Adobe Photoshop CS4 Performance

To measure performance under Photoshop CS4 we turn to the Retouch Artists’ Speed Test. The test does basic photo editing; there are a couple of color space conversions, many layer creations, color curve adjustment, image and canvas size adjustment, unsharp mask, and finally a gaussian blur performed on the entire image.

The whole process is timed and thanks to the use of Intel's X25-M SSD as our test bed hard drive, performance is far more predictable than back when we used to test on mechanical disks.

Time is reported in seconds and the lower numbers mean better performance. The test is multithreaded and can hit all four cores in a quad-core machine.

Adobe Photoshop CS4 - Retouch Artists Speed Test

Photoshop CS4 continues to be more comfortable with Intel CPUs, as even the Core 2 Quad Q9400 is able to outperform the X4 955. The cream of the crop here is Intel's Core i7 though, even a 920 is able to outperform the fastest Core 2 Quad we have here.

SYSMark 2007 Performance DivX, x264 & WME Performance
Comments Locked

65 Comments

View All Comments

  • Procurion - Thursday, April 23, 2009 - link

    Cool. My next question would be to wonder why it didn't kick in for the other tests? I guess it wasn't enabled for them? Looks good overall.
  • JarredWalton - Thursday, April 23, 2009 - link

    See page 4 - Turbo mode tends to activate pretty much any time a load is on the CPU. But it's not really "unfair" as all i7 users get that benefit without doing anything extra, plus i7 chips still overclock far beyond that point.
  • ChemicalAffinity - Thursday, April 23, 2009 - link

    Best post ever.
  • whatthehey - Thursday, April 23, 2009 - link

    Congratulations on the cryptic post... or is that pointless post? I'm guessing you're suggesting that the words listed were used with two different companies - AMD and Intel - but if so they certainly weren't used in this article in any way I can see. Care to enlighten the rest of us on the point of your comment?

    Some people are too clever for their own good; others merely think they're clever. Guess which one you are.
  • Lokinhow - Thursday, April 23, 2009 - link

    Oh man, I thinking about the OC
    3.9GHz on Vista x64
    4.2GHz on Vista x86

    Why it happens?
    Does the results are the same using XP x86/x64 and Windows 7 x86/x64?

    That would be interesting to see if it is possible to reach 4.2GHz on Windows 7 x64
  • Griswold - Thursday, April 23, 2009 - link

    Dont hold your breath. Theres more registers (etc) in use under a 64bit OS than a 32bit one. Its highly unlikely that there will be any difference on the exact same hardware. And even if there is a difference between xp/vista/7, 32bit 7 will outdo 64bit 7 as well. 64bit was never the ideal choice for overclocking records...
  • Spoelie - Thursday, April 23, 2009 - link

    In the CS4 test, given the large increase in performance when just going from DDR2 to DDR3, would a faster NB clock (2->2.6/2.8ghz) and faster than DDR1333 memory, while keeping the core at default clock, level the playing field with the core2 processors?

    Seems that in this particular test the phenom is starved for data.
  • duploxxx - Thursday, April 23, 2009 - link

    why do you use these 1GB dimm's in ddr3 config? I would assume you have more oc issues with 4 dimms in stead off 2 dimms?

    G.Skill DDR2-800 2 x 2GB (4-4-4-12)
    G.Skill DDR2-1066 2 x 2GB (5-5-5-15)
    Qimonda DDR3-1066 4 x 1GB (7-7-7-20)
    Corsair DDR3-1333 4 x 1GB (7-7-7-20)
  • Holly - Thursday, April 23, 2009 - link

    Nice article :-)

    btw... last paragraph on the first page... "faster than the Core 2 Duo Q9550." should say "faster than the Core 2 Quad Q9550."
  • ibm386 - Sunday, June 27, 2010 - link

    Intel and Amd are owned by the same person. Since a person can't have monoply in U.S. It has been divided into two different names and obviously diff. CEOs.

    cheers.

Log in

Don't have an account? Sign up now