Slashdot Mirror
Intel And AMD's Dual-Core CPUs Investigated
Hack Jandy writes "Anandtech has a bunch of insider information concerning Intel and AMD's move to dual-core CPUs. The article has lots of great information on how the move to dual-core processors affects modern computing - in particular, Anand sees more promise in multiple CPU cores that perform different operations, rather than just stamping two identical cores on the same processor like AMD and Intel are doing now."
Moving processing out into special purpose processers, and then back into the main one again as Moore's Law takes effect has been known about since the term the wheel of reincarnation was coined back in 1968.
Well, if you tried working on SMP machine it's quite a bit different feeling really. You can't quantify it but it flows smoother. Which is not too surprising IMHO. I wished sub-$150 SMP motherboards for AthlonXP become commonplace (even if now it's a bit too late, but maybe socket754 ones). As for single CPU at higher clock speed, well 2x mainstream frequency CPUs are often simply not available, even if they are, they cost much, much more than 2x.
The way I see it, every CPU package has essentially a 'thermal envelope' that you can't go beyond without drastically changing case designs or cooling methods. For passively cooled CPU's this would be in the order of 10W, for actively cooled CPU's the ~100W figures for some desktop Pentium 4's are pushing the limit.
Instead of pushing things like BTX cases or watercooling, I'd rather see chipmakers use new technology to improve thermal/power ratio of their chips. I don't need a CPU that's 3 times as fast, upping power consumption once again. Give me a CPU that does twice the work using a smaller amount of energy.
There's lots of room for improvement here. Examples: when a CPU sits idle, does that mean a drastic drop in power consumption? In many cases: no. Win9x systems drop into a full power no-op running loop, and 'halt' state power consumption only works well with newer CPU's when chipsets are configured to enable a low-power state. Often, this isn't the case, for whatever reason.
Then take mobile CPU's (in same physical package), and features like varying core voltage with CPU load (Speedstep, PowerNow! or whatever). Nice, but many desktop motherboards or BIOS'es don't support it, or have it disabled. IMHO, chipmakers like AMD or Intel would better focus on improved motherboard/chipset/BIOS support for these things (through co-operation with mobo makers), than just making their CPU's faster.
And yes, I do know AMD is on the right track here with their x86-64 chips ('Cool 'n Quiet'). Maybe one reason their desktop market share is doing so well lately? I'd go for it, anyway.
Treat mod points like diseases - get rid of them as quick as you can.
Multiprocessing doesn't give you speed improvements for a single-threaded application, but it sure as hell makes a system a lot smoother and more responsive when it's running multiple applications concurrently.
And don't forget, hyperthreading is like adding a second CPU that's always partly loaded. It's not the same as adding another core.
On a single CPU system, the X client and server compete for time. It can sometimes be faster to run certain apps over a fast network than locally on the same machine.
On a dual machine or multi-core machine the client and server can both be given time on separate CPUs or presumably different cores on the one CPU.
Deleted
Maybe we'll see dual-core CPUs where the second core does some
of the 3D-calculation today's graphics chipsets do?
That would certainly be useful for some fields of math.
This is a tricky time for hardware manufacturers - how to promote upgrades which are essentially placeholders for a new hardware generation - and hope like hell that Microsoft will actually promote applications that will use that new functionality. Because Microsoft can afford to lose their R&D money, Intel and AMD cannot.
Don't get me wrong, I'm looking forward to true 64-bit dual core architectures on the PC platform, but unless something amazing happens in the next 12 months, Microsoft will again be the gatekeeper to the mass uptake of that hardware, geek rage and linux notwithstanding. The shark will get it's DRM when the makers are appropriately terrified, and even then they may not make their money back.
From a manufacturer/reseller point of view, it's not looking all that certain. Uncertainty is deadly to the CPU/mainboard market, and I'm seeing it in the hedged bets of computer swapmeets and resellers. The explosion of mp3 players, digital cameras, dvd burners and the astonshing fall in solid state memory might take up the slack for now, but that still means those crucial early-adopters aren't looking at the new goods.
We live in interesting times.
insecurity asks the wrong question irritation gives the wrong answer
Everyone multitasks nowadays anyway... most everyone has a firewall, a virus scanner and an instant messanger system and/or email program running on their desktop at all times, no? Laptop users usually have several applets running on top of these as well.
Beyond those basics, most ppl I know that use a computer have a great deal more running in the background.
The idea that "Joe Average" doesn't multitask might have been true at one point, but it isn't anymore.
-1 Uncomfortable Truth
Intel's P4 can't go any faster because of heat, and they can't do anything about it.
The hell they can't. Three words would fix Intel's heat situation easily: Desktop Pentium M. Where can I buy such a motherboard?
There were some wierd Mac variations in the 1980s with a second CPU on a plug-in board. They could run Photoshop faster, but otherwise were useless.
There are really only two multi-CPU architectures that are generally useful: shared-memory symmetrical multiprocessors, and networked clusters with no shared memory. Many other architectures have been tried - partially shared memory machines, shared-memory machines where some CPUs lacked some features like floating point, hypercubes, single-instruction-multiple-datastream machines, and dataflow processors. None has achieved lasting success.
About the only unusual architecture ever sold in volume is the Playstation 2, with two vector processors. Even there, the vector processors are mostly used as a GPU. (Although one major game physics engine actually runs in the PS2 vector processors, an impressive achievement.)
Programming for wierd architectures is hard, requires much tool development, and results in programs tied to specific hardware. So it doesn't happen much. That's why the wierd architectures fail. They're never that much faster, and by the time the software works, the hardware market is somewhere else.