Photo Processing Performance

We turned to the Retouch Artists Photoshop Speed Test for measuring CPU performance in Adobe's Photoshop CS3 beta.  The benchmark applies a number of actions to a test image while we measure the total time elapsed during the active portion of the test.  We report results in seconds, with lower scores denoting higher performance. 

We set history states to 1 and cache levels to 4; CS3 was configured to make use of all available system memory. 

Adobe Photoshop CS3  

The speedup from going to four cores isn't as great in Photoshop as in the 3D rendering tests, but it's still significant (and worth it if you spend a lot of time in Photoshop). The AMD/Intel breakdown remains the same as we have seen in all of our other tests.

Our next test is one recommended by Intel, but the test itself appears to be fair as it is a simple task using one of Vista's built in applications: Windows Photo Gallery.  This test simply measures the amount of time required to print four sheets of thumbnails; of course we don't measure actual printing time, rather the benchmark exports the pictures to an Excel spreadsheet.  Time is measured in seconds, with lower times resulting in better performance:

Windows Photo Gallery  

Finally we have a benchmark that was one of the first tests AMD sent around a while back to showcase what 64-bit processors could do for performance.  The application is called the Panorama Factory and it is used to stitch together multiple digital pictures in order to make one larger picture, or a panorama.  The stitching process can be quite CPU intensive so we used the benchmark to stitch together 10 6MP images of a room and reported the total process time:

Panorama Factory 64-bit

3D Rendering Performance Gaming Performance
Comments Locked

34 Comments

View All Comments

  • Sc4freak - Sunday, April 15, 2007 - link

    It's one of the few games out there that benefit greatly from multi-core. It would have been interesting to see how this new CPU benefitted one of the most CPU-bound games out there right now.
  • SilverMirage - Wednesday, April 11, 2007 - link

    AT fails to be completely honest with the situation:

    1. AT conveniently publishes this on the exact day AMD's price cuts come into effect. That's interesting. Although AT mentions this, they could have mentioned that AMD's previous prices were not able to compete.

    2. Benchmarking the 5000+ against the e6300 is inherantly biased since it will be the e6320 which is contending with the 5000+

    "5000+ will have to contend with the E6300"

    3. Now this depends a lot on the mobo, but I'd say that the conclusion from these benchmarks is that the E6320 and E6420 will be better for their price in a week or two.

    he Athlon 64 X2 6000+ is a realistic alternative to the E6600/E6400, the 5600+ competes well with the E6400/E6300 and the 5000+ can hold its own against the E6300/E4300

    (AT fails to mention again that the E6300 is an unfair comparison)
  • duploxxx - Monday, April 16, 2007 - link

    In the beginning of C2D launch we saw many reviews reducing the multiplier to see what 4mb of cache could do against 2MB of cache... it was only a few % depending on the type of apps... so stop the crap that a 6320 will outperform a 5000, same with the e6400 vs 5600. because for sure it will not!

    As for power consumption, yes a K8 consumes more power at load, It also consumes A LOT LESS in idle, how long is you're system idle a day? And buy a normal ATI chipset like the asus M2R32-MVP and the total power consumption at load will be less than the C2D system...

    any system can be oc'ed.... one bether than the other. you are talking about 5% of users maximum. the allendale tend to oc worse these days......

    nice review but start using the ATI chipsets also, they are equal performers against NVidia and cunsume a lot less and also cheap these days.
  • yyrkoon - Wednesday, April 11, 2007 - link

    It is funny, you come here saying the Anandtech crew is full of BS, yet you do not bring any proof with you, so excuse me if I call BS on you. Things do not magically work one way, instead of another, JUST BECAUSE *you* say so.
  • DeepThought86 - Tuesday, April 10, 2007 - link

    I don't understyand why only the CPU prices are considered?? Shouldn't the overall cost including a motherboard be a much more realistic measure? What about a performance/overall (CPU+MB) cost metric be very useful
  • Griswold - Tuesday, April 10, 2007 - link

    I just skimmed over the article, but where are the numbers for power usage?
  • RedWolf - Tuesday, April 10, 2007 - link

    One thing that is in AMD's favor is that Dell is now selling AMD machines. The college I work for is buying all AMD machines this year. Even the slowest C2D machines are a few hundred dollars more than AMD machines. All of our machines this year, including laptops, are Athlon X2 powered machines because the price was so attractive. I simply could not configure a C2D machine that came close. That price difference allowed us to go to 2 gb of ram and still be under C2D pricing for the same machine. Granted we aren't building enthusiast machines or buying for business but we are buying AMD and getting them at great prices.
  • dm - Monday, April 9, 2007 - link

    quote:

    The April 22nd price cuts aren't terribly aggressive, but they do restore a little balance to the equation . The 6000+ goes back to compete with the E6600 instead of the E6400, which does change things thanks to the E6600's larger L2 cache. The 5600+ now goes head to head with the E6400 instead of the E6300, and the 5000+ will have to contend with the E6300.


    It is important to note that Intel is also coming up with a better Intel® Core™ 2 Duo E6300 and Intel® Core™ 2 Duo E6400, which are Intel® Core™ 2 Duo E6320 and Intel® Core™ 2 Duo E6420. Both have full 4MB L2 cache and will be a lot better performer. I have done quite a few tests with them here (and it includes Intel® Core™ 2 Duo E4400 as well):

    http://fanboyreview.blogspot.com/2007/03/brag-fanb...">http://fanboyreview.blogspot.com/2007/0...g-fanboy...

    quote:

    The price is obviously quite steep, and those who are not opposed to overclocking would be better off buying a Q6600 and simply overclocking it to QX6800 speeds.


    You missed a wonderful processor, which is the quad core Intel® Xeon® X3210 (2.13GHz/8MB L2/1066MHz) which is an LGA775-socket compatible CPU and would appear to be binned to worked at a lower voltage. And according to guru3D (http://www.guru3d.com/newsitem.php?id=4949)">http://www.guru3d.com/newsitem.php?id=4949) the price will be hovering the $430 range. I have done some testing with this Intel® Xeon® X3210 here:

    Part I (Stock Benchmark): http://fanboyreview.blogspot.com/2007/04/article-l...">http://fanboyreview.blogspot.com/2007/0...icle-lit...
    Part II (Overclocked up to 63%): http://fanboyreview.blogspot.com/2007/04/article-l...">http://fanboyreview.blogspot.com/2007/0...e-little...

    Anyway, overall, nice article!!!
  • skrewler2 - Tuesday, April 10, 2007 - link

    Doing a google search, I see the price is around $750-800.. Too bad, you got me excited too
  • yacoub - Tuesday, April 10, 2007 - link

    DM I didn't see any head-to-head comparison of 6300 to 6320 and 6400 to 6420 in your review of them. Am I reading your graphs wrong?

Log in

Don't have an account? Sign up now