Linux and EM64T; Intel's 64-bit Suggestion
by Kristopher Kubicki on August 9, 2004 12:05 AM EST- Posted in
- Linux
Conclusions
Although the Athlon 64 3500+ and the Xeon 3.6GHz EM64T processors were not necessarily designed to compete against each other, we found that comparing the two CPUs was more appropriate than anticipated, particularly in the light of Intel's newest move to bring EM64T to the Pentium 4 line. Once we obtain a sample of the Pentium 4 3.6F, we expect our benchmarks to produce very similar results to the 3.6 Xeon tested for this review.Without a doubt, the 3.6GHz Xeon trounces over the Athlon 64 3500+ in math-intensive synthetic benchmarks. Again, not that it is really a comparison between the two chips yet anyway, but perhaps something of a marker of things to come. However, real world benchmarks, with the exception of John the Ripper is where AMD came ahead instead. Even though John uses several different optimizations to generate hashes, in every case, the Athlon chip found itself at least 40% behind. Much of this is likely attributed to the additional math tweaking in the Prescott family core, and the lack of optimizations at compile time.
That's not to say that the Xeon CPU necessarily deserves excessive praise just yet. At time of publication, our Xeon processor retails for $850 and the Athlon 3500+ retails for about $500 less. The 3.6F processor the Xeon represents does not even exist in retail channels yet. Also, keep in mind that the AMD processor is clocked 1400MHz slower than the 3.6GHz Xeon. With only a few exceptions, synthetically the 3.6GHz Xeon outperformed our Athlon 64 3500+, whether or not the cost and thermal issues between these two processors are justifiable.
We will benchmark some SMP 3.6GHz Xeons against a pair of Opterons in the near future, so check back regularly for new benchmarks!
Update: We have addressed the issue with the -02 compile options in TSCP, the miscopy from previous benchmarks of the MySQL benchmark, and various other issues here and there in the testing of this processor. Expect a follow up article as soon as possible with an Opteron.
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...