PAR2 Multithreaded Archive Recovery Performance

Par2 is an application used for reconstructing downloaded archives. It can generate parity data from a given archive and later use it to recover the archive

Chuchusoft took the source code of par2cmdline 0.4 and parallelized it using Intel’s Threading Building Blocks 2.1. The result is a version of par2cmdline that can spawn multiple threads to repair par2 archives. For this test we took a 708MB archive, corrupted nearly 60MB of it, and used the multithreaded par2cmdline to recover it. The scores reported are the repair and recover time in seconds.

Data Recovery - par2cmdline 0.4 Multithreaded

Microsoft Excel 2007

Excel can be a very powerful mathematical tool. In this benchmark we're running a Monte Carlo simulation on a very large spreadsheet of stock pricing data.

Microsoft Excel 2007 SP1 - Monte Carlo Simulation

The same is true for our Excel Monte Carlo simulation - where there's an Intel optimization, the performance is predictable.

Sony Vegas Pro 8: Blu-ray Disc Creation

Although technically a test simulating the creation of a Blu-ray disc, the majority of the time in our Sony Vegas Pro benchmark is spend encoding the 25Mbps MPEG-2 video stream and not actually creating the Blu-ray disc itself.

Sony Vegas Pro 8 - Blu-ray Disc Image Creation (25Mbps MPEG-2)

More of the same here - the 965 BE is faster than any LGA-775 Intel CPU here, but compared to i7 it's noticeably slower.

Sorenson Squeeze: FLV Creation

Another video related benchmark, we're using Sorenson Squeeze to convert regular videos into Flash videos for use on websites.

Sorenson Squeeze Pro 5 - Flash Video Creation

I'm running out of ways to say that the standings remain unchanged.

WinRAR - Archive Creation

Our WinRAR test simply takes 300MB of files and compresses them into a single RAR archive using the application's default settings. We're not doing anything exotic here, just looking at the impact of CPU performance on creating an archive:

WinRAR 3.8 Compression - 300MB Archive

The standings remain unchanged.

3D Rendering Performance Gaming Performance
POST A COMMENT

58 Comments

View All Comments

  • werfu - Thursday, August 13, 2009 - link

    What AMD needs is a way to improve performance per clock, that's it, either K11 or something new. There's no way they'll be able to scale much past the 4Ghz point. Imagine the boost they would get, if they could provide 10% more clock efficiency, at the clock they are currently that would be a huge boost. They also need to improve the IMC. Going for 4 memory stick with AMD for now is a no go if you want to have high ram speed. Memory bandwidth is definitely a huge Intel advantage. And something like Hyperthread could be nice too. Reply
  • TheHolyLancer - Thursday, August 13, 2009 - link

    uncore? isnt this HTT?

    Reply
  • JumpingJack - Sunday, September 21, 2014 - link

    No, uncore is not HTT.... Reply
  • medi01 - Thursday, August 13, 2009 - link

    "The problem with the $245 price point that AMD’s flagship sells at is one of positioning. It is dangerously close to the $284 price of a Core i7 920, which is generally a faster chip."

    Sorry, but shouldn't you also include motherboard price into calculation?
    Reply
  • C'DaleRider - Thursday, August 13, 2009 - link

    Well, really depends upon where you buy your parts from, doesn't it?

    Given that I have a MicroCenter and Fry's handy, the price for Intel's Core i7 cpu is $200. Combine that with an inexpensive X58 motherboard, like the MSI X58M, that has gotten quite good reviews for what it is, retails for $170.

    That gives a $370 price for mb and cpu to move to i7....cost of DDR3 memory is a wash due to both platforms requiring it.

    Of course, for those that depend upon Newegg's pricing for cpus, I feel for you....getting ripped off and all. Horrible how the 'Egg gouges on cpu prices these days.
    Reply
  • mohindar - Thursday, August 13, 2009 - link

    How you can fit this processor onto socket LGA775, as mentioned in the final page... Reply
  • mohindar - Thursday, August 13, 2009 - link

    Sorry, wrong comment. Reply
  • Ben90 - Thursday, August 13, 2009 - link

    the SYS Mark 2007 Chart has the i7 920 @ 2.8 ghz... dont know if its on purpose or a typo Reply
  • MODEL3 - Thursday, August 13, 2009 - link

    Well if it's true that Core i5 750 is going to launch at 6th of September at 196$,
    then the only option for AMD is to drop the price around what you suggested! (199$)
    Traditionally AMD official pricing translates around 5% lower (in actual street price) than Intel equivalent price
    (although in the recent years Intel had various questionable tactics like direct rebates to Retailers & to System Builders without a specific sales target - in the Europe region)

    I just hope that AMD is clever to understand, that in no way has to release a higher clocked model (975 3,6GHz, & 985 3,8GHz)
    before Intel release in Q1 2010 & in Q3 2010 the higher clocked models of i5 7XX (i5 760 2,8GHz & i5 770 2,93GHz) (if this is indeed the Intel future roadmap at 196$)

    Already some sites, that are with Intel side can easily fix the testing method, in order the Core i5 750 to appear more powerful than even a future 975 3,6GHz!

    The performance difference between Phenom II architecture & Nehalem architecture can have wide variation depending on the testing method!

    So if Intel wants, it can influence some sites to use specific methods to declare a Core i5 750 better than even a future 975 3,6GHz!

    What good will do to AMD to release a 975 at a 245$ in Q4 2009?

    Of cource AMD can price it at at 219$ (20$ difference with 965) but the whole situation is becoming depressing (they are fighting for +20$ for only a quarter until Q1 2010)

    Well, i guess they must make everything, in order to survive!
    Reply
  • GeorgeH - Thursday, August 13, 2009 - link

    "AMD ought to get rid of the Xn suffix and just use simple model numbers at this point."

    I understand what you're saying, but I think it's the most straightforward processor naming scheme in a long time. You get the architecture, cores, relative speed, and locked/unlocked instantly. Unless AMD is going to stop selling 2 and 3 core chips and never offer more than 4 cores in the consumer space, I say keep the "Xn".

    Intel could really learn from AMD here; from your writeup on ix branding, I fully expect to be needing a decoder ring to figure out what a particular i3/i5/i7 really is.
    Reply

Log in

Don't have an account? Sign up now