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

Hyper Threading does have a real benefit in Photoshop and thus we see the Core i5 750 suffering a bit. It's still faster than the Phenom II 965 BE but it is marginally slower than the i7 920. The 870 is bested only by the i7 975.

SYSMark 2007 Performance Video Encoding Performance
Comments Locked

343 Comments

View All Comments

  • HexiumVII - Tuesday, September 8, 2009 - link

    I must say that Lynnfield is the best stock processor ever. It will o/c itself without you having to touch it at all. Nearly perfect for the masses. I absolutely can't wait for the notebook incarnation.
  • ClagMaster - Tuesday, September 8, 2009 - link

    The performance of these processors is what I thought they would be based on your May Preview Article. Its great the NDA is lifted and we can now see what this processor can really do.

    This is hardly a Celeron. I know a troll in earlier Lynnfield/P55 that should be eating crow.
  • Apahutec - Tuesday, September 8, 2009 - link

    Not sure what "core parking" priorities are (reduce power consumption by grouping tasks on active CPUs, or tune performance by taking into account cache trashing in scheduler decisions), but it sounds like it could even be beneficial on my Core 2 Quad: single socket, no HT, but two Core2 Duo (each with its own L2 cache) glued together.
  • erple2 - Tuesday, September 8, 2009 - link

    Sounds like it, but the logic that controls that on the CPU is on the CPU, and uses up a couple million transistors. That would require a re-spin of the Core 2 parts (which, given the P55 platform release, I think is a safe bet won't happen), however.
  • Obsy - Tuesday, September 8, 2009 - link

    I don't get how Turbo Boost ends "dual-core or quad-core?" I know that an on-die IGP is a selling point for the upcoming 32nm dual cores, but wouldn't they be clocked higher than these quads and have Turbo Boost too? There will be dual cores clocked higher than quads again. Or is Intel not clocking their dual cores past the speeds of quads?
  • macs - Tuesday, September 8, 2009 - link

    Would be interesting an article about P55 mobo with nf200 chip and 2 gpu...
  • Ryan Smith - Tuesday, September 8, 2009 - link

    We talked to NVIDIA about that scenario a couple of weeks ago. A NF200 chip would not make a significant difference in performance, which is why they're letting manufacturers go ahead and just split lanes with a straight-up bridge chip.
  • Darkanyons - Tuesday, September 8, 2009 - link

    Thanks for this great article!!
  • Tomzi - Tuesday, September 8, 2009 - link

    Do the PCIe controller's voltage demands impose stricter limits on undervolting in the case of Lynnfield processors compared to Bloomfield? I can run my i7 920 at stock frequncies undervolted to 0.9xx V VCore. How much voltage (power consumption) reduction can we expect from the an i5 750?

    This might not be a hot topic so close to the release of the new chips when everyone is focused on top performance comparisons but I've always been interested in undervolting/clocking and would like to see a more complete picture.
  • Tomzi - Tuesday, September 8, 2009 - link

    750 and 870 undervolted by ~0.1V reported on silentpcreview.

Log in

Don't have an account? Sign up now