Sign in with
Sign up | Sign in
Your question
Closed

Intel's 12-Core Xeon With 30 MB Of L3: The New Mac Pro's CPU?

Tags:
  • ivy-bridge-ep
  • CPUs
  • Intel
Last response: in Reviews comments
Share
a c 199 à CPUs
a b å Intel
August 12, 2013 9:16:54 PM

Quote:
The 32-bit build of Geekbench uses x87 code


Typo, top of page two.
Score
-6
a c 127 à CPUs
August 12, 2013 9:44:06 PM

Someone Somewhere said:
Quote:
The 32-bit build of Geekbench uses x87 code


Typo, top of page two.


Where is the typo? Do you mean the x87? That's not a typo.

This is interesting but not uncommon. The server market needs the boosts while most consumer desktop CPUs are already faster than most software can go.

Of course in 5 years a SB i5 will be no longer relevant but until then it will serve just fine. Even a x58 i7 is still a viable option for a CPU and its been out for at least 4 years.
Score
0
Related resources
a b à CPUs
August 12, 2013 9:57:06 PM

Interesting article. Must admit though, while the Mac Pro's performance is certainly impressive, the overall pace of development in the high-end has been rather boring for the past 2 years. can't wait to see what Haswell-E can do late next year.

"Regardless of whether you love or hate the “wastebasket” design, the system’s specs are very impressive for the volume of space it occupies."

And this remark touches on the core of the problem. these are a specialized, niche market of professionals who're buying this uber-expensive desktop for PRODUCTIVITY. sure it should look nice, especially in the office of a professional designer. but must it be SMALL? honestly, build a giant aluminum bookshelf if you have to. make it look elegant and artistic, maybe give people some power to customize it's looks, but ultimately give people the ability to customize the machine and buy the level of productivity they need. Apple, you've done some great things, as well as some things that I don't particularly like. but watching you kill the freedom of the small group of designers who love your products is rather sad...
Score
8
a c 199 à CPUs
a b å Intel
August 12, 2013 10:45:13 PM

jimmysmitty said:
Someone Somewhere said:
Quote:
The 32-bit build of Geekbench uses x87 code


Typo, top of page two.


Where is the typo? Do you mean the x87? That's not a typo.


Hmm, on a quick Wikipedia read, x87 was the instruction set used for the floating point instruction sets in the 8087 and later FP co-processors. Interesting.

Oops... sorry.
Score
6
August 12, 2013 11:35:40 PM

In a years time with the haswell refresh and series 9 chipset it will still make everyone yawn even if it was this year. Everything has been going into mobile since Nehalem. On the bright side, phones and tablets will start slowing down very soon once they too reach the same manufacturing node as enthusiast pc's, since the node determines the power envelope achievable, thus mobile is about to hit the same wall.
Score
4
a b à CPUs
August 13, 2013 12:30:49 AM

What I expected for the Mac Pro's CPU was a different CPU optimized for the Mac Pro. Would be surprised if the temps of made by this 12Core beast keep things cool. But hey , this isn't final , right ? Lets hope for the best ( and an affordable Mac Pro :)  )
Score
-5
a c 199 à CPUs
a b å Intel
August 13, 2013 1:54:39 AM

CommentariesAnd More said:
What I expected for the Mac Pro's CPU was a different CPU optimized for the Mac Pro. Would be surprised if the temps of made by this 12Core beast keep things cool. But hey , this isn't final , right ? Lets hope for the best ( and an affordable Mac Pro :)  )


Nobody optimizes CPUs for anything. The set up costs are ridiculous. The closest you'll get is a custom config, like a chip with (for example) both multi-socket support and overclocking or something, but you'd have to show up to intel with a truck full of cash.
Score
7
August 13, 2013 3:00:22 AM

as usual the folk running intel have become lazy and stupid and the developments in the desktop have gone down the hole. They just add some extra cache and extra threads and then act like they did something.Wow. ( at the stupidity).

Instead of pushing out code or getting the rest of the industry to use more threading applications and develop it to make it more stable and useable. Nothing.
I guess when we have a third world america. You might as well go back to a decade 1368x738 with it being the most popular in 2006. Who can afford it? It the retro push backward.
Score
-12
a c 199 à CPUs
a b å Intel
August 13, 2013 3:16:29 AM

Intel can't really do much about forcing the industry to use more threaded apps.

Not their job to write code, other than drivers. They do make x86 Android though, because the drivers are pretty much hardcoded.

Do agree on the 1366x768 though. It's the same number of lines as XGA, just with a few pixels on the side. Maybe Intel should have forced a PPI measurement on Ultrabooks - that might have helped.
Score
1
August 13, 2013 3:54:43 AM

For the extremely limited market that want's the higher performance per node in x86-64 code no matter the cost, this processor exists.

For the rest of us, i'm fine with two 6-core Xeon instead of one 12-core that is 4x the price.
Score
5
August 13, 2013 3:58:07 AM

Intel Xeon? That's a server-class CPU.
Score
-2
August 13, 2013 4:32:30 AM

"The solution was to REM out Sandra from the power run"
Program DOS batch files much? :-)

Once again, thanks for including the Visual Studio compilation benchmark runs. I find it quite interesting to see the trends with core count and how it impacts build times.
Score
1
a b à CPUs
August 13, 2013 10:19:01 AM

The really interesting stuff will be coming out in another year or two. Next gen consoles are all x86 with 8 cores (4 modules) and may give AMD a little edge on performance. Unless games somehow start supporting hyperthreading technology (HA!) then Intel may very well need an 8 core offering for desktop systems. Not sure that it needs to be a full Xenon offering with all of that floating point goodness... but perhaps a straight 8 core offering with no iGPU, no HT, no HSF, no multi-CPU support, and perhaps no visualization support would be called for. Make it a viable option for next gen game rigs, but just neuter it enough so that it does not eat into server and workstation markets.
Perhaps a locked 2-2.9GHz option for ~$400, and a 4+GHz capable K skew for ~$600?
Score
-5
August 13, 2013 10:27:14 AM

So would folks recommend building a 4th gen haswell for general everyday computing and mid-midhigh gaming?
Score
-2
August 13, 2013 11:38:46 AM

impressive, though i thought that 12 cores will double the performance at least of an intel 3930k. I'm saving for haswell e can't wait to have it next year.
Score
0
August 13, 2013 12:02:16 PM

Duckhunt said:
as usual the folk running intel have become lazy and stupid and the developments in the desktop have gone down the hole. They just add some extra cache and extra threads and then act like they did something.Wow. ( at the stupidity).

Instead of pushing out code or getting the rest of the industry to use more threading applications and develop it to make it more stable and useable. Nothing.


Actually, Intel has done quite a bit toward pushing the industry into multi-threaded applications. Intel Threaded Building Blocks is one such example:
http://en.wikipedia.org/wiki/Intel_Threading_Building_B...
or even their Automatic threading built into their compilers (or did you not know Intel releases compilers?):
http://software.intel.com/en-us/articles/automatic-para...

Either way, your comment is uninformed and ignorantly misleading. Except the incremental upgrades to the IPC. It's not nothing, but it's not a P4 -> Core2 jump either.
Score
1
August 13, 2013 12:31:57 PM

I don't want to be like BIll Gates and say that nobody needs more than 640k of memory.

But I do have to say, as disappointing as it is to be a tech enthusiast right now and just seeing so little jumps in the industry, our current tech is pretty frigin good. I have a 3770k, 7970ghz, 1866 and an SSD, and there's just not too many things that I find myself waiting around for or craving better performance..

However, everyone benefits when the enthusiast benefits (i.e. low end CPUs that are in a lot of computers get faster too)....

It's really a rock and a hard place right now I feel for the industry, I think we all want Intel to be that leader that just stays committed to making all CPU life better for everyone and constantly strives to make the best improvements it can. But Intel's just a business and a business needs customers. And most customers are fine with mobile CPU computing power and 5-6 year old system performance....

And then there's always that finger crossing that AMD will just surprise the world and release the next big thing...

It's a tough time to be an enthusiast right now for sure
Score
-2
a b à CPUs
August 13, 2013 3:58:07 PM

Gentlemen?,

For those of us handcuffed to workstations for eternity, a new top end Xeon is always interesting- we can begin the delightful process of imagining how fast animations of 8,000 part CATIA assemblies will run and the painful process of imagining the eventual price and how to pay for it.

But, and I say it reluctantly, the thorough tests and considerations by Chris Angelini fall a bit short as it only included comparison to one processor that resembles a competitor to the E5-2697 V2, which is the 8-core and $1,950 E5-2687W.

I can't think that anyone using a i7-3770K will wake up one day and realize that, instead of a $325 quad core, what they really need is a $2,800-$3,100 (guessing) 12-core- and 256GB of ECC Ram. The E5-2697 V2 will be considered by those with single CPU LGA 2011 workstations using the lowly E5-1650, E5-1660, E5-2XXX six core and the E5-2643 and E5-2687W 8-core, as a way to have 12 cores / 24 threads for without starting over and more probably, by those making the calculations for and against having to buy a dual CPU system with two $1,500-$2,000 CPUs. And, because multi-core applications are still so rare- rendering is the most common, plus scientific like MATLAB and certain custom code scientific modeling, and mathematical / financial analytics, the market will be specialized and limited.

What would be very useful would be to compare the E5-2697 V2 to various dual four, six, and eight-core systems. There are a lot of advantages to dual CPU's as they support more memory and have more PCIe lanes, which can add CUDA or Xeon Phi co-processors, RAID controllers, and etc, but importantly, the fewer the cores on a CPU, the higher the clock speed. The quad core $360 E5-1620 has a base clock speed of 3.6GHz, a similar amount of cache per core, and runs on the first core at 3.8. One could argue that on the majority of applications including most of Autodesk, Dessault, and Adobe, the 1620 at 1/8 the price could perform in the realm of the E5-2697 having a base speed of 2.7 and on one core up to 3.5Ghz. The next step up is the six-core E5-1650 at 3.2 / 3.8 at $600 and it takes the $1,100 E5-1660 to have both six cores and the 3.6 speed of the 1620 at 1/3 the cost. Then, one can move into the realm of dual six-core Xeons which can have higher clock speeds than the 2697 and may be temptingly near in cost to the single one. This is only a sample of the difficulty in judging the usefulness and cost / performance of these very high-end CPU's. It has to be reverse analyzed from the applications and even then the cost may not be justified for only occasional bursts of maximum performance.

The speculation as to the E5-2697 use in the new "dustbin" Mac Pro is interesting. The Dustbin Pro is entertaining and has some excellent thinking behind it in being airflow-centric, but it also has aspects of style over substance and exudes a sense, whether fair or not, of being static- that it can never be changed, or you have to find curved Quadros not more than 14cm long and hang additional drives off USB cables. Of course, it may be very flexible, as Apple must know that in the increasingly specialized and optimized world of high-end workstations, hot-rodding is absolutely essential. Still, it's bit sad to see Apple plodding in the decorative rather than the striking game-changing innovations of the Jobs era.

So, the E5-2697 V2 is very welcome, but to run the complex equation that would determine if it's worthwhile- and the price- there needs to be a comparison with a variety of single and multiple quad, hex and octo-core Xeon systems running multi-core benchmark tests or better, the applications of the kind for which this category of CPU's was intended. And, all of that is academic and still limited until the cost is known.

Oh, and one more thing, how well does a pair of E5-2697 V2's do? I need to make a dynamic 3D model of the entire atmosphere,...

Cheers,

BambiBoom

Score
4
August 13, 2013 5:06:19 PM

bambiboom said:
Gentlemen?,

For those of us handcuffed to workstations for eternity, a new top end Xeon is always interesting- we can begin the delightful process of imagining how fast animations of 8,000 part CATIA assemblies will run and the painful process of imagining the eventual price and how to pay for it.

But, and I say it reluctantly, the thorough tests and considerations by Chris Angelini fall a bit short as it only included comparison to one processor that resembles a competitor to the E5-2697 V2, which is the 8-core and $1,950 E5-2687W.

I can't think that anyone using a i7-3770K will wake up one day and realize that, instead of a $325 quad core, what they really need is a $2,800-$3,100 (guessing) 12-core- and 256GB of ECC Ram. The E5-2697 V2 will be considered by those with single CPU LGA 2011 workstations using the lowly E5-1650, E5-1660, E5-2XXX six core and the E5-2643 and E5-2687W 8-core, as a way to have 12 cores / 24 threads for without starting over and more probably, by those making the calculations for and against having to buy a dual CPU system with two $1,500-$2,000 CPUs. And, because multi-core applications are still so rare- rendering is the most common, plus scientific like MATLAB and certain custom code scientific modeling, and mathematical / financial analytics, the market will be specialized and limited.

What would be very useful would be to compare the E5-2697 V2 to various dual four, six, and eight-core systems. There are a lot of advantages to dual CPU's as they support more memory and have more PCIe lanes, which can add CUDA or Xeon Phi co-processors, RAID controllers, and etc, but importantly, the fewer the cores on a CPU, the higher the clock speed. The quad core $360 E5-1620 has a base clock speed of 3.6GHz, a similar amount of cache per core, and runs on the first core at 3.8. One could argue that on the majority of applications including most of Autodesk, Dessault, and Adobe, the 1620 at 1/8 the price could perform in the realm of the E5-2697 having a base speed of 2.7 and on one core up to 3.5Ghz. The next step up is the six-core E5-1650 at 3.2 / 3.8 at $600 and it takes the $1,100 E5-1660 to have both six cores and the 3.6 speed of the 1620 at 1/3 the cost. Then, one can move into the realm of dual six-core Xeons which can have higher clock speeds than the 2697 and may be temptingly near in cost to the single one. This is only a sample of the difficulty in judging the usefulness and cost / performance of these very high-end CPU's. It has to be reverse analyzed from the applications and even then the cost may not be justified for only occasional bursts of maximum performance.

The speculation as to the E5-2697 use in the new "dustbin" Mac Pro is interesting. The Dustbin Pro is entertaining and has some excellent thinking behind it in being airflow-centric, but it also has aspects of style over substance and exudes a sense, whether fair or not, of being static- that it can never be changed, or you have to find curved Quadros not more than 14cm long and hang additional drives off USB cables. Of course, it may be very flexible, as Apple must know that in the increasingly specialized and optimized world of high-end workstations, hot-rodding is absolutely essential. Still, it's bit sad to see Apple plodding in the decorative rather than the striking game-changing innovations of the Jobs era.

So, the E5-2697 V2 is very welcome, but to run the complex equation that would determine if it's worthwhile- and the price- there needs to be a comparison with a variety of single and multiple quad, hex and octo-core Xeon systems running multi-core benchmark tests or better, the applications of the kind for which this category of CPU's was intended. And, all of that is academic and still limited until the cost is known.

Oh, and one more thing, how well does a pair of E5-2697 V2's do? I need to make a dynamic 3D model of the entire atmosphere,...

Cheers,

BambiBoom



We'll be able to answer all of those questions soon enough. This was more of a thought experiment/preview based on architecture (rather than specific SKUs and full-on workstation configurations). A full review will need to wait until after Intel's launch. I'm expecting to have a dual-proc configuration prior to then, and will make an effort to get my hands on more processor pairs to chart out in more workstation-specific benchmarks.
Score
-1
August 14, 2013 5:00:31 AM

Funny thing is that... the FX8350 just appears in the benchmarks where he loses to the intel cpus... why it doesnt show up in the ones he wins?
Score
-1
August 14, 2013 7:34:06 AM

Retired Babyboomers and Depressions Babies ( me) only want faster inernet and wireless service. If that can stay in balance with fast processors --great. I will wait until this desktop breaks before buy another. I will be sur my new one has faste r upload/download times with SSD, etc . And I want good quality monitor; do photo's. Speed for everday processing is all I want. I get into some games, but not an enthusiest.
Just want reliable top speed whever I go..
Score
0
August 14, 2013 8:41:42 AM

re-play- said:
Funny thing is that... the FX8350 just appears in the benchmarks where he loses to the intel cpus... why it doesnt show up in the ones he wins?


Because it never wins. The way it worked was this: I used the same chart size as my previous -4960X preview. I dropped the two bottom-performing CPUs from every single chart, and added the -2697 V2 and -2687W. Where you see the FX, that's because it bumped off two Intel CPUs. Where you don't, that because it was bumped off. Same-sized charts; fewer super-long bars to screw up the scale.
Score
1
August 14, 2013 12:57:11 PM

I'm interested in seeing what the lineup of Ivy Bridge-EP Xeons will be.
It would be nice to see a balance of clock speed for single threaded applications vs. core count for multi-threaded programs. Hopefully the lineup will include an 8-core around 3.2 or 3.4 GHz.
Score
0
August 14, 2013 1:24:12 PM

The article is very good, early and clarifying, and great for my 3D interest. Thank you!

For Pro users, and specifically for Mac users figuring out what to expect also remember the most important feature for the next small cylinder is the dual FirePro cards and the new SSD from Apple. It looks like Apple gave up on the dual CPU Xeon part and is now focusing on dual GPU processing power instead.

To me it will all depend on Apple's effort to put those Pro GPUs to their top performance everywhere possible and also at what price point the Mac Pros will be.

However I am not expecting the next Mac Pro even a 4-core model to start selling under 3K as they will include those dual FirePro GPUs by default.

Being realistic I will need to see something amazing on the next Mac Pros, and I am sure the amazing part wont come from 8 or 12 core Xeons as they will be very pricy and included on the top end. But for sure I will be watching more pedestrian options at 4 or 6 cores. If the GPUs don't deliver something special I will continue updating with my Dual Mac-PC desktops one at a time.
Score
0
August 14, 2013 4:58:44 PM

savvy tech peple will not buy an expensive macpro because they know macpros dont worth the price and steve wanted to smash the pro division could he knew that pros cant be fooled easily unlike teens or old people that think like teens
Score
0
August 14, 2013 11:56:47 PM

Nice primer for the subject.

cangelini said:

We'll be able to answer all of those questions soon enough. This was more of a thought experiment/preview based on architecture (rather than specific SKUs and full-on workstation configurations). A full review will need to wait until after Intel's launch. I'm expecting to have a dual-proc configuration prior to then, and will make an effort to get my hands on more processor pairs to chart out in more workstation-specific benchmarks.


I really hope you can put two E5-2643W V2s (3.5GHz 6-core) up against the E5-2697W V2, also two E5-2650 V2s (2.6GHz 8-core). A lot of enthusiasts are going to see that 12-core CPU and talk uninformed nonsense to those wanting more than 6 cores in their system. While a single CPU is a simpler choice, and certainly more worthwhile to those upgrading existing SB-E systems, a dual E5-2642W V2 system may be cheaper to build as the E5-2643s currently are $900 each and would only consume 0.1 kWH under load - even with the issues of power requirements, cooling, extra heatsink, more considered air flow. I can't imagine that such a system will be cheaper from a tier 1 vendor due to DP workstation premiums, but for system builders it shouldn't have a higher TCO. Other advantages of course being the benefits of double memory capacity and double the PCI-E lanes. Current 32GB DIMM pricing also means it is much cheaper to get more than 128GB RAM on a dual CPU system - although probably out of the realm of interest for most readers of this site.

Also in your article you say SB-E has been out nearly 2 years. It was a late March "launch" and they didn't ship until June 2012.
Score
0
August 15, 2013 12:38:24 AM

Yesterday night I had to advise to clean (blow out) the dust on his you beaut i7 and Nvidia 550M combo because it was BSODing due to excessive heat.....After swearing head off at his $2500 machine, he understands that he needs to keep pristine or else....

so

hehehehhe! At 130 TDP it's no wonder Mac have made something that resembles a chimney or a smoke stack :-)
Score
0
August 15, 2013 3:31:48 AM

"The New Mac Pro's CPU"

Is this also going to be available for HP/Dell/Etc servers or is this another Apple advert?
Score
0
a c 199 à CPUs
a b å Intel
August 15, 2013 3:40:03 AM

It will be. It's just that Apple doesn't want you to think that way, and to have people subconsciously link them to 12-core chips.

In fact, you'll even be able to run two of them (or even four) in many servers/workstations.
Score
0
a b à CPUs
August 15, 2013 8:30:15 PM

Textfield said:

I see one of the largest issues being the lack of an HDD, so far as we know. I get the use of solid-state storage, but even multiple 1TB SSDs won't provide all the space a creative professional might demand, assuming they are high-capacity SSDs. The Thunderbolt connections make it obvious Apple is assuming you'll connect to an external Thunderbolt storage setup, but that just makes the system even more confusing.

Companies have no reason to need this smaller form factor, and the lack of internal storage complicates matters for everybody, since they have to come up with a centralized storage mechanism fast enough for the professional workloads of their employees. And if I'm independant or work at home, I'm already cashstrapped. Saying I have to buy a large, external setup just to have high-capacity storage for a small system is like saying I have to take a diesel generator with my electric car to keep the batteries charged. It defeats the purpose.

This is what's so confusing about the device, because it seems aimed at independant professionals in private studios. I don't see why a company would need such a small computer. Large towers under the desk do fine. And like you said, the independant professional is used to large systems. If they made it a bit larger and fit a couple HDDs in there, it'd make more sense, but I think taking away HDDs is one step too far.

Apple is used to taking steps in odd directions, but they always end up making sense. I'm not sure that's the case with this one, and if it is, I think they've gone the wrong direction.


To me, in this day and age, a creative professional don't necessarily NEED an internal HDD. an external one, or uploading to a NAS or proper server, would be a fair alternative. this is even more true in scientific applications, I have two guys in my lab spitting out modeling data output sometimes exceeding 150MB/s. The data would always be cached in memory. if an SSD is fast enough, it can be cached in the SSD as well, and later transferred for long-term storage.

as for form-factor, I agree with 100%. and not just for companies. This kind of form-focused design is only useful for a professional's home-office, or that professional work area that is often shown off to potential customers and clients. Apple needs to realize that while their designs have been successful in the personal space, to break into business space and replace productivity oriented workstations, they absolutely CANNOT sacrifice function for aesthetics. sure, a pretty workstation is great, but no professional will buy it if it can't do what they need it to do, and there are very few managers out-there who will approve large amounts of funding for a non-up-gradable workstation.

In the end, I agree with your conclusion. this "dustbin" design makes no sense. it's an elegant design, sure. but it only gives us half the package any professional would want.
Score
0
a b à CPUs
August 15, 2013 8:38:26 PM

To all those who think the desktop will go extinct: the only thing dying in desktop market is 'budget desktops'. just to add to your point, recently released GPUs from Nvidia have also demonstrated that they're interested in stripping down workstation oriented parts to sell them at a lower price for the general consumer, AMD will probably move to do the same. will people be spending $400-500 on a desktop to surf the web and check facebook 5 years from now? probably not. but if you drop say $2k on a desktop build around Sept or Oct next year, you can get a nice Octacore-Haswell CPU, DDR4, Nvidia Maxwell GPU or AMD volcanic islands. and even leaving gaming aside, these high-end desktops will give you the kind of content creation and modeling capabilities no laptop or tablet can touch in probably 5+ years.

Basically, for those of us who love the desktop, either buy it now, or be prepared to spend about twice the amount you would expect for something nice. the lower end of the desktop market is vanishing rapidly. but the desktop form factor will never go away
Score
0
a c 199 à CPUs
a b å Intel
August 15, 2013 8:58:12 PM

While they do not necessarily need an internal HDD, it's still somewhat faster than a NAS unless you have 10GbE. And external ones are a waste of desk space and power points, and cause cabling mess.

The workstation GPUs are already much the same as the desktop GPUs - AMD's top-end card, the W9000, is based on Tahiti. nVidia's GPUs are typically based on the same GPU too, but the 680 kind of broke with tradition, with a GK104, not the GK100.

Score
0
August 15, 2013 10:11:31 PM

How well does it overclock?

Score
0
August 16, 2013 8:52:58 AM

Why are the graphic charts overlaying most of the text on all of the benchmark pages? Is this a layout issue or is it a page rendering issue? Can you fix it?
Score
0
August 20, 2013 6:14:55 PM

razor512 said:
How well does it overclock?



It doesn't overclock due to locked multis. At best you can adjust BCLK, and those increments have shown to be unstable at anything over 3%.

This has been the case since Westmere-EP, and will continue to the case for the prospective future in Xeons.

Which is one of the reasons why I continue to use dual X5680s, OC'd stable to 4GHz @ 200 MHz BLCK. Great performance at a low cost.

Score
0
August 25, 2013 10:43:23 PM

ammaross said:
Duckhunt said:
as usual the folk running intel have become lazy and stupid and the developments in the desktop have gone down the hole. They just add some extra cache and extra threads and then act like they did something.Wow. ( at the stupidity).

Instead of pushing out code or getting the rest of the industry to use more threading applications and develop it to make it more stable and useable. Nothing.


Actually, Intel has done quite a bit toward pushing the industry into multi-threaded applications. Intel Threaded Building Blocks is one such example:
http://en.wikipedia.org/wiki/Intel_Threading_Building_B...
or even their Automatic threading built into their compilers (or did you not know Intel releases compilers?):
http://software.intel.com/en-us/articles/automatic-para...

Either way, your comment is uninformed and ignorantly misleading. Except the incremental upgrades to the IPC. It's not nothing, but it's not a P4 -> Core2 jump either.


Wow. You can cut and paste from the advertising rubbish they print out. Sorry but making examples and putting out threaded real world apps is a big difference. You have no idea. Go and read up the rubbish they make up and pretend there is something happening. The hard work is making threaded stuff work and showing that is is possible to make the applications run things in parallel. Its a big difference between the reality of the situation.
Here is the first example for you. The idiot pcs usually hang and sit around waiting for the internet to work. These are pcs with many threads. Why can't one thread be used for the internet and the other thread for rest of the pc. Why? It is because Intel is a failure and so is anyone who can't understand how easy it would be for it to be done. if the hardware was designed to do that. BUt it is not. Its not done because they are incompetent morons or stupid idiots on the hardware side. Anyone who does not believe it is either on there payroll or ignorant. There is no grey area here. This is just one example of the failure. The multi core processors are not really multicore. They are just B.S. Else these types of things would be normal. When you cr+ppy expensive pc hangs. Its because the processes are in sequential order. When you have to wait for things to load up and the screen is white or something else. Its the sequential order of loading aps. GET IT? Somewhere in the hardware. I can't be bothered to work out where everything is running sequential. Maybe its on the bus access to the card. There is your problem. The drivers written by intel are just written for the threaded aps to run and they just pay lip service for stuff that is not on super computers. These problems should of been solved years ago. They are not. WHy? I told you why. If the pc loaded 3 different apps on different cores. It means that the white screen or other blank screens would not effect your ability to run other apps. or access the hard drive. Whatever the problem is. Its hardware/device drive. Its not the programmers. Faster load times. blah blah. These intel F+cks over paid lousy F+kers have done squat. I don't care what they write. LOAD UP THE APPs in separate cores. THAT SIMPLE> geez. Access to the other parts is sequential. You KNow squat.


Score
0
August 25, 2013 10:48:13 PM

Someone Somewhere said:
Intel can't really do much about forcing the industry to use more threaded apps.

Not their job to write code, other than drivers. They do make x86 Android though, because the drivers are pretty much hardcoded.

Do agree on the 1366x768 though. It's the same number of lines as XGA, just with a few pixels on the side. Maybe Intel should have forced a PPI measurement on Ultrabooks - that might have helped.


Whatever. Lets understand it. We have 10 million elite programmers. We have Intel. Where do you think the problem lies with threaded apps? The 10 million idiot programers who are obviously fools or One company that has a monopoly who has crap hardware. Answer that?
Score
0
a b à CPUs
August 25, 2013 11:01:51 PM

I wonder what other CPUs will Apple offer for the Mac Pro as they offer the choice to select CPU right ? This one ought to be the best one. Also realised my previous comment was a bit above dumb :p 
Score
0
a c 199 à CPUs
a b å Intel
August 25, 2013 11:35:31 PM

Duckhunt said:
Someone Somewhere said:
Intel can't really do much about forcing the industry to use more threaded apps.

Not their job to write code, other than drivers. They do make x86 Android though, because the drivers are pretty much hardcoded.

Do agree on the 1366x768 though. It's the same number of lines as XGA, just with a few pixels on the side. Maybe Intel should have forced a PPI measurement on Ultrabooks - that might have helped.


Whatever. Lets understand it. We have 10 million elite programmers. We have Intel. Where do you think the problem lies with threaded apps? The 10 million idiot programers who are obviously fools or One company that has a monopoly who has crap hardware. Answer that?


'Elite'? Think that's a bit of an overstatement.

The only ones who I would consider that actually should spend lots of time optimizing is when there is a ridiculous amount of processing going on. Wait, I just realized, Photoshop, Acrobat, HandBrake, etc. all are multithreaded.

For most programs, the maxim that programmer time is worth more than processor time is correct. Do you want Notepad to be rewritten to use all available threads?

The only thing intel can do is release things that make it easier to build your apps multithreaded - think, would you bother to include hashing in a website authentication system if you had to write your own implementation of SHA256?
Score
0
August 29, 2013 6:31:08 PM

the comments to this article REEK of the misunderstanding, either intentional (hoping/wishing/delusional dreaming) or unintentional (uninformed), regarding SERVER vs CONSUMER hardware.


Server/mainframe CPUs are TERRIBLE for video games. They are TERRIBLE for running just a few productivity programs like Word, Excel, several tens of browser tabs, a multimedia playback program, etc.


Secondly:

video games still lag horrendously behind software. No video game currently in existence can operate on all 8 threads of a 4 core hyperthreading Intel CPU. No video game currently in existence can operate on all 8 or 12 cores of an AMD or Xeon CPU.


This is because the programmers who write the software for the video game have not developed their software to utilize the super high parallel processing capabilities that have become inherent in semiconductor design (especially multiple distinct cores per die, cheating moore's law)


Video games are not the only class of software that lags considerably behind the current industry-wide hardware standards....

Even the most sophisticated software packages that are explicitly designed to run on 10,000+ core mainframes at LANL or Livermore or any research university, developed in house by a bunch of graduate students and post docs in materials science or ECE or something....

even that software never ever ever uses more than 66-75% of the total processor capacity.
Score
0
a c 199 à CPUs
a b å Intel
August 29, 2013 9:48:25 PM

Quote:
Server/mainframe CPUs are TERRIBLE for video games. They are TERRIBLE for running just a few productivity programs like Word, Excel, several tens of browser tabs, a multimedia playback program, etc.


Mainframe, yes. But mainframes are basically dead now.

Server chips are just desktop chips with ECC enabled, and in some cases a change in the core/clock/TDP balance. An a name and price change.

That doesn't make much difference, as both are more than fast enough.

EDIT: Webkit-based browsers would run beautifully on many-core CPUs; it's exceedingly well threaded.
Score
0
September 3, 2013 4:42:24 AM

Someone Somewhere said:
Server chips are just desktop chips with ECC enabled, and in some cases a change in the core/clock/TDP balance. An a name and price change.
You forgot about Virtualization Technology that's typically disabled on almost all of Intel's desktop chips.
http://www.cpu-world.com/Glossary/V/Virtualization_Tech...
Score
0
September 4, 2013 5:13:30 AM

Thanks for the link.
Score
0
a b à CPUs
September 5, 2013 12:23:00 AM

Someone Somewhere said:
List of all 22nm Intel chips with VT-d and VT-x enabled: http://ark.intel.com/search/advanced/?s=t&LithographyVa...

That looks like pretty much all their desktop chips. Exceptions are i3s, Pentiums, and Celerons. Some mobile chips too.

And you can add in the rest of them as well, if you take off VD-d – and a huge percentage of virtualisation doesn't need it, especially in a desktop rather than server/workstation environment.
Score
0
!