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
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