Synthetic Benchmarks

Our Nocona server was setup in a remote location with little access, so we had limited time to run as many real world benchmarks as we are typically accustomed to. Fortunately, there are multitudes of synthetic benchmarks that we can use to deduce information quickly and constructively.

Sieve of Atkin (primegen)

Primegen is an older, but still useful library for generating prime numbers in order using the Sieve of Atkin. We compiled the Bernstein implementation by simply running "make". We ran the program as so:

# time ./primes 1 100000000000 > /dev/null

primegen 0.97

We found the benchmark to be extremely reliable and we replicated our figures continually with less than 1% difference.

Super Pi

We ran the Linux compilation of Super Pi 2.0, which is a closed source application. We are not aware of which optimizations are compiled with the program and we are prohibited from redistributing the binaries. Please download the latest binaries from ftp://pi.super-computing.org/Linux. We ran the command:

# ./super_pi 20

Below is the program's output of calculation time in number of seconds.

Super Pi 2.0

After re-running the program several times, our benchmarks never deviated outside of 1%. In a mathematical operation-only situation, the Intel processor has outpaced the AMD offering twice now.

Content Creation Synthetic Benchmarks (continued)
Comments Locked

275 Comments

View All Comments

  • manno - Monday, August 9, 2004 - link

    Come on people this is Anandtech, have they ever appeared to be anything, but honest, and unbiased in their reviews? These are the number they got using these benchmarks. They did the work, and gave you the numbers. This site isn't here to advertise for AMD, or Intel. They give you the information, and you use it as a tool for you own purposes from there. I mean come on take of your uniforms, and accept what you see in front of you. This should be looked at as a favor. I don't see any other sites posting benches of Intel's EM64T chips, do you? You came to this site by choice, they don't charge you dime one for the service they provide, and you get pissed at them for not bending the truth so you can to advance your own personal agenda.

    Say thank you, and be on your way.

    These guys work hard, and they do a fantastic job supplying the enthusiast community with some of the best benchmark numbers around. They just posted numbers showing that EM64T is a huge step forward in terms of P4 performance. So what? If you want to buy an A64 or P4 Prescott and get worse performance in those benches then go out and buy one. I was just about tho buy a some PC's for the office here, and they were all going to have A64's in them. Thanks to Kristopher I've decided to sit on the fence a little longer.

    Again Thanks for the early release, it really and truly helped. I hope these fanboy's don't affect you decision to post early numbers in the future.

    -manno
  • WizzBall - Monday, August 9, 2004 - link

    Is this what you call these days a *benchmark*? Just wondering... o.O
  • nastyemu25 - Monday, August 9, 2004 - link

    hello. someone effed up :(
  • coldpower27 - Monday, August 9, 2004 - link

    Not a bad article, though it might have been better if an Opteron 150 was benched which is priced @ 637US or the Athlon FX 53 @ 827US those would be closer in comparison to the Pentium 4 3.6 Nocona EM64T

    Though eventually a fairer comparison would be the Pentium 4 3.6F vs the Athlon 64 3500+ or Athlon 64 3700+. You could also throw in the Pentium 4 3.4F and Athlon 64 3400+.

  • noxipoo - Monday, August 9, 2004 - link

    at least compare the same thing, if you don't have the same class CPU for testing THEN DON'T POST THE ARTICLE.
  • tpinckney - Monday, August 9, 2004 - link

    Given the numerous errors in this article, I believe it is prudent that it be removed from Anandtech.

    This ludicrous article has damaged my opinion of Anandtech.
  • SKiller - Monday, August 9, 2004 - link

    Wow... and a big fat Intel ad at the bottom of the article. Never thought I'd see the day.
  • manno - Monday, August 9, 2004 - link

    Good review, thanks for the early benchmark release. I'm not going to lie to you I like AMD, and I own a bunch of Athlon 64s. But before I think I'll hold off on buying any new hardware until I get to see how well these new P4's do. Any chance we can get some Doom 3 numbers up? Again thanks for giving us the heads up. Looks like things could start heating up in the Chip market soon!

    -manno
  • peter79 - Monday, August 9, 2004 - link

    wow intel fanboy alert.
    I also joined the forum just to post here.

    Numerous forums are all comenting on this article. Anand's is even compared by some to THG. So I think an update is appropriate here. A delete to.

    T8000, maybe you should read some of those comments, you would discover that , compared to an opteron, results would be very different. Results that aren't even correct btw. And that the benchmark choice is awfull.
  • redpriest_ - Monday, August 9, 2004 - link

    The gcc options used don't generate 64-bit binaries.

Log in

Don't have an account? Sign up now