventing a few wheels was going in the right direction and later versions were very close to bulletproof. The early marketting decision to hobble it to be backwards compatible with the 286 CPU messed things up. Unfortunately IBM & Mickeysoft fell out and pure 386 Windows gained ascendency.

Having spare CPUs for some tasks is quite handy, but there is a law of diminishing returns for N>4 unless your problem has special properties.

My PC is analysing a chess game with another CPU as I type this. Apart from the additional fan noise there is no performance hit. If I allowed it to use both CPUs the keyboard lag would be painful.

Regards, Martin Brown

...

The rule: for acronyms of five letters or more, capitalize only the first letter (e.g., Unicef).

Is there really a "rule" ?:-)

...Jim Thompson

SEX...

..

o.

=A0 =A0 ...Jim Thompson

Yes, and if you break it Eeyore will spank you.

Yes. But I think that stuff like FPU sharing could be done in hardware, with the OS cpu just setting up the rules. Really scary stuff line memory sharing/moves, disk writes, and DMA - things that work across all physical memory - could only be done by a manager cpu, never by an application. VMS had some protective features like that, and ran dozens of hostile users for months at a whack.

But only one executive manager boss. It could be a structured heirarchy: one cpu runs the top-level OS, the thing that gets booted and sets up/supervises everybody else; a few file managers; a bunch of hardware device drivers; a user/GUI interface cpu per screen; some TCP/IP managers, one per port maybe; finally at the bottom of the stack would be applications, which would be rigidly hardware-constrained from doing harm.

The only thing wrong with running all this one a single shared cpu is that nobody seems to be able to do it right. The multi-cpu thing isn't about performance or even architecture: it's a way to force programmers into a new set of rules, because they sure can't manage the ones they have now.

Oh, yeah, dump virtual memory. It was a bad idea when memory was scarce, and a worse one now that ram is bucks per gigabyte.

John

I have only one rule: always make your own rules.

John

Who is this Eeyore? I don't see any posts from him, or any responders (troll feeders) to his posts, so I guess I don't need to concern myself :-)

...Jim Thompson

computation when N>4. N>>>> with the Chinese usage (ie big iron box didn't work and had service engineers tending it daily for about 6 months after delivery).

broken

If it's easy, why are "home pc" OS's flakey gigabyte monsters that even professionals don't understand and struggle to maintain? And why would *any* OS be subject to acquiring a virus by just viewing a web page? And why does doing routine operations sometimes hang all tasks for tens of seconds?

I'm just not seeing the "easily done" part; the Mac OS's come closest, I guess.

Yes. But the only thing that will break the paradigm is a totally new hardware architecture. The multiple cpu's could be virtual (ie, a register that selects the "current cpu", and all of its contexts, instantly) but multiple cores with true concurrent execution is probably a better use of silicon and a better way to manage resources, especially the most difficult resource: time [1]. The point is that new hardware is needed to constrain bad programmers (ie, most programmers) from trying to do complex, clever things that they rarely do right. A cpu is a tiny spec of silicon these days.

John

I have a Vista-based laptop that has blue-screened twice now, and on both occasions it corrupted something in the initial boot bits of Windows such that it refused to boot anymore. Running the automated repair routine from the install CD did fix it, but what a pain in the arse!

A lot of machines from, e.g., Dell, Asus, etc. use "tweaked" drivers and often can't be replaced with newer ones from nvidia.com... yet the ones from the OEM lack the nVidia ones by many months. (I realize you can just head on over to laptopvideo2go.com and download a modified .inf, but that's something the average user isn't aware of.)

---Joel

Mine is closer to, "special rules for special people."

Mac OS X and MS XP seem to me to be equally stable.

My wife (XP on Fujitsu laptop) is an avid surfer and downloader of various file types, but, except for the new applications I install for her, the only executable files are MS updates. It is about 6 years old and I have never had to anything more than clean-up the HD.

I currently have one computer (Compaq) running XP, and one with OS X and XP. Both of them run as clean so far. These computers are exposed to a variety of executable files as my whimsy dictates.

I wish I understood more about how some people have continuous dire problems that we manage to avoid.

A programmer friend was yesterday showing me a shiny new book he'd just bought to assist in some PC programming. It's a big Yellow thing with 1400 pages dealing with C# and .NET. He then took great amusement in randomly quoting inanities contained within. Point is, as a 'self trained' hardware, C and assembler programmer, he understood and could see the book for what it really is. Very few 'computer science' graduates are capable of making this distinction.

From experience with two of my offspring, good programming seems to come from good language skills (daughter and son are both multi-lingual), irrespective of training in "computer science" (a term I consider an oxymoron, right up there with "political science").

...Jim Thompson

I think, in the case of Windows, it's mostly a matter of luck. We have a dozen identical HP machines, all running the identical (OEM!) XP/SP2 versions, and some are reliable, some are not. Some crash apps, some never crash those same apps.

John

At Borders Books, there's a huge computer section, but *nothing* about hardware-level stuff. There's a shrink-wrapped ".NET BASICS" set of books almost 2 feet long, must be ballpark 10,000 pages, for about $1200.

We program in PowerBasic a lot, the Console Compiler version. You can write a 1-screen program to open a TCP/IP socket and do useful device control over Ethernet.

For some reason, ex-chemists make very good programmers.

John

How about one of these

martin

They're just reflecting demand, of course, although occasionally a place like Borders will have a "Getting started with PICs"-type of book If you go to a decent technical book store (such as Powell's Technical Book Store in Portland) there's tons of hardware books... there are also all sorts of intriging books on other nichey technical areas like soil analysis, dam constructions, ordinance disposal, etc. Walking through the aisles is a real eye-opener for just how "deep" some other fields are out there.

The computer industry -- and Microsoft in particular -- seems to have realized that to continue to grow at the rate they'd like to, they have to constantly (attempt to) change the programming paradigm so that there's constant demand for continuous training, new tools, etc. Look at Vista: They don't officially support Visual Studio 6 (except for Visual BASIC), yet it's quite trivial to get C++ up and running as well (plenty of write-ups on the web, taking no more than a paragraph to describe the meat of the matter... and I suspect most of the other components of Visual Studio, but realistically >90% of Visual Studio users are probably looking for VC++ or VB6). It's hard to believe that Visual Studio 6 support was dropped for primarily technical rather than political reasons, i.e., Microsoft wants everyone to switch to C# and the other .Net languages.

While good programmers can become noticeably more productive on, say, large applications by switching from, say, C to C++, a large percentage don't seem to make the "good" cut and hence end up writing VB.net code that's no better than the crappy old VB 6 code they used to write. The other big problem I see with programmers is that the not-so-good ones seem to want to make things far more complicated than the need to be... often with the full support of a big IT staff who needs to justify spending $25,000 on their next SQL Server box. See:

---Joel