Forgot your password?
typodupeerror

Generational Windows Multicore Performance Tests 228

Posted by CmdrTaco
from the spinning-yer-wheels dept.
snydeq writes "Windows XP, Windows Vista, and (soon) Windows 7 all support SMP out of the box, but as InfoWorld's Randall Kennedy notes, 'experience has shown that multiprocessing across discrete CPUs is not the same thing as multiprocessing across integrated cores within the same CPU.' As such, Kennedy set out to stress the multiprocessing capabilities of Windows XP, Windows Vista, and Windows 7 in dual-core and quad-core performance tests. The comprehensive, multiprocess workload tests were undertaken to document scalability, execution efficiency, and raw performance of workloads. 'What I found may surprise you,' Kennedy writes. 'Not only does Microsoft have a firm grasp of multicore tuning, but its scalability story promises to keep getting better with time. In other words, Windows Vista and Windows 7 are poised to reap ever greater performance benefits as Intel and AMD extend the number of cores in future editions of their processors.'"
This discussion has been archived. No new comments can be posted.

Generational Windows Multicore Performance Tests

Comments Filter:
  • So what? (Score:5, Insightful)

    by fpophoto (1382097) on Thursday January 22, 2009 @12:25PM (#26560925) Homepage Journal
    Are we supposed to be surprised that the leading OS vendor, who's had deep, intertwined relationships for decades with hardware makers is exploiting that hardware properly?

    Honest question: where's the news here?
    • Re:So what? (Score:5, Insightful)

      by Anonymous Coward on Thursday January 22, 2009 @12:43PM (#26561191)

      The news is that nobody can say anything non-critical of Microsoft without being accused of advertising or astroturfing.

      Oh wait, this is Slashdot. Nevermind.

    • The Money Quote (Score:5, Insightful)

      by d3ac0n (715594) on Thursday January 22, 2009 @12:56PM (#26561395)

      Basically, this article states the obvious: Windows XP 64 is just plain faster than Vista 64 or Win7 64. By a factor of 20-40%. But to understand why, you need to read the MONEY quote. Here it is:

      In the end, it all comes down to the complexity of the execution path. With its simpler legacy kernel devoid of DRM hooks and other performance-sapping baggage, Windows XP provides a cleaner code path for the workloads to navigate as they execute. This, in turn, translates into better overall performance with lower consumption of CPU cycles.

      It's the DRM baby. You strip that out of the Kernel, and Vista and Win7 will EASILY outpace XP with their more advanced and flexible SMP capability. Until Microsoft understands that people DO NOT WANT DRM and removes it from their newer OSes, these new OSes will continue to suffer from performance problems, and thusly, acceptance and sales problems.

      Come on Microsoft. Apple has figured it out, DRM is a sales loser. Do you really want to keep wasting time on a loser technology in the midst of a global recession? You blew it with Vista, but you still have a chance with Win7. Offer people a DRM-Free kernel and Win7 will FLY off the shelves.

       

      • Re: (Score:3, Insightful)

        by aliquis (678370)

        I've never understood why the DRM crap matters as long as you don't run anything using it but whatever. Sounds like a bad excuse.

        • Re:The Money Quote (Score:5, Interesting)

          by d3ac0n (715594) on Thursday January 22, 2009 @01:11PM (#26561623)

          Because ALL software has to run the DRM hook gauntlet. basically, the way Microsoft has set it up is that the DRM processes are ALWAYS running and CANNOT be disabled. So every single bit of data is processed through the DRM loop, slowing everything down.

          • Re: (Score:2, Troll)

            by aliquis (678370)

            No matter how Windows is coded and designed is the problem really the DRM or Microsofts implementation of it?

            • Re:The Money Quote (Score:5, Informative)

              by D Ninja (825055) on Thursday January 22, 2009 @03:02PM (#26563593)

              It's with handling DRM (not specifically Microsoft's implementation). The fact that Microsoft MUST handle DRM is the slowdown.

              Take a look at it this way:

              Code Execution Path w/out DRM
              Run
              Function
              Function
              Function
              End

              Code Execution Path w/ DRM
              Run
              DRM Check
              Function
              DRM Check
              Function
              DRM Check
              Second DRM Check
              Function
              End

              One is obviously taking longer than the other.

              • Bullshit (Score:5, Interesting)

                by im_thatoneguy (819432) on Friday January 23, 2009 @04:17AM (#26571801)

                Complete and utter bullshit.

                We're a VFX company. We work with all manner of multi-core applications. Cloth simulation, Global Illumination, Caustics, Optical Flow tracking, compositing etc etc.

                Every single one of our computers are 64 bit. We have Windows XP x64 and we have Vista x64.

                I'm looking at a chart right this very second of render times for our current job. 9 million polygons, 6GB of RAM usage, 100% CPU usage across all 4 cores. NO RENDER PERFORMANCE HIT. Render software scales better than just about anything else on earth. Each core renders its little slice of the scene and returns it to the application. There is no cross talk, it scales pretty much linearlly with very very little overhead. If anything is going to expose some sort of massive performance hit, it would be rendering.

                If Vista x64 is running a DRM check on every ray casting function we would see it. If Vista was running 118% slower we would see it. We have identical machines running the identical piece of software and they're returning on average statistically identical results.

                I've got millions of photons bouncing around a scene and supposedly each calculation is being 'taxed' by some DRM check? I don't see it.

                They're all generating pixels, what could be more "DRM related" than reading footage, processing footage and creating new footage?

                Maybe this test found some piece of software that doesn't run well on Vista. I can buy that argument. But Vista and Windows 7 are not substantially slower than XP at processing. In fact they seem to be no slower from my experience with a wide variety of extremely processor and memory intensive tasks.

          • Re:The Money Quote (Score:5, Informative)

            by Toreo asesino (951231) on Thursday January 22, 2009 @01:38PM (#26562077) Journal

            Oh? That's quite a claim.

            "DRM" only kick in the moment you play hi-def media with copy-protection bits enabled only. Vista is in some tests ever-so-slightly slower than XP, but then XP was to 2k, 2k to 98, etc, etc. It's a phenomenon known as "more code".

            I'd appreciate it if you could justify any of these claims with say some evidence? Not the Auckland guy though, his claims were debunked rather thoroughly a long time ago.

            • Re:The Money Quote (Score:4, Insightful)

              by CannonballHead (842625) on Thursday January 22, 2009 @02:01PM (#26562429)

              That's an itneresting point. I wonder why they didn't test 2k, 98, and 95?

              I could test an old DOS game vs. [insert new game here] and see the FPS in [insert new game here] be so, so much lower. [insert new game here] must be horrible, DRM infested, and we should all use old DOS games.

              Granted, Vista does seem a bit on the slow side (although on my Q6600 w/ 7GB RAM, it runs pretty quickly all in all), and Windows 7 *seems* to run slightly faster even in a VM... but I'm so tired of reading the "XP (read: an operating system that came out many years ago) is faster on current hardware than Vista/Windows 7!"

              I may as well come out and say Ubuntu is so stupid, I could run [insert random distro] on my old 486 faster than Ubuntu on my modern hardware! Or whatever. The general idea is there.

              • Re:The Money Quote (Score:5, Insightful)

                by setagllib (753300) on Thursday January 22, 2009 @07:30PM (#26567849)

                Unlike Windows, if you install a very lean Linux distribution, even one with up-to-date package versions, it will be absurdly fast as you'd expect from modern hardware. Just because Ubuntu is being burdened doesn't mean the FOSS landscape itself is.

                The algorithms and data structures in almost all open source applications have either stayed the same over the years, or gotten better, with the notable exception of some programs like GCC which have used the increase in system resources to advance compiled code optimisation rather than compile-time performance.

                This whole "of course newer is slower" thing is just Microsoft brain damage. Apple is another company which regularly improves performance and scalability in its software products, even with DRM problems similar to Vista.

                Did you know that by now hundreds/thousands of Windows *system* *calls* have built-in backwards compatibility checks to support programs whose source code is not available for maintenance? You're paying a performance penalty every time you make a system call, with no option to turn it off, just because someone somewhere might want to play The Sims. Open source solves this problem by fixing the program, rather than hacking every layer of the OS to support old bugs. You can't spell "backwards compatibility" without "backward".

            • Re:The Money Quote (Score:4, Informative)

              by Anonymous Coward on Thursday January 22, 2009 @02:17PM (#26562719)

              All you MS apologists and shills have the same talking points: (1) DRM is harmless because it isn't invoked unless you're play DRMed content (in which case you *want* it), and (2) Don't quote Peter Gutmann (the "Auckland guy") because he's been debunked.

              "The Auckland guy" has most definitely not been debunked. The only serious (using the term loosely) efforts I know of have come from Microsoft itself and from the Microsoft's ad agency, ZDNet. Gutmann showed the ZDNet critics for the idiots that they are (not that it wasn't already pretty obvious on the face of it), and the Inquirer exposed the Vista team's response for the spin that it was.

              "The Auckland guy" is a respected academic computer scientist and security and cryptography expert who is talking in his field of expertise. Everything he says is based on Microsoft's own developer docs or device manufacturer docs. He cites his sources. He explains it all in technical detail. And unlike his opponents his fortunes aren't tied to this argument.

              The truth scares you shills so much you have to try to discredit and suppress him at every turn. That's why you say thing like "Stop quoting the Auckland guy, he's been thoroughly debunked." I hate to break it to you, but this random debunked guy from Auckland has Bruce Schneier on his side. It's not hard to tell the difference between the experts and the shills in this debate, as long as the experts get the exposure they deserve. That's why people keep posting links to the "Auckland guy" despite your desperate protests. I know who I trust.

              Read Peter Gutmann's excellent article here:
              http://www.cs.auckland.ac.nz/~pgut001/pubs/vista_cost.html

              • Re: (Score:3, Informative)

                by oddfox (685475)

                I like Schneier and respect him with regards to a lot of positions but on this particular topic I don't think I can. You say that Bruce is on Gutmann's side as if Schneier had some some sort of analysis on Gutmann's claims in order to verify their authenticity. He did not [schneier.com], he simply discussed the article in question and said that he agrees. Nobody has ever posted an actual analysis of the XP and Vista systems to see if indeed the DRM path is the culprit in anything. Maybe instead of attacking the DRM path f

              • Re: (Score:3, Insightful)

                by Toreo asesino (951231)

                The best thing about you "Linux shills" is that you make outrageous claims about Windows while in the same breath letting it known publicly you've never touched it with a 10-foot pole [theinquirer.net].

                And I include Peter Gutmann in that bracket too; find me a single example where one of his claims has been substantiated with actual hands-on testing.

                It's awesome; kinda like you build up an almost convincing argument, only to smash it down again in the next paragraph.

          • Re: (Score:2, Troll)

            How do you know? Do you have the source code to Windows Vista?

            Everyone I've seen that blames "DRM" for Vista being slow has no idea what they are talking about, and are just going "Vista has DRM and is slow, therefore it must be slow because of DRM".

            Correlation is not causation people!

            • Re:The Money Quote (Score:4, Interesting)

              by 0123456 (636235) on Thursday January 22, 2009 @02:10PM (#26562591)

              "How do you know? Do you have the source code to Windows Vista?"

              Do you?

              "Everyone I've seen that blames "DRM" for Vista being slow has no idea what they are talking about, and are just going "Vista has DRM and is slow, therefore it must be slow because of DRM"."

              At a minimum, the changes to the driver model required to support DRM add a whole load of extra bloat that sucks performance; code that previously would have been tightly integrated into drivers now involves a lot of interaction with the OS.

              • As far as I know the only DRM is a check that runs before a protected video plays, that verifies that the hardware you're using for playback is all approved, and you're connected to the TV by a HDCP-encrypted connection, etc.

                AFAIK, it doesn't do anything to non-protected videos, and nothing at all to non-video.

                It certainly doesn't have a check in every command to the driver trying to figure out if you are watching an illegal xvid rip of something copyrighted like everyone suggests.

                Now prove me wrong.

                • DRM Check (Score:2, Insightful)

                  by Gonoff (88518)

                  How does the system 'know' when to start running the DRM? There must be something running at all times "just in case" the paying customer decides to excersise their right to play their own stuff.

                  Whether it is a service, thread or whatever, it doesn't matter. Some system resources have to be used in advance. That can only drop the performance.

                  • Re: (Score:3, Insightful)

                    How about "when the user presses the play button"?

                    I'd expect it to be called from the codec's initialize function myself.

                  • Re:DRM Check (Score:4, Informative)

                    by drsmithy (35869) <drsmithy.gmail@com> on Thursday January 22, 2009 @03:24PM (#26564001)

                    How does the system 'know' when to start running the DRM?

                    The application goes "Hey ! Windows ! I need a protected path before I can play this media."

                    There must be something running at all times "just in case" the paying customer decides to excersise their right to play their own stuff.

                    No, there does not.

                    It is not the OS's job to check whether or not a given file (more accurately, byte stream) is DRM-encumbered, nor does it make any attempt to do so. It is only the OS's job to provide DRM-capable output (and ensure it remains DRM-encumbered) when an application asks for it, which is what it does.

                    In short: If you aren't playing DRM-encumbered content, the DRM does NOTHING.

                  • Re: (Score:3, Insightful)

                    by sexconker (1179573)

                    I don't know the details of Vista/7's implementations, but come on - just use your head.

                    If the file header has the broadcast flag, or otherwise indicates the file is DRM crippled, the DRM checks begin.

                    If no, then DRM checks aren't going to run.

                    It's about the same level as:

                    OH NO. My PC is automatically adjusting my clock for daylight saving time. MY FUCKING CLOCK CYCLES ARE BEING STOLEN!

                    • Re: (Score:3, Insightful)

                      by makomk (752139)

                      If no, then DRM checks aren't going to run.

                      Well, the DRM checks aren't. The system integrity checks to prevent users bypassing the DRM, OTOH, still have to. For example, Windows Vista has code running to detect unauthorised changes to the kernel and reboot, even when no DRMed video is playing (officially to prevent developers from doing things that could affect system stability). I suspect there's overhead in the video card driver model too, to prevent stuff like a hacker setting up the card state so they have read access to the framebuffer via some

          • Re: (Score:3, Informative)

            Wrong. About the only source you could use to back up that claim would be troll fodder pumped out by the likes of Peter Gutmann, who himself doesn't really have a firm grasp of what he's talking about. As we can see with Modern Benchmarks [extremetech.com], Vista can match or even beat XP in terms of performance.

            But wait, that can't be. You are stealing me that evil DRM hooks are stealing clock cycles. XP doesn't have those hooks, so how can it do worse in some tests?

            • by nabsltd (1313397)

              Unless the CPU is 100% loaded, then you won't shouldn't notice DRM affecting actual speed.

              This is because a 30 frame-per-second video will play back at 30fps on any machine that is fast enough to handle it. A theoretical quad-core 10GHz processor with a GPU capable of handling 1000x the processing of current units would still only play back that video at 30fps.

              The difference is that with DRM, more CPU is used. Even though it might not be enough extra CPU usage to cause an issue, it is something.

              And, it's

          • by drsmithy (35869)

            Because ALL software has to run the DRM hook gauntlet. basically, the way Microsoft has set it up is that the DRM processes are ALWAYS running and CANNOT be disabled. So every single bit of data is processed through the DRM loop, slowing everything down.

            If this were true, then non-DRM-capable outputs (VGA, DVI, SPDIF, etc) would not work with Vista at all.

        • I have yet to have drm hinder me in any way. I routinely copy dvd's, recode them to whatever I want them too, or just simply burn them to another dvd. I've downloaded music from whatever had what I wanted. I've never had windows tell me it won't do something.

          What I'm saying is DRM does nothing to hinder us that don't care about the rules. Those that do care follow the rules so the DRM doesn't apply to them ether. DRM is useless.

        • You have to realize, what TCPA means. It means that *everything* is encrypted, all the time. Your HD? Encrypted. Bus transfers to the graphics card? Encrypted. And re-encrypted. For output over HDMI and DVI, to reach your display and be decrypted again. Sound card? Sure.

          So I bet even inter-process-communication is.

      • by wyoung76 (764124)
        And yet the average Joe won't know nor care if it has DRM built-in or not...
        • You're right, all Joe cares about is can he get what he needs to do, done, and can he do it quickly. The GP is just stating that Joe would be happier without the sludge because his OS would be that much more responsive. I took Windows 7 *and* Vista for a tire kicking experience last weekend. I was happy until I got to games and other CPU/GPU activities. Strip out the sludge so they run as well are better than on XP and you'll have me sold, too.

        • O rly? I think they do care [mako.cc].
      • Re:The Money Quote (Score:5, Insightful)

        by quo_vadis (889902) on Thursday January 22, 2009 @01:20PM (#26561775) Journal
        I have never been a "windows fanboi"( In fact this is being posted from a linux computer) and I am no defender of Microsoft's business practices. However without doing code analysis, it is impossible to say that this slowdown is because of DRM. Nowhere in the article does it suggest that they were able to do a profile analysis of the kernel codes and compare what modules on the path were causing the delays. So while it is theoretically possible(and likely) that the source of the delay was DRM related, one cannot be sure. If you possess knowledge otherwise, please feel free to cite it and correct me.
        • They obviously grabbed a hack from thepiratebay.org which did nothing except disabling the DRM, and saw a performance gain of 20-40% ;)

      • Re:The Money Quote (Score:5, Insightful)

        by rossjudson (97786) on Thursday January 22, 2009 @01:58PM (#26562389) Homepage

        This is yet another one of those times when I wish Slashdot wasn't so ridiculously hostile to Microsoft. What we need here is some informed, possibly even official commentary from someone in the know at MS. Exactly why is a workload slower on Vista? Where's that time going? Right now something like 60-70% of corporate workloads still run on Windows OS, so gaining an understanding of exactly why is important.

        When the difference is on the order of 20-40% (if the article is to be believed), we're looking at some level of system-call "tax" under Vista, or we're looking at a different _capability set_. If the workload on Vista is in a secured environment, and the same workload runs faster on XP in an unsecured environment, we're talking apples and oranges.

        It could be the case the even for workloads running as root equivalents in Vista execution times are worse...but we don't really know from what's quoted in this article, and there isn't any response from MS.

        I think Vista is a pretty important upgrade for most users. Even if its security mechanisms are intrusive, at least they're _there_, and that's a step in the right direction.

      • by Ed Avis (5917)

        Apple has figured it out, DRM is a sales loser.

        Really? I thought Apple were busy adding more DRM to their products [eff.org].

      • NUMA (Score:5, Informative)

        by jpmorgan (517966) on Thursday January 22, 2009 @02:09PM (#26562579) Homepage

        As a HPC developer, there's a few areas where XP falls down. With the release of the new Core i7 line from Intel, the end of the FSB is in sight. Both Intel and AMD now use a ccNUMA memory architecture, which has tremendous implications on software design. In short, if your software isn't aware of the system's memory topology, you're going to end up with most of your memory traffic going over the processor interconnects and that's a substantial performance hit over going directly to memory (2-4 times slower).

        XP's NUMA support is very weak. Sometimes the easiest solution is to write your own allocator (and preallocate huge chunks of ram).

        And before somebody comes along and says 'no real HPC is done in Windows!' there are a lot of old, crusty engineering software packages that everybody is scared of porting.

      • by drsmithy (35869)

        But to understand why, you need to read the MONEY quote. Here it is:

        The "MONEY quote" just demonstrates the author doesn't know what he's talking about in that regard.

        The DRM subsystems are only engaged at the request of an application that needs it for DRM-encumbered media. Otherwise they do nothing.

    • Re: (Score:2, Insightful)

      by kno3 (1327725)
      Ha, I can't believe that you could be so biased against Microsoft that you would even turn an example of them doing well into an insult. And yes, I have many a Linux obsessed friend that have argued with me saying: Vista's 64 bit support is terrible and it is unable to utilise more than one core. Fact is that it does so very well, and I am very glad of this article as it is a great thing to cite when I get told bulls**t again.
    • by jedidiah (1196)

      Yes actually.

      How long did it take them to fully exploit the 80386?

      Some of us have a long memory and hold grudges.

    • Re: (Score:2, Interesting)

      by Locutus (9039)

      look up the performance of Windows 95( the 32bit OS as MS claimed ) on the then new PentiumPro( the 32bit optimized CPU Intel claimed ). hint, an old 150MHz Pentium outperformed a 150MHz PentiumPro when running Windows 95. Real 32bit OSs like *nix, OS/2, and Windows NT showed vast performance increases running on the 32bit PentiumPro. It then took Intel almost 2 years to bring back 16bit optimizations into their latest CPU hardware.

      I don't think this is about Microsoft being buddies with the hardware peopl

      • by drsmithy (35869)

        hint, an old 150MHz Pentium outperformed a 150MHz PentiumPro when running Windows 95.

        A frequently-repeated and commonly exagerated urban myth, but one that isn't supported by evidence [byte.com].

        Yes, in a worst case scenario (16 bit applications, hardware requiring legacy DOS thunking drivers, etc) you might see the sort of numbers you refer to, but on a properly configured Windows 95 system (32 bit applications, 32 bit drivers) the Pentium Pro performed measurably better than the Pentium (albeit not as relatively

    • Since when did you run your high throughput transaction processing system on a desktop OS? These numbers are basically meaningless in the sense that they don't reflect anything anyone would actually do with the software that was tested.

      Now, a comparison between 2000 Server, 2003, and 2008 would have been more useful.

      As you say, I suppose this whole thing demonstrates that MS can make progress optimizing an SMP kernel. Sure would be pretty surprising if they couldn't!

      Maybe someone will make some comparisons

  • by Compholio (770966) on Thursday January 22, 2009 @12:26PM (#26560937)

    'What I found may surprise you,' Kennedy writes. 'Not only does Microsoft have a firm grasp of multicore tuning, but its scalability story promises to keep getting better with time. ...'

    Not really, wasn't one of the major complaints about Vista that they were changing the OS architecture to tune multicore processors to the detriment of single core processors?

    • by Calinous (985536)

      XP support 1-2 processors (or cores?). XP Professional might support 4 processors/cores, but I'm not sure on this

      • by nabsltd (1313397)

        XP home supports a single CPU socket, while XP Pro supports up to two CPU sockets.

        Either OS can support a maximum of 32 total cores.

  • 118% slower (Score:5, Insightful)

    by TheMeuge (645043) on Thursday January 22, 2009 @12:28PM (#26560967)

    Roughly 118 percent slower than XP on dual-core

    Some great mathematics in this review... it also appears as if Vista isn't just not solving the problems presented to it, but also adds new ones to increase its own workload.

    Fascinating...

    • by jc42 (318812) on Thursday January 22, 2009 @01:02PM (#26561493) Homepage Journal

      Roughly 118 percent slower than XP on dual-core

      Some great mathematics in this review...

      Yeah, I was sorta wondering about that. Anyone know what the denominator could have been in this calculation? Are they really claiming that it runs the code backwards, undoing the calculations and going from a programs outputs to what its inputs had to be? If so, that could be a major technological advance all by itself. Imagine the useful things you could do with this capability ...

    • by Lonewolf666 (259450) on Thursday January 22, 2009 @02:05PM (#26562525)

      From page 2 of TFA:

      In terms of raw application throughput, Windows XP clearly is still king of the hill. However, despite its current edge on dual-core and quad-core systems, Microsoft's 8-year-old OS is beginning to show its age. For example, when you contrast the dual- and quad-core transaction times for the ADO (database) and MAPI (workflow) workloads, you see that scalability -- in terms of a percentage improvement from dual-core to quad-core -- is capped at 265 percent for the database tasks and 32 percent for the messaging workflow tasks. While excellent by legacy Windows NT standards, these improvements pale next to the 571 percent boost witnessed for the same SQL-driven database workload under Windows 7, or the 58 percent improvement for the MAPI message store workflow task under Windows Vista.

      (emphasis mine)
      So we are supposed to believe that the database test on Windows 7 runs 571 percent faster on a quad-core compared to a dual core?
      That would be a factor of 6.71, or in terms of performance per core, a factor of 3.355. In other words, the quad core would do 3.355 times more work per core than the dual core. That sounds not very believable, considering similar tests the German C't magazine has done in the past (for Linux and Windows 2000). In those tests, both OS scaled at best linear with the number of CPUs, so the "performance boost" from going from dual to quad core was at best 100% (in most tests more like 80%).

      Maybe I'm misunderstanding what Randall C. Kennedy wanted to say. Here it would have helped if he posted his raw data and test configuration, as most reputable testers do. But as he only posted a few end results, I can only say that his numbers seem bogus. I rated the Infoworld article with 1 of 5 points.

      • On rereading, I found a link ("How I tested") that gives at least an overview of the configuration. For the hardware:

        I repeated this scenario across all three Windows operating systems installed in a triple-boot configuration on both dual-core and quad-core test beds (a Dell OptiPlex 745 with Core 2 Duo E6700, 4GB RAM, and 10K RPM SATA disk and an HP EliteBook 8730w with Core 2 Extreme Q9300, 8GB RAM, and 7200 RPM SATA disk, respectively).

        So on one hand, I have to apologize for dissing Mr. Kennedy on lack o

      • by Calinous (985536)

        There is a possibility - that the dual core is forced to switch threads much more often than the quad core. However, while this kind of workloads definitely exist, the chances of stumbling upon it are small to say at least

    • by adisakp (705706)
      It'd be much nicer if he just gave us the Raw Benchmark times and let us calculate the correct values rather than his statistic percentages which seem to change how they are calculated depending on the case and are sometimes wrongly describe (as in the impossible scenario you mention in your post - more than "100% slowdown "is awfully hard to get without warping reality).
  • My experience... (Score:2, Informative)

    by Smidge207 (1278042)

    I run both XP and Vista on Core2Duo processors.

    I'm certain with XP and less certain with Vista (I don't use it for production work) that I can get better performance by forcing everything but EXPLORER.EXE to use the second core at a low priority.

    Then as I run programs, they automatically go to the first core (with EXPLORER.EXE).

    This allows me to run FOLDING, an RSS reader, LogMeIn all the time but on the second core.

    I especially notice a difference when I copying files at the command prompt.

    The program is c

    • My experience is that if you set a programs ( notepad for example ) affinity to the second core and then set it to 'realtime', Windows slows to an agonising crawl with the first core usage at 0% and the second at 100%. As far as I am concerned, SMP doesn't work ( at least, not on WinXP SP2/SP3 ).
      • by mobby_6kl (668092)

        This is not what happes at all, at least not on XP SP2.

        Setting notepad's affinity only to CPU 3 and priority to Realtime does absolutely nothing: the overall CPU usage stays at about 1-2% and Windows is perfectly responsive. But the thread is idle, I hear you say! Well doing the exact same thing to a working WinRAR process just results in 25% overall usage and ~100% core 3 utilization, leaving the system as responsive as ever.

        • I'm guessing your using a quad core machine, perhaps the behaviour is different on dual cores ( maybe an important Windows process/thread was on core 2 as well as notepad ).
  • by ameline (771895) <ian.ameline@nOSPAM.gmail.com> on Thursday January 22, 2009 @12:31PM (#26561027) Homepage Journal

    And XP is still faster than vista or 7, even on 4 cores... And he speculates that it would be faster on 8 (although he didn't measure that)

    Scalability doesn't matter if you're still slower in absolute terms on systems that are available commercially at a reasonable price. (going past 8 cores these days is a very large price jump per core)

    • by rbanffy (584143)

      "(although he didn't measure that)"

      Most probably because XP can't do 8 cores.

    • by SerpentMage (13390) <[ChristianHGross] [at] [yahoo.ca]> on Thursday January 22, 2009 @12:43PM (#26561189)

      Ok so who is faster XP, or Vista?

      The header says Vista and Windows 7, but yet in the article:

      It should come as no surprise that Windows 7 performs very much like its predecessor. In fact, during extensive multiprocess benchmark testing, Windows 7 essentially mirrored Vista in almost every scenario. Database tasks? Roughly 118 percent slower than XP on dual-core (Vista was 92 percent slower) and 19 percent slower than XP on quad-core (identical to Vista). Workflow? A respectable 38 percent slower than XP on dual-core (Vista was 98 percent slower) and 59 percent slower on quad-core (Vista was 66 percent slower).

      http://www.infoworld.com/article/09/01/22/03TC-windows-multicore_4.html [infoworld.com]

      So therefore Vista and Windows 7 suck in performance to XP?

      • by quo_vadis (889902)
        XP is still faster by a large margin(20% to 40% depending on load scenario). FTFA

        If you take the raw transaction times for the database and workflow tasks, then factor them against the average processor utilization for these same workloads, you see that Windows XP consumes roughly 7.2 and 40.7 billion CPU cycles, respectively, to complete a single pass of the database and messaging workflow transaction loops on our quad-core test bed. By contrast, Windows Vista takes 10.4 and 51.6 billion cycles for each workload, while Windows 7 consumes 10.9 and 48.4 billion cycles. Translation: On quad-core, the newer operating systems are at least 40 percent less efficient than XP in the database tasks and roughly 20 percent less efficient in the workflow tasks.

      • I would think XP would be faster depending on the scenario. Although the OS might be better tuned in Vista and Win7 for multi-cores, the applications that run on the OS may not be yet. As time goes on and applications are better tuned for multi-cores, that may change. Most applications today assume that there is one core and they must share it with other applications in Windows. The OS has to play a larger part in determining which core runs the app. In the future, multi-core apps might work better wit
      • by erroneus (253617)

        This would seem to add credence to my assertion that Windows 7 is just "Mojave" thrust upon the world. They aren't changing anything! They are just rearranging the deck chairs... on the titanic.

    • I have 4 q6600 quad computers. One is running vista, one is running xp and two of them are running ubuntu. I do volunteer work for world community grid. The number of results for the last 14 days are as follows: vista 184, xp 127, ubuntu1 150, ubuntu2 210. They all have different motherboards but have the same amount of ram memory. The Ubuntu computers are running 64 bit version while the vista and xp are 32 bit operating systems. Here is an article http://www.computerworld.com/action/article.do?comm [computerworld.com]
  • Where's the beef? (Score:5, Informative)

    by gzipped_tar (1151931) on Thursday January 22, 2009 @12:38PM (#26561117) Journal

    I tried RTFA (sorry, please mod me done for this ;) but, after clicked the "print" version, I couldn't find anything that looked like a benchmark report. No numbers. No tables. No graphs. All I saw was a page of [[weasel words]] or something like that.

    Sigh..

    • All I saw was a page of [[weasel words]] or something like that.

      [[citation needed]]

    • by gknoy (899301)

      This is something that needs to be brought up with the publisher of the online resource. Tell them that if their "printable view" doesn't show the charts from an article whose main substance is charts, then you are uninterested in visiting their site.

      You might get a "Thanks, that's nice" response -- if you're bypassing ad revenue in the first place, you're not really their ideal customer.

      • Re: (Score:2, Informative)

        by gzipped_tar (1151931)

        But this article has no charts in the first place! There's no presentation of data in either the normal page view or the printable view.

        This has nothing to do with the ad policy. I believe this is the result of the author's lack of presentation skill (applying Halon's razor). Even Phoronix's one-paragraph-per-page benchmark reports does a better job.

    • by IorDMUX (870522)

      I tried RTFA (sorry, please mod me done for this ;) but, after clicked the "print" version, I couldn't find anything that looked like a benchmark report. No numbers. No tables. No graphs. All I saw was a page of [[weasel words]] or something like that.

      I agree. I guess I've been spoiled by *real* benchmarks by spending the week on Tom's Hardware...

      Though this article did give us the following gem:

      Windows 7 essentially mirrored Vista in almost every scenario. Database tasks? Roughly 118 percent slower than XP on dual-core

      ...Would any CS grad student like to step in and inform us what 118% slower means in software terms? Does Windows 7 cause the CPU's program counter to mysteriously run backwards, now?
      ...*confused*...

  • Interesting (Score:5, Insightful)

    by quo_vadis (889902) on Thursday January 22, 2009 @12:42PM (#26561173) Journal
    It is interesting that WinXP is still better in terms of performance than either. The article suggests that Win7 and Vista would be better on systems that hypothetically had 16+ cores.

    But nowadays, especially in tech savvy crowds like on /., the most popular thing to do is run VMs with virtual instances of Windows, which reduces all the hassles associated with dealing with win cruft. Got a worm? restore machine. Drivers made system unstable? restore machine. The vms are typically only given 1-2 cores, the exact use case where WinXP does way better than its successors.

    So even if we move to a world with 16+ core processors, if Win7 cannot do better than a 10 year old OS, in common scenarios, how can that be called progress?
    • Re:Interesting (Score:5, Insightful)

      by blankinthefill (665181) <(blachanc) (at) (gmail.com)> on Thursday January 22, 2009 @01:32PM (#26561989) Journal
      Try running Win 98 on Vista's minimum hardware. Hell, lets go whole hog here. Try running Win 3.1 on Vista's minimum hardware. (Okay, you might have to do a lot of work to get it running, but I'm just trying to make a point). I guarantee you that both 98 and 3.1 will run faster than XP on that hardware. By a lot. If it surprises you that vista and xp run slower on the same hardware than xp, then either you're not thinking things through, or you're not very bright. As stated, they are far newer. This means they have a much higher assumed baseline of technology that they can run against, which means that they have far more assumed resources to play with. So yeah, on the same system, Vista runs slower than XP. No surprise (at all, as far as I'm concerned). Honestly, all this speed stuff is pretty pointless. The question with OSes is never really about the fastest, or we would all still be using DOS. The question with OSes is are the fast ENOUGH. This is very subjective, but it basically boils down to: will they run what we want them to run in an acceptably small amount of time. On its original release, Vista did not. However, right now Vista is certainly running fast enough for me, and I expect Win 7 will to. But you're ALWAYS going to take a performance hit moving to an OS that utilizes new technology, and I don't care what OS you use.
      • Try running Win 98 on Vista's minimum hardware. Hell, lets go whole hog here. Try running Win 3.1 on Vista's minimum hardware. (Okay, you might have to do a lot of work to get it running, but I'm just trying to make a point). I guarantee you that both 98 and 3.1 will run faster than XP on that hardware. By a lot.

        That comparison falls apart as soon a you go to a dual core CPU and more than 512 MByte RAM. Most new PCs will have that and Win 98 cannot utilize it. At best Win 98 will run using only half of the

      • Re:Interesting (Score:4, Insightful)

        by EvilJohn (17821) on Thursday January 22, 2009 @02:54PM (#26563455) Homepage

        Terrible analogy.

        Windows 98 or Windows 3.1 can't run the exact same applications. The author's point is a good one. Why does running the exact same application under VISTA or W7 cost 20 to 40 more cpu cycles?

        In business terms: Why do you have to buy 20 to 40% more hardware to get the same result as I have today?

    • if Win7 cannot [...] how can that be called progress?

      It's the new thing, the one created by the progress of time. Microsoft is generating profit, I mean progress, with their new OS.

      It's progress in the sense that it allows Microsoft to survive off of a market it has already saturated and progress forward towards idunno by putting a "progress" sticker on their old^Wnew product.

      </snark>

  • by HockeyPuck (141947) on Thursday January 22, 2009 @12:44PM (#26561207)

    Ok, so if the average user is still doing the same basic tasks, browser/email/word processing it kills me that I'm now requiring the CPU power of yesterdays servers to do these basic tasks. Having multicore systems enables software vendors to increase the bloat, because the increase in cpu/ram will take care of it; therefore hiding this increase in bloat from the user. It's no difference in converting all cars to lead bodies; as long as we put 1000hp engines in them. The user experience doesn't change b/c they still have the same 0-60 times.

    For example, I've always wondered how much CPU time is wasted due to anti-virus software? Let's say you have a large windows on VMware environment. Each VM needs to have antivirus on it, if you've got a server with 10-20 VMs on it; you've got 10-20 instances of anti-virus running. There's gotta be some way to calculate the total amount of CPU and power (W) wasted on this single server to just running the antivirus scanning...

    How about an increase in CPU, but either keeping the bloat the same?

  • by segedunum (883035) on Thursday January 22, 2009 @12:45PM (#26561229)

    Not only does Microsoft have a firm grasp of multicore tuning, but its scalability story promises to keep getting better with time.

    When you see bullshit buzzwords in articles that look as if they've been written by marketing people then look out. Marketing-led, buzzword-laden people always have stories. Are we really supposed to be impressed that the richest OS developer in the world can actually create a SMP capable OS that actually works reasonably given that SMP systems have been around for years? From the tone of the article it's like they're shocked that it works.

    • From the tone of the article it's like they're shocked that it works.

      They're obviously familiar with Windows ME.

  • The software developers will quickly undo all the speed advances that should result from multi-core CPUs. Software has a much shorter development time than hardware, so all the advantage in this contest is with the software.

  • by Animats (122034) on Thursday January 22, 2009 @01:26PM (#26561877) Homepage

    First, go to the real story [infoworld.com], bypassing an intermediate blog and two interstitial ads.

    Second, the article says the performance of the newer OSs is worse than XP. "In fact, during extensive multiprocess benchmark testing, Windows 7 essentially mirrored Vista in almost every scenario. Database tasks? Roughly 118 percent slower than XP on dual-core (Vista was 92 percent slower) and 19 percent slower than XP on quad-core (identical to Vista). Workflow? A respectable 38 percent slower than XP on dual-core (Vista was 98 percent slower) and 59 percent slower on quad-core (Vista was 66 percent slower)."

    Third, there are no tables or graphs anywhere in these articles, and very few numbers. As a benchmarking article, this is awful.

  • I'd like to see how Server 2003 and 2008 stand up - since longer, less interactive processing is what they are tuned for. XP, Vista and 7 are tuned for quick user response.

  • by wonkavader (605434) on Thursday January 22, 2009 @01:39PM (#26562099)

    It's great that MS was able to tune the Vista kernel to avoid locks which reduce performance on multiple cores, but I'd rather see the same work done for XP, giving us something MUCH faster on a high number of cores, rather than a pig we can compensate for with many cores.

  • by CannonballHead (842625) on Thursday January 22, 2009 @02:12PM (#26562629)

    Nobody is going to argue that if you run one single application (a database something), a "small" OS will work better. There are Linux versions that are specifically geared towards doing that sort of thing, right? Ubuntu is probably slower at something than [insert other dist].

    The real question is, though... what about normal usage? Unfortunately, that's hard to measure... but how does Vista/Windows 7 affect normal user productivity and speed as opposed to simple benchmarks designed to test out efficiency at doing ONE thing?

    If Vista and Windows 7 were designed to have a lot of background processes to help the user do this or that, then why not test that, too? XP wasn't designed that way, apparently, while Windows Vista/7 are more designed that way. So give it a level playing field and test what it was designed to do.

    I don't have an answer of whether or not Vista/Win7 are slower or faster when doing other things (like, say, searching for a file because you can't remember where you put it, running multiple applications, using something DRM enabled, or whatever), but it'd be interesting to try to test it rather than a generic "XP runs a single application faster than Vista because Vista has more stuff running in the background." It'd be interesting to try to physically load the system with lots of applications and see which is better then.

    • by b4dc0d3r (1268512)

      Under normal usage with a single application, multiple threads still play a big part. When you hit WIN+R to open the Run dialog, and a number of other places, Explorer (the shell functions of Explorer anyway) starts a new thread to run the dialog, so that the shell doesn't stop responding. Threading 101 I know.

      With Windows XP at least, it uses QueueUserWorkItem [microsoft.com] to start the thread, instead of a CreateThread/Ex call. QueueUserWorkItem uses thread pools, so I often get stuck with my work notebook (not my h

  • I have a Core2 Duo machine running a basic configuration of XP. Its quite fast. The only time I've seen it get bogged down is when it has to pull calendar information from Exchange, and that's not the workstation's fault.

    That having been said, I'm perfectly happy with my dual P2 running NT4 you insensitive clods!

  • Unix kernel coders have written NUMA-aware stuff for years. When MS is late to the party, why not just say so? And if they're always late, why bother with them?

  • They've got a great story, you betcha! And it's only going to get better! Rah rah! Sis boom bah!

    It's disgusting. I wanna puke.

He's dead, Jim.

Working...