Microprocessor Report: Intel, Fix the PC!

[Star72]

"He criticized the fact that performance of CPUs isn't growing fast enough to find the interest of consumers."


I had to laugh hard at this because it certainly has nothing to do with the performance of the CPUs. Right now the average consumer wants mobility which doesn't have anywhere near the power of a desktop pc. In addition to that, when the average consumer is at home a pc with an average dual-core (from 2-3 years ago) is going to do the job for them, but they probably won't even use that in favor of a phone or tablet simply because they can't take it with them throughout their house & frequently "check in" regardless of where they are. It's not about power for the average consumer, they only care about power if it's in a mobile form. Also, I don't say "they" to sound negative, I just prefer my more powerful pc whenever I can use it & therefore don't consider myself as an "average" consumer.

 

[teodoreh]

Patents and lack of competition is the two main reasons that Intel don't care on stregthing their portofolio. They have great success improving the x86 architecture due to monopoly and huge cash of R&D money, but they failed on several other occations like VGAs and ultra low power processors.

By the time AMD presented the Bulldozer fiasco, Intel just slowed down their Ivy Bridge plans. And even if it wasn't the Bulldozer fail, after 486SX, Intel screwed the floating point unit, and *boom* 20 years later, GPUs arrive and say "do you want x10 speed on your PC"?.

Tbh, I don't believe Intel cares. They want to play on the brand new market of SSDs and ultra power processors. I just hope they won't buy NVidia or something - this will be the end of GPU development as well..

 

[Lord Captivus]

We dont have to forget that theres a natural limit for microprocessors.
How small can you get? How cool can you get? How fast can you get? Those are the questions at this moment.
If i came up with a new gadget it will probably increase performance quickly, the problem is that PC are already knocking on "not possible conditions".
Users have change, console players dont neet a lot power. I have a lot of friends coming to my home and saying: WOW!! This game looks so much better on your PC than it does on my console!!....
So??? My friends dont say: Ok, lets get a pc!...they dont. They know its "better", but they dont do anything, they dont care...and thats ok...sadly it affects PCs marke.

 

[cogito1965]

[citation][nom]wavetrex[/nom] A true 3D immersive user interface, fun to use (in which I could "walk" inside my computer's content and place and arrange items spatially)[/citation]

Hell, people can't even handle "tiles", nevermind a 3D interface!

 

[GreaseMonkey_62]

My problem is that I don't have enough Frakking money to do a decent upgrade. Between the bills and family and everything else I haven't done an upgrade in years. Of course my PC can still play any games I've thrown at it decently enough.

 

[GreaseMonkey_62]

We dont have to forget that theres a natural limit for microprocessors.
How small can you get? How cool can you get? How fast can you get? Those are the questions at this moment.
If i came up with a new gadget it will probably increase performance quickly, the problem is that PC are already knocking on "not possible conditions".
Users have change, console players dont neet a lot power. I have a lot of friends coming to my home and saying: WOW!! This game looks so much better on your PC than it does on my console!!....
So??? My friends dont say: Ok, lets get a pc!...they dont. They know its "better", but they dont do anything, they dont care...and thats ok...sadly it affects PCs marke.

Normal Silicon is reaching it's limit. They're going to need new material(s) or architecture. Quantum computing is still far off and nothing else promising is on the horizon.

 

[loomis86]

[citation][nom]GreaseMonkey_62[/nom]Normal Silicon is reaching it's limit. They're going to need new material(s) or architecture. Quantum computing is still far off and nothing else promising is on the horizon.[/citation]

There is no limit for the next 10 years at least.

 

[loomis86]

[citation][nom]Duckhunt[/nom]There is your problem. They pay the CEO and upper management too much. Then there is no money for R&D. We need to make the PC more energy efficient and also we need to make it do more. I want the manufacturers to start adding passive sensor technology on the pc gear. I want the BIOS to recognize these things. Where is the R&D to futher integrate the pc into the home. I want the pc to talk to the fridge, toaster,tv,fridge. I want the go home and say, TV turn on. Or maybe say " Computer what happened?" It goes through the video footage around the house and i know what happened.We can't have all this. WHy? The rich folk stole all the money. We bailed out the banks. We bailed out the rich folk. The rest of us can go to hell. YOu want to understand why the economy does not work? Simple. It works on credit. There is not wrong with that. The problem is when 99% of the people are not credit worthy enough to borrow any money ( get credit) the system falls apart.When we have a recession this is what happened. The only way to fix it. We need to redistribute the wealth by taxing. That simpleThey stole it. We tax it back. Under FDR we taxed the wealthy at 93%. We need to tax anyone with an income over US250k a year at 90% .[/citation]

wonderful!

If we had more people thinking like you we could be a third world hell hole just like the middle east and africa.

 

[wavetrex]

Hell, people can't even handle "tiles", nevermind a 3D interface!

Hehe, you're right on that one. Sometimes I forget how dumb most people can be...
Oh well.

P.S. - Haswell seems to be delayed ( again ) Now new desktop PC for me in the next 7 month... uhhh.

 

[InvalidError]

There is no limit for the next 10 years at least.

While the ultimate limits of silicon lithography may be ~10 years away, the stagnation for conventional desktop CPUs for anything other than transistor count has been going on for most of the past decade.

In the past, until about 2004, die shrinks used to mean 40-60% higher clock speeds but between 90nm and 22nm which is four process generations, there has been only a 30% increase there... and in terms of easily achievable OCs, many would even say we are starting to go backwards with Ivy Bridge. With essentially only architectural improvements to rely on since the Core2 in 2006 and for the foreseeable future, it is understandable that some people may feel like silicon has reached its limits - the stuff that can still be improved upon yields little to no obvious benefits.

Progress would be more obvious if desktop CPUs could afford sacrificing single-threaded ILP for multi-threading resources (put transistors into extra cores/threads/ALUs rather than extend the out-of-order structures to improve ILP by 2-3%) like what is happening in the server space. But since so few desktop applications/games make meaningful use of more than two cores/threads, such a desktop CPU would be obsolete long before a meaningful number of mainstream applications would make use of it.

You are right, things are improving. Just not in a way people notice or care (much) about and not as fast as they would like them to.

If AMD/Intel want to twist programmers' arms into embracing threaded programming on the desktop, they would need to bring something similar to Xeon Phi to desktop CPU sockets... so-so single-threaded performance but 16 cores and 64 threads.

 

[photonboy]

[citation][nom]Marcus52[/nom]The modern CPU and its supporting chipset are very limited as products for my purposes. There are too few PCI lanes, no on-board Thunderbolt support, and much is wasted by software engineers who refuse to take advantage of multiple cores, and it becomes apparent that the CPU and OS are going to have to force software into better performance by making use of the added cores themselves. The SATA 3 interface is already being saturated.The ATX mainboard form is sadly out of date, and there seems to be no mainboard manufacturer willing to support someone who might want to build a system with a decent RAID card, 3 graphics cards, and a decent sound card. If you want any one of those you are okay, but all 3, you are SOL.Could we get like at least a PCIe x1 slot above the first PCIe 3 x16 slot? Could we get some PCIe slots that aren't covered up by PCI x16 video cards? Hasn't anyone figured out a modern high end graphics card takes up at least 2 expansion slots worth of room?I have a 2560x1440 LCD that can overclock to 120Hz, and I'd like to run 3 of them in surround, but I'd also like to slap in a decent sound card, too. I don't really need a RAID card (well of course it's all one giant toy anyway, so I don't "need" any of it, heh), but I don't see why I can't build a high-end rig that's really high-end all the way. I could use the power today - and what will the future bring? What happens when we start getting real high-density monitors, capable of running decent refresh rates to support those high frame rates that give us nice smoothness when we pan our cameras in games?I'm looking forward to Haswell, but at the same time, I wish the whole industry would get out of yesteryear thinking and bring us into what we all know is possible.[/citation]

Plenty of ATX boards have a x1 PCIe slot as the first slot. You haven't looked very hard.
Plenty of ATX boards have eliminated PCIe slots below primary PCIe slots since they aren't needed.

Extended-ATX exists for those who wish a 3x Crossfire/SLI solution.
Extended-ATX exists with Creative audio solutions on the motherboard eliminating the need for an addon sound card.

Thunderbolt exist on several motherboards. I'm not sure of your issue with this.

RAID cards aren't that important anymore since good onboard RAID is excellent.

4xCrossfire/SLI is achievable via 2x (dual-GPU) cards.

SUMMARY:
Much of what you complain about exists or isn't a big deal. I think you misunderstand how quickly the software and hardware worlds work. Adobe for example, can't start optimizing code for OpenCL until it's actually released then it could take years to really make a big difference.

I'm really not sure why you think there SHOULD be a market currently for PC hardware to create a 3x 2560x1440 environment with RAID etc in one PC. Hardware and software are advancing at a pace dictated by the consumer. Triple-monitor support is coming, but's simply not a big deal for most.

Maybe you should look back 20 years and realize just how far we've actually come..

 

[InvalidError]

[citation][nom]photonboy[/nom]4xCrossfire/SLI is achievable via 2x (dual-GPU) cards.[/citation]
Some LGA2011 motherboard also support x16x8x8x8 for quad-GPU using single-GPU cards.

Some even have PLX's PCIe switch ICs to allow x16x16x16x16 but those motherboards cost around $600.

 

[Fulgurant]

[citation][nom]wavetrex[/nom]The problem is in the software and peripherals. I've been waiting and hoping for stuff like this for a long time:- Star-trek like voice recognition (ability to detect free speech of anyone without any training)- Star-trek like speech generation (natural voice, indistinguishable from a normal human voice)- A true 3D immersive user interface, fun to use (in which I could "walk" inside my computer's content and place and arrange items spatially)- Image content recognition (categorize my thousand photos by what's inside them, without forcing me to "tag" or "put in folders")- AI capability (let me talk with my computer and ask him his opinion on various stuff that he's aware of)- VR headsets for games and interactive movies (ability to watch a movie's action from the perspective I want, like in a ST holodeck)(and many more stuff we've seen in movies)We're still stuck with mouse/keyboard and clicking links and buttons on webpages. (Everything has just become bigger, to adapt to the higher resolution screens of today). Can't really call that progress...And now a tablet, small laptop or other internet-enabled device can do that, why on earth would a common person need many-core CPU's which eat 100-200Watts of energy in a big case, just to point and click on a website?Yes, give us software stuff that a tablet/small laptop CAN'T do, and we'll definitely buy new powerful desktop PC's ![/citation]

Submitted for your consideration:

Top 10 Movie UI blunders

2D is better than 3D

8 Characteristics of Successful User Interfaces

All of the stuff you list sounds very cool, but a lot of it really isn't practical for every day use. The mouse and keyboard may seem primitive, but they're (thus far) the best option we've conceived for general productivity.

True photo recognition would be great, though. Oh, and I could really use a holodeck.

 

[Fulgurant]

I have a 2560x1440 LCD that can overclock to 120Hz

That's pretty sweet. How much did ya have to up the voltage on that bad boy?

 

[photonboy]

That's pretty sweet. How much did ya have to up the voltage on that bad boy?

Those monitors are notorious for bad pixels and other failures. My Dell U2711 cost $900 on sale (probably TWICE the cost of the Korean versions) however it came with a 3-year warranty which replaced my monitor when it failed in ONE DAY at a cost of NOTHING (packaging and pre-paid waybill came with the replacement).

Dell has a similar 27" 2560x1440 monitor which just came out which is better and a couple of other companies have them but you're talking $800 to $1000 for most of them. Still, it's worth it to me.

For under $700, this new monitor from Dell is truly awesome (with a great warranty):
http://accessories.dell.com/sna/products/Monitors_Flat_Panel_Widescreen/productdetail.aspx?c=ca&l=en&s=dhs&cs=cadhs1&sku=225-4015&~ck=baynoteSearch&baynote_bnrank=2&baynote_irrank=0