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."
And let's call it, say, the x87 math co-processor? :)
Naw, you really need two of the same chips in there. Too much steering of processes and whatnot otherwise.
-m
http://www.invisik.com
The P4 already does this. It will turn down the speed and even disable individual cpu components in order to save its life if it begins to overheat.
TomsHardware produced this video a while ago, detailing what happens when the heatsink and fan is removed during workload. They test both AMD and Intel processors from back then.
I remember that the older AMD proccessors would start smoking and then effectively stop working.
Change is certain; progress is not obligatory.
Processor: shall be defined as all processors where the Oracle programs are installed and/or running. Programs licensed on a Processor basis may be accessed by your internal users (including agents and contractors) and by third party users. For the purposes of counting the number of processors which require licensing, a multicore chip with "n" processor cores shall be counted as "n" processors.
This is from Oracle's "Licensing Definitions Document," the emphasis is mine. I found it on the partner web site, which I'm pretty sure is inaccessible to the general public.Of course, I expect this to change (esp. on Windows) p.d.q. given Microsoft's recent announcement.
Because even though Firefox is 10 threads, having a 10 core system wouldn't make Firefox 10 times more responsive/less consuming per one CPU. With two cores, you might see a 20% or even 30% improvement in a variety of processes. You're unlikely to see a 100% improvement unless you're doing just the right type of task. So, the majority of people would be better off with a 20% to 30% improvement in the performance of one CPU for the cost involved. It's only really that as it stands a 20-30% improvement in one CPU is unobtainable (short of massive, massive cache plus some mHz increase plus some unconventional cooling). So, dual cores are what Intel and AMD are trying to push for people wanting that next boost in performance.
Eurohacker European paranoia, gun rights, and h
Certainly about how AMD do dual-core, which as it has been detailed since 2001 (and talked about since 1999) I think is extremely poor for a large website like Anandtech to get wrong.
See comments 50, 51 and 54 that go with the story to see how AMD actually do dual-core (they don't 'fuse' hypertransport links together, like the article says they do)
What is sadder is that they haven't corrected the story even though the incorrectness has been pointed out to them in the feedback, and presumably via e-mail as well. Nothing in the article can be trusted in any way because if basic facts are ignored, then what about the rest?
I certainly do not think that such poor articles should be linked from Slashdot. Why should AnandTech get rewarded for such shoddy work?
Intel's math's co-processors were a marketing scam to encourage you to buy the same chip twice.
The processor and the co-processor were basically the same part, except that the processor had the math part disabled. When you plugged in the "co-processor" it disabled the original processor and took on all the work itself. There was certainly no multithreading going on.
I would rather have multiple cores than a faster processor. The combined clocks of my old dual processor system ran just over half that of my current (similar core) processor, yet the feel of it on the desktop was far better. None of the little hitches, glitches and rogue processes that plague me on the uniprocessor system.
Usually dual-cpu systems have better bandwidth on the motherboard, which impacts performance in any but the most cpu-bound tasks a lot more than a faster cpu does. For years the bottlenecks on most systems have been the hard disk, the motherboard/memory bandwidth, and the video card. A fast cpu just does not matter that much if you don't spend all your time compiling or rendering 3D art.
They mention in the article specifically how intel's design foolishly decreases bandwidth per cpu to make the dual-core magic happen. Since the xeon's will arrive so much later that leads me to conclude they know performance is going to be abysmal, but they're going for the "dual" buzzword because amd is, and at the same time they're re-engineering their bus tech for the xeon line to improve bandwidth so the dual core nature actually becomes useful.
No, The point was that the P4 thermal management was on the core, and would dynamically reduce the clock speed when overheating, whereas the athlon thermal management was on the motherboard and the diode which were used couldn't react quickly enough to a sudden loss of cooling. THG under no circumstances "disabled" the thermal management.
Here is the original article
THG got a lot of grief over this from AMD fanboys until AMD came clean and admitted this was a problem
AMD's response to the article
The only processor where your claim is true, is the 486SX, which had indeed the floating point unit disabled. When you bought the 487 (or Overdrive, not sure there), it was essentially a 486DX processor which turned off the 486SX processor.
The joke on the customer here was that SX and DX means something completely different on the 386 chip. (bus speed was doubled on a 386DX and not on a 386SX)
Ahhh...the great dumpster continuum. Many a free computer will be found there. -- sowth (748135)
And that is a problem how?
NUMA aware OSes on x86/AMD64 are available from all kinds of directions nowadays.
Linux has NUMA support since 2.6, Windows has NUMA in Windows XP (since SP2) and Windows 2003 Server, to mention a few.
while true; do eject; eject -t; done
I can testify to this... This summer I built a new gaming desktop and wanted to try out SMP. So I decided on a dual opteron setup. Finding dual opteron boards is not a problem. What is a problem, unfortunately, is finding a desktop class board, ie. one that doesn't have 64-bit pci, onboard SCSI, 8 banks of RAM, and a price tag of $400...
Ultimately, I only found 2 boards in the $200 range that were dual capable and had AGP: MSI and Tyan. And both were fairly difficult to get ahold of. But it was worth the hassle in the end, as I'm extremely happy with the new system.
It's OK! I'm a limo driver!
I wanted a PPC system. But where do you get the motherboard? That is not apple, and in the under $300 level.
/went with socket 939 AMD64 3500+
badness 10000
The K8s are much better than the K7s at power management. Granted the P4 still wins with the "never shutdown feat" the 99.999% of the time where your heatsink/fan is working fine the K8 will be taking less power, making less heat and computing more IPC.
In my experience it's the heatsink that matters the most. My fan runs at 2500RPM [constantly. It's a thermaltake K8 silentboost] and doesn't really move that much air. I'm sure it helps by a half-dozen degrees C or so but it's not as important as the HUGE BLOCK OF COPPER stuck to it.
So do you buy a P4 for that once in a million time where your heatsink falls off or a K8 which will run more efficiently?
Tom
Someday, I'll have a real sig.
Big ditto here. My desktop is a dual PIII 750 and it's miles and miles more responsive than my work's P4 2.4ghz machines. I'm only working with 512 megs of RAM (PC100 even), but it's still great.
:)
And, I feel your pain regarding current dual setups: Dual Opterons (out of my price range), dual Xeons (out of my price range) or Athlon MP's (more reasonable). It seems Apple is the only company doing dual anything for the desktop these days, which is just fine by me (based upon my iBook usage).
If you were me, you'd be good lookin'. - six string samurai
I have a dual Athlon MP 1200 board, and before that, an Abit BP6 (dual celeron). There are advantages to having dual CPUs. One of them is, if a rogue process suddenly starts using up an entire processor (a situation that would bring single cpu systems to a hard-lock) you might not even notice a performance problem until you try and use that process. You can run twice as many processes and won't see a performance hit (provided you have the RAM). For example: I can run about 4 instances of Diablo II Expansion, Firefox with about 10 pages open, and tons of other little things in the background. I'm currently running 46 processes, including 3 diablos, Firefox with 7 pages open, AIM, Rapidbackup, Google desktop search, gmail notifier, getright, Ultraedit, TrayIt, Windows Sniper, Clipomatic, Transtext, Tclock, stickies, powermenu, winbar and all the usual system processes. This is the normal state of windows for me and it runs just fine.
However there are disadvantages too. Good luck finding a soundard with lots of features that gets along with dual CPUs. Creative has awful drivers and I'd almost swear they don't bother testing them, most other soundcards do just as bad or worse and offer fewer features. I built this machine back in fall of '01 and it wasn't until about a year ago that they released a set of drivers for the Audigy that I couldn't cause a BSOD at will with. If I ran Winamp using the directsound out and seeked around within a song repeatidly really fast it would BSOD 100% of the time. Not to mention you have to buy TWO processors rather than one, and the board was ~$500, is E-ATX, barely fits in an Antec SX1200 (HUGE case). In fact the hds stick out over the DIM slots and almost over the 2nd CPU. My case is gigantic and its too small for this motherboard.
Question everything
It was pretty useful for playing Nibbles and Gorilla. Otherwise, it wasn't very useful, even in terms of backwards compatibility. Even if you it was able to clock a Pentium down to 10Mhz, the computer was still worlds faster than a 8088, so all the programs that were hardwired for 4.77Mhz still ran too fast.
You can refer to recent story on Slashdot Particuly Anandtech comparison. If you want to compare performance : AnandTech (same article) or ExtremeTech.
So don't think Intel had any interest in low power consuption, they were for the gagihertz race. Now tings are changing, they canceled everything (think of 4Ghz) to work "around" the CPU. They surrender to AMD. Race for Gigahertz is over. Dual core is the way to go, particularly specialysed ones.
If you want to reduce your CPU temperature about 20deg C try Athcool on GNU/Linux. It shuts down northbridge went idle. Obviously, you lose 5% performance, but it's your choice. It can be activated at will!
By the way, I'm talking about desktop.