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 CS3 - Retouch Artists Speed Test

While our Photoshop CS4 benchmark clearly prefers Intel's CPUs, the results aren't so clean cut. The entire Phenom II 800 and 900 lineup falls short of their competitors, but the Phenom II X3 720 can equal its rival: the Core 2 Duo E7500. It's slower than the more expensive E8400, but it's at least competitive.

This is where AMD has some potential to do well. As a result of its larger die, the 720 has one more core than Intel's svelte Core 2 Duos. In well threaded applications, the X3 could come out ahead.

DivX 8.5.3 with Xmpeg 5.0.3

Our DivX test is the same DivX / XMpeg 5.03 test we've run for the past few years now, the 1080p source file is encoded using the unconstrained DivX profile, quality/performance is set balanced at 5 and enhanced multithreading is enabled:

DivX 6.8.5 w/ Xmpeg 5.0.3 - MPEG-2 to DivX Transcode

Both the Phenom II 900 and 800 series parts are competitive here. The Phenom II X3 720 actually beats out both competitors here, the E7500 and E8400 are close but no faster than the 720. Here's a benefit of that extra core at work.

x264 HD Video Encoding Performance

Graysky's x264 HD test uses the publicly available x264 codec (open source alternative to H.264) to encode a 4Mbps 720p MPEG-2 source. The focus here is on quality rather than speed, thus the benchmark uses a 2-pass encode and reports the average frame rate in each pass.

x264 HD Encode Benchmark - 720p MPEG-2 to x264 Transcode

The first pass of the x264 benchmark is actually an analysis pass, the real encoding is done in the second pass. There are apparently quite a few unaligned cache accesses in this test which severely penalize the Core 2 processors; Core i7 is unaffected. Because of the unaligned cache access performance penalty, AMD owns the price/performance comparison here.

x264 HD Encode Benchmark - 720p MPEG-2 to x264 Transcode

The actual encode workload is much more competitive. The Phenom II 800 and 900 series chips cluster around each other, remaining competitive but not really any faster than the equivalently priced Core 2 Quads. The Phenom II X3 720 continues to be faster than its competitor thanks to its core count advantage.

Windows Media Encoder 9 x64 Advanced Profile

In order to be codec agnostic we've got a Windows Media Encoder benchmark looking at the same sort of thing we've been doing in the DivX and x264 tests, but using WME instead.

Windows Media Encoder 9 x64 - Advanced Profile Transcode

Here we've got, once again, a competitive AMD but there's something very interesting going on with the triple core 720. WME9 doesn't make use of the third core as it is hard coded to use powers of 2 for the number of processor cores. There are some applications that will exhibit this sort of behavior, although in our testing the numbers are limited. With its third core out of the picture, the 720 is slower than Intel's Core 2 Duo E7500.

SYSMark 2007 Performance 3dsmax 9, Cinebench, POV-Ray and par2 Performance
Comments Locked

77 Comments

View All Comments

  • Casper42 - Monday, February 9, 2009 - link

    In the Sysmark benchmark results, you have the following comment:

    Against to its Intel competition, the Phenom II X3 720 falls short of the Core 2 Duo E7500 and the E8400. The X4 810 also falls short of one of its intended targets: the Q8200.

    While the X3 720 does fall to the E7500 (didnt bother comparing against E8400), the second line about the X4 810 losing out to the Q8200 is totally unfounded. The Sysmark results have the AMD chip losing in only 1 test set and the AMD wimming in the other 4 or 5.

    I would probably buy the Intel anyway in today's market, but you should at least keep your review as honest and accurate as possible.
  • Lokinhow - Monday, February 9, 2009 - link

    I've seen some scores with the X4 810 at ~3.7GHz, but not with a 2.7GHz NB clock.
    That would be nice to see some benchmarks at this clock speeds to know what is the boost in performance with a so higher nb clock speed.
    Including a simillar clocked Core2Duo would be very nice too.

    ps: yeah, my english is not so great, so sorry if there is some gramatical erros ;D
  • TA152H - Monday, February 9, 2009 - link

    I'm really surprised that no one there put any thought into testing the difference between the memory controller and L3 cache running at 2.0 GHz instead of 1.8 GHz.

    I mean, you have a BE edition, with the 940, so what would have prevented you from running at at, say 2.6 GHz, like the 920, putting them on the same platform, and then benching them so we could see the difference the "uncore" speed makes.

    It's really an important consideration, because obviously AMD will be releasing Phenom II's at 2.8 and 3.0 GHz, with 2.0 GHz uncore speeds, on AM3, and it helps people make a decision whether to wait or not. With AM2+ is shackled with DDR2 (I don't buy that there's no difference between DDR2 and DDR3, especially when other websites have identified them to be roughly 2%), the degenerate speed of the uncore could exacerbate this issue.

    My other question is, does the uncore on the 910, et al, still run at 2.0 GHz when running in the AM2, and AM2+ platforms? I don't see why it would, but anything is possible.

    I think two sets of benchmarks would be interesting. An underclocked 940 (to 2.6 GHz) versus a 910 processor. One on an AM2+ (yes, it's obsolete, but people will still buy it for a while) with the exact same memory. This assumes, of course, the uncore runs at 2 GHz for the 910 on this platform. The other is the 940 in its obsolete platform running at 2.6 GHz, against the 910 running on the modern AM3 platform, with high performance memory. If you really want to be thorough, you can run the 910 on both the AM3 and AM2+, each with the best memory available for it. I think these would all be helpful.
  • jchan2 - Monday, February 9, 2009 - link

    Any word if there will be a Phenom II Black Edition in the near future?
  • WillR - Monday, February 9, 2009 - link

    Do you mean another Phenom II Black Edition? Is the 940 not good enough for you?
  • jchan2 - Monday, February 9, 2009 - link

    Why not? Imagine the ghz you can gain if there was one. AMD did it before, why not now?
  • jchan2 - Monday, February 9, 2009 - link

    Nvm, didn't realize the 940 was already BE

  • WillR - Tuesday, February 10, 2009 - link

    Yep. And it makes sense imo for only the highest clocked quad core and the highest clocked tri core to be Black Editions rather than also having an 8xx BE. I've heard they should have a 990 BE out Q3 or Q4 this year.
  • strikeback03 - Monday, February 9, 2009 - link

    Such as the 720 Black Edition tested here?
  • jchan2 - Monday, February 9, 2009 - link

    Yeah, besides the 720 such as the 800 or 900 series.

Log in

Don't have an account? Sign up now