Intel Dual Core Xeon Benchmarked 335
An anonymous reader writes "A few weeks back, Intel launched a new dual core chip with little applause. It appears we know now why, as the chip has been benchmarked by the chaps at GamePC. In tests against the dual core AMD Opteron processor, Intel's new chip gets thoroughly thrashed, losing out in terms of raw performance while eating a lot more power. "
great (Score:2, Funny)
Re:great (Score:4, Funny)
I'm kinda shocked... (Score:2)
I don't know what's going on behind the doors of Intel, but have people in business department been cutting back on the R&D again?
Re:I'm kinda shocked... (Score:2)
Re:I'm kinda shocked... (Score:3, Insightful)
Re:I'm kinda shocked... (Score:2)
Re:I'm kinda shocked... (Score:2)
(Insert inane Seinfeld reference here.)
Re:I'm kinda shocked... (Score:2)
Intel somehow just can't achieve former glory. And it won't. Intel was always just boosting and never stand behind the words. Anyone remembering 64-bit RISC based Merced. Well, Merced was out (with
Re:I'm kinda shocked... (Score:3, Insightful)
Intel is trying to save their exclusive customers, like Dell. Dell and the others needs something to compete with AMD or else they are going to have to start using AMD. Intel does not want that. They don't want to lose their exclusive deals, so they give them just enough to please them.
They don't have to win the speed race. They don't have to make it better than AMD in any way. They just need something
Re:I'm kinda shocked... (Score:3, Interesting)
But the PHBs don't have to work with the shit like their techies do. I work in in an all Dell shop and it's staggering how the quality of their desktops and more recently their servers has declined lately. And Intel has to partly shoulder the blame because these machines run hot. So hot that our air-con in the server rooom can't cope with the flames our new racks throw out.
But it would be a brave techie to stand u
AMD's dual cores are great (Score:5, Informative)
I had been considering an Intel dual core but it sounds like I need to aim for an AMD instead.
Re:AMD's dual cores are great (Score:4, Funny)
I just bought my wife a dual core
Lucky you...she asked me to buy her a diamond core...
Re:AMD's dual cores are great (Score:2)
Re:AMD's dual cores are great (Score:3, Insightful)
Re:AMD's dual cores are great (Score:5, Informative)
No, they are honest-to-goodness real dual cores. Two fully functional cpus in a single socket.
The problem is that the socket only has enough memory bandwidth for one cpu's worth of work. So, even if you double the number of cpus, you still can't shovel the data in and out fast enough to keep up with the work being done. Thus one of the two cores is almost always stalled out waiting on memory.
The AMD chips have got more memory bandwidth, so they can keep both cpus fed with data reasonably well.
Re:AMD's dual cores are great (Score:5, Insightful)
Not just that. The AMD dualcore chips have an on-chip connection between the cores: both cores share a crossbar fronting the memory controllers and have the on-chip equivalent of a coherent HyperTransport connection. So, you see, the AMD design is in fact a real dual-core design. The current Intel dual-cores, on the other hand, share nothing on-chip.
Re:AMD's dual cores are great (Score:4, Insightful)
This is exactly right. It is really surprising that Intel has focussed so completely, almost obessively, and for so long, on the problem of supplying the maximum number of work-cycles per unit of time (GHZ, Pipelining, Itanium's EPIC design) while seemingly paying so little attention to supply-of-work-to-do (FSB speed and architecture)
AMD has paid quite a bit of attention to the work-supply and has a much more efficiently balanced work-cycle-supply/ data-for-work design. http://www.hypertransport.org/ [hypertransport.org] gives AMD a big leg-up over Intel.
If Intel fails to do something spectacular to FSB speeds, AMD is sure to continue to pull away from Intel. The more cores and threads per CPU, the greater AMD's lead over Intel will become (at least from a performance point of view), until Intel addresses this problem.
Re:AMD's dual cores are great (Score:5, Funny)
Just specced out an AMD system for MHD modeling (Score:5, Informative)
So, er, Xeon is teh 5uk and Opteron Pwns.
Stupid pre-retail release (Score:5, Interesting)
This release seems dumb for Intel. No optimized motherboards, outrageous power requirements and a really inefficient core? It isn't even alpha-release worthy. Why would Intel release a product that is just waiting for a poor review? Is the high end market that hungry?
The article didn't need 15 pages to explain Intel's mistakes. Intel will lose more customers to AMD than if they had waited until they had a viable and competitive product.
400W while idling? For sub-standard performance? Yay.
Re:Stupid pre-retail release (Score:5, Interesting)
No, the high-end market is waiting for something that has "Intel" and "Dual Core" written all over it. Everything else is irrelevant.
Dude, you're getting whatever we sell you! (Score:5, Insightful)
Re:Dude, you're getting whatever we sell you! (Score:5, Insightful)
If I could upgrade my existing 2P dell servers to even inefficient dual cores that run too hot, I'd do it. But I doubt my existing servers would be able to cool them, so it's probably not going to happen anywyas. If we could get 2x dual-Opteron servers, we'd jump on it for all our ESX servers - especially with ESX3 and native x64 memory support. SWEET! But no, we'll be stuck with Xeon "EMT64" bastardized x64 CPU's because we're locked into Dell.
Re:Dude, you're getting whatever we sell you! (Score:2)
The least they could do is supply some of their customers instead of none at all. They could also price the systems higher to keep demand lower until supply increased...
On the other hand, the fact that dell claims AMD couldn`t meet supply suggests that dell knows the AMD systems would sell like hotcakes.
As for being locked in to dell, how come? Hardware isn`t such a lockin scheme as software is, you can easily drop in a sun or hp serve
Re:Dude, you're getting whatever we sell you! (Score:3, Insightful)
He probably works for a big company with a list of approved vendors.
His CIO probably plays golf with the Dell rep.
Re:Dude, you're getting whatever we sell you! (Score:3, Informative)
So, which current AMD vendor(s) would you like to sacrifice to all-mighty Dell, praytell?
Re:Dude, you're getting whatever we sell you! (Score:2)
If you need a big name company, then HP and SUN would be good alternatives, both offer Opteron-based servers and workstations.
Wow (Score:3, Interesting)
we were curious if having eight processors (four physical cores + four virtual processors) would cause operating system-related licensing issues. After all, even multi-threaded operating systems like Windows XP Professional are sold with a "2 Processor" limitation. While technically the system still only has two physical processors, dual-core and Hyper-Threading technologies are certainly pushing this limitation further than Microsoft originally intended.
I find it interesting how, in a world of IP, somebody out there ( Intel ) can still 'cheat' the system by creating dual core CPU's which still count as a single processor, thus allowing for a system like this.
Re:Wow (Score:2)
This isn't cheating. Microsoft & others must update their licensing to accomodate. And its not as clear as the Hyperthreading issue that they will. On the bright side, you can usually turn off Hyperthreading in the short term, to get it down to a "managable" 4 CPU's
Microsoft licensing (Score:2, Informative)
Re:Wow (Score:2)
Time changes: One upon a time multi-CPU was high-end and expensive. But now you'll find them on consumer PC very soon (in the form of dual core CPU), and Microsoft along with others will steadily relax the CPU count requirements. Of course, Intel is not "cheating" the system: they just make CPUs...
Counter-Wow (Score:2)
And I can find it interesting how one can give a meaningful and valid explanation of why the hell should an OS have different license prices based on number of physical processors ? (Specialy when taking in account that the different versions (1/2/4/8/... CPUs) are basically all the same technology onl
Re:Wow (Score:2, Informative)
Extra set of registers, yes, but no context switching. CPUs have a few different operational units, one or two dedicated to integer math, a seperate one for floats, one for memory I\O and mabey a unit for vector operations (SSE). A proccess isn't going to be using every resource at once. The whole thing can sit idle if it has to wait on something to get pulled from memory. Hyperthreading takes advantage of this by using a fancy scheduler that can juggle the needs of two proccesses at once. Only needs b
Power Consumption (Score:5, Funny)
Re:Power Consumption (Score:3, Funny)
Re:Power Consumption (Score:2)
Now I just need to hope that no one lets loose one of those extremophiles...
Re:Power Consumption (Score:3, Insightful)
Re:Power Consumption (Score:2)
Re:Ecology (Score:3, Funny)
Next point, instead of no one being able to use electricity why don't we tell a few hippies to shut up and build a nuke or build a hydroelectric dam.
Everyone switching to a Pentium M won't do shit to oil consumption. The solution is to tell the hippies to shut up and start building some nukes.
We don't need to find alternative energy sources, we just need to get rid of the red tape and let th
Bah (Score:5, Insightful)
First concern is that though the chip has been released, motherboards configured for it aren't close to release yet. I'd rather see it benchmarked as distributed, since that's what really matters to the end user.
Second concern is power usage and heat production. If you can't make a chip as powerful as your competitors, you better make sure it is not as expensive to operate. Really, why would someone choose to use a chip that is less powerful, intrinsically costs more to operate, and costs more to cool? Chips are cheap enough that the operating costs are often now more expensive than initial cost.
Re:Bah (Score:3, Informative)
Regrettably, because it has the Intel logo on it. I'm lucky working in a company where if I say I want AMD, I get AMD. I'm sure there's plenty of hardware geeks on
FWIW, AMD recently launched the new single-core Opteron 254 [techreport.com] and it u
Re:Bah (Score:3, Insightful)
Although, I do think AMD could do a better job of advertising to the masses... which would definitely help with mindshare.
Re:Bah (Score:3, Insightful)
Don't worry (Score:4, Insightful)
A good example of marketing management (Score:2)
Intel can release an underpreforming platform in the server area because "it's validated for a server environent." Otherwise, people can purchase a P4 based server from IBM or some such. By not making noise that the unit has been released, people will assume that it has been on the market for a while - and that's why it is slightly less preforming. It's a
Re:A good example of marketing management (Score:2)
Well, I RTFM and it seems the difference is definetely more than 10%. There are some benchmarks like, MPEG to WMV encode where the fasters Opteron is 100% faster than the fastest Xeon. In MP3 encode, Opteron is 50% faster.
Re:A good example of marketing management (Score:2)
mmmmmm, fungus - ahhhhhh
Re:A good example of marketing management (Score:2, Insightful)
Actually, you are wrong and you would not even have to read the article to check that. Both the dual-core Intel Xeon and the dual-core AMD Opteron are designed to work in a server environment. These are the chips that you find in the latest blade systems from several vendors (IBM, HP, Sun, Dell, etc.) and they are targetting big businesses, not the average consumer as you imply.
And the results are actually not good at all for Intel. "trashed" is not about 10% faster, but about a significant gap: 2 or 3
Is GamePC really Intel's target here? (Score:5, Insightful)
Who would be suprised? (Score:4, Interesting)
The big question will be who is the leader next year! As far as i'm concerned the opteron/amd64 has already proven intself against p4/xeon arch and it's up to the next gen chips to see who will stomp on who.
Will AMD pull some new tech? Will Intel be able to deliver or will sun come around and smack everyone with the new Niagra chips?
Coral cache link (Score:5, Informative)
Seems it's slashdotted already after 8 posts. Finally when will all slashdot-links be coralized automatically?
Re:Coral cache link (Score:2)
Stock market (Score:5, Funny)
strange. (Score:4, Insightful)
Its really surprising to think AMD blind-sided intel this badly (multi-core/x64), but I guess they really did. Good for them, and great for us. Once again supply and demand in the free market prevails.
Nice, but.... (Score:3, Insightful)
Re: (Score:2, Offtopic)
Intel is all about the Mhz (Score:5, Interesting)
It seems to me that Intel procs these days are more of the same but overclocked; while AMD has been making their procs more efficient, by running cooler and streamlining the instructions.
Faster isn't better these days and Intel needs to realize this before it's too late.
I just picked up a +3200 AMD Sempron which is clocked at 1.8Ghz and compre that to the AthlonXP +1600 at 1.4Ghz I had before, it has well over double the perfomance in almost every application. From doubling the fps in Doom3 to cutting compile times down by half. For a 400Mhz difference there is a lot more going on then just 'speed'
Re:Intel is all about the Mhz (Score:2)
I have a +3100 AMD Sempron not a +3200 AMD Sempron
Re:Intel is all about the Mhz (Score:5, Interesting)
Since you brought up IA64...
While I'd be one of the last to argue against the ugliness of the x86 instruction set, that does not mean that IA64 is necessarily better. From an instruction architecture point of view, IMHO IA64 looks like an academic exercise got sold to the executives well before it was really ready for prime time. Look at the sheer amount of money Intel and HP have dumped into IA64, Sure, they can get some impressive results, but I suspect that given THAT amount of cash, time, and engineering, x86, Alpha, Power, etc all could have reached at least the same performance level.
It's necessary to realize that the number 1 problem it was designed for had nothing whatsoever to do with performance. IMHO, the prime purpose of IA64 was to prevent cloning. Neither Intel nor HP hold any of the IP on IA64 - it's all held by a third company, and Intel and HP are the licensees. That's because both Intel and HP are extensively cross-licensed with others in the business, including AMD. Had Intel and HP owned the IP for IA64, it would have come in under those cross-licensing agreements. By setting up the third company, there is no cross-licensing involved, and ONLY Intel and HP can product IA64.
So IA64 is a product of "corporate myopia," of Intel being more concerned about it's internal problem of cloning than customers' external problems of power and performance, and I once heard it was another attempt by Carly Fiorina to "reset the clock" on her tenure by announcing a grand new strategy that needed her at the helm. Both are driven by internal politics, not the marketplace. It's a classic problem of big companies
Why always gaming? (Score:4, Insightful)
Check this out image [libtomcrypt.org] where "nocona" is a Pentium 820D [dual-core 64-bit P4].
Those are cycle counts for RSA-x private key operations [with padding] on various processors.
TFM == tomsfastmath
LTM == libtommath
DC == dual-core [two threaded] tomsfastmath
Tom
Re:Why always gaming? (Score:2, Informative)
ops per second [libtomcrypt.org].
FWIW, the AMD64 is at 2.2Ghz, AMD32 [Athlon-XP-M] @1.8Ghz, P4 @3.2Ghz, Nocona @2.8Ghz.
So yes, a 3.2Ghz P4 Prescott gets roughly the same number of RSA/sec as a 1.8Ghz Athlon-XP
Tom
Re:Why always gaming? (Score:2)
Re:Why always gaming? (Score:2)
As for where it falls? VIA processors are *less* efficient than a P4. Sure they take no power to run but they also take many times the cycles to do anything.
Tom
Re:Why always gaming? (Score:2)
Re:Why always gaming? (Score:3, Interesting)
Go to the store, buy two boxes, one an Intel Pentium 620, another an AMD Athlon64 3200+ or so [roughly price compariable I think].
Grab two blank hard disks, two gentoo cds and one local distfile mirror. Start from stage1 and build a good 700 or so packages. Tell me how many ***hours*** of work you can complete on the AMD box before the Intel box is even finished.
Not fair enough? Ok, try measuring the latency of ECC P-256 and RSA-2048 operations with the fastest co
Re:Why always gaming? (Score:2)
Generally the P4 is crap compared to the AMD64. In crypto [ciphers and hashes] it always takes more cycles to complete the same work and even with the clock advantage it rarely beats the AMD64 in walltime. Basically to reliably beat an AMD64 in cipher operations [w.r.t. walltime] you'd need to pit a 3.6Ghz or 3.8Ghz P4 against a 2.2Ghz AMD64. Below tha
Re:Why always gaming? (Score:2)
If I'm reading it right, the graph is measuring the number of cycles it takes to perform the encryption operation. The Intel P4 takes an insane number of cycles, and the new Nocona processors are substantially better. But then the AMD64 blows them all away.
--
Unrelated to the above posts, I've been impressed with my new AMD64 Cool and Quiet technology. In Linux (I'm not sure if Windows does this, I hope it does) it scales the processor's frequency based on it's load.
Whe
Re:Why always gaming? (Score:2)
TFM, LTM and LTC are freely accessible public domain libraries.
And besides that, custom hardware [re: MUCH SMALLER] can do it with less latency.
Tom
HORUS (Score:5, Interesting)
AMD looks like it's going to continue to be the winner on performance for the foreseeable future, especially with it's totally awesome HORUS chipset on the horizon which might just hail the beginning of commodity super computing.
For anyone wondering what HORUS is, it's an SMP system that can link 4 Opteron's together over HTT. The real killer is that it can it's self be linked to 4 other HORUS chips over InfiniBand. A HORUS SMP system appears as another Opteron chip to the other HORUS groups. AMDs current plans are for HORUS to scale to 32 CPUs in a hot swappable configuration. It's going to be great.
Re:HORUS (Score:2)
BTW, Horus doesn't use Infiniband. Maybe it uses IB cables.
Intel Dual Core: Worse Perfomance, Better Pricing (Score:3, Informative)
Intel knows AMD Opteron Dual Cores are faster. That's why this generation dual cores (at least P4D's) from Intel are so cheap aside from the ridiculous "Extreme Editions".
I recently bought a Dell computer. I had a choice of getting a dual core for $50 more. Now I can rip a CD to MP3's using EAC/LAME in about 3 minutes when it used to take 15 on my old computer. I'm happy with my $50 doubling my performance for MP3's and xVID (DivX) creation.
I really wanted a higher-performance dual core AMD computer but when I was pricing those out, the price of the upgrade to a dual core AMD *ALONE* was around the price of my entire Dell computer.
Re:Intel Dual Core: Worse Perfomance, Better Prici (Score:2)
RIAA lists Dell and Intel as major contributors to Internet piracy -- subpoenas to follow...
I only wish.
Re:Intel Dual Core: Worse Perfomance, Better Prici (Score:3, Informative)
AMD have a faster memory interface to begin with, and in a multiprocessor system each processor has it`s own connection to memory...
Although the 2 cores on a single AMD processor share their connection to memory, they dont share with other chips in the same machine and their connection to memory is still faster than intel`s. Also AMD have an internal co
Re:Intel Dual Core: Worse Perfomance, Better Prici (Score:2)
As an AMD enthusiast... (Score:4, Funny)
(points at intel)
MWA HA HA! HA HA!
MWA HA HA! HA HA!
Ah... felt so good. Thanks
signote (Score:2)
--
Submitters: Use Coral Cache!
Before: website.com/path
After: website.com.nyud.net:8090/path
just a note on your sig,
as you can see the following link
http://www.gamepc.com.nyud.net:8090/labs/view_cont ent.asp?id=paxville&page=1 [nyud.net]
is also slashdotted. why do people think that mirrors can handle the load when the main site cant? you do realize if everyone started linking ALL their stories to coral cache, coral cache would have to bare the load of every slashdot story right? how long do you think they would foo
xeon has no chance vs opteron.. (Score:3, Interesting)
P/W (Score:2)
AMD should be touting its own Performance per Watt figures right now, rather than waiting for Intel to eventually catch up.
Re:P/W (Score:2)
AMD knows better. They don't brag where they can't.
Re:P/W (Score:2)
AMD should be touting its own Performance per Watt figures right now, rather than waiting for Intel to eventually catch up.
Maybe, though I wonder if the Pentium M (AKA Pentium 3 but they can't call it that anymore) still holds the title for P/W. The mobile stuff seems to be Intels last technological lead over AMD.
Intel's problem is that the Pentium 4 architecture isn't very good, they had a really great chip design in the Pentium Pro, then when downhill with the Pentium II, when the Pentium 3 came out
Intel - Itanium and r&d resources vs. x86 (Score:4, Interesting)
The next generation of chips may be different. Competetion is good.
I'm pretty chip agnostic, although a while back I had an cyrix 486 chip in a notebook and didn't even know it wasn't an intel.
Redheaded stepchild? (Score:3, Interesting)
Re:Redheaded stepchild? (Score:2)
The glowing cherry red on top of the chip packaging stepchild.
Re:Nothing to see, move along. (Score:3, Insightful)
I'm seeing Intel dual-core processors appearing in devastates AMD, as somehow their dual-cores are far less expensive.
I've yet to see a mainstream PC with a dual-core AMD on the other hand.
Re:Nothing to see, move along. (Score:2)
Intel used to own the X86 server market now you are seeing AMD making big strides in the servers. This l
Re: $700 - correction (Score:2)
The electricity costs , (Can't see how much more hungry it is ) but the Summary says a lot more so i can only assume a difference of 50W which over the course of a year can really add up if it's a server and/or always on.
how valuable is your processing time
All of these things can really add up over a servers life spa
Re: $700 - correction (Score:5, Interesting)
You're talking about Pentium-D of course, not Xeon...
At any rate, that is actually bad for Intel. AMD brought out enterprise-class dual core CPUs that have obvious applications on workstations/servers, which run lots of tasks and threads, and can always use more horsepower for higher throughput. Intel brought out, at about the same time, the Pentium-D for consumers. Not only is it clocked at about 1 GHz. slower than the fastest single-core Pentium, but desktop PCs don't typically run large thread and process workloads like servers. In fact, the Pentium D runs games substantially slower than cheaper, single-core Pentia. So, I expect a lot of consumers are out there scratching there heads over whether or not to buy Pentium-D.
AMD's dual core chips, on the other hand, only run 200 MHz. slower than the corresponding single core chip. Game performance suffers hardly at all. AMD will ramp up production of dual-core consumer chips once it feels it has a firm hold on the workstation/server side. Then we'll see the prices drop, and dual core will become mainstream. Maybe game developers will even start programming multithreaded games. ;-)
In summary, AMD is laughing all the way to the bank, while Intel has to content itself with low consumer product profit margins. It seems this new Xeon won't change that dynamic much.
Re: $700 - correction (Score:3, Informative)
Re:Nothing to see, move along. (Score:2)
Hyper Threading (Score:4, Informative)
- HyperThreading is Intel's name for Simultaneous Multithreading [wikipedia.org].
Basically, a CPU isn't always using 100% of all its function.
The CPU may be waiting for something in the cache.
Or the application is maybe using only a small portion of the CPU.
In other words, the CPU waste its time sitting and doing nothing.
If you manage to use those unused ressource, you can squeeze more performance out of your CPU.
Before Simultaneous Multithreading, the only way to do so is "Out-of-Order" execution.
- In plain english : maybe some of the next steps of the programm don't need to wait the curent stuff to finish, and we may already fill unused parts of the CPU with these instruction.
With Simultaneous Multithreading, this time, you're trying to find something for your CPU to do from *another program*. This program must wait for something from the cache ? Let's run another in the meantime.
----
Alternate explanation :
Multi tasking/ Multi Multithreading is when several program share the same CPU by quickly alternating between them.
Simultaneous Multithreading is when 2 program run at the same time so less parts of the CPU are just sitting unused.
Re:Dual Core Apples (Score:3, Funny)
Re:Dual Core Apples (Score:2)
Re:Yet strangly... (Score:5, Informative)
Did you miss the part where they said this chip consumes more power and runs hotter than Opterons?
Re:Yet strangly... (Score:3, Insightful)
WTF??? We're talking about servers, not laptops.
Re:Yet strangly... (Score:3)
I know this is
Re:Yet strangly... (Score:5, Insightful)
Intel's sales will again beat AMD's by several fold.
Perhaps, although AMD has made impressive inroads into the server/enterprise marketplace and there's no sign of it slowing down.
The reason seems to be that most PC and server purchases are not intended for games, beyond Solitare of course,
Non sequitur, Opterons smoke Xeons at enterprise tasks like web serving, database hosting and so on, in almost every benchmark. Especially in the more enterprise-relevant 2-way and 4-way (4 or 8 core) configurations.
and people prefer the reliability, power savings and lower temperatures of the Intel chips.
RTFA. For several YEARS AMD's chips have been lower power and cooler than Intel's - a combination of doing more work at lower clock frequencies, and SOI. You're recalling something from the K6 days that is totally backwards today.
AMD should be happy they ran Cyrix out of the business but, they should have realized by now that they will not impact Intel sales no matter how vocal their fanboys might be.
AMD has already impacted Intel's sales in a big way. Did you hear about Intel's disappointing earnings today? Even worse for Intel, AMD has *creamed* the Itanium. Now 90% of what were potential Itanium customers (big bucks for Intel) are now going to do AMD64 instead...even if it happens to run on Intel silicon. Itanium is a financial and technical disaster for Intel.
Remember the days when AMD cloned Intel's instruction sets, not vice versa?
BTW, could I borrow your Opteron, I need to fry an egg for breakfast.
Wow, how...witty. At any rate, looks like Xeons are the hot ticket there... ;-)
Re:Yet strangly... (Score:2)
Re:Yet strangly... (Score:3, Funny)
The 90's called. They need their processor bigotry back.
Re:AMD and motheboard issues (Score:2)
In response to the GP, I've been experiencing quality problems with my MSI board as well, so I switched to a Biostar. I have similar problems with that as well. It could just be the drivers though.
Re:Xeon, Opteron, Chipsets and the Busses (Score:3)