#46; the 8 way record claim was for a 64-bit JVM. The PowerPC result you reference was for a 32-bit JVM. specjbb stresses the memory architecture heavily (there's no I/O); the submitted result from IBM include a machine with 64GB of RAM, while the Sun Opteron box had 16GB, and they are running different JVM versions. If you look at the lower numbered runs you'll notice they're pretty close (the Opteron being slightly ahead), but that it hits it's wall much earlier due to significantly less RAM.
#34 That is plain stupid, it isnt from been taken out that it will protect him (if thats the true), or the microsoft guys cant read forums where the article have been already posted.
Microsoft only have to look for who usually talk with anand.
Den: Very true but recall that our previous test was done on Opteron 850s instead of Opteron 852s. The 852 performs a bit better than th 850.
opus13i: We have been stuckin MI redtape land for some time. It wouldn't make sense to change the benchmark at this point either because our previous tests used the 32-bit single core solution. Since they don't seem to have much desire to provide us with the correct license we will probably drop that benchmark in favor of something a little more versatile.
I dont care who made the hardware, its a hell of a machine. I wish Intel had to rely on inovation and good products to survive like AMD does. Intel really doesn't have many products capable of out performing AMDs equivalent anymore.
Did you even bother to check with mental images? With a simple phone call you could have had the proper licensing in place for 8 cores, as well as every possible variation of 64bit possible.
"We include Mental Ray and Shake as a point of reference, although both applications are strictly 32-bit at this time. Mental Ray is further hindered by the fact that the version we have is not SMP-aware."
way to go detective, i dont suppose you actually looked at teh specifications did you?
You folks are giving Sun a bit too much credit on the hardware portion of this review. In reality, the system OEM is a company called Newisys, a subsidiary of Sanmina-SCI.
Interesting article, I am confused why you are dissapointed in the GCC complile time though. The dual core machine took 369 seconds (with 9 jobs) and the single took 603.18 seconds (with 5 jobs). 603.18/369=1.635 or 63.5% faster which is well in the 50-80% range. Your article says 43% faster, so maybe the GCC compile conclusion is based on a typo?
I saw the title to the PS3/XBOX article. It was a different one than the original article from last week. I clicked on it to read it and nothing showed up. It was an article critical of the CPU's on the two systems I believe. Matbe Anand find some insider stuff that was only limited to a few people inside MS. If so, I think the potential rewards of protecting the source is much better long term than getting them in trouble and burning a bridge. Along with the long term effects of insiders trusting Anand.
You can no longer get v20z via ebay. I managed to buy a half-dozen of them for $1200-$1500 each, although I admit I had to collude with another buyer to do so. Probably Sun has enough traction with the v\d+z series that they no longer need the eBay channel.
The only beef I have with the v-series is Sun can ben recalcitrant about supplying the voltage regulator modules. In the v20z there are four removable VRMs and if you bought a single-CPU machine, you only get 2. Additional VRMs sell in pairs for $175 but the lead time is indeterminant and sometimes very long.
Actually, no its not. RHEL is by far and away more widely distributed, and more likely to show results to the people who can most relate to this review.
If whomever is really worried about protecting his "insider" source, you might want to contact Google to have them clear the article from their cache (I don't even know if that's possible).
The Database benchmarks are likely bottlenecked on storage. Attach a high-speed array with multiple disks, and the scaling would be much more linear vs. 2-way.
It would be nice if other Opteron-builders would add to the test so we can get an idea of how well the Opteron is implemented.
I'd say webspace is best served with dualcore Opterons. 90% gain! Holy moly!
#23 I have worked as a temporary at Sun in The Netherlands in 1987 when they were about to release their 4/ series. Their 3/ machines were already considered top notch then. They offered workstations with an optical mouse that moved over a special gridpad and full color screens. That was really something special then. No AMD CPUs at that time.
To be perfectly honest as well, I also didn't know them before I worked there ;-)
hondaman: This is why we used SLES this time around instead of RH9. Unfortunately the previous single-core V40z tests were all done a few months ago when we had that machine.
Wow, I wish my company had a use for a system like that. I'd take a paycut just to be able to play with it for a while... damned fine enginering on both Sun and AMD's part. And to be prefectly honest, I never really payed Sun that much attention until they started using AMD procs. Everyone else needs to get with the program and give AMD the market share they deserve...oh wait...I'll stop there.
#21: Read the comments and you'll find your answer.
Kristopher: Page 7, "Apache Benchmarks" text:
"It's also interesting to note the difference between Solaris 10 and SLES 9 here. As the threads increased, there was a wider gap between performance of the Solaris configuration and the SLES configuration in favor of Solaris."
The graph on that page shows the opposite, with SLES outperforming Solaris.
Does anyone know if the v20zs were dual core-capable? I heard that if you negotiate with sun (go to sun's ebay sale for the v20z), you can get really good deals. I'd love to just get two 270s if/when the prices come down.
I think everyone has read the PS3/360 article but me, its been linked on Ars and it was out long enough that someone at MS could have downloaded the whole thing.
But if there a re liability and/or other issues that might come from leaving it up, than I will just have to wait.
Without much pressure from Intel, Sun has been pretty free to do what they want with AMD's processors. Sun is even going a bit on the offensive with Intel trade-in programs. Even though both AMD and Sun have been through some hard times recently, Sun is a great ally for AMD for two reasons; first, Sun knows servers - this is a critical market for AMD. Second, Sun isn't afraid of Intel and doesn't have nearly the problems AMD does with their customers.
HEhuehueh... that's the reason why Sun server is still the best AMD server out there. HP and IBM should learn from them on how to build a good Opteron server.Anyway, Cray implementation of Opteron is still unmatched.
One question, why the lack of apples to apples os comparison between the two systems? You talk about S10 for two pages yet you dont list it as being tested on the Dual Core machine. That and you do not use the same linux versions on the two machines.
To me that makes this comparison a whole lot less usefull. Granted, the perf should not vary to much between SuSE 9 and 9.1 but to not include S10 in the Dual Core comparo seems kinda silly.
Ecmaster76: Eh, something was messed up with the content management system. PS3 article is pulled for now because Anand is worried about MS tracing his anonymous insider.
Ah, rendering problems. Thats why this article isn't on the main page (2461, the console article is a dead link, and it occured to me that number was about three articles to high, easy guess).
Shame on you for pulling stuff when you could just leave a little 'were working on it'.
AMD doesn't have "problems with it's customers" at all. AMD has problems with Intel's illegal Biz practices which have prevented many AMD customers from selling AMD products. With any luck HP, Sony and a Helleva lot of other PC companies will finally put Intel execs in prison where they belong. And you can bet all the companies that have been blackmailed by Intel will be a LOT more interested in selling AMD products now that the shit has hit the fan and they can come out of hiding.
Is it just me, or is it normal to have problems reading anything but the first page? When I click to go to the next page, it just brings up the "article search" box. The print version also doesn't work.
Using Firefox on linux. All extensions were disabled for the purpose of troubleshooting, with the same response.
As it is right now, even clicking the article results in the "Article Search" box, rather then the article. I was able to read the first page about 5 min ago, though.
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
47 Comments
Back to Article
nottlv - Tuesday, July 5, 2005 - link
#46; the 8 way record claim was for a 64-bit JVM. The PowerPC result you reference was for a 32-bit JVM. specjbb stresses the memory architecture heavily (there's no I/O); the submitted result from IBM include a machine with 64GB of RAM, while the Sun Opteron box had 16GB, and they are running different JVM versions. If you look at the lower numbered runs you'll notice they're pretty close (the Opteron being slightly ahead), but that it hits it's wall much earlier due to significantly less RAM.jjames5 - Tuesday, July 5, 2005 - link
8 way jbb2000 world record - right!This result is a year old and still bests the sun with over 50%:
http://www.spec.org/jbb2000/results/res2004q3/jbb2...
nserra - Friday, July 1, 2005 - link
#34 That is plain stupid, it isnt from been taken out that it will protect him (if thats the true), or the microsoft guys cant read forums where the article have been already posted.Microsoft only have to look for who usually talk with anand.
Opteron - Friday, July 1, 2005 - link
Forget my last comment...ps. i missed 4 way Xeon and Itanium systems :D
Opteron - Friday, July 1, 2005 - link
There is miscalculations about percentages, those are calculated wrong.In http://images.anandtech.com/graphs/sun%20fire%20v4...
comment is:
" We see a 43% performance increase over the quad Opteron 250 V40z; certainly impressive but we would like to see more."
But actually it's almost 64% since there is no point in comparing 5 threads vs 5 in a 8core system..
Googer - Friday, July 1, 2005 - link
Where did the article go?KristopherKubicki - Thursday, June 30, 2005 - link
Den: Very true but recall that our previous test was done on Opteron 850s instead of Opteron 852s. The 852 performs a bit better than th 850.opus13i: We have been stuckin MI redtape land for some time. It wouldn't make sense to change the benchmark at this point either because our previous tests used the 32-bit single core solution. Since they don't seem to have much desire to provide us with the correct license we will probably drop that benchmark in favor of something a little more versatile.
Kristopher
Kristopher
jkostans - Thursday, June 30, 2005 - link
I dont care who made the hardware, its a hell of a machine. I wish Intel had to rely on inovation and good products to survive like AMD does. Intel really doesn't have many products capable of out performing AMDs equivalent anymore.opus13i - Thursday, June 30, 2005 - link
ugh.Did you even bother to check with mental images? With a simple phone call you could have had the proper licensing in place for 8 cores, as well as every possible variation of 64bit possible.
"We include Mental Ray and Shake as a point of reference, although both applications are strictly 32-bit at this time. Mental Ray is further hindered by the fact that the version we have is not SMP-aware."
way to go detective, i dont suppose you actually looked at teh specifications did you?
http://www.mentalimages.com/2_1_2_configurations/i...
no 64 bit indeed.
Xunilla - Thursday, June 30, 2005 - link
You folks are giving Sun a bit too much credit on the hardware portion of this review. In reality, the system OEM is a company called Newisys, a subsidiary of Sanmina-SCI.
Den - Thursday, June 30, 2005 - link
Interesting article, I am confused why you are dissapointed in the GCC complile time though. The dual core machine took 369 seconds (with 9 jobs) and the single took 603.18 seconds (with 5 jobs). 603.18/369=1.635 or 63.5% faster which is well in the 50-80% range. Your article says 43% faster, so maybe the GCC compile conclusion is based on a typo?Kilim - Thursday, June 30, 2005 - link
I saw the title to the PS3/XBOX article. It was a different one than the original article from last week. I clicked on it to read it and nothing showed up. It was an article critical of the CPU's on the two systems I believe. Matbe Anand find some insider stuff that was only limited to a few people inside MS. If so, I think the potential rewards of protecting the source is much better long term than getting them in trouble and burning a bridge. Along with the long term effects of insiders trusting Anand.jwbaker - Thursday, June 30, 2005 - link
You can no longer get v20z via ebay. I managed to buy a half-dozen of them for $1200-$1500 each, although I admit I had to collude with another buyer to do so. Probably Sun has enough traction with the v\d+z series that they no longer need the eBay channel.The only beef I have with the v-series is Sun can ben recalcitrant about supplying the voltage regulator modules. In the v20z there are four removable VRMs and if you bought a single-CPU machine, you only get 2. Additional VRMs sell in pairs for $175 but the lead time is indeterminant and sometimes very long.
Houdani - Thursday, June 30, 2005 - link
32: The article was pulled in order to protect one of the anonymous sources (see comment #10).hondaman - Thursday, June 30, 2005 - link
Actually, no its not. RHEL is by far and away more widely distributed, and more likely to show results to the people who can most relate to this review.finbarqs - Thursday, June 30, 2005 - link
i did read the comments, but i still don't know why it was taken down... it just said that it wasn't up to kris to take the article down.Houdani - Thursday, June 30, 2005 - link
30: What's with the hate?And it was quite obvious to me there were multiple sources.
Questar - Thursday, June 30, 2005 - link
So that article was based upon one source?!?!translation: It was crap, our source was an idiot.
yacoub - Thursday, June 30, 2005 - link
Is there no performance increase seen with PC3200 RAM over PC2700?PrinceXizor - Thursday, June 30, 2005 - link
If whomever is really worried about protecting his "insider" source, you might want to contact Google to have them clear the article from their cache (I don't even know if that's possible).P-X
kbsartain - Thursday, June 30, 2005 - link
The Database benchmarks are likely bottlenecked on storage. Attach a high-speed array with multiple disks, and the scaling would be much more linear vs. 2-way.ceefka - Thursday, June 30, 2005 - link
It would be nice if other Opteron-builders would add to the test so we can get an idea of how well the Opteron is implemented.I'd say webspace is best served with dualcore Opterons. 90% gain! Holy moly!
#23 I have worked as a temporary at Sun in The Netherlands in 1987 when they were about to release their 4/ series. Their 3/ machines were already considered top notch then. They offered workstations with an optical mouse that moved over a special gridpad and full color screens. That was really something special then. No AMD CPUs at that time.
To be perfectly honest as well, I also didn't know them before I worked there ;-)
sprockkets - Thursday, June 30, 2005 - link
SuSE Linux Enterprise not enterprise enough for u?KristopherKubicki - Thursday, June 30, 2005 - link
hondaman: This is why we used SLES this time around instead of RH9. Unfortunately the previous single-core V40z tests were all done a few months ago when we had that machine.Kristopher
Xenoterranos - Thursday, June 30, 2005 - link
Wow, I wish my company had a use for a system like that. I'd take a paycut just to be able to play with it for a while... damned fine enginering on both Sun and AMD's part. And to be prefectly honest, I never really payed Sun that much attention until they started using AMD procs. Everyone else needs to get with the program and give AMD the market share they deserve...oh wait...I'll stop there.slashbinslashbash - Thursday, June 30, 2005 - link
#21: Read the comments and you'll find your answer.Kristopher: Page 7, "Apache Benchmarks" text:
"It's also interesting to note the difference between Solaris 10 and SLES 9 here. As the threads increased, there was a wider gap between performance of the Solaris configuration and the SLES configuration in favor of Solaris."
The graph on that page shows the opposite, with SLES outperforming Solaris.
finbarqs - Thursday, June 30, 2005 - link
wait why the xbox360/ps3 article taken down?hondaman - Thursday, June 30, 2005 - link
can you swap suse with a real enterprise os like rhel?themelon - Thursday, June 30, 2005 - link
I guess I should have kept reading.Sorry.
I have one of the v40's in my lab with 4 of the 875's. Very nice machine.
Doormat - Thursday, June 30, 2005 - link
Does anyone know if the v20zs were dual core-capable? I heard that if you negotiate with sun (go to sun's ebay sale for the v20z), you can get really good deals. I'd love to just get two 270s if/when the prices come down.KristopherKubicki - Thursday, June 30, 2005 - link
Ecmaster76: It wasn't my decision to remove the article, and I agree with your thoughts as well.Kristopher
mastashake57 - Wednesday, June 29, 2005 - link
Let me tell you, we have the first generation v40z, and it's a total crusher in comparison to our Dell PowerEdge 6650s. Way to go SUN!Intel XEONs can't hold a candle to it...
Ecmaster76 - Wednesday, June 29, 2005 - link
that should read:But if there are liability and/or other issues that might come from leaving it up, than I will just have to wait.
Ecmaster76 - Wednesday, June 29, 2005 - link
KristopherKubickiI think everyone has read the PS3/360 article but me, its been linked on Ars and it was out long enough that someone at MS could have downloaded the whole thing.
But if there a re liability and/or other issues that might come from leaving it up, than I will just have to wait.
Ahkorishaan - Wednesday, June 29, 2005 - link
#11 Solaris 10 is on the graphs, he jsut forgot to add it to the chart.Hey guys in Anandtech, think we could grab a review of the new Sun Ultra 20 workstation? It looks pretty sweet.
prd00 - Wednesday, June 29, 2005 - link
Without much pressure from Intel, Sun has been pretty free to do what they want with AMD's processors. Sun is even going a bit on the offensive with Intel trade-in programs. Even though both AMD and Sun have been through some hard times recently, Sun is a great ally for AMD for two reasons; first, Sun knows servers - this is a critical market for AMD. Second, Sun isn't afraid of Intel and doesn't have nearly the problems AMD does with their customers.HEhuehueh... that's the reason why Sun server is still the best AMD server out there. HP and IBM should learn from them on how to build a good Opteron server.Anyway, Cray implementation of Opteron is still unmatched.
themelon - Wednesday, June 29, 2005 - link
One question, why the lack of apples to apples os comparison between the two systems? You talk about S10 for two pages yet you dont list it as being tested on the Dual Core machine. That and you do not use the same linux versions on the two machines.To me that makes this comparison a whole lot less usefull. Granted, the perf should not vary to much between SuSE 9 and 9.1 but to not include S10 in the Dual Core comparo seems kinda silly.
KristopherKubicki - Wednesday, June 29, 2005 - link
Ecmaster76: Eh, something was messed up with the content management system. PS3 article is pulled for now because Anand is worried about MS tracing his anonymous insider.Kristopher
Ecmaster76 - Wednesday, June 29, 2005 - link
Ah, rendering problems. Thats why this article isn't on the main page (2461, the console article is a dead link, and it occured to me that number was about three articles to high, easy guess).Shame on you for pulling stuff when you could just leave a little 'were working on it'.
:p
Beenthere - Wednesday, June 29, 2005 - link
FWIW,AMD doesn't have "problems with it's customers" at all. AMD has problems with Intel's illegal Biz practices which have prevented many AMD customers from selling AMD products. With any luck HP, Sony and a Helleva lot of other PC companies will finally put Intel execs in prison where they belong. And you can bet all the companies that have been blackmailed by Intel will be a LOT more interested in selling AMD products now that the shit has hit the fan and they can come out of hiding.
KristopherKubicki - Wednesday, June 29, 2005 - link
It brings up the Article Search box because I had to disable the article until we figure out the IE problem.Thanks,
Kristopher
yelo333 - Wednesday, June 29, 2005 - link
Is it just me, or is it normal to have problems reading anything but the first page? When I click to go to the next page, it just brings up the "article search" box. The print version also doesn't work.Using Firefox on linux. All extensions were disabled for the purpose of troubleshooting, with the same response.
As it is right now, even clicking the article results in the "Article Search" box, rather then the article. I was able to read the first page about 5 min ago, though.
mircea - Wednesday, June 29, 2005 - link
Page 3, 2nd last pharagraph, 4th line "we were ample to use the analyzer"I guess you want to say "able".
jm20 - Wednesday, June 29, 2005 - link
wierd rendering in IE, does not produce a background and the formatting looks off. Also page 2 is not visible and sends me to the article search page.Marlin1975 - Wednesday, June 29, 2005 - link
yea weird rendering to say the least, that and nothing after page 2?BurntKooshie - Wednesday, June 29, 2005 - link
http://www.anandtech.com/systems/showdoc.aspx?i=24...Shouldn't the first graph list SLES9 as one of the test parameters isntead of two Solaris 10's?
KristopherKubicki - Wednesday, June 29, 2005 - link
If anyone is getting weird rendering in IE, please email me [email protected]Kristopher