Linux and EM64T; Intel's 64-bit Suggestion
by Kristopher Kubicki on August 9, 2004 12:05 AM EST- Posted in
- Linux
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
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.
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.
Facebook
Twitter
RSS
275 Comments
View All Comments
tfranzese - Tuesday, August 10, 2004 - link
Which tests were re-ran? I guess I should ask that first.KristopherKubicki - Tuesday, August 10, 2004 - link
#203 can you be more specific? What is wrong with my conclusion.Kristopher
tfranzese - Tuesday, August 10, 2004 - link
What more do we want? Fix the rest of the article, including the conclusions you drew.KristopherKubicki - Tuesday, August 10, 2004 - link
#200:Jasons article is seperate from mine. His is running on windows anyway with two processors.
"f-off people" is strictly not my attitude. I have made changes to the article that were suggested; i fixed the broken makefile, i even did another article on my vacation with an opteron 150 to be posted within the next 24 hours.
What more do you want? Really?
Kristopher
MikeEFix - Tuesday, August 10, 2004 - link
There is nothing wrong with an engineers’ pov. We tend to like symmetry and base results on facts. Unfortunately there is little symmetry and too many variables for accurate results.Experiments should be kept in the lab
allnighter - Tuesday, August 10, 2004 - link
A few days ago when Nocona was announced I shouted I wanted some benchmarks.When Jason Clark mentioned AT is working on some benchmarks I was very excited. Now I am am not. This article is... well in attempt to be polite... of a very questionable quality or simply crap.As many people posted their observations, whith most of which I agree, this is not quality we're used to from AT. And all the AMD and Intel fanboyish escapades in here are just making all this worse.
I feel like something should be done. I have no idea what but just one 'f-off people' type of comment from the author is just not doing it for me. This is bad.
Pumpkinierre - Tuesday, August 10, 2004 - link
Good on ya Kristopher, you got a bit of scientist in you unlike some of these machine like engineer types. Some of us know where you are coming from (and it aint Intel). A little knowledge can be a dangerous thing but its still better than no knowledge at all. Looking forward to your later articles on the subject.MikeEFix - Tuesday, August 10, 2004 - link
Well the nvidia 250 reference board isn't exactly a Tyan Thunder K8W(S) either.The Xeon is using platform $600.00 server mainboard while the desktop variant, a64, is using the generic desktop solution.
Macro2 - Tuesday, August 10, 2004 - link
This is the kind of article i'd expect from Tom's not Anandtech. I guess Anand is out with the lady.srg - Tuesday, August 10, 2004 - link
Well with these refinements an updates to the benchmarks, not forgetting setting them up right, the gap is closing to what I would have though it would have been, although the Jon-The-Ripper benchmark does seem odd (explained better my an earlier poste, if he's right then the 3500+ is basically running 64-bit'ised K6 code).I think what Kris has learnt here will be valuable for later reviews (and no, the simple fact that Intel beat AMD won't bring a torrent of flames like this one).
srg