Linux and EM64T; Intel's 64-bit Suggestion
by Kristopher Kubicki on August 9, 2004 12:05 AM EST- Posted in
- Linux
Audio Encoding
Lame was compiled from source without optimizations. We only ran ./configure and make, without any flags. We realize that some people would like to verify our binaries and sample files for their own benchmarks. In order to save bandwidth and prevent copyright infractions, we will provide our test files and binaries under limited circumstances to serious inquiries. We ran lame on a 700MB .wav file using the command equivalent to the one below:# lame sample.wav -b 192 -m s -h >/dev/null
Encoding time, lower is better.
POV-RAY
Although POV-RAY is limited in application (particularly when compared against Mental Ray), it does provide a free open source solution for basic rendering. POV-Ray 3.50c was our choice of render engine for this benchmark. For benchmark specifics, we run the exact benchmark as specified by the POV-Ray official site. We use the precompiled RPM for this test.Render Time in Seconds, less is better.
POV-Ray does not have multithread support, so we were not surprised to see the HyperThreading configuration slowing down to the configuration without HT. We see the Athlon 64 processor pull way ahead; render tasks are extremely CPU and memory dependant. With the memory controller on the CPU, Athlon 64 becomes the stronger offering in this situation.
GZip
To throw in some rudimentary tests for GZip, we used the included GZip 1.3.5 to compress the .wav file from the benchmark above. We do not want to limit our I/O on writing to the hard drive, so the operation is performed as below:# time gzip -c sample.wav > /dev/null
Intel wins their first bout of the analysis, albeit not by much. We will find a recurring pattern later on with integer based calculations and the Nocona Xeon processor. The entire Prescott family of Intel CPUs received a dedicated integer multiplier rather than continually using the floating point multiplier. This becomes extremely useful in some of our other benchmarks.
Database Performance
We will run the standard SQL-bench suite included with RPM MySQL 4.0.20d.
Of all our benchmarks, the SQL-bench becomes the most baffling. The extremely threaded database application performs particularly poorly with HyperThreading enabled. The Althon 64 outperforms Intel again in this benchmark, and a lot of it is almost certainly accredited to the on die memory controller again.
Update: We copied the 32-bit marks from our benchmark in previous testing instead of the 64-bit. You can view the previous articles here from a month ago. The graphs have also been updated.
Facebook
Twitter
RSS
275 Comments
View All Comments
saechaka - Tuesday, August 10, 2004 - link
i don't know much about cpu but this thread has been a great read. to fifi, i don't think you thank the garbage man if he spews garbage on your driveway, but if he picks it up, you should. props to kris for picking up the garbage. maybgherald - Tuesday, August 10, 2004 - link
I think this article can be best characterized as "useless" or perhaps "how to not benchmark processors."I'm pretty sure Kris will take it as a lesson learned, and anticipate any follow ups will be more interesting/informative.
To those who allege Kris or Anand have somehow been paid by Intel: quit talking out of your ass. Seriously, I've got better things to do than read your senseless drivel.
People make mistakes, and that's all we should take away from this.
fifi - Tuesday, August 10, 2004 - link
I don't understand, what's with the thanking Kris ?Do you THANK your newspaper editor? do you THANK a TV news reporter? do you THANK your mailman?
This is his job, he is supposed to do it right. If he screws up, then he gets told off. That's all.
If he does a good job with it, then he is told that it's a job well done, more than that, AT gets visitors, gets sponsors and ads.
But he screws up major and we are supposed to THANK him for screwing up?
Do you THANK your garbage collector for spewing garbage all over your driveway? Do you thank your TV news reporter for giving you wrong *news*?
No, I am not grateful that this *review* was posted. It was incomplete, misleading, confusing and factually incorrect.
MikeEFix - Monday, August 9, 2004 - link
"Those who pay attention to our other articles should know the 3.6F and the 3500+ are in fact marketed against each other."This statement is incorrect
Viditor - Monday, August 9, 2004 - link
G'day Kris!Thanks for the reply! I can imagine that it's not easy to deal with all of the yammering...!
"I'll just remove all the 3500+ marks and you can all look back at my previous articles to see where this 3.6F stands"
PLEASE DON'T!!
If you could just post an Update saying that some possible errors occured and that you're looking into them, that would be much better...
"There was a problem with the MySql graphs. We posted the 32-bit marks on accident instead of the 64-bit"
I figured it was something like that...
"i'm open to retest and revise as many times as it takes to provid ethe best information i can"
Many thanks! That's all that most of the intelligent posters can ask for...please try to ignore the rest.
dtobias - Monday, August 9, 2004 - link
This article was either the perfect marketing gimmick for Anandtech.com, or a colossal screw up. This was like Coke saying they were pulling Coke Classic off the market. We'll know that it was nothing but a publicity stunt when Anand gets back from vacation and prints a retraction. If not, then we'll start looking for the new intel ads to pop up at Anandtel.com Hey - if they paid you then you have to put the ads up, right?plus - Monday, August 9, 2004 - link
Anand,Do the right thing. Take it down tonight, repost it when you believe it's accurate.
Don't be the next Tom's Hardware. Too many people count on Anandtech.com.
Plus
KristopherKubicki - Monday, August 9, 2004 - link
Alright.Heres the deal. I'll just remove all the 3500+ marks and you can all look back at my previous articles to see where this 3.6F stands.
Second, I asked if anyone wanted the binaries or test files from this review. I just went over my email and from the 120+ emails i got flaming me, 3 people asked for the binaries. I'm probably just going to give open shell access to the machine and let you guys find out for yourself where this machine stands.
There was a problem with the MySql graphs. We posted the 32-bit marks on accident instead of the 64-bit. The comments we posted on the benchmark magically still lined up.
DJB is one of my professors and i will discuss some of the issues raised with him concerning primegen. Thats if he doesnt cut my head off first for posting his program without his permission.
I need to persue the issues with TSCP. I'll admit, the only reasons i posted it here was because i saw it in Ace's benchmarks; whom i draw and extreme amount of respect from.
Regardless of what you may or may not think about the marks from the review, i'm open to retest and revise as many times as it takes to provid ethe best information i can. Simply stating "this review sucks" or "why did you compare these chips" without digesting the entire article has been extremely discouraging.
Oh and for all those people who think Intel paid me for this review or whatever; yeah right they dont even know i have their chips! Good luck trying to prove that one.
Kristopher
KristopherKubicki - Monday, August 9, 2004 - link
Testsnorre - Monday, August 9, 2004 - link
Slash dotted!http://linux.slashdot.org/linux/04/08/09/136230.sh...