Linux and EM64T; Intel's 64-bit Suggestion
by Kristopher Kubicki on August 9, 2004 12:05 AM EST- Posted in
- Linux
Since the excuse to not compare Athlon 64s to Intel Pentium based processors has always been "you can't compare apples to oranges," we found ourselves fairly entertained to come into the possession of a 3.6GHz EM64T Xeon processor. Intel's EM64T is Intel's true x86_64 initiative. This 3.6GHz Xeon processor is actually the exact same CPU in as the LGA775 Pentium 4F we will see in just a few weeks. We are offering a preview of an unreleased processor on 64-bit Linux systems. Now, we have Intel and AMD 64-bit x86 processors, 64-bit Linux operating systems and a few days to get some benchmarking done.
We are going to run the benchmarks for this review slightly different than we have in the past. We want to make our numbers easily replicable for those who have the necessary components, but we also want to show the fullest capabilities of the hardware that we have. Many of our previous benchmarks are not multithread (POV-Ray) or do not scale well. Unfortunately, this forces us to use a lot of synthetic benchmarks; but we feel the overall results are accurate and reflective of the hardware used.
The delicate bit for this review was using the SuSE 9.1 Pro (x86_64) installation rather than compiling it from scratch (à la Gentoo). This was done to preserve the ability to replicate our benchmarks easily. Fedora Core 2 refused to install on the IA32e machine because there was no recognized AMD CPU.
As there may have been a little confusion from the last review, the DDR PC-3500 only runs at 400MHz. The Infineon Registered RDIMMs used on the Xeon runs at slightly high latencies. All memory runs in dual channel configurations. We removed 1 CPU for the tests in this benchmark, but since HyperThreading was enabled, we used the SMP kernel. During the second half of the benchmarks, SMP was disabled and the tests were re-run under the single CPU generic kernel. These are both 64-bit CPUs, and so, all benchmarks are run on 64-bit OSes with 64-bit binaries wherever possible.
We are going to run the benchmarks for this review slightly different than we have in the past. We want to make our numbers easily replicable for those who have the necessary components, but we also want to show the fullest capabilities of the hardware that we have. Many of our previous benchmarks are not multithread (POV-Ray) or do not scale well. Unfortunately, this forces us to use a lot of synthetic benchmarks; but we feel the overall results are accurate and reflective of the hardware used.
The delicate bit for this review was using the SuSE 9.1 Pro (x86_64) installation rather than compiling it from scratch (à la Gentoo). This was done to preserve the ability to replicate our benchmarks easily. Fedora Core 2 refused to install on the IA32e machine because there was no recognized AMD CPU.
| Performance Test Configuration | |
| Processor(s): | Athlon 64 3500+ (130nm, 2.2GHz, 512KB L2 Cache) Intel Xeon 3.6GHz (90nm, 1MB L2 Cache) |
| RAM: | 2 x 512MB PC-3500 CL2 (400MHz) 2 x 512MB PC2-3200 CL3 (400MHz) Registered |
| Memory Timings: | Default |
| Hard Drives | Seagate 120GB 7200RPM IDE (8Mb buffer) |
| Operating System(s): | SuSE 9.1 Professional (64 bit) Linux 2.6.4-52-default Linux 2.6.4-52-smp |
| Compiler: | GCC 3.3.3 |
| Motherboards: | NVIDIA NForce3 250 Reference Board SuperMicro Tumwater X6DA8-G2 (Only 1 CPU) |
As there may have been a little confusion from the last review, the DDR PC-3500 only runs at 400MHz. The Infineon Registered RDIMMs used on the Xeon runs at slightly high latencies. All memory runs in dual channel configurations. We removed 1 CPU for the tests in this benchmark, but since HyperThreading was enabled, we used the SMP kernel. During the second half of the benchmarks, SMP was disabled and the tests were re-run under the single CPU generic kernel. These are both 64-bit CPUs, and so, all benchmarks are run on 64-bit OSes with 64-bit binaries wherever possible.
Facebook
Twitter
RSS
275 Comments
View All Comments
snorre - Wednesday, August 11, 2004 - link
"202 - Posted on Aug 10, 2004 at 7:51 PM by KristopherKubicki[...]
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."
24 hours have passed now, so where's the proper review you promised?!
SDA - Wednesday, August 11, 2004 - link
Easy there, ss284. Try not to get the froth on your keyboard.Really, there's no foul play involved. It's just a series of poorly conducted benchmarks. People wouldn't've liked seeing a Xeon beat an A64 to begin with, and now that it's shown that the benchmarks are meaningless poor Kris is getting torn apart. Everyone makes mistakes... I'd advise just taking this review down before it festers, myself, but that's just my opinion.
ss284 - Wednesday, August 11, 2004 - link
Oh dang is that an AMD logo I see on anandtech's site? OH NOES! AMD IS PAYING OFF ANANDTECH! TIME TO START TALKING OUT OF MY ASS!Jesus christ will people stop accusing intel of paying him off? Muks75, you're an utterly useless and pathetic moron. Its pretty obvious you havent taken a look at anything between pages 1 and 13. Try reading the entire discussion before posting your useless crap here.
muks75 - Wednesday, August 11, 2004 - link
Seems like Intel is paying for the advertisements here. I am disappointed with AT, for such a pathetic comparison. And Kristopher, your post saying it did "pretty good for 500$ less" is the lamest excuse to defend the utterly useless comparison you have done.MrEMan - Wednesday, August 11, 2004 - link
#232 stated:"I praise AMD for bringing 64bit cpu's to the home user but any business in their right mind would never purchase a clone/emulator cpu as of AMD.".
Based on your comments, I guess most Intel-only businesses must not be in their "right minds".
As for X86-64, AMD is the innovator, and Intel is the cloner. It is the Itanium (which is the emulator of the two CPUs) which is most likely going to die or at the very least be severly as far as sales go. As a reminder, many of the Athlon64/Opteron engineers worked on the DEC Alpha, which has a great reputation.
The articles I have read stated that board manufacturers really dislike BTX and that DDR2 will be implemented by AMD when there is an actual performance reason to do so (now the only thing that DDR2 increases is the cost).
As a reminder, you are getting much greater performance (per $) out of your Intel-based systems because AMD is forcing them to cut their huge profit margins and actually get back to competing based on value (performance per $) delivered.
As for the review, I totally agree with those who stated that the article should have been pulled mainly because the conclusion has not been corrected since it was based on BS testing methods.
I will be curious to see what Anand's view of this fiasco is when he returns.
Macro2 - Wednesday, August 11, 2004 - link
It appears to be about some bogus benchmarks, particularly John The Ripper. The program looks to Intel in the code. We've seen that trick before in benchmarks so no wonder a lot of people are skeptical.ALSO, the REMOTE location of the Intel server. Which, for some strange reason has never been dilvulged, yet we are supposed to take the word of the person in front of the "remote server"?
chaosengine - Wednesday, August 11, 2004 - link
Intel has the knack to intoduce System packages much before they are market ready....Rambus & i820 are few things that went haywire.... If they try to rush things like this DDR2 will be just where RAMBUS went...in the dustbin
Viditor - Wednesday, August 11, 2004 - link
porkster - "any business in their right mind would never purchase a clone/emulator cpu as of AMD"I disagree. I think Intel made the smart move in copying AMD's x86-64. While obviously their first chips will perform at a substantially lower level, I'm confident that they will have some excellent designs out by 2006.
"I'm a programmer and also want future ready items like PCIe, BTX design, DDR2"
Huh? What does one have to do with the other?
As to being "future ready", BTX looks to be nearing an early retirement...DDR2 is more expensive without any appreciable gains yet...and PCIe has not shown any improvements yet (though it will be much more important to a platform that doesn't have Hypertransport...)
allnighter - Wednesday, August 11, 2004 - link
to 236:He he, he's probably not a programmer. What does BTX have to do with programming. It's just a form factor, and some are arguing that the only reason it's been brought to the market is to make sure that components are rearranged in a way that will ensure Prescotts and other new chips get good enough airflow inide a case cause they're too runnig too hot.
Locutus4657 - Wednesday, August 11, 2004 - link
#232: Your comments about not wanting an AMD chip because you are a programmer confuses me. I am also a programmer and I bought my A64 3000+ because of that. A64's excel in our work evironment e.g. Code Compiliation, Web Serving, Database serving etc.... Why would you choose an inferior product? How does PCIe help you write better code?