Xeon vs. Opteron Performance Benchmarks

QuickSand writes "Anand got his hands on some of Intel and AMD's enterprise processors including 4MB L3 Xeons, and put them to the test. Results were a little varied as 4-way Opteron systems seemed to fare the best, although dual Xeon configurations almost always beat dual Opterons. The exact benchmarks are here."

Comments

IA-32e vs IA-32

[Stonent1]

Can somebody tell me if the IA-32e processors will be in the socket 478 format to work with existing boards, or will they require a whole new socket and chipset (rather than a bios update) If they really are just "extensions" then I don't see why anything special would need to be on the motherboard correct? The cpu should switch into 64bit mode whenever the OS tells it to right?

Re:IA-32e vs IA-32

[irokitt]

I don't really know, but I think Intel's 64-bit chips will probably use a Tejas-style clip system, not pins. Technology that won't work in a current motherboard. But, once AMD upgrades to socket 939 for the FX-51, it won't work in current boards either. AMD and Intel are both set to release the new sockets at about the same time PCI-Express comes out, so upgrade-happy people will need to buy new motherboards anyway.

Re:IA-32e vs IA-32

[adler187]

Technically since the new Prescott chips have the instructions on them, yes you could buy a 478 Prescott. You would just have to hack the chip to activate the instructions (good luck with that!).

As for a real IA-32e chip with the instructions enabled, Intel has stated that they arent coming out for while, and since Intel is moving the P4 to the new 775 chipset in a few months, I would bet that they would also be released under this new chipset. Heck, they might not even release their IA-32e chips within the lifetime of the 775 chipset.

Personally my Athlon 2600 just fine enough for me.

Re:IA-32e vs IA-32

[Anonymous Coward]

need to buy new motherboards

This makes me want to throw up. The last motherboard purchase I made, it was a chore finding one with the _least_ amount of features. Need an AMR riser slot? Fuck no, I'd rather have the PCI slot back. Need integrated sound? No, integrated sound makes my already bad speakers sound worse. It must've been tough figuring out how to make a decade's worth of improvements in technology amount to nothing. I have an ISA soundblaster from 10 years ago that sounds better than the onboard sound on my last motherboard. Need integrated video? I won't begrudge you this. Some people build clusters with their motherboards, and a video card is needed to boot, but if I have a choice I won't buy a mobo with integrated video.

In short, I want a motherboard with slots for RAM, an AGP slot, a socket/slot/hole for a CPU, PS/2 hookups, serial and USB connectors, and the rest of the board filled up with PCI (or PCI express) slots. That's the ticket.

Re:IA-32e vs IA-32

[Loki_1929]

" Can somebody tell me if the IA-32e processors will be in the socket 478 format to work with existing boards, or will they require a whole new socket and chipset (rather than a bios update)"

They're disabled in all socket 478 chips. The new Pentium 4e chips (Prescott core) supposedly have the extensions, but they remain disabled. Technically, it may be possible to gain access to those instructions through some sort of BIOS hack, but you would also need to use an Operating system that can detect, support, and make use of those new instructions. Also, you risk using unfinished or untested parts of the CPU if you do manage to gain access and use the extensions. There would be no benefit other than simple tinkering.

"If they really are just "extensions" then I don't see why anything special would need to be on the motherboard correct?"

You still need a CPU that supports the instructions, and which has them enabled. Technically, if Intel released Prescotts in S478 form with IA-32e enabled, it should work fine with an existing motherboard which would otherwise support the Prescott chip you're using. The probablility of Intel taking the time and effort to do this less than a quarter away from a whole new socket is virtually nil.

"The cpu should switch into 64bit mode whenever the OS tells it to right?"

That's not entirely accurate. Technically, what happens under AMD64 (the basis for IA-32e), is that specific instructions can be sent to the CPU to have it run code in what's called "Compatibility mode", which essentially allows it to behave as though it were a 32-bit CPU. The difference is that you're not 'switching' to 64-bit mode. You're either in 64-bit mode with the option for compatibility mode when needed (meaning you need a 64-bit capable OS), or you're in 32-bit and you're stuck in 32-bit.

If you're looking for 64-bitness, you may simply want to get an Athlon64. If you're waiting for 64-bitness on the Intel side of things, you'll be waiting until some time towards the end of this year. Good luck.

Re:IA-32e vs IA-32

[LordHunter317]

This makes me want to throw up. The last motherboard purchase I made, it was a chore finding one with the _least_ amount of features. Need an AMR riser slot? Fuck no, I'd rather have the PCI slot back.
You do realize it costs much less to put a AMR or CNR slot on a motherboard then a PCI slot right?

Need integrated sound? No, integrated sound makes my already bad speakers sound worse. It must've been tough figuring out how to make a decade's worth of improvements in technology amount to nothing. I have an ISA soundblaster from 10 years ago that sounds better than the onboard sound on my last motherboard.
Now its obvious you're trolling. Say what you want about AC97-based onboard sound (which nearly everythign is), but its good enough. Your speakers are much more likely the problem. The long and short is that all PC sounds cards equally suck until you get to professional grade gear.

Need integrated video? I won't begrudge you this. Some people build clusters with their motherboards, and a video card is needed to boot, but if I have a choice I won't buy a mobo with integrated video.
What does having this cost you? Its not like you have to use it, or that boards with onboard video cost signifcantly more.

Re:IA-32e vs IA-32

[Yokaze]

> Now its obvious you're trolling. [...] The long and short is that all PC sounds cards equally suck until you get to professional grade gear.

You must be joking. Most of the integrated sound I've had the joy to listen to produced noticeable background-noise. The most obvious one was the Eden-M board. Most mb-producers don't give much about seperating the analogue part from the digital, so accompanied with an intergrated graphics card, you can practically hear how a window is restored. It is usually not the quality of the on-board sound, which sells it, but purely the capability of producing some sound.

Pffft. These Intel vs. AMD flamewars are pointless

[Can it run Linux]

because EVERYONE knows that Intel always wins.

xeons/opterons market share

[chef_raekwon]

dual xeons have owned the market for a long time...it will be difficult (although not impossible) for AMD to topple this.

many people did not upgrade to Intel's Itanium, but rather were upgrading to their high end dualie xeon systems -- they run very reliably, and very fast. a few instances where we've put in dual 2.x ghz xeons for web/mail servers...and only a slashdotting could bring them down...(well, an exaggeration...but you get the point).

Re:xeons/opterons market share

[ePhil_One]

many people did not upgrade to Intel's Itanium

Folks were avoiding the Itanium because it was a disaster; slow and expensive. We've been looking at 64 bit computing for a while, because of the seamless > 4GB RAM capabilities. Intel's PAE extensions are OK, but they really didn't solve any of the problems we were having.

The net result was we went to 64 bit PPC architecture 3 years ago on those critical systems, And everything has been fine. AIX works great, and IBM's embrace of GNU/Linux means an easy learning curve for us Linux users.

Re:xeons/opterons market share

[hackstraw]

I have not heard that the Itaniums were slow since Intel came out with the Itanium2. Yes, the Itanium1's were dog slow. I've got 65 Itanium2 processors downstairs, and I'm happy with them. For our purposes (crunching numbers on very large datasets) the Itanium2 was the platform of choice because of its 64bit addressing, high memory bandwidth and good processor speed.

I wish we could get by with cheap Xeons, but they just don't cut the mustard for our applications.

Re:xeons/opterons market share

[flaming-opus]

Itaniums are expensive, but not outrageous compared to other high-end processors like Power4 or ultrasparc. They also perform quite well. They are definately better performers than xeons for most of our apps.

The problem with itanium is not that they aren't a good technology, but rather that intel is trying to shove them into the high-end of the market, which is a difficult place to compete. sparc, power, pa-risc, alpha have all been around for years, have established customer bases, and lots of businesses have invested tons of money in running them. It's a difficult place to introduce any new products.

Intel has been stymied trying to sell ia64 into that space, and has undercut itself, by continuing to improve xeon, which performs pretty well and is comparatively inexpensive. Most segments are going to migrate to the all-american mantra of "GOOD-ENOUGH, and CHEAP!" which describes xeons/opterons perfectly. The market segments that won't migrate in that direction are willing to pay the big bucks for stability, and reliability. They are very slow movers. Intel might sell some itaniums to these customers, but they'd better be willing to wait a long time.

I think a lot of people judge itanium by the yardstick of Xeon, and maybe should not. If itanium ends up simply as a replacement for pa-risc, alpha, and MIPS in the SGI and HP portpholio, that may be a success by some measures.

Re:xeons/opterons market share

[Loki_1929]

The Itanium2s and up are pretty decent so long as you're working with code designed for 64-bit/EPIC. Where you run into problems is with 32-bit code, or pretty much any code not designed/optimized for EPIC. There's nothing wrong with Itanium in-and-of itself; it's just not cut out for compatibility the way x86 is. Had Intel stuck with the original plan for IA-64 (which was to replace x86 from top to bottom), this would have been fine. You simply would have lost the ability to use old applications, but new ones would run reasonably fast. 10 years later, Itanium has its niche, does quite well within that niche, and sucks for everything else. :)

"I wish we could get by with cheap Xeons, but they just don't cut the mustard for our applications."

This is exactly why Opteron DOES compete with Itanium - if only indirectly. Opteron will never hit the big-tin niche, simply because it was never designed, nor intended to do so. What Opteron does is bring 64-bitness, and all the benefits therein to the mid-range crowd. This forces Intel to choose between giving up on Itanium as anything other than a big-tin chip, or losing half its mid-range customers to AMD. Losing such a lucrative market would be far worse for Intel in the long run than losing the 10 years of R&D sunk into Itanium, so they've chosen to bring the Xeon line to the 64-bit world. With the new Potomac core (Q1/H1 '05), the XeonMP will be the CPU of choice for Intelphile mid-range customers in need of Itanium's benefits, but conscious of cost. The result will be that Itanium's legs will finally be completely taken out from under it, and it will be resigned to little more than a handfull of extremely high-end big-tin servers each year.

Does this mean Intel should continue to develop Itanium, even if it becomes clear it can no longer sustain its own R&D? I don't know - I think that's a question for Intel's board to answer. What I do know is that AMD had it right in '98/'99 when they decided to help transition people to 64-bit CPUs without losing x86's incredible compatibility. The bottom line is that someone like you would have gladly gone with either Opterons or Xeons had the choice been given to you. Unfortunately for Intel's margins, you and those in your position now have that choice.

Re:xeons/opterons market share

[Loki_1929]

"People bash the x86 architecture and at the same time, bash anything that isn't x86."

Well, I think that people look at the x86 architecture, and they can see the many, many horrible hacks that have been used to sustain it. That much is pretty obvious if you spend even 10 minutes looking over things. You sit there scratching your head and going, "What the hell? Why'd they do that?", and then realize it's because something, somewhere, was broken until they did it. The reason people don't like to start looking into replacement architectures is exactly as you expressed; the must-have software. You can try running that software under emulation, but the best architecture in the world is always going to take a performance nosedive when running code under emulation. I can look at what IBM has been doing, or even at what Intel was doing with EPIC back in the day, and I can say, "wow, that's pretty cool". But what I can't do is put down the x86, toss all the old software, and hope that all the new software, written for a completely new architecture, is going to work in some sort of reliable fashion. What you really get with x86 is 20 years of experience, and thus, a measure of predictability. In essence, you're paying for predictable problems (much better than unpredictable ones) with old, poor architecture.

"The AMD solution doesn't do away with x86"

AMD64 actually does get rid of a lot of garbage in x86 that is no longer in use. Take a look at the presentation (link at Ace's) by the guy who designed AMD64. He was actually pretty thrilled (well, as thrilled as this guy gets) about being able to dump a lot of the cruft x86 has accumulated. Unfortunately, many things had to remain intact, for the obvious reason of compatibility. I have to warn you though, the guy from the AMD presentation is a real ball of fire. (Although, the ex-Intel guy from the other presenation was pretty interesting and funny)

Re:xeons/opterons market share

[Loki_1929]

If you're interested in the architectual aspects, you really need to watch the presentation linked to by Ace's. It's an hour long, but it's well worth it if you're into that sort of thing. This is the 'father' of AMD64 talking about his baby, and then taking questions from reasonably intelligent people at the end.

A point that isn't made in the artical

[Pingular]

Xeon's are almost always for servers, wheras Opeteron's can be for anything. Try running a windows xp workstation on a dual Xeon system and you'll be very disappointed.

Re:A point that isn't made in the artical

[hackstraw]

Xeon's are almost always for servers, wheras Opeteron's can be for anything. Try running a windows xp workstation on a dual Xeon system and you'll be very disappointed.

OK, lets go over this again. There is nothing really special about Xeons vs a P4 except the P4 is crippled so that it cannot do SMP, and there may be more cache options on a Xeon. Performancewise they are the same @ the same clock speed. FWIW, I've been dissapointed with XP regardless of the hardware :)

Now, back to this benchark thingy. 1st, I would appreciate in the article writeup that it said that it was only doing a simple read/write database benchmark, and that was it, but we don't come to slashdot for the stories, right? Also, in my opinion there was no significant difference between the two platforms regarding their speed on this benchmark. The difference between 1st and 2nd place, regardless of who won that test, was between 5 and 12%. I don't start to get interested until there is at least 20% difference, and even then that would only determine my choice for an initial purchase, I would never upgrade a system unless there was at least 100% speedup, preferably 200 -> 400% is worthy of doing an upgrade.

It would have been interesting to see results like this for more platforms, because I have not seen any significant numbers from the Opteron yet. For example, the memory bandwidth of the Opteron is 1/2 that of the Itanium2's.

Re:A point that isn't made in the artical

[Pingular]

I disagree. I'm running a Windows XP workstation with dual 2.4 GHz Xeons, and I'm not at all disappointed... neither are the 50 or 60 other developers surrounding me which are running on the same boxes.
What exactly would be our grounds for dissapointment?
That your company spent $3750x2x55= $412500 on processors alone (assuming you have the 1mb MP model Xeons), when you could have the same performance for a quarter of that price.

Re:A point that isn't made in the artical

[Laur]

Also, in my opinion there was no significant difference between the two platforms regarding their speed on this benchmark. The difference between 1st and 2nd place, regardless of who won that test, was between 5 and 12%. I don't start to get interested until there is at least 20% difference

How about cost? The Xeons cost twice as much as the Opterons, and the Opterons give equivalent or better performance! Although you are correct that the performance difference may not be staggering (and between top of the line chips, who would expect it to be?), the price/performance ratio certainly is.

Re:A point that isn't made in the artical

[cnkeller]

I don't start to get interested until there is at least 20% difference, and even then that would only determine my choice for an initial purchase, I would never upgrade a system unless there was at least 100% speedup, preferably 200 -> 400% is worthy of doing an upgrade.

Good post. However the one comment that I didn't agree with was the above.

My guess is that you aren't involved with any applications where compute time = money. When you are running simulations (say large CFD runs for example) that can takes days or weeks per run, a 50% improvement in speed is a major breakthrough if you get it by not touching code, ie hardware upgrades. Optimzing code is great and all, but it can introduce bugs and other expected behavior. Plus, us development people are pricey. Hardware is relatively cheap. Add in the fact that you generally get charged for CPU time on these big machines (or clusters of little ones), then *any* speed that you get is a major breakthrough, ie you can run more simulations in the same time for the same money.

In your environment, it's probably okay for you to only upgrade every three years when you get a doubling or more of performance, but there are enviroments where any speed increase is sought after highly, even if it's 20%. I suspect this is true of the special effects industry too, guys like Pixar, ILM, etc. If they can render more frames in the same time or even render the frames in the same time at a higher level of detail, that's worth paying for. Perhaps someone who knows more would care to enlighten us, I'm curious if I'm interpreting that correctly.

Re:A point that isn't made in the artical

[dave420]

Errr...

$332x2x55=$36,520

Those are 2.8ghz Xeons, btw, so more expensive. They're also the price on their own, bought singularly. $37k for 55 developers CPUs is pretty good, and could undoubtedly be bought down to nearer $20k when bought bulk.

Seriously, price arguments about Intel don't work that well any more. They used to cost shedloads, now it's only their top-of-line processors (such as the extreme edition, and new models) that carry the weight (after all, if you need the fastest processor available, you can afford to pay for it :-P).

Re:A point that isn't made in the artical

[imsabbel]

The 4MB Xeons MP are MUCH more expensive than the normal dual Xeons.
One 3Ghz XEON MP cost about 3500$

Re:A point that isn't made in the artical

[dcam]

Not only that, but when they were comparing prices, they said that the 2Mb cache Xeons were twice the price of the Opterons. Howevere in the article they tested the *4Mb cache Xeons*, which you can expect to be even more expensive.

In terms of bang for your buck Opterons rock.

Quick Link to Test Results

[hng_rval]

Test Results can be found here:
http://www.anandtech.com/IT/showdoc.html?i=1982&p= 6

summer cottage?

[SuperBanana]

for-your-summer-cottage's-data-farm

Ah, so for all our college-student friends, that would be "the parents' house"?

Cache always help

[Anonymous Coward]

I remember AMD's K6-3 would blow away the K6-2 at the same clock speed with the major difference being the cache.

I recommend Glasses

[Avrice]

Whomever is citing Anandtech as claiming the dual Xeons almost always beat the dual-Opterons needs to read the article again. Both Architectures in a dual configuration tended to perfom about the same with Opteron and Xeon each winning some of the time. The Opteron scales better above dual configurations. However the Opteron is HALF the price of a Xeon! Cost/performance (or else we would all have 12th generation DECAlphas or Power5s by now) is easily handed to Opteron. Nice spin!

Re:I recommend Glasses

[embarcadero]

In addition, Anand used sub-optimal memory in the Opteron, and non-NUMA config. Looks like he had some Intel "assistance" in designing the "benchmarks" as well... the database read/write ratio is not at all realistic, favors the Xeon.

Re:Why benchmark games?

[Lomby]

Hmmm, you should read the article before commenting.

The last two articles on Xeons used their forum database as the workload for the benchmark. In the current article he even managed to use an unnamed enterprise order management system.

Then, if you have the games and the 64 bits systems at hand, why not do a quick benchmark?

Their review of windows64 highlighted some obvious problems, probably with drivers/PCI, that may be relevant for professional use (think of CAD).

NUMA means Opteron is Better

[Anonymous Coward]

At two processors Xeon is still ok because the bandwidth of the memory coherency still isn't in serious contention. However, as the systems scale larger support for NUMA is critical to reducing memory latency because it means that memory does not have to flow in from the controllers on other processors.

That is why Opteron is required for good performance with eight to sixteen processors, and you can even see the improvement on the four way tests that Anand ran.

Re:NUMA means Opteron is Better

[Anonymous Coward]

NUMA is rarely employed in systems at the 8 to 16 processor size. Those are typically SMP.

Saying Opteron is better for 16 way means nothing as those systems do not exist.

NUMA architectures are not without issue. I emphasize the "NON UNIFORM" aspect of the acronym. Even if SGI wants to change it to "nearly uniform". Sounds like you've been reading too much of their properganda.

Re:NUMA means Opteron is Better

[flaming-opus]

You will find that most high-end Xeon systems are also NUMA systems. IBM, Unisys, HP all construct their really big xeon boxes as NUMA-clusters of 4-processor SMPs. They create a distributed memory machine at the chip-set level. This is actually what the opteron does, except that the chip-set (well, the memory controller part of it) is built into the processor.

I think the above poster had the correct idea about NUMA, but worded it in a misleading way. A NUMA design (either of opterons, or of Xeon-quads) will have to do some memory access through the memory controllers on other nodes. This increases the latency of memory access, and can clog up the inter-processor links if lots of memory loads/stores go to remote memory. Thus NUMA-aware operating systems and system libraries are necessary to maximize the amount of memory access that is local, and minimize the usage of the inter-processor links.

While the opteron design is elegant, and fast, it is not the only smart way to do things. It offers great aggregate memory bandwidth, but can slow things down in the worst case. Most large NUMA systems are created by linking 4-way SMP nodes. (Examples: Sunfire, HP alphaservers, Cray X1, NEC SX-6, Unisys 7000, IBM xseries 4xx xeon, IBM xseries 4xx itanium,...) Apart from opteron systems, the only systems I can think of that do NUMA per processor are the cray T3E, SGI origin, and intel paragon, all of which are Massively parallel supercomuters.

It is safe to say, however, that a shared bus system does not scale well beyond a few processors. This is best demonstrated by the 36 processor SGI-challengeXL, which was significantly bottle-necked at the memory bus.

food for thought.

Re:NUMA means Opteron is Better

[Fnord]

I don't think you really understand how NUMA works. The whole point of NUMA is that memory DOES have to flow from controllers on other processors. Xeons use a uniform memory architecture, meaning that they all share a memory controller. Even if that memory controller is faster than a single proc system's memory controller, they're still contending for it. However, they do all have equal access to it.

NUMA is a tradeoff. Each processor has its own memory controller and its own bank of memory. Therefore each processor has preferential access to that bank of memory. If, however, a processor attempts to access memory in another processor's bank, its slower. This cost is mitigated by intelligent VMs that attempt to put the memory for processes in the memory bank controlled by the processor running that process. If this is done efficiently enough, the benifit of having 4 memory controllers far outweighs the cost of possibly having to get memory slowly from another processor.

Re:Why benchmark games?

[Judg3]

It's probably due to the lack of knowledge/tools to benchtest anything else. I'd like to see SQL benchtests, IIS/Apache test/etc but just like a lot of other people, I don't know exactly how to do that. Though if I ran a site which made it my business to test hardware I'd definately find out and learn how to do it.

I'd like to see more "Consumer Reports" type tests to. Test hardware configuration X as a high-volume SQL server, and show me how it's held up after a month, 3 months, 6 months, and a year. Yes, maybe I'd upgrade before then, but not everyone would, and I'd like to see common failures and problems down the line - not a 1-2 day test.

Can someone please clear my ideas about this

[SlashingComments]

I saw this yeasterday on his site. Pretty good.

One thing I did not understand is how come the 3MB cache is helping with big database query ? I thought that will thrash the cache and there will be not much performance gain if you are working with bigger code/data set. Also, for the four CPU opteron, do they have hyper transport going from every cpu to every cpu ? Is it like a mesh or like a ring where every cpu has only two connections to it's next ones.

Another thing I did not get is how linux is handling ( not handling ) the local memory to the CPU. This thing looks like a mini-numa type system. Does linux actually try to keep the data in the RAM and process it with the cpu it is connected to ? how does this really work ?

May be you guys can help clear my ideas .

Re:Can someone please clear my ideas about this

[chef_raekwon]

ne thing I did not understand is how come the 3MB cache is helping with big database query

this is interesting, and i don't have an answer, except to say that SQL servers generally try to load all of the tables into available RAM. If the data is too large, then simply the indexes(??). If the server ever has to go back to the harddrive for data (which would make it bloody slow for a query) it will check recently cached stuff first - and larger caches means reduced time pulling data sets from a raid array or single harddrive.

that is atleast my take...it generally differs from server to server....MySQL does not run exactly the same way as MSSQL as Oracle. (which means I've generalized.)

Re:Can someone please clear my ideas about this

[Twillerror]

SQL servers use a page caching system generally. That is the database exists on the harddrive as a series of xK pages ( 8k pages for MS SQL server ).

As a page gets loaded from the harddisk it is loaded into the server's cache. Any read/writes are done to memory and not the disk. Background process write the pages to disk that are dirty. All transactions are written to the transaction log so if the server crashes before this happens recovery can happen when the db starts back up.

This means that a large portion of the data is already in memory. Servers usually pre-allocate gigs of memory for this purpose, the more the better and a big reason for 64 bit on large dbs.

Under x86 caching schemes, the CPU does speculative loads. It "guesses" what memory the processor is going to need and starts loading it into high speed cache. This is perfect for a db since most of the time the db pages you need are in sequential order. Especially when you are talking about pages that only include indexing data. The query usually does most of it's work using indexes, and then at the end will actually "lookup" the data.

So bigger caches mean that these big binary trees get loaded into cache and the algorythms can loop through them faster and pull off the cache.

Take this into the Itanium world and we can start to get even better performance. The thing people tend to forget about Itanium is that you can tell it to load you data into cache. So an optimized DB server can have it read this large section of code into the cache while it does calculations. Itanium allows 3 instructions to be loaded. Once hypertheading is put into Itanium you will see these DB apps really fly. Itanium is showing good promise in this arena, even at 1.5 GHZ. Clock that up to 2 to 3ghz with multiple hypertheaded cores and we are going to have one fast chip for dbs.

The big issue is the price, if you are going to spend that much money, go with the proven Sun/IBM. Itanium is set to replace the Xeon by 2007 ( I'm guessing before then because of scaling issue on the Xeon and x86 emulation software giving decent 32 bit for legacy apps ).

I really think Intel needs to push their Itanium. MS likes it, Linux likes it, a few db servers like it, and a slew of other high performance, server based things. I don't see how Intel is going to scale against the Oppie. Not unless they stick a on-die memory controller. Hypertheading and the new thread based instructions will help though. Should be an inresting battle. I'll be happy if AMD can get 10% to 20% marketshare, then we will see some true competition and innovation like we have on the desktop.

Importance of compilers

[Anonymous Coward]

Believe it or not, Intel's compiler generates very good code for the Opteron. Far better than GCC or generic IA32 compilers.

So in any evaluation, the compiler and binaries that are used is an important question.

There was no mention of this in the article.

Re:Importance of compilers

[Aardpig]

Believe it or not, Intel's compiler generates very good code for the Opteron. Far better than GCC or generic IA32 compilers.

This is the experience I've had with the Intel Fortran compiler (ifort) on an Athlon XP. Codes compiled with ifort are around twice as fast as those compiled with GNU g77 (for Fortran 77), and around 1.5 times faster than those compiled with Lahey lf95 (for Fortran 95).

OS

[millahtime]

So I see that M$ Windows was used as the OS. Unless this was a prerelease of the 64bit XP then they were running a 32bit OS on the chips. So, wouldn't that mean that this isn't a true test of the power?? Your not taking full advantage of the 64bit power.

Back to Intel Fanboy

[superpulpsicle]

Alright I have had about 3 AMD processors die on me. I have owned about 4 Intel processors all the way back from original Pentium. Not one has ever had a problem.

Now... given this kind of statistics, as sad as it may sound I'd say I am willing to pay anything for an Intel just to avoid the headaches.

Re:Back to Intel Fanboy

[tuffy]

I've owned 5 AMD processors from the K5 to an Athlon64 and all are still in perfect working order. But these sorts of anecdotes aren't very helpful in determining average chip reliability.

Re:Back to Intel Fanboy

[hng_rval]

Alright I have had about 3 AMD processors die on me. I have owned about 4 Intel processors all the way back from original Pentium. Not one has ever had a problem.
Now... given this kind of statistics, as sad as it may sound I'd say I am willing to pay anything for an Intel just to avoid the headaches.

That is an interesting use of the word statistics. In order to determine if your next processor is likely to break, you should look at thousands or hundereds of thousands of Intel procs and AMD procs. Your 7 processor study is inherently flawed.

Re:Back to Intel Fanboy

[hyperstation]

you know, you're supposed to outfit those AMD processors with fans, heatsinks, and some of that thermal paste....

Re:Back to Intel Fanboy

[John Courtland]

Wow, I have a working AMD 386/40. Yet I have a score of dead Intel 286/386/486's. I just evened out your "statistics". Not to mention the 5th gen and above x86 class processors I have.

Re:Back to Intel Fanboy

[Mr Guy]

And, as we all know, the plural of anecdote is indeed "data".

New hammers on the way.

[eddy]

Some info here. SSE3 is the big thing.

Re:Suck...

[scharkalvin]

Why can't AMD make a Dual AMD64?
They DO. It's called an Opterion!
Guess you are refering to the Athlon64 which is a one way processor (just like the Pentium 4).

BTW the Opterion is made in 3 flavors, the 100 series is a SINGLE way cpu with NO smp support. It's very nearly the same as the Athlon64-FX. The Opterion 200 series is a 2 way (2 cpus), and the Opterion 800 series supports up to 8 cpus. AMD dropped plans for a 400 series, but you can use the 800 series chips to build servers with 1-8 cpu's.

Basically... if you have more then 2 use AMD

[Fallen Kell]

The jist of the whole thing is that Intel's achitecture has a huge bottleneck in its FSB. All the processors share the same FSB and quickly max it out if there are more then 2 processors. So anyone building or buying systems with more then 2 processors will get much better performance out of an AMD opteron system then an Intel.

Price vs. Performance

[maharito]

I attend a university that is currently building a beowulf cluster, and when it came down to making a decision, the deciding factor was price/performance ratio. While it may make sense for enterprises to go with the Xeon, the Opteron is a clear winner, in my mind, when money is an object. Of course, if you have the money to burn, the Xeon may seem to be the more obvious choice.

Re:Price vs. Performance

[Pingular]

I attend a university that is currently building a beowulf cluster, and when it came down to making a decision, the deciding factor was price/performance ratio. While it may make sense for enterprises to go with the Xeon, the Opteron is a clear winner, in my mind, when money is an object. Of course, if you have the money to burn, the Xeon may seem to be the more obvious choice.
Even if someone has money to burn, wouldn't it be better to get more performance anyway?

memory controllerS?

[Bender Unit 22]

But these days days with all the virtualization getting hot(vmware etc), a server architecture with a single memory bus/controller is getting old.
I'd like to see some test on servers like the IBM x445 with NUMA.

Re:Suck...

[Fulcrum of Evil]

Why can't AMD make a Dual AMD64?

They do - it's called an Opteron 2xx.

The Usual Problem

[Sloppy]

We've seen this same type of benchmark over and over. It wasn't interesting then, and it's not interesting now.

The tests in this article, involved running the same exact binaries (out-of-the-box Microsoft 386 stuff) on both types of CPUs, rather than the code being compiled to run natively. The Opterons were fighting with one hand tied behind their backs.

In other words, this benchmark is mainly only of interest to Microsofties. If that's what you run, then fine, the article may be useful to you and you may get something out of reading it.

If you are trying to maximize speed, though, then the software contraints that this test took place under, are totally contrary to what you'd actually be doing (running code that is appropriate for the hardware).

BTW, another weird thing I noticed about this article: these guys use flash for static images of bar graphs. WTF? Anandtech, your w3b d3$1gn3rz R S0 31337!!!1

Article on one page

[mulle]

Full text

Re:Suck...

[Hektor_Troy]

It's called an Opterion!

Well, you can get dual Opterions, that is correct, but they seem to be contact lenses. Not sure you're like to plug that in to a motherboard ... at least not while wearing them.

Hmm

[Trailer Trash]

...4-way Opteron systems seemed to fair the best...

Did they fare well, also?

-5, Clueless

[Gothmolly]

Firstly, Anandtech uses flash for its images so that people w/o the plugin can't see the data. This forces you to install it, so that you can see their OTHER Flash pieces... ads.
Secondly, you are not going to get MS to recompile an MS-SQL for Opteron. You're not going to get IBM to support a Linux installation, after you've rolled your own ueber-NUMA-patch-level-42 kernel.
The test was clear - out of the box, plug in servers, load OS, load app, run benchmark.
And the outcome was clear, the Opteron architecture is vastly superior, both performance and price-wise.
The MHz myth is over, at least in Slashdot and Anandtech circles.

Conclusion...

[ERJ]

Anand seems to conclude something a bit different then the submitter:

The comparison we've made here is a very important one; it identifies Intel's strengths and their weaknesses with Xeon, and it crowns Opteron a clear multiprocessor winner. An area that we didn't touch on is cost, which is where AMD truly shines. The Opteron 848 processors we tested are around 1/2 the price of Intel's 2MB L3 Xeon MPs and we have not seen retail data on how expensive the 4MB parts will be.

In a 4-way configuration AMD's Opteron cannot be beat, and thus it is our choice for the basis for our new Forums database server.

Apples, Oranges, and Efficiency

[Phaid]

It's interesting to notice that in these tests, the Opterons were clocked quite a bit slower and had a lot less cache than the Intel CPUs, yet performed comparably in 2-way and better in 4-way than the Intel chips.

The Opteron clocked at 2.2ghz with 1MB of cache was very close in 2-way performance with the Xeon 3.0 and 3.2 ghz each with 4 and 2 mb of cache respectively. The 1.8ghz Xeon compared well with the Xeon 2.8ghz with 2MB of cache. The Opterons were typically within 3% or so of their Intel counterparts in 2-way benchmarks and closer to 10% ahead in 4-way.

If nothing else, this says a lot about the efficiency of the Opteron's design. Less silicon, and more importantly for AMD, less expensive silicon, manages to achieve very close results.

Anandtech isn't biased.

[brucmack]

The purpose of the test is not to test the memory, but to test the processors. Thus, they used the same memory in testing each processor configuration.

One of the purposes of the test was to show how the memory bandwidth bottleneck of the Xeons limits their effectiveness in 4-way configurations, which the Opterons do not have that problem. Doing this comparison with different memories would make things more complicated.

Additionally, you'll notice that Anand's final words recommend the Opteron for being at least equivalent and much cheaper than Xeon. This was also the selection process for their new forum servers, so you can bet that they aren't getting any kickback from Intel, or those would be Xeons.

If you still have doubts about the validity of Anandtech's testing, check out the benchmarks from their AMD vs. Intel web server test in December: http://www.anandtech.com/IT/showdoc.html?i=1935&p= 9. All on dual processor configurations. There is definitely no Intel bias in that test.

Really, I think some people ought to think before they flame like this. The benchmarks are showing the Opterons to be equivalent or faster in 2-way configurations and definitely faster in 4-way configurations, so what is there to complain about? The fact that Anandtech has consistently recommended AMD's processors just makes it doubly silly.

Re:Anandtech isn't biased.

[hackstraw]

The purpose of the test is not to test the memory, but to test the processors. Thus, they used the same memory in testing each processor configuration.

Then they should not have done an memory intensive and disk intensive benchmark like a database, now should they?

Comparing Prices

[gbulmash]

4 AMD Opteron 248's at Newegg: $5876 ($1469 ea)
4 Xeons (@Intel's announced pricing): $14768 ($3692 ea)

Did the quad Xeon system outperform the quad Opteron by a factor of 2.5:1? No. In fact, in some cases, the quad Opteron outperformed the quad Xeon. The Xeon had advantages of hyperthreading, 4x as much cache, and a clock speed 800mhz higher than the Opteron, ans still got beat.

Clock speed may sell in the consumer market ("Me want bigger!"), but in the server market, Opterons getting better performance for half the price are going to win more and more converts.

- Greg

Re:Why benchmark games?

[Zeriel]

*raises hand* I'm a corporate IT type, and I read his benchmarks. Along with about three others on a regular basis. Because sometimes, "real work" tends to scale pretty similarly to game performance--especially when that real work is a lot of 3D graphic operations.

Story submitter -5 Ray Charles

[Loki_1929]

"although dual Xeon configurations almost always beat dual Opterons."

Perhaps the submitter's screen reader doesn't work well with flash, but in the 2-way benchmarks, Opteron was on top twice, and Xeon was on top 3 times. All the 2-way benchmarks were fairly close (within 5%), and the Xeons never beat the Opterons by a margin greater than 1.7%. I don't quite know where 40% wins translate into "almost always" loses. In other words, the story submitter is a moron, or simply didn't look at the article.

"Results were a little varied as 4-way Opteron systems seemed to fare the best,"

Seemed? Let's see, out of five 4-way benchmarks, Opteron won... all of them - performing about 10% better than Xeons each time.

Since when did we start letting Tom Pabst submit articles to /. ?

Note to editors: When the submission is non-sequitur, either reject it or edit it.

Dual Xeon's beat Dual Opteron's? I think not.

[prisoner-of-enigma]

Opteron systems seemed to fare the best, although dual Xeon configurations almost always beat dual Opterons.

Perhaps the benchmarks show the 2P Xeon's doing OK against 2P Opteron's, but for the price of two Xeon MP chips you can buy five Opteron 848's. Rounding that down, I wonder how well the 2P Xeon does against the 4P Opteron? Oops, Anand already though of that. He says "it would not be pretty." Indeed.

Re:Dual Xeon's beat Dual Opteron's? I think not.

[NerveGas]

Yes, the tests weren't exactly apples-to-apples - the outcomes are actually much better for AMD than the graphs would initially appear.

The graphs mean that Opterons with a "measly" 1 meg of cache are beating out Xeons that have (a) four times the cache, (b) 50% higher clock speed, and (c) a price tag that's three times higher.

Hats off to AMD. In times past (K2/K3), price was the only thing they had better than Intel. Now they've got both price and performance.

steve

Re:Why are there so many Opteron/Athlon64 sockets?

[Hoser McMoose]

They WILL standardize on a socket, it's just that the socket will be Socket 939 and not the current one.

It's pretty much the same story with SlotA/SocketA. They had an initial design that was quickly replaced. The second socket then stuck it out for the duration.

Intel did pretty much the same thing with their P4, initially releasing it on socket 423 and then quickly moving to socket 478 which has lasted for several years now (though it too will soon be replaced).

Markets change, technology changes, and sometimes sockets need to change with them. Remeber that the specification for Socket 754 and Socket 940 for current Athlon64 chips was set in stone about 3 years ago (before the first beta chips tapped out), and a lot has changed since then. AMD has gone to great lengths to minimize socket changes, but there's only so much that they can do.

Re:Pffft. These Intel vs. AMD flamewars are pointl

[Shadow99_1]

"Currently Intel's latest 3.0+ GHz offerings are spanking Athlon 64s in benchmarks with 32 bit applications."

What a bunch of crap! That's almost as big a lie as Intel makes of AMD cpu's. I didn't even bother reading the rest when you are obviously delusional.

BTW A64 chips can be had for the same prices as their A32 counterparts in the same speed rating, Motherbaords are almost equally expensive whether A32 or A64, & outperform them by up to 30%. ...

Ok well now I have read the rest of your comments & I have to reply to those as well:

"they're going to go to Intel because it has more upgrade possibilities"

What possibilities? They force upgrades way more often than AMD, & are known for being the best money sink for performance users.

"is cheaper than the Athlon 64 for the same level of computing power"

Uh not really, A64 costs the same or less than Intel for comparable performance as long as you don't follow the rule of 'Mhz/Ghz equals performance'. Take a look at pricewatch or Newegg and see for yourself...

"currently performs better"

Hogwash.

"So this is more of a plea for AMD to extend the Athlon "32" line a bit further. Please AMD, don't prematurely kill off 32-bit Athlon chip development!"

Uh they are building them at least through the end of this year, & probably next to some degree. The thing is their is no real future for A32, performance has been decreasing performance-wise in comparison & wasn't keeping up. AMD realized their best bet was to focus on A64 with it's integrated memory controller & higher IPC than A32 has. A64 is a real contender where as A32 wasn't keeping up & they knew it.

Re:Pffft. These Intel vs. AMD flamewars are pointl

[Ian Wolf]

I think time will show (barring any major gaffes) that AMD made the right move. First and foremost, the Athlon XP appeared to be reaching the end of its run. Cranking up the speed of the processor didn't really seem to yield comparable performance gains. In the early days the performance ratings on the XP line were a little iffy, but they were close enough that most people didn't really care. With the XP 3000, and 3200 though those ratings were dubious at best. The speed ratings ratings for the Athlon 64, however, are pretty accurate, even understated in some areas.

I recently upgraded my principle system and at the time, I was determined that the P4 2.8HT CPU was going to be the chip the machine was built around. It clearly trounced the Athlon XP 2800 in all tests for about $100 more. I was about to order when the AMD Atlhon 64 3000+ was released. It outperformed the Intel chip in most areas, was 64 bit, backwards compatible, and only $20 more. In my opinion, and Anandtech and Tom's Hardware agree, the AMD Athlon 64 3000+ is the best bang for the buck CPU out there.

Pricewatch's Lowest Prices are...

AMD Athlon 64 3000+ - $205
AMD Athlon 64 3200+ - $251
AMD Athlon 64 3400+ - $401

Intel Pentium 4 3.0 (800) - $209
Intel Pentium 4 3.2 (800) - $273
Intel Pentium 4 3.4 (800) - $420

AMD Athlon XP 3000+ - $158
AMD Athlon XP 3200+ - $194

Looking at these benchmarks here and on the following page here. You can see, with the exception of pure media encoding, the Athlon 64's perform better. The margin is slim in some areas, and quite large in others. All this and the chips are a little cheaper.

In my opinion, the XP line was dead. It had gone as far as it was going to go. I think AMD knew that the 3000 and 3200 were more like the 2850 and 2900 and they weren't going to get any more mileage out of the design. I definitely think AMD made the right call putting all their eggs in the Opteron/Athlon 64 basket.

Re:Question For Geeks Intel Hyperthreading

[Hoser McMoose]

Definitely not BS, though whether or not it's useful depends heavily on your application.

The idea behind hyperthreading is that the P4's long pipeline will often stall with only a single thread going through. With hyperthreading you run two threads at once, so when one thread stalls you just start up the other thread and go with that one for a while. In a way it's almost like a poor-mans dual-processor system, giving you two logical processors on a single chip.

Now, obviously there are a few things to consider here. First off, if ALL of your processing is being done in a single thread then you aren't going to see any benefit to hyperthreading, and in fact the extra overhead might even make things a bit slower (usually only 1-2% slower).

Games almost always do all their major processing in a single thread. Even if they have extra threads hanging around, you almost always spend 99%+ of your time in a single thread. For this reason, games see virtually no benefit to hyperthreading (they don't see much/any benefit from dual-processor setups either).

On the other end of the spectrum, some applications see up to a 25% performance boost when hyperthreading is enabled. The tests I've seen show the biggest improvement have been things like Photoshop and rendering applications. Some server applications should benefit as well.

The other boost that hyperthreading gives you, like with a real dual-processor setup, is that it makes multitasking a bit "snappier". This is by no means a night-and-day difference here, but it is there.