Intel Dual Core Xeon Benchmarked
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. "
yeah, but can it run Duke Nukem Forever?
Intel knew what they were up against and somehow didn't cut it? Intel has been the masters of their domain for a long time and I'm rather astounded that they couldn't come up with something to 1-up the competition this go-around. They have so much in the way of resources to throw at this too.... why?
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?
I had been considering an Intel dual core but it sounds like I need to aim for an AMD instead.
Agile Artisans
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.
From the article... 4 cores with 4 Virtual CPU's. What a beast. And they even talk about licensing issues
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.
This sig is definitive. Reality is frequently inaccurate.
How can you call the most prevalent x86 server cpu the redheaded step child. I would say the itanium was the redheaded stepchild not the popular xeon.
Sorry, teleporters just kill you and then make a copy. A perfect, soul-less copy.
mmmm.. an apple with dual cores.. I'll have to get a new apple corer of course...
Don't anthropomorphize computers: they hate that.
This is the 21st century in North America, since when do we care how much power a CPU uses. *Drives away in Hummer*
LINUX ONLINE POKER: Linux Poker
Got through several pages of the benchmarking before it appeared /.ed.
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.
"Trolls they were, but filled with the evil will of their master: a fell race..." -- J.R.R. Tolkien on Olog-hai
Intel is notorious for "Unnouncements". They will simply unnounce some strange new technology that is "coming real soon now" but they will leave out all of the details. This might just keep Dell from leaving them.
More
Is GamePC the best place to read benchmarks on a dual core Intel Xeon chip? The article appears to be /.ed already (or just REAAALY slow at my end) so I can't read the results, but I can't help but think somewhere called GamePC isn't exactly Intel's target audience here.
Intel is engineering for it's next gen chips that are still vaporware as far as i'm concerned. AMD put out some great technology that works today.
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?
http://www.gamepc.com.nyud.net:8090/labs/view_cont ent.asp?id=paxville&page=1
Seems it's slashdotted already after 8 posts. Finally when will all slashdot-links be coralized automatically?
Hello, Stock market? Please read slashdot. I need to sell my AMD stock and buy a new amp.
We all know AMD's dual core lineup trashes intel.
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.
You would think with all their resources intel could start to make a chip to compete with AMD.
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.
Dell is locked into Intel and they really needed dual core, so there it is.
Amd has thrashed intel for a few years now in terms of cpu performance so this is no surprise. What they really need to do is become more marking savvy. Most people don't know amd even makes chips. That includes many computer literate people as well, whereas even the luddites know who intel is
Geez, I didn't preview so I suffer.
"I'm seeing Intel dual-core processors appearing in < $700 PCs. From that angle Intel absolutely devastates AMD, as somehow their dual-cores are far less expensive."
Is dual core the same as Intels Hyper Thread ? sorry for the noob question.
If you get an older version of Windows, that machine will count as having eight processors. With Windows XP, Microsoft has clarified their view, namely that they count sockets, not cores or virtual cores. So Intel isn't cheating on this, they are doing exactly what Microsoft wants.
No.
Duke Nukem Forever is being rewritten to run on XFORMs. Thought that was sorta funny.
> see http://211.28.70.211:1337/?page_id=23
thank you thank you I been looking for a live update site for ages. looks apple banned such updates.
Why is it that every time I see a story about this processor, I keep thinking about the Star Trek Nazi episode?
-jcr
The only title of honor that a tyrant can grant is "Enemy of the State."
Intel has been really slacking more and more since AMD beat them in the 1GHz race. After that Intel has seemingly been focusing on making the 'fastest processor' and not improving on the design much.
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'
"Some things have to be believed to be seen." - Ralph Hodgson
Intel's sales will again beat AMD's by several fold. The reason seems to be that most PC and server purchases are not intended for games, beyond Solitare of course, and people prefer the reliability, power savings and lower temperatures of the Intel chips.
Did you miss the part where they said this chip consumes more power and runs hotter than Opterons?
Why do they always do gaming as the benchmark? It's a server processor!!! Do some crypto!
:-) Shameless plug but also good numbers when doing RSA work I guess.
Check this out image 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
Someday, I'll have a real sig.
These have been availible in Dell servers for a while now according to the online store. Intel are truly screwed for at least the next 6-12 months by the looks of things unless they are hiding something seriously good. I had thought that perhaps they had been based on Apple's decision to switch, it looks like they might just be pretending to be better than they really are though.
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.
a $700 PC where it costs you $45 a month in electricity just to run the chip isnt cheap anymore.
No. Dual core puts two processor cores on the same chip. Each of these cores may have hyperthreading, which essentially splits up the core into a big powerful section for high-power processing and a smaller section for simpler stuff which will just help keep things chugging along while the powerful section is working out a hard SIMD vector multiplication problem or something...
WTF??? We're talking about servers, not laptops.
No folly is more costly than the folly of intolerant idealism. - Winston Churchill
The article is dead but there are a few more things to take into account bar base cost . ,This is another major issue .Again no benchmarks , but the term " thoroughly thrashed" is not promising.
.. well I surmise you may not be saving that much if anything . Perhaps it may even turn out to be more expensive .
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 span . Plus many things I have not accounted for.
A short term saving perhaps , but long term
The only things certain in war are Propaganda and Death. You can never be sure which is which though
...and people prefer the reliability, power savings and lower temperatures of the Intel chips.
/. and all, but next time you might want to try and RTFA.
I know this is
Beware of he who would deny you access to information, for in his heart he dreams himself your master.
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... ;-)
Galileo: "The Earth revolves around the Sun!"
Score: -1 100% Flamebait
Without reading the article, I'm going to make some assumptions. (Like "thrashed" means 10% faster.) In which case, this is a case of market management.
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 case of perception more than fact.
At some point, Intel will have to start preforming. For now, they can get away with promising that they will preform in the near future, and have a competing (not competative) product in the area. AMD may have started taking the consumer chip crown, but the office environment is still aways off.
$.02
This is just about Intel Dual Core in general.
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.
These are server class cpus that where bench-marked not PC class. You are not likely to see them in a "mainstream" PC. Your right Intel is selling a lot of lower end dual core cpus. AMD is selling all the high end chips it can make. If you want the fastest right now you buy AMD. Let's not forget the 64 bit line of single CPUs as well. At this very moment only the Pentium M line is a bright spot for Intel.
Intel used to own the X86 server market now you are seeing AMD making big strides in the servers. This looks like it will only increase for the time being.
Intel better get moving. Finally
See my blog http://ilovecookes.blogspot.com/ for light hearted technical information.
Of Intel, maybe.
These would have been sweet for my dual Xeon workstation :(
Anyone know if they are supposed to work with existing motherboards?
Everything I need to know about copyrights I learned from Slashdot.
allow me to share my excitement.
:)
(points at intel)
MWA HA HA! HA HA!
MWA HA HA! HA HA!
Ah... felt so good. Thanks
Firefox loaded the page in few seconds and I am finished reading the article but internet explorer is still struggling to load the main page. Looks like wintel days will get over sooner than anybody thinks!
They called me mad, and I called them mad, and damn them, they outvoted me. -Nathaniel Lee
..as long as opteron has seperate ram (chips+bus) for each CPU and xeon doesn't. I assume intel knows this.
And if you can put in a whole rack of new servers and not have to upgrade your airhandler or your UPS, wouldn't that be a good thing?
AMD should be touting its own Performance per Watt figures right now, rather than waiting for Intel to eventually catch up.
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
Do you have any idea how much it costs to have a computer in every house, each one consuming about 300 Watts*hour?
Only when the world's oil supplies are limited, researchers are struggling to find alternative energy sources (fuel cells, flexible solar cells, etc.). But right now the majority of energy plants burn fuel to generate electricity.
By making CPUs save power, the chip manufacturers are indirectly fighting against the greenhouse effect.
I work at best buy and last I checked we have a 3800+ X2 Athlon64 for less than $900 sitting right next to the other HP's. I'm on Geek Squad and all of us make the sales people convince the customers to go AMD because about 1/10 of the Pentium D's overheat out of the box or are dead already. The amount of heat coming out of those things are ridiculous. Also an "Advanced Security" (NAV2K5, Spysweeper, and Critical Updates install) takes far less time on our AMD systems so we prefer to work on them.
Marky Mark Killed Jason Bourne!
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.
Galileo: "The Earth revolves around the Sun!"
Score: -1 100% Flamebait
--
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_con
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 foot the bill for that. 1 maybe 2 days?
Its just funny how everyone thinks "USE TEH MIRRARS!!!!!1" is the solution to slashdotting, when really there is no defence.
I'll just use my special getting high powers one more time...
Yeah, c'mon Steve, I want that dual-core OS X/x86 monster! And a pony!
- chrish
The reason that Intel's dual core processors can sell for less than AMD's is the same reason they get thrashed; Intel dual cores are simply a normal Intel dual proc setup in one package, while AMD's dual cores have a single die. The Intel offerings use the woefully slow FSB for intercore communication, whilst AMD uses a dedicated, full-speed bus.
"Because Science" is one step from "Because old book". Try "Because of my experiment testing my falsifiable assertion".
RIAA lists Dell and Intel as major contributors to Internet piracy -- subpoenas to follow...
I only wish.
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
I built two AMD computers using the MSI Platinum board, with SLI running two Ge Force 6800 video cards. Now I have been building computers since I was 18, and I am 35 now. I am not sure if it's me, or the MSI motherboard, but the USB2 interfaces only work as USB1. I get an error with all devices that I am plugging in a USB 2 device into a USB 1 spot. When I shut down the PC, it automatically reboots. I have to physically turn off the power supply. And this is with Both PCs. Just last weekend, one of them completely crapped out. I am going to diagnose the issue, but I can't even turn it on. I am so ready to just buy an AMD PC, but Dell doesn't carry them, I guess I can do Falcon or something. I remember the good old days when AMD made their own chipset on motherboards. Now you are stuck with VIA, and I never had much luck with them. I really wish Dell would wake up and start selling AMD PCs. I am ready to retire building PCs and focus on different things in life.
The HP A1250N (X2 3800) is in all the big box retailers at $849 after rebate, and I haven't seeing anything with an Intel dual core with equivalent specs cheaper. If BestBuy, Circuit City, and Frys all carry it I'm thinking that qualifies as "mainstream PC"
Its pretty clear that intel is sliding in the x86 race. The reason has to do with development cycles and all the work and money Intel spent on that risky itanium venture. Itanium diverted R&D funds from x86 and when Itanium failed in the market place, intel wasn't working hard enough on x86 and fell behind.
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.
Only they're not quite double the performance, because they share the memory bus. Any memory intensive application will hit contention between the 2 cores...
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 connection between the 2 cores on a single chip whereas intel`s chips need to go via the processor bus.
http://spamdecoy.net - free throwaway anonymous email - avoid spam!
No it isn't. Dual core means two processors on chip. Hyperthreading is an interesting but not incredibly useful technology intel uses that makes one processor look like two slower processors, for instance, 1 3.0GHz processor turns into 2 1.5 GHz processors. I won't go over how it works. In fact, the new Xeons support both, so when you boot, it looks like you have four processors, two actual ones each pertending to be two more.
Likewise - I got a Dell (mainly for the sweet deal on the 24" LCD) and went with the dual core Pentium D, just the 2.8ghz version. Its a remarkably responsive machine, for not a huge amount of money. Powerful, quiet, and cheap. I'd like to have gone AMD, but on the (relatively speaking) low end, Intel's pricing just spanked theirs for dual core.
You're special forces then? That's great! I just love your olympics!
wow!
seriously though, I'd rather save $400 and just go for the intel
HyperThreading is a cheesy Intel hack that lets Windows see two logical processors. For the apps i've run on Windows, there has been absolutely no gain in performance under heavy load. Maybe someone else can share a different experience...
If you think
+5 Insightful should be good
well, although you're pretty much right on, even the 32 bit athlon xp/mp processors were quite warm. my 3200+ and 1900+ both ran about 130 degrees farenheit (with the right fans temps would drop 10-15 degrees), whereas my 3200+ amd 64 runs about 90 degrees with a stock/retail-box fan. if anything, an amd64 is worth buying for the low cost, low temp, low fan noise, high output nature of it.
"but money is the God of Algiers & Mahomet their prophet." - Rich. O'Bryen June 8th 1786
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 only locked to different maxima !)
OTH, providing different prices & licenses for different support schemes, ranging from Ultra-Cheap for students and developping world You've got what you bought - don't blame us if you have difficulties booting it whith your weird computer license, up-to Maxi premium ultra 'sell your organs on black-market to pay it' Deluxe 24h/7days on-site availability to assist using it on your beowulf cluster, that's something I'ld understand.
-----
Note that Microsoft has said that, in part because of the high requirement (dual core almost required) of next-gen bloat^H^H^H^H^H Vista Windows, their reconsidering the way they handle per CPU/license. So Intel isn't actually cheating, just following the trends.
Note also that I use almost only Linux (despite that fact that i'm not in computer science at all. Did study old languages and then medecine), so maybe there's a perfectly normal and morally acceptable reason for this stuff that I'm unaware of. (I mean other than "ripping more money from the customers").
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
This guy isn't trolling, he's putting out a valid point. Apple is releaseing Dual Cores to the public in a way that intel certainly won't. Do you think that ALL intel towers will have dual core xeon chips? Nope. But all full sized apples will. I'd like to see a performance comparison of them.
Tibbon
tibbon.com
I'm a huge AMD fan, and almost all of my machines are running either A64's or Opterons. But when it was time to build a file server, I went Xeon.
Why? No one offers a motherboard like this on the AMD side of things. The Tyan mobo just sprouts high-speed expansion busses, perfect for a box that will have multiple bonded gigE adatpers, multiple RAID controllers, etc. And everything was recognized by Linux the first time - total piece of cake install. This is because Intel makes **excellent** supporting chipsets that have all of their features well supported by Linux.
AMD boxes need more attention during install for things like gigE controllers and the like - at least that's been my experience. NVidia chipsets are simply not fully supported, and I'm not going to trust backwards-engineered stuff or binary-only releases over Intel-supplied, in-kernel drivers. VIA doesn't make really high-perfomance stuff, either, or at the very least no one is offering it as such.
Sorry, AMD, but until you continuously offer your own chipsets that offer all the options under Linux (and not rely on erstwhile partners like VIA and NVidia), Intel is going to continue to dominate. Intel makes motherboards and chipsets for a reason.
jh
BTW, could I borrow your Opteron, I need to fry an egg for breakfast.
The 90's called. They need their processor bigotry back.
Amazingly, Intel seems to have forgotten what got them dominance. It's all about the binaries. People will buy new processors if they run their old binaries faster. Period. They won't buy based on the promise of running some new, as yet non-existent, binariese faster in the future. AMD understood this when they came up with the Athlon64 architecture. Not only did it extend the instruction set to add 64-bit instructions, but it also sped up 32-bit applications. Intel completely dropped the ball with the Itanium debacle. It looks to me, from this latest announcement, that they still don't know where the ball is.
Funny, the same can be said for Microsoft, only they still get it. New OS's must be binary compatible with old OS's. If they aren't, people stay away in droves (phrase credit: Yogi Berra), This is the main weakness, in my opinion, of the whole FOSS movement. Most people don't want to "simply recompile".
It's the binaries, stupid!
The more you regulate a company, the worse its products become.
Care to provide more details? A retail HP A1250N is $849 after rebate, the cheapest Dell I can configure with equivalent memory and disk with a much slower 820D processor is at least $200 more. Dell does have some nice 24" LCD deals, but you can get those without buying a computer.
In my experience support from both Dell and HP is equally bad for their home buyers, so not much to sway the decision there.
Additionnally to what other have said, I may add :
- HyperThreading is Intel's name for Simultaneous Multithreading.
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.
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
Running a Xeon dual-core is like mounting a Chevy big-block engine under a VW carburetor. The memory access just isn't there. Most of my stuff (modeling the solar corona) is RAM-bound anyway, so there's no win to be had at all by running the dual Intel cores. The Opterons have better RAM latency, which is a win -- but, more importantly, the two cores communicate cache-to-cache at the CPU clock speed, so dual-threaded processes run amazingly fast. If they're sharing memory, you effectively double the L2 cache size of both cores, which is a big win all around.
So, er, Xeon is teh 5uk and Opteron Pwns.
"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."
That's not because of AMD's pricing, that's because of Dell's pricing. Dell's standard configuration templates are based on Intel chips, so subbing in another brand takes it out of the regular production line.
Try HP for cheaper AMD dual-core processors. I'm sure there are other MFGRs out there, but if you're buying from Dell, then HP should be a good alternative for you.
"Trolls they were, but filled with the evil will of their master: a fell race..." -- J.R.R. Tolkien on Olog-hai
I don't think this is the case. Intel is a behemoth with enough money to fund hundreds of major projects concurrently. They can throw hundreds of man years on a project on a whim. This is not a resource limited start-up we're talking about.
Now for the tin foil hat part: Their x86 products fell behind not because of lack of R&D funding, but because some idiot(s) up in management decided that they'd rather have everyone migrate to IA64 by buying a new PC rather than migrating to a backwards-compatible EM64T architecture.
Intel's sales will again beat AMD's by several fold. Apparently you haven't read AMD beats Intel in September US retail desktop sales What were you saying again? By what math is 46% of the market considered beating 52% of the market "by several fold"???
I've abandoned my search for truth; now I'm just looking for some useful delusions.
save $400 and just go for the intel
So Intel is selling a dual core Xeon for $75? That's a deal I must agree. You will have to tell me where you can buy one for that price.
Somebody recently told me ... it may have been Sun or AMD, or an industry analyst, I forget who ... that some of the customers clamoring the loudest for high-performance, low-power systems are on Wall Street. Aside from the heat concerns mentioned elsewhere (and remember, more heat means more air conditioning which means still more power -- AC is always a line-item on any datacenter budget), a lot of customers run into the problem of there simply not being enough power infrastructure to go around. If you're running a datacenter with a whole bunch of systems in the middle of downtown Manhattan, you can't just pull in a few thousand more watts on a whim.
Breakfast served all day!
Or replace existing servers and save a ton of money on cooling costs.
On the topic, Intel is focusing on their power scaling tech for their next generation of cpu's.
...I doubt DNF is ever going to come out. If only because Jack Thompson would describe it as, "The game--long-awaited in the gaming community--where police are mutated into hogs and shot."
tasks(723) drafts(105) languages(484) examples(29106)
My applications require certified or factory built hardware, for support purposes. A Dell dual Xeon Precision workstation was $1500 more than a dual PowerPC PowerMac so I opted for the Apple.
The new PowerMacs are supposed to sport dual dual-core PowerPC processors and be priced the same as the current dual 2.7 Power chipped machines. Sweet.
I don't really have the time to build my own system or what not, so I was going to pick up a Dell 9100 with the following processor: Pentium® D Processor 820 with Dual Core Technology (2.80GHz, 800FSB) My impression is that for day to day stuff and some gaming (Civ 4, Football Manager- the latter is fairly CPU intensive) that this would be a better bet than say a P4 630 w/HT Technology (3.0GHz,800FSB). Am I off base in this belief ? I admit to knowing nothing about dual-cores, so I'm wondering if its worth paying the 100 bucks or so extra for the former as opposed to the latter
It's "too", not "to", as in "This takes too much time."
Read your own article. That's retail market. Like you know... It's only counting stores you walk into. It's not counting companies like sayyyyyyyyyyy Dell?
Yes.. The K7 series ran "hot" in the end of each core model, and the Althon64/Opteron (K8) was a redesign with new technology (die shrink, SOI from IBM).
Anticipating the latest shrink and move to dual core was sheer genious on the part of AMD. They designed their interconnets, sockets, and power envelopes to support the larger Opteron cores, and the benefits from the shrink allowed them to "drop" dual core onto the existing platforms (very nice).
What you are seeing from Intel is the end of the road for the P4/Xeon design (evidenced by High heat and cheap tricks like their larger caches, new instructions, and slapping together dual cores at the last minute).
I'd never count Intel out, but they're definately falling behind in this battle. AMD's only problems are lack of production capacity, and intel "lock-in" of certain teir 1 vendors (it will be interesting to see how the lawsuit goes).
Beowulf Cluster, my friend. Just imagine a Beowulf Cluster of these. This is a TRUE geek's system.
Again, a very independantly wealthy geek, that is.
Hyperthreading allows 1 thread to use the integer operations and another thread to use the floating point operations simultaneously. The integer and floating point execution areas are separate and can be used independently. Hyperthreading allows 2 paths into the cpu to allow them to be used simultaneously. A properly written program can benefit greatly from hyperthreading. In some application testing I've done in the hpc market, some codes have run ~30% faster with hyperthreading turned on since the physical cpu can be better utilized.
However.. we still sell >90% opterons, with a growing number of dual core opterons. All the xeon dual core stuff I've seen is garbage and totally wasteful. Their next line of dual core stuff should be better though (from what we've been told).
simply set your power management to "Minimal" for a desktop and it uses C'N'Q, or at least id does on my Athlon64 d'top.
I've also got an AMD Turion 64 based laptop and for that, the good ol' laptop setting also makes it kick in.
I am NaN
gp: and people prefer the reliability, power savings and lower temperatures of the Intel chips
WTF??? We're talking about servers, not laptop
When you have one room that is cooled by 20 tons of AC for 10 racks of computers, power and heat dissipation start getting important. It burns your wallet at both ends, the power end and the cooling end. It is really that big of a deal.
The Tyan K8WE is the best board for Opteron I've seen so far.
...)
2x PCIe
2x PCI-X 100
1x PCI-X 133
1x PCI
2x Gigabit Ethernet (not on any of the above buses)
Up to 16 GB memory
SATA-RAID
2x U320 SCSI
Firewire
USB 2.0
Audio
That's pretty much all I want from a fast workstation or server system (well, actually I don't need Audio for that
Linux support is a tricky issue. It worked for me, but yeah, support could be better. I hope nvidia will listen some day.
Let me guess, your not in IT. :-)
Environmentals are VERY important for reasons that are kind of obvious.
1) It costs money to cool servers.
2) It costs money to power servers.
3) Saving money is good.
4) Intel Xeon chips don't have better environentals than AMD Opterons.
If you have a computer A that performs better than computer B, and it costs less to power, and it costs more to cool.. It is kind of a no-brainer.
You essentially throw electricity down the toilet by having anything that isn't as efficient as possible.
v4sw6PU$hw6ln6pr4F$ck 4/6$ma3+6u7LNS$w2m4l7U$i2e4+7en6a2X h
I just picked up a new Dell 9100 2.8 ghz dual-core machine - its not at zippy as I expected in day-2-day operations, but the power of this beast really shines in a "multi-task" enviornment. I trying taking it though its paces when I first set it up, simultaneously installing several pieces of software, backing up the machine, while playing a high end 3-D game, while playing music. Brilliant! And it boots up remarkably fast as well.
Horns are really just a broken halo.
Many of the benchmarks show the Opterons being nearly twice the speed.
When I see such a wide margin when dealing with multiple processors I begin to wonder if the benchmark is using all the CPU's. It just seems like the Xeons weren't using all the cores or something in some of the tests.
I don't know why that could happen but there is just too wide a margin in many of those tests. Something seems not right. I mean, I know the Opterons are generally faster, but I have never seen them be that much faster.
You forgot one thing: the AMDs are much more expensive, the premium to pay for the dual core Opterons over the single core ones is quite a lot higher than for the intel dual cores. You're correct in saying that Intel is targeting the consumer/low end business market with their dual core CPUs, but it's not just in terms of performance, it's more so in terms of price, and I really think that for now, intel is selling orders of magnitude more of dual core CPUs than AMD does.
That's not because of AMD's pricing, that's because of Dell's pricing. Dell's standard configuration templates are based on Intel chips, so subbing in another brand takes it out of the regular production line.
Um... no. Dell ONLY ships Intel. So I was comparing Dell with dual core Intel Chips vs others with other brands. You can get DellSB - Dimension 9100 Desktop with 2.8Ghz P4 820 Dual Core, 512MB DDR2 SDRAM, 80GB S-ATA, 48x CD-Rom, 128MB ATI Radeon X300 SE for $679 after Rebate including 19" LCD Monitor. Check out http://www.gotapex.com/ for details.
A quick check on www.mwave.com shows the cheapest AMD X2 to be nearly $350 and that's the recently released 3800+ X2. When I bought my computer, the cheapest one was the 4200+ X2 which is just shy of $500 range. That's for the BARE CPU. With the DELL, you get the whole computer and a 19" LCD.
Only they're not quite double the performance, because they share the memory bus. Any memory intensive application will hit contention between the 2 cores...
I realize that not all applications are 2X faster. For example, non-multithreaded apps see a benefit only when you're multitasking.
However, I *ONLY* mentioned 2X performance for MP3 and xVID / DivX. These are two extremely CPU intesive applications with much lower memory bandwidth (CPU is bottleneck, not RAM) and are two REAL-WORLD cases where the performance for dual-cores (even on Intel) is VERY close to 2X the speed of a single core.
Check out www.gotapex.com to see how to configure a Dell dual core for $679 with a 19" LCD. Intel dual core pricing has gotten so ridiculously low at Dell if you know the right deals that it's beginning to compete with their Celeron offerings.
Intel used to have the class products and AMD was the inexpensive copy. Now, AMD is selling the classy stuff and Intel sells the cheap, junky stuff. I am amazed at how poorly the Intel dual-core performs compared with the AMD. Even if Intel couldn't replicate the lower power consumption of the AMD product, it seems like they should have been able to at least come a little closer to the performance. It is just embarrassing to see how far Intel has fallen.
Intel's marketing must be awesome if they can get knowledgable IT pros to buy the dual-core Xeons instead of the dual-core Opterons. I'm thinking the Intel marketing guys could sell sunshine to Hawaiians.
You're sure about your point 3, are you? ;-)
No folly is more costly than the folly of intolerant idealism. - Winston Churchill
speaking of dual core any apple users we have live updates of the apple event in one hour. Dual Dual-Core Powermacs expected.
And be sure to get them while they are good - that is, before Apple switches over to the power hungry, poor performing Intel dual core chips.
Or better yet, just get an AMD system.
"I'm seeing Intel dual-core processors appearing in
$746 isn't that bad. Shipping included.
LK
"Hi. This is my friend, Jack Shit, and you don't know him." - Lord Kano
...watch for the "Dempsey" in Q1 and the "Woodcrest" low power, high thoughput in Q2.
The Paxville DC is a stopgap.
400W while idling?
Did you notice that the 2.8GHz quad core system, which GamePC claims to consume 393W while idle, only consumes an extra 35 watts when the system is under "full load"? That means the difference in power consumption for each 2.8GHz Pentium 4 core between idle and full load is apparently less than 10 watts, even if you assume that no other component in the system (memory, chipset, video card, hard disks, etc) consumes any more power when the system is fully loaded. This could be true for the video card and hard disks in their test, but highly unlikely for the memory and chipset.
Am I the only person to have spotted this, despite there being >300 replies already? I sure hope not.
This is really wierd. Intel targeting the Cheap Market and AMD going after the server market. Just remember what AMD's rep was before the beat Intel to the GHz mark.
If someone is passing you on the right, you are an asshole for driving in the wrong lane.
I personally don't subscribe to point 3, but some people down the hall are big on it.
:-)
The OP had to be teh troll.
I'm actually the guy who wants all of our workstations to run CentOS/Fedora Core with a yum server instead of shelling out the bucks for RHEL... so yeah. I don't like paying too much for things.
v4sw6PU$hw6ln6pr4F$ck 4/6$ma3+6u7LNS$w2m4l7U$i2e4+7en6a2X h
"You keep saying that word. I don't think it means what you think it means."
How is it Intel has the slower chip and has been slacking if they have been focusing on "faster"? I think you mean "clock speed." As in, "Intel has been focusing on having the highest clock speed, regardless of whether it gives them the faster chip."
Program Intellivision!
They added a Montgomery multiplier on their chip recently. Useful to implement fast RSA.
You're looking at it the wrong way. The only question you need to ask is "Is AMD selling all the dual core CPUs it produces?". If the answer is yes, then AMD is making a lot more money PER CHIP than Intel is. Why would AMD want to sell their chips at a lower price? Supply vs. demand, eh?
Once Fab 36 kicks in, AMD dual cores will drop in price a whole lot. Intel will be hurting even more. Count on it.
Galileo: "The Earth revolves around the Sun!"
Score: -1 100% Flamebait
The grammer nazi strikes again! my bad
;-)
funny that everyone else seamed to 'get it' though...
You might want to fix your sig, links to parked domains are no fun to view
"Some things have to be believed to be seen." - Ralph Hodgson
Just what are the Pentium II shortcomings? IIRC Pentium Pro was a very expensive and difficult chip to manufacture even given that they'd broken it up into two separate dies. In addition they never could get the clock rate up over 200MHz with it, and could not (or it wasn't worth it) include new SSE instructions into it.
P-II bundled 512KB of half-speed L2 cache into the cartridge that worked pretty well. So well that early P-IIIs with half that amount of full-speed cache on the die itself were outperformed in some areas (e.g. SETI screensaver) by the P-II due to the L2 cache limitations.
So what parts of the P-II were particularly bad? I wonder, because I'm still running 3 of them.
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
I remember running tests and findiing that 233Mhz and 266Mhz PIIs were noticably slower than a 200Mhz Pentium Pro, the 300Mhz PII's were about the same speed as a 200Mhz Pentium Pro and it wasn't until the PII was at 350Mhz that it was noticably fatser.
The PII was a design change just to make it so AMD (& Cyrix at the time) had to start reverse engineering all over again. The same thing with the fancy new slot packaging that was such a success. They also wanted to ramp up the clock speed without paying the premium to have full speed cache memory like the Pentium Pro.
That's not unexpected since the P-Pro L2 cache ran at full core speed, while the P-II cache was running at half processor speed. This meant that it took a P-II twice as long to get data from the L2 cache as the P-Pro. P-Pro remained an excellent server chip for long after P-II was running at much higher clock rates.
But the P-Pro's problem remained that it was both very expensive to produce, and they never could get the clock speed up over 200MHz, perhaps in part because of the distance between the processor die and the L2 cache die. The inability to increase speed along with the high price I believe doomed it from the very beginning.
As for the P-II 350MHz being noticably faster, it darn well should have been. That was the step, from the P-II 333MHz where they increased the memory bus speed from 33MHz to 66MHz. Literally double the main memory bus bandwidth and of course you are going to see some significant speed increases. In fact, this is the last time Intel actually doubled memory bus speed, since DDR isn't twice as fast in the entire memory transaction as SDRAM.
But thanks for the answer otherwise.
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
Technically, I was being a semantics Nazi as opposed to a grammar Nazi above. :-)
As for my sig, thanks for the tip. I guess Art of Espresso let their domain registration lapse. That's too bad. It's a nice little coffee shop. I'll have to think up a new sig. Thanks.
--Joe
Program Intellivision!