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
Denial - Monday, August 9, 2004 - link
Doesn't Anand usually author the CPU articles himself? You'd think he would have definitely written this article since it represents such a major change in CPU's. I get the feeling he didn't want his name associated with the article or the chip.TechnoBabble - Monday, August 9, 2004 - link
I can't even believe someone did a review of a Xeon processor and a 64-Bit Athlon. Did the "author" even realize that the cache on the AMD was HALF of the cache on the Intel? Did he even DO any research on these two chips? I mean c'mon...let's rate apples to apples here. Or are the rmors correct and is this guy just a fan-boy or a payola-recipient of Intel??Hey, I have an idea...why don't you do the next "review" between a P4 EE and a Sempron? That would make for some GREAT reading just like this review did!!
Lucky this isn't a paysite because there could be a mass-exodus because of this crap-tacular article.
GEEZ...maybe Tom ISN'T that bad...
JGunther - Monday, August 9, 2004 - link
Such bad press all over tech websites... primer or no, if I were someone over there at AnandTech, I'd rip this thing down before it does any more damage to the site's reputation.opposable - Monday, August 9, 2004 - link
AnandTech has a right to compare any processor they wish. I don't care if they compared the Celeron to the Opteron, so long as the benchmarks and review were articulate and accurate. The cloudiness over what 'bit' some of the benchmarks were run at, the discrepancy between the benchmarks in the article and benchmarks from other sources (including AnandTech itself), and the errors and omissions are what really struck me about this article.I don't care if this was a 'primer,' it was poorly articulated, inadequate, and in some places potentially wrong. I certainly hope that this is not a trend, for AnandTech's sake.
JGunther - Monday, August 9, 2004 - link
An actual 3.6GHz Pentium4 (still a heck of a lost more costly than a 3500+) is compared at Ace's Hardware to some of AMD's offerings. Check it out here:http://www.aceshardware.com/read.jsp?id=65000316
It's not a 3.6F, but from what we've heard, 64bits shouldn't much affect 32bit performance.
Sorry if this has been posted before.
liquidrage2000 - Monday, August 9, 2004 - link
What I don't like about the review is that while the everyday visitor to the site is technical, these reviews show up in searches by people that are not technical.The two CPU's are not geared for the same market, and they aren't priced in the same ballpark.
Hell, the blurb on /. basically just said in a nutshell that Intel thrashed AMD.
So ignoring all the errors and problems with numbers, reviews like this shouldn't be published in this manner unless it's very clear that you're comparing apples to oranges. And it's not clear. Something like "Intel's Server line vs AMD's lowend new desktop" would be better. But overall, you just shouldn't have done this review. It's misleading.
RyanVM - Monday, August 9, 2004 - link
"Relax, its just a primer for future articles. A 3.6F is supposed to compare with a "3600+" rated Athlon 64 isnt it?"Be sure to let me know where I can buy a 3.6F for $350.
JGunther - Monday, August 9, 2004 - link
Viditor: Then why make it? Surely the FX-53 would have made for a better, if still not entirely fair (desktop vs. server) comparison.JGunther - Monday, August 9, 2004 - link
Hrm... just punched in the numbers, and the Intel CPU here is a laughable 240% more expensive than the AMD unit. Let's see the next part of this review: The AMD Opteron 250 vs. the P4 3.4GHz Northwood. Same price ratio.Haha better yet, let's see the A64 3500+ against the P4 2.6GHz w/ 533FSB. Again, 240% price difference.
Viditor - Monday, August 9, 2004 - link
"How, by any stretch of the imagination, is this a good comparison"Kris actually acknowledged that it wasn't in the review...
His point was to try and predict what the P4f will be like when it is finally released.
The only real problems with the review if looked at in that light are:
1. Many of the results appear to be in error
2. Only 1 gig of ram was used on a 64-bit system
3. He mixed 32 bit and 64 bit apps without being completely clear on it
4. He didn't publish memory timings
It has been speculated that he made errors with his makefile, and that he didn't compile for AMD when he tested the A64...