General Use Performance

We'll start out our tests with the 7-zip benchmark, a CPU bound multithreaded integer workload that looks at 7-zip compression/decompression algorithms where the IO subsystem is removed from the equation:

7-zip Benchmark

7-zip is almost the perfect scenario for AMD's Vishera: a heavily threaded integer benchmark. Here the FX-8350 is able to outperform the Core i7 3770K. In fact, all of the Vishera parts are able to outperform their price competitive Ivy Bridge alternatives. The old Core i7 920 does pretty well here thanks to its 8-thread architecture.

Next up is Mozilla's Kraken JavaScript benchmark. This test includes some forward looking js code designed to showcase performance of future rich web applications on today's software and hardware. We run the test under IE10:

Windows 8 - Mozilla Kraken Javascript Benchmark

If the 7-zip benchmark is the best case scenario for AMD, Mozilla's Kraken test is among the worst. Largely dominated by single threaded performance, the FX-8350 is significantly slower than a Core i3 3220. Only Intel's old Core i7 920 is slower here, and that's a chip that debuted in 2008.

Although not the best indication of overall system performance, the SYSMark 2012 suite does give us a good idea of lighter workloads than we're used to testing.

SYSMark 2012 - Overall

Overall performance according to SYSMark 2012 is within striking distance of Ivy Bridge, at least for the FX-8350. AMD seems to have equalled the performance of last year's 2500K, and is able to deliver almost 90% of the performance of the 3750K. It's not a win by any means, but AMD is inching closer.

SYSMark 2012 - Office Productivity

SYSMark 2012 - Media Creation

SYSMark 2012 - Web Development

SYSMark 2012 - Data/Financial Analysis

SYSMark 2012 - 3D Modeling

SYSMark 2012 - System Management

Par2 File 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.

Par2 - Multi-Threaded par2cmdline 0.4

Crank up the threads and once again you see Vishera do quite well. The FX-8350 outpaces the Core i5 3570, and the FX-4300 falls only slightly behind the Core i3 3220.

Excel Math Performance

Microsoft Excel 2007 SP1 - Monte Carlo Simulation

Introduction Video Transcoding & Visual Studio 2012 Performance


View All Comments

  • apache1649 - Friday, November 29, 2013 - link

    I'm sorry, this is a bit off-topic to the processors (although I can't say I'm partial to either, I'll be using an AMD because it works in the motherboard I want and performs well with all the other parts I want, but I have used my friend's i5 build and it runs very nicely) but how do you say that Linux is only for servers and bargain builds? Besides the fact that I have seen $600 builds that blow away multiple thousand dollar builds, Linux has become an extremely advanced OS in the last few years. The desktop environments available are all more intuitive than either Windows or Mac, given that they can be customized to the user's preferences down to where they interact directly with the kernel. Not to mention they offer a vast array of features that Windows and Mac don't, as well as using far less resources. I have Linux operating systems that will idle around 1.2% CPU usage. Windows 7 idles around 5%-6%. It manages network connections more efficiently, utilizes the resources it does use much more effectively, and in general just gives a much more immersive and intuitive user experience if you know what you're doing. I would really like to see more support for Linux, because if software and firmware that is available for Windows was available for Linux without the use of WINE, I would use Linux exclusively because it would be so much more efficient, and at this point it has become so streamlined and beautiful that most people who have seen me using it and are Windows users say they would switch because of it's ease of use and visual appeal if only all the software they use on Windows was available. Oh and putting servers and bargain builds in the same group really wasn't well thought out... Most servers have high end components to be able to handle large amounts of traffic and heavy loads on resources. Reply
  • apache1649 - Friday, November 29, 2013 - link

    Also X is not the only option. There are other, more functional, less bulky alternatives Reply
  • Taft12 - Tuesday, October 23, 2012 - link

    Ad hominem fallacy. Address his arguments, not the slang.

    Windows is inappropriate for many important purposes, it says so right there in the EULA.
  • jabber - Tuesday, October 23, 2012 - link

    Indeed, reading a lot of comments over the past 18 months you would think AMD were still pushing their old K6-2 CPUS from the turn of the century.

    Build a AMD machine or an Intel one and average Joe Customer isn't going to notice.

    If honest, most of us here wouldn't either probably.
  • CeriseCogburn - Tuesday, October 30, 2012 - link

    Funny how the same type of thing could be said in the video card wars, but all those amd fanboys won't say it there !

    Isn't that strange, how the rules change, all for poor little crappy amd the loser, in any and every direction possible, even in opposite directions, so long as it fits the current crap hand up amd needs to "get there" since it's never "beenthere". LOL
  • whatthehey - Tuesday, October 23, 2012 - link

    We've heard all of this before, and while much of what you say is true, and ignoring the idiotic "Windoze" comments not to mention the tirade on "evil Intel", Anand sums it up quite clearly:

    Vishera performance isn't terrible but it's not great either. It can beat Intel in a few specific workloads (which very few people will ever run consistently), but in common workloads (lightly threaded) it falls behind by a large margin. All of this would be fine, were it not for the fact that Vishera basically sucks down a lot of power in comparison to Ivy Bridge and Sandy Bridge. Yes, that's right: even at 32nm with Sandy Bridge, Intel beats Vishera hands down.

    If we assume Anand's AMD platform is a bit heavy on power use by 15W (which seems kind as it's probably more like 5-10W extra at most), then we have idle power slightly in Intel's favor but load power favors Intel by 80W. 80W in this case is 80% more power than the Intel platform, which means AMD is basically using a lot more energy just to keep up (and the Sandy Bridge i5-2500K uses about 70W less).

    So go ahead and "save" all that money with your performance-for-dollar champion where you spend $200 on the CPU, $125 on the motherboard (because you still need a good motherboard, not some piece of crap), coming to $325 total for the core platform. Intel i5-3570K goes for $220 most of the time (e.g. Amazon), but you can snag it for just $190 (plus $10 shipping) from MicroCenter right now. As for motherboards, a decent Z77 motherboard will also set you back around $125.

    So if we go with a higher class Intel motherboard, pay Newegg pricing on all parts, and go with a cheaper (lower class) AMD motherboard, we're basically talking $220 for the FX-8350 (price gouging by Newegg), $90 for a mediocre Biostar 970 chipset motherboard, and a total of $310. If we go Intel it's $230 for the i5-3570K, and let's go nuts and get the $150 Gigabyte board, bringing us to $380. You save $70 in that case (which is already seriously biased since we're talking high-end Gigabyte vs. mainstream Biostar).

    Now, let's just go with power use of 60W Intel vs. 70W AMD, and if you never push the CPUs you only would spend about $8.75 extra per year leaving the systems on 24/7. Turn them off most of the day (8 hours per day use) and we're at less than $3 difference in power costs per year. Okay, fine, but why get a $200+ CPU if you're going to be idle and power off 2/3 of the day?

    Let's say you're an enthusiast (which Beenthere obviously tries to be, even with the heavy AMD bias), so you're playing games, downloading files, and doing other complex stuff where your PC is on all the time. Hell, maybe you're even running Linux with a server on the system, so it's both loaded moderately to heavily and powered on 24/7! That's awesome, because now the AMD system uses 80W more power per day, which comes out to $70 in additional power costs per year. Oops. All of your "best performance-for-the-dollar" make believe talk goes out the window.

    Even the areas where AMD leads (e.g. x264), they do so by a small to moderate margin but use almost twice as much power. x264 is 26% faster on the FX-8350 compared to i5-3570K, but if you keep your system for even two years you could buy the i7-3770K (FX is only 3% faster in that case) and you'd come out ahead in terms of overall cost.

    The only reason to get the AMD platform is if you run a specific workload where AMD is faster (e.g. x264), or if you're going budget and buying the FX-4300 and you don't need performance. Or if you're a bleeding heart liberal with some missing brain cells that thinks that support one gigantic corporation (AMD) makes you a good person while supporting another even more gigantic corporation (Intel) makes you bad. Let's not use products from any of the largest corporations in the world in that case, because every one of them is "evil and law violating" to some extent. Personally, I'm going to continue shopping at Walmart and using Intel CPUs until/unless something clearly better comes along.
  • DarkXale - Tuesday, October 23, 2012 - link

    I would also add in the cost of getting a 100W more powerful power supply. (At least)

    The cost of the better cooling (either via better/more fans or better case), And the 'cost' of having a system with a higher noise profile.
  • Finally - Tuesday, October 23, 2012 - link

    That talk suffers from the same inability to consider any other viewpoint but that of the hardware fetishist.

    If you are fapping to benchmarks in your free time you are the 1%.
    The other 99% couldn't care less which company produced their CPU, GPU or whatever is working the "magic" inside their PC.
  • dananski - Tuesday, October 23, 2012 - link

    I agree with you but stopped reading at "uses 80W more power per day" because you have ruined your trustworthyness with unit fail. Reply
  • CeriseCogburn - Tuesday, October 30, 2012 - link

    Hey idiot, he got everything correct except saying 80W more every second of the day, and suddenly, you the brilliant critic, no doubt, discount everything else.
    Well guess what genius - if you can detect an error, and that's all you got, HE IS LARGELY CORRECT, AND EVEN CORRECT ON THE POINT concerning the unit error you criticized.
    So who the gigantic FOOL is that completely ruined their own credibility by being such a moronic freaking idiot parrot, that no one should pay attention to ?

    Here's a news flash for all you skum sucking doofuses : Just because someone gets some minor grammatical or speech perfection issue written improperly, THEY DON'T LOSE A DAMN THING AND CERTAINLY NOT CREDIBILITY WHEN YOU FRIKKIN RETARDS CANNOT PROVE A SINGLE POINT OF THE MANY MADE INCORRECT !

    It really would be nice if you babbling idiots stopped doing it. but you do it because it's stupid, it's irritating, it's incorrect, and you've seen a hundred other jerk offs like ourself pull that crap, and you just cannot resist, because that's all you've got, right ?

    LOL - now you may complain about caps.

Log in

Don't have an account? Sign up now