Slashdot Mirror
Intel Yonah Performance Preview
illusoryphoenix writes "Anandtech has an interesting preview of the successor to Dothan (Pentium M's second generation), Yonah, with tests run on an engineering sample. It seems like latest Pentium M is still lagging in the floating point area, but has gained some ground overall. It's also interesting to note their comparisons to the Pentium D/Netburst based dual core."
I just bought a brand-new Pentium M (Dothan) laptop a few weeks ago, and then this new uber processor comes out. Well, that's the computer industry for you...
"it's not about aptitude, it's the way you're viewed" - Galinda
Wow, a 65nm chip consumes slightly less power and performs slightly worse compared to AMD's bottom-of-the-line 90nm X2. Who's amazed? Aren't we just applauding because we see Intel as the big retarded kid who's just managed to tie his own shoes? What I'm trying to say is that this is no big accomplishment. If AMD's 65nm chips were turning out these sorts of performance numbers, we'd all scream about how this is a huge letdown, a step backwards, is this finally the end of AMD, etc.. So let's keep some perspective.
Er, the 2.0GHz Yonah in these tests is slower in nearly all cases than the Athlon 64 X2 3800+, which is the slowest CPU in AMD's lineup. The _top_ of AMD's line would be the Opteron Model 880. The best CPU they market for the desktop is the Athlon 64 X2 4800+, which has double the cache and runs at a 20% higher clock speed than the 3800+. So, Intel's upcoming chip /barely/ hangs with AMD's bottom of the line. Compared to AMD's current best, Yonah would be left standing in the dust. And Yonah hasn't even been released yet.
About the only good thing I can say about Yonah is it will run MacOS X.
that's total system power, not just the proc. That's going to include the chipset, disk, peripherals, USB devices, and the GPU.
Why should we be impressed again? AMD's top mobile CPU, the Turion 64 ML-37, is equivalent to the Athlon 64 X2 3800+, which is the CPU that beats Yonah in all these tests. So the only thing to be happy about here is that Powerbook and iBook battery life will probably be pretty good. And of course those models are currently using ass-slow G4 chips, so anything is an improvement.
But for iMac and Powermac buyers what this means is being stuck with Intel CPUs that really can't hang with AMD's offering. I mean seriously, AMD currently offers FIVE models that are faster than this Yonah thing, all of which are also faster than the best of the Pentium 4 line.
Of course, it may have to get rid of its inventory of desktop Pentium 4 chips and might conflict with Intel commitments to Dell not to obsolete all of their offerings. Intel has to change fabs to make the new chips in larger amounts. All of the marketing about higher clock speeds have to go out the window, too. Furthermore, Intel has to concede that it made a huge mistake and that AMD was right all along with regard to the performance per cycle/pure megahertz debate.
A NYC lawyer blogs. http://www.chuangblog.com/
It consumes less than a 3800 X2? Isn't the fact that a laptop chip is even being *compared* to a dual core desktop chip in terms of power consumption quite worrying? And for that same "little big less power" they're getting a "little bit less speed"? I thought this was all about performance per Watt?
My 3D Texturing Skinning work (under construction)
Yeah sorry, I was only thinking about single-threaded performance. I too would like to see the MT Turion compared, but I believe there's no 2.0GHz part in that line (yet). You'll hear no argument from me about Intel's 65nm process and wonderfully low power consumption. It's obviously going to make from great mobile Macs.
FWIW, unlike Intel which is still bottlenecking memory access over the FSB through the northbridge, for AMD64 series CPUs the FSB speed is largely irrelevant to performance. FSB only really matters when you're using it to talk to RAM, and all the AMD64's have HyperTransport on-die memory controllers running at 800mhz. At present the Turion is only single-core and has only a single channel on-die memory controller, compared to dual core, dual channel for the X2. As I understand it though, the Turion will be dual core and dual channel as well Q2 2006.
If a job's not worth doing, it's not worth doing right.
Many Dothans died to bring us this information.
I had but a simple dream, to destroy all humans.
[1]In those days Da-than begat Yo-nah, which was the fruit of his circuitboard, strong by nature and a good processor. [2]Now Da-than looked on Yo-nah and said, "Yea shall I call you the Slayer of the Amd-ites, for thou shalt go out into their pastures and you shall slay their benchmarks utterly; [3]for thou art pleasing and art born of good silicon." [4]But Yo-nah saw, when he went out into the land of Cun-sumer, how despised he was among the buyers of chips; and he did gnash his teeth and beat his transistors saying: [5]"Oh wherefore was I not left dead on the test-bench and why was my die not broken the day I was born? [6]for I am inferior to my brethren the Amd-ites who run much better than I and cost way the hell less." [7]And he went out into the dust and wandered for a year, until the new product cycle taketh him away.
It's for several reasons:
1. There is no real support for Windows x64, there's no virus protection and very few device drivers. Why go out of your way to support 1% of your users who would actually run a native 64-bit OS?
2. Intel's 64-bit extensions actually slow their chips down. That's right, they added 64-bit instructions to their microcode, but they still get broken down to the same old instructions on the i686 core that the old ones did, and the 64-bit ones take longer to digest. It was a move for buzzword compliance only.
Want to prove it? Get a pentium D830 machine, compile Gentoo on it, first a 32-bit install, then the AMD64 install. Compile both with the same options, but one with 32-bit instructions, and one with 64. The Intel 64-bit Linux will be slower than the 32-bit. The opposite is true with an AMD K8 chip, because the core was designed from step one to be 64-bit.
3. Intel doesn't forsee you needing (or being able to fit) over 4GB of RAM in a portable or business desktop for several years, after the lifetime of this chip revision. If you insist on a 64-bit Intel chip, you must be running a server, workstation, or other high-end rig, so fess-up and buy an appropriately-classed chip (the D830, EE, or Xeon).
4. They need to deliver this chip to market NOW, Intel's stronglest lead right now is with mobile platforms. These chips are in demand as-is; Apple and other vendors want them NOW, not in a few months with 64-bit extensions.
"Sometimes, I think Trent just needs a cup of hot chocolate and a blankie." -Tori Amos on Nine Inch Nails
More specifically,
OS X is mostly 32bit. 64bit libraries are available. You can run native 64bit integer math with the accelerate framework so you can do your fast, high-precision work on a G5.
The big problem is, the GUI parts of the OS (most notably) are still 32bit. GUI apps must be 32 bit. Apps like Mathematica run kind of like X-Window.. they have a GUI and a mathematical engine running in the background. It's kind of client/server. Wolfram has a 64bit engine, but not a 64bit GUI but you don't need the GUI to be 64bit native.
The problem is, other apps aren't logically de-coupled like this so it's difficult write these 32bit/64bit applications. The big issue, as I understand it, is that there needs to be a distinct separation of 32bit native and 64bit native code.. not just in spawned threads but in actual binaries that are compiled. In Mathematica, the front end is a separately compiled binary from the computation engine.
ffakr.
I'm not feeling witty so bite me