Windows 7 build 7057 - Performance that blasts past XP, Vista and previous builds

Windows 7 build 7057 - Performance that blasts past XP, Vista and previous builds

Summary: Over the weekend I've been spending time with the latest leaked build of Windows 7 - build 7057. While this isn't the release candidate (RC) build that some people claim it is, this build is certainly pretty close to being RC.

SHARE:

Over the weekend I've been spending time with the latest leaked build of Windows 7 - build 7057. While this isn't the release candidate (RC) build that some people claim it is, this build is certainly pretty close to being RC.

How can I tell that we're close to seeing an RC build? Well, mostly it's a gut feeling based on the fact that features-wise Windows 7 has been finished for a long time and that now Microsoft seems to be at the stage of adding new wallpapers, tweaking default account pictures, and generally polishing a few aspects of the UI. However, I don't want to underestimate the importance of getting a look at this build, because it's the first 32-bit build I've seen since the beta 1 release (which was released back in January, but had a build date going back to December 08). Only the 64-bit flavor of build 7048 emerged earlier this month. Build 7057 also the freshest build - the build date stamp, 090305-2000 translates into 5th Mar 2009, 8:00pm - so this is literally just over a week old.

Check out the Windows 7 build 7057 gallery!

Rather than give you a blow-by-blow account of everything that's different about this build compared to every previous build that we've seen (I'll leave that to others), I'm going to concentrate on the one area that interests me (and many of my readers) the most - performance.

Note: Before I go any further, I feel the need to emphasize that build 7057 is still a beta build and nothing can be taken as being final at this stage.

Important note: I have on several occasions contacted Microsoft for feedback on benchmarking Windows 7 and at this point the company is not ready to discuss performance testing.

Rather than publish a series of synthetic benchmark results for the different operating systems and builds (Microsoft frowns upon benchmarking beta builds, not to mention the fact that the final numbers only really matter for the release candidate and RTM builds), I’ve decided to put Windows 7, Vista and XP head-to-head in a series of real-world tests to find out which OS comes out top.

Let’s look at the test systems and the tests …

The tests -->

The test systems

I’ve used two desktop systems as the test machines:

  • An AMD Phenom 9700 2.4GHz system fitted with an ATI Radeon 3850 and 4GB of RAM
  • An Intel Pentium Dual Core E2200 2.2GHz fitted with an NVIDIA GeForce 8400 GS and 1GB of RAM

The tests

There are 31 tests in all, most of which are self-explanatory:

  1. Install OS - Time it takes to install the OS
  2. Boot up - Average boot time to usable desktop
  3. Shut down - Average shut down time
  4. Move 100MB files - Move 100MB of JPEG files from one hard drive to another
  5. Move 2.5GB files - Move 2.5GB of mixed size files (ranging from 1MB to 100MB) from one hard drive to another
  6. Network transfer 100MB files - Move 100MB of JPEG files from test machine to NAS device
  7. Network transfer 2.5GB files - Move 2.5GB of mixed size files (ranging from 1MB to 100MB) from test machine to NAS device
  8. Move 100MB files under load - Move 100MB of JPEG files from one hard drive to another while ripping DVD to .ISO file
  9. Move 2.5GB files under load - Move 2.5GB of mixed size files (ranging from 1MB to 100MB) from one hard drive to another while ripping DVD to .ISO file
  10. Network transfer 100MB files under load - Move 100MB of JPEG files from test machine to NAS device while ripping DVD to .ISO file
  11. Network transfer 2.5GB files under load - Move 2.5GB of mixed size files (ranging from 1MB to 100MB) from test machine to NAS device while ripping DVD to .ISO file
  12. Compress 100MB files - Using built-in ZIP compression
  13. Compress 1GB files - Using built-in ZIP compression
  14. Extract 100MB files - Using built-in ZIP compression
  15. Extract 1GB files - Using built-in ZIP compression
  16. Compress 100MB files under load - Using built-in ZIP compression while ripping DVD to .ISO file
  17. Compress 1GB files under load - Using built-in ZIP compression while ripping DVD to .ISO file
  18. Extract 100MB files under load - Using built-in ZIP compression while ripping DVD to .ISO file
  19. Extract 1GB files under load - Using built-in ZIP compression while ripping DVD to .ISO file
  20. Install Office 2007 - Ultimate version, from DVD
  21. Open 10 page Word doc - Text only
  22. Open 100 page Word doc - Text and images
  23. Open simple Excel doc - Basic formatting
  24. Open complex Excel doc - Including formula and charts
  25. Burn DVD - Win 7 beta 1 .ISO to disc using CDBurnerXP
  26. Open 10 page PDF - Text only, using latest Adobe Reader 8
  27. Open 100 page PDF - Text and images, using latest Adobe Reader 8

These series of tests will pitch Windows 7 build 7057, 7048 (64-bit) and 7000 32/64-bit against Windows Vista SP1 32-bit and Windows XP SP3 32-bit.

The scoring

The scoring system that I use seems to have confused some readers. It's actually very simple. We run each test for each OS in turn and the time taken to complete the task is noted (average of three runs). The fastest OS is given a score of 1, the runner ups 2, 3, 4, and respectively and the slowest OS scores a 6. The scores are added up and the OS with the lowest score (that is, the one that performed the best overall) at the end is the winner.

Let’s check out the results …

Next -->

The results

OK, so here are the results ...

(click for larger image)

(click for larger image)

Conclusions ...

Next -->

Conclusions

After I carried out the performance test on Windows 7 build 7048 I commented that I thought some of the results were all over the place. However, on looking at this latest build, I've no doubt that not only will Windows 7 will be fast. In fact it will blow away all previous Windows OSes, including the sainted Windows XP.

Note: Why haven't I just published raw benchmark results? Simple - it's not allowed under the terms of the EULA.

So far it seems that on the hardware platforms that I've used that the 32-bit flavor of Windows 7 is faster than the Beta 1 build (significantly faster in some of the tests). Will this be true of the RC and RTM builds? Initially, I expect it to be the case unless you are throwing a lot of RAM and CPU at the OS. I suspect that the cause for this is immature drivers and that once we see an RC build vendors will put more effort into optimizing the drivers for both 32-bit and 64-bit.

I'm still confident that we're on target to see the Windows 7 RC appear sometime during April.

<< Home >>

Topics: Operating Systems, Enterprise Software, Hardware, Microsoft, Mobility, Processors, Software, Storage, Windows

Kick off your day with ZDNet's daily email newsletter. It's the freshest tech news and opinion, served hot. Get it.

Talkback

147 comments
Log in or register to join the discussion
  • Will you be able to post the actual times?

    Just wondering.
    storm14k
    • ....

      Can he post something that is actually useful such as a <a href="http://en.wikipedia.org/wiki/Changelog" target="_blank">Changelog</a>.

      Enough with the Icons and the seat of the pants speed test.
      The <a href="http://www.tomshardware.com/reviews/xp-vs-vista,1531.html" target="_blank">predecessor</a>(s) had both.

      ^o^
      <br>

      n0neXn0ne
    • Actual times

      I was brave enough to post actual results (Adrian is too high-profile to get away with it). It's the January Beta, though.

      * Boot time: 1:40
      * Shutdown time: 0:18
      * Memory use at boot with no extra programs running: 319 MB
      * Memory use with four Google Apps tabs (GMail, Docs, Calendar, Photos), Browser, Movie Player, and Image Viewer: 460 MB
      * Geekbench score: 1299

      Of course, Windows 7 weighs in at about 5GB installed, while Ubuntu 9.04 only takes up about 3GB. In addition, the Ubuntu release boots 40% faster, shuts down 39% faster, uses less memory both at boot (55%) and with apps running (40%), and benchmarks significantly (17%) higher. If you're not tied to Windows (via a specific application or Windows-only hardware), you should give 9.04 a try when it's released.
      daengbo
      • Only true in limited cases

        For the audience on this blog your point is [i]probably[/i] valid. For the general population, Ubuntu is not ready for prime time. It's a good OS, but even though the UI is superior to most *nix OS's, it's not easy enough for the typical windows or Mac user. I guess OS X is technically the best *nix UI, but that's another argument.

        Then again, I suppose anyone that's really concerned about performance (and not playing games) can probably use Ubuntu or doens't mind making the effort to learn a new OS.
        notsofast
      • Better than Vista?

        My actual times for Vista SP1 (system: Intel DG965WH; C2D 6600; 4 GB 567-MHz RAM; 2x WD 10K 150GB, RAID 1; NV 8500GT 512 MB; WEI 5.0):
        * Boot up: 1:00 (to desktop display)
        * Shutdown: 0:18
        All this with 15 apps running in the System Tray. Bootup to Win Explorer, IE 7.0, and Yahoo IM all connected and running: 1:15. For this I should upgrade to Win 7? I don't think so.
        flboffin
      • No Linux is Ready for Consumer Primetime

        I have NEVER attempted a Linux install
        (including Ubuntu) that didn't end up with
        serious command line install scripts for some
        peripheral (or even installed component) driver
        issue. Sure, there are lots of hard working
        open source advocates out there writing
        esoteric drivers - a very dedicated bunch - but
        when the average user can barely deal with
        Windows Update, these special install scripts
        to get an Intel wireless driver installed (a
        ThinkPad x60s in this instance), this is
        unacceptable.
        dkstrauss
        • strangely enough

          I've never attempted a Linux install which DID end up with command line install scripts for anything.

          I've installed Xubuntu on 4 PCs, Linux Mint on 2, Ubuntu on 2 and PCLinuxOS on 1.

          My machines are an old Emachine, a Dell, Compaq, Acer Extensa 5420, several generic machines built at a local computer shop or repaired there and a few others I've salvaged from neighbors. They're all worked properly, no trouble.

          However, I have seen twice where Windows refused to boot. I used a Puppy LiveCD to save the files from one before it's owner upgraded and the other, I installed Xubuntu on. It still boots properly, though the HD is failing (the first one is now running Linux Mint).
          tmsbrdrs
      • Realy?

        What Hd were you using because that is quite slow.
        My pc from a standard HD booted windows 7 in about 45 seconds including bios.
        jdbukis@...
  • a lot of work, but...

    where's the beef.
    Many people don't care about windoze anymore.
    The real test can be only against Linux and OSX.
    Linux Geek
    • Just curious

      do you actually [i]enjoy[/i] sounding unintelligent?

      At least most of the trolls here do make the attempt (as lame as it comes off) to sound like they are posting some type of relevant "fact".

      You just seem to shoot right out of the gate with the "look at me, I am a fool" type comment.

      I was just curious.
      GuidingLight
      • Nicely Put (NT)

        (NT)
        safesax2002
      • he must be working for MS

        his efforts at trolling are so transparent and lame you wonder if maybe he's cointelpro - seriously? - nah, he's probably just a maladjusted 18 yr old with nothing better to do
        eggmanbubbagee@...
        • He's already killed his parents

          and probably the next door neighbors as well, and can't find anyone else to kill today. So that leaves trolling.

          Save yourselves, pay for your software!

          Linux - Who do you want to kill today?
          jackbond
          • re: murder by Linux

            The comments above yours were actually funny and contained some truth.

            Yours on the other hand were just bad. You took a perfectly good thread and turned it into Linux bashing.

            Whether you like it or not, when you make a comment, make it worth the time it took me to read it.
            tmsbrdrs
    • Re: deluded lintard

      Right! 'Cause it's the year of the Linux desktop again.

      Go back to your cave.
      s32432432
    • Test againt Linux?? Why?

      Thats a total falsehood,linux on the desktop is less the 1% get that? 1%. Thats means for a fact none cares about linux.Billions use MS and OSX everyday and just get there work or play done.
      So why test against Linux? its a vaporware, a nothing when it come to the desktop so just get over it.
      People don't care about OSS philosophy,don't care if it doesn't get malware,don't care it rarely gets viruses,don't care if the software that comes with is free,don't care its free

      People just don't care and the proof is that after what, 15 years it only has still less then 1% of the desktop market share.
      The vast majority that do use linux are corporations that don't even give there customers a price decrease by using Linux.
      I personally don't care if anyone uses Linux,but stop pretending that linux on the desktop comes even close to competing on the desktop market,i just doesn't, still after 15 years it still doesn't.

      End rant
      Stan :)
      Stan57
      • Try 4%. Probably because...

        ...you haven't come out of your cave in a few years. Link: http://www.w3schools.com/browsers/browsers_os.asp
        This past weekend I installed Ubuntu ( http://www.ubuntu.com/getubuntu/download ) on an old HP 800MHz PIII laptop with 256MB of RAM. It runs as well as that same laptop did with the Windows 2000 it came with, and it was a snap to install. I didn't have to compile a single kernel! Heck, I didn't even type anything except a machine name, account name and password!
        Linux, try it, you may like it. You can even run it off of the CD without touching the harddrive, so you don't even need to dedicate a machine if you don't want.
        Disclaimer: to be fair, once I did the install, it did download something like 175 updates (took about 1/2 an hour over 155Mb line), but I set up a network printer in like 45 seconds and it recognized all the "stuff" in the laptop including ethernet port, modem, trackpad, "cat's tongue" pointer, audio (including hardware controls that required a special driver in Win2k), graphics, wireless PCMCIA card and wireless mouse. I was impressed.
        914four
        • 4% of web developers looking to learn HTML

          Those logs were from their site alone. That in no way accounts for how many people are using Linux in the real world. To do that you have to look at sites that gather and report data from multiple high-traffic sites, like NetApps:

          Windows - 88.4%
          Apple - 9.61%
          Linux - 0.88%
          iPhone - 0.48%

          http://marketshare.hitslink.com/operating-system-market-share.aspx?qprid=8

          It doesn't matter how much you want it to be untrue, Linux desktop adoption just hasn't happened yet. While you personally may have a ton of Linux friends, note there are vastly more Windows users who are quite happy with their PC.
          de-void-21165590650301806002836337787023
          • I reread their description...

            ...and you are right, it [i]is[/i] from their site alone. I find myself with egg on my face and in your debt de-void.
            I am going to talk very sternly to the intern who provided me the link. Well, maybe not so sternly, she's cute and I'm sure she [i]wanted[/i] Linux to have 4% market share...
            914four
      • GNU/Linux has 10 percent of the desktop

        Look at your sources. They show MacOS has 10 percent but Apple only claims 3 percent in filings with SEC. Your stats are seriously over-sampling the USA which is big but just a small part of the PC world. China has more browsers and is sampled at 1-2 percent typically.

        Surveys show Germany was at 8 percent GNU/Linux years ago. Brazil is at 20 percent now. Brazil, Russia, and China have governments promoting FLOSS. The world is quite different from the USA.

        On side-by-side tests I have done booting XP and GNU/Linux on the same hardware (identical PCs in a lab), I find GNU/Linux boots to a usable desktop several times faster than XP. Booting an even older PC as a thin client is several times faster again. So, it makes a lot of sense to test against GNU/Linux. You would expect to find GNU/Linux wins out because it does not waste time with anti-virus scanning, pre-loading apps that will not be run, DRM, phoning home, re-re-reboots, fragmenting storage, not sharing RAM for multiple users, etc.
        pogson