Feature Article

The Past, Present, and Future of the CPU, According to Intel and AMD

Power trip.

Ten years ago, if you were to buy the best CPU for gaming or otherwise, you'd have chosen AMD's Athlon 64. My, how times have changed. While AMD has struggled to rekindle its glory days as the CPU-performance leader, Intel's CPUs have gone from strength to strength over the past decade. Today, Intel's CPUs perform best, and use the least amount of power, scaling admirably from powerhouse gaming PCs all the way down to thin and light notebooks and tablets--segments that didn't even exist a decade ago. But this return to CPU dominance might never have happened had it not been for the innovations taking place at AMD back in the early half of the 2000s, which makes the company's fall from grace all the more galling.

The 64-bit extensions of AMD's Athlon 64 meant it could run 64-bit operating systems, which could address more than 4GB of RAM, while still being able to run 32-bit games and applications at full speed--all important considerations for PC players at the time. These extensions proved so successful that Intel eventually ended up licensing them for its own compatible x86-64 implementation. Two years after the launch of the Athlon 64, AMD introduced the Athlon 62 X2, the first consumer multicore processor. Its impact on today's CPUs cannot be overstated: everything from huge gaming rigs to tiny mobile phones now use CPUs with two or more cores. It's a change that even Intel's Gaming Ecosystem Director, Randy Stude, cited when I asked him what had the biggest impact on CPU design over the last decade.

Cores

AMD's Athlon 64 kickstarted the 64-bit revolution. Image credit: flickr.com/naukim

"So, the answer to the question is cores," Stude tells me. "I was here at Intel through the Pentium IV days. We hit a heat issue with that part and took a big right turn and introduced a very efficient product out of Israel [the Core CPU] that helped us take over performance leadership that--for the most part--we've enjoyed for the better part of a decade. We've been able to add cores quite efficiently, and that's led to some substantial performance gains for the PC in general."

This focus on cores has dominated the last decade of CPU development. Prior to the introduction of multicore CPUs, the focus was very much on increasing clock speeds. This gave games and applications an instant performance boost, with very little effort required from developers to take advantage of it. Moore's Law--which states that the number of transistors in a dense integrated circuit would double around every two years--was in full swing in the 90s and early 2000s. In the period from 1994 to 1998, CPU clock speeds rose by a massive 300 per cent. However, by the mid 2000s, power consumption and clock speed improvements collapsed, with both Intel and AMD fighting the laws of physics. The solution was to introduce more cores, so that multiple tasks could be executed simultaneously by individual CPUs, thus increasing performance.

The trouble is, unlike increasing clock speed, increasing the number of cores requires developers to change the way their code is written in order to see a performance increase. And, in the case of games development, that's been a slow process.

Games like Battlefield 4 that make use of multiple CPU cores are still the exception, rather than the rule.

"[Multicore CPUs] have required that the software industry come along with us and understand the notion of threading," says Stude. "For gaming, it's been challenging. Threading on gaming is a much more difficult scenario that both us and AMD have experienced. In general, you've got one massive workload thread for everything, and up until now that's been handled by, let's say, the zero core. The rest of the workload, whatever it might be for a particular game, goes off to the other cores. Today, game engine success is a bit hit and miss. You have some games, the typical console games that come over, that don't really push performance at all, and isn't threaded or lightly threaded."

"[Multicore CPUs] have required that the software industry come along with us and understand the notion of threading. For gaming, it's been challenging." - Intel

"The nature of development work for those platforms, especially in the early years, is that you'd get your game running and publish it and you'd rely heavily on the game engines that you as a publisher own, or that you acquire from third parties like Crytek and Epic," Stude continued. "If Epic and its Unreal engine on console don't have a threaded graphics pipeline--which to date they don't--then you're looking at the same issue that you see on the PC, which is a heavily emphasised single-core performance workload, and then everything else that happens like physics and AI happens on the other cores. It's not a completely balanced scenario, because by far the biggest workload is that render pipeline."

The problem has been more pronounced for AMD. Its Bulldozer CPU architecture (which all of its recent processors are based on modified versions of) tried to both ramp up clock speeds by lengthening the CPU’s pipeline, increasing latency (an approach not too dissimilar to the disastrous Prescott Pentium 4 from Intel), and by increasing the number of cores by sharing resources like the scheduler and floating point unit, rather than by duplicating them like in a standard multicore CPU. Unfortunately for AMD, Bulldozer's high power consumption meant that clock speeds were limited, leaving the CPU dependent on software that made use of those multiple cores to reach acceptable performance. I asked Richard Huddy, AMD's Gaming Scientist and former Intel and Nvidia employee, whether chasing more cores was the right decision. After all, to this day, Intel's Core series of CPUs consistently outperform AMD's.

"So if you talk to games programmers--there are other markets as well--they have typically found it easy to share their work over two, four cores," says AMD's Huddy. People have changed the way they program for multi-core stuff recently over the last five years to cope with six-eight cores. They understand this number is the kind of thing they need to target. It's actually genuinely difficult to build work-maps of the kind of tasks you have with games to run on something 32 cores or more efficiently."

AMD's Richard Huddy had a hand in creating Direct X, as well as stints at ATI, Intel, and Nvidia.

"The more cores you have, the harder it gets, so there is a practical limit," continued Huddy. "If we produced 1000-core CPUs then people would find it very hard to drive those efficiently. You'll end up with a lot of idle cores at times and it's difficult. From a programmer's point of view it's super-easy to drive one core. So yeah, if we could produce a 100 GHz single-core processor, we'd have a fantastic machine on our hands. But it's mighty difficult to clock up silicon that fast, as we're up against physical laws here, which make it very difficult. There's only so much you can do that ignores the real world, and in the end you need to help programmers understand the kind of constraints they're building to."

"I'd love for us to build a single-core CPU. Truth is, if you built a single-core CPU, that just took all of the power of the CPU and scaled up in the right kind of way, then no programmer would find it difficult to program, but we have to deal with the real world."

The Death of Moore's Law?

The real world is Moore's Law, or rather, the end of it. The death of Moore's Law has been talked about on and off for years, and yet Intel and AMD have continued to see significant performance boosts across their CPU lines. But the upcoming launch of Intel's Broadwell architecture and its die shrink from 22nm to 14nm has seen several delays, prompting many to call out the death of Moore's Law once again. Certainly, both companies face a number of technical challenges when working at such small manufacturing processes. Intel, for example, developed its 3D Tri-Gate transistor technology--which essentially allows three times the surface area for electrons to travel--to deal with current leakage at 22nm and beyond.

"For the last decade--which is a strong portion of our existence, the dominant decade in terms of our revenues and unit sales--we were told Moore's law was dead and that the physics wouldn't allow us to continue to make those advances, and we've proven everyone wrong," says Intel's Stude. "I'm a futurist as a hobby, and I've learned a lot being at Intel. The day I started we had introduced the Pentium and even then the conversation was about what was possible from a die shrink perspective. I'm not ever going to believe in my mind that the pace of innovation will outstrip the human brain."

"I just don't subscribe the concept that there isn't a better way. I think that evidence of the last 50 years would argue that we've got a long way to go on silicon engineering. What we think is possible may completely be eclipsed tomorrow if we find a new element or a new process that would just flip everything on its head. I'm not going to play the Moore's Law is dead game, because I don't think it will be dead. Maybe the timeline slows down, but I just can't subscribe it dying based on what I've seen at my time at Intel."

Intel's "tick-tock" strategy has helped the company stick to Moore's Law, but how just long can it last?

AMD's Huddy shares a similar viewpoint: "Moore's Law looks alive and well, doesn't it? It's always five years from dying. For all practical purposes, I expect us to live on something very much like Moore's Law up until 2020. Our biggest problem is feeding the beast, it's getting memory bandwidth into these designs. I want the manufacturers of DRAM to just keep up with us, and give us not only the higher density--and they do a spectacular job of giving us more memory--but also make that memory work faster. That's a real problem, and if we could just get a lot of super fast memory and not pay the price of that wretched real world physics that gets in the way all the time. I blame them, it's all down to DRAM!"

Better Integrated Graphics

While cores have dominated CPU development over the last decade, both AMD and Intel have made great strides in bringing other parts of a system onto the CPU to improve performance and decrease system size, most notably with graphics. Until recently, Intel's integrated graphics were considered a poor choice for gaming, with performance that was only really good for rendering the 2D visuals of an operating system, rather than sophisticated 3D graphics. But this has changed of late. While Intel's Iris Pro integrated graphics can't compete with a separate GPU, they are able to run many games at acceptable frame rates and resolutions. There have even been some neat small-form-factor gaming systems designed around Iris Pro, such as Gigabyte's Brix Pro.

But when it comes to integrated graphics, AMD is far and away the performance leader. The company's purchase of ATI in 2004--despite some integration issues at the time--has given the company quite the performance lead; AMD's APU range of CPUs with built-in Radeon graphics are the best choice for building a small gaming PC without a discrete GPU. It might be just a small win for the company on the CPU side, but it's one that has had a significant impact on the company's focus.

"We took a decision 18 months ago to focus heavily on graphics IP," says Darren Grasby, AMD's VP of EMEA. "Driving the APU first, first with Llano, and fast forward to where we are today with Kaveri. Kaveri is the most complex APU ever built, and if you look at the graphics performance within that, you're not going to get the high-end gamers with that. But if you look at mainstream and even performance gaming, an A10 Kaveri is your product to get in there. And you don't have to go spend $1500 or $2000 dollars on a very high-spec gaming rig, that quite frankly, a mainstream or performance gamer isn't going to be using to its full capability."

"If you think about it from a gaming aspect, what are gamers looking for? They're looking for the compute power from the graphics card. The CPU almost becomes secondary to it in my mind." - AMD

"So you're right on the ‘halo effect’ on the CPU side," continued Grasby. "Obviously we can't talk about forward-looking roadmaps, but it's leaning into where the graphics IP is, and where that broader market is, and where the real revenue opportunities sit within that. That's why, if you look at Kaveri, if you look at the mass market and gaming market you're getting right up there. Then you start to get into 295 X2, and then you're talking about where the gamers are. If you think about it from a gaming aspect, what are gamers looking for? They're looking for the compute power from the graphics card. The CPU almost becomes secondary to it in my mind."

The Growing Threat of ARM and Mobile

While Intel continues to lead on pure CPU performance and AMD leads on integrated graphics, both companies have stumbled when it comes to mobile, which is problem as PC sales continue to decline. All-in-one system on a chip designs based on designs from the UK's ARM Holdings power the vast majority of the world's mobile devices--and that doesn't just mean cellphones and tablets; Sony's PlayStation Vita is built on a quad-core ARM chip. Intel has tried to stay the course with X86, creating the Atom line of processors specifically for low-power devices like phones and tablets. They haven't exactly set the world on fire, though. Intel's Mobile and Communications group lost over $900 million earlier this year.

AMD, meanwhile, took a different path and signed an ARM license to begin developing its own ARM processors. The question is--with the vast majority of the company's experience being in X86 architecture--why?

Phones and tablets like the Nvidia Shield mostly make use of ARM processors, rather than the traditional X86-based designs that AMD and Intel produce.

"Did you see Intel's earning results yesterday? [Note: this interview took place on July 17, 2014] Just go and have a look at their losses on mobile division," says AMD's Grasby. "I would suggest at some stage their shareholders are going to have a challenge around it. I can’t remember the exact number, it’s on public record, but I think it was 1.1 billion dollars they lost on 80 million dollars of turnover. Our clients suggest that isn’t the best strategy. I encourage them to keep doing it, because if they keep losing that amount of money, it’s definitely not good...the primary reason why we signed the ARM license was because two years ago we bought a company called SeaMicro. We were basically after its Freedom Fabric [storage servers], and that’s why we signed the ARM licence, to go after that dense, power server opportunity that’s out there. It’s a huge opportunity."

"As soon as we got the ARM 64-bit license, other opportunities opened up on the side. Think embedded, for example. Embedded from an AMD perspective had always been an X86 Play. Just to give you an idea, ARM and X86 are a nine to ten billion dollar business. Take ARM out of that it comes to around four to five billion dollars. It’s to exercise the opportunity."

PC Market Decline

Despite AMD's efforts, though, its ARM strategy and planned turnaround hasn't gone entirely to plan. The company posted a $36 million net loss in its recent financials, and predicted that its games console business to Sony, Microsoft, and Nintendo--which, to date, has been one of its biggest successes--would peak in September. Shares plummeted by 18 percent after the announcement. The still declining PC market means both Intel and AMD are looking for ways to expand beyond the desktop, but the companies maintain that their CPU lineups, and in particular their CPUs aimed at gamers and overclockers, remain an important part of what they do.

Despite a decline in recent years, overclocking is still alive and well.

"The overclocker market certainly is relevant," says Intel's Stude. "Every time we come out with a part there's a fraction of a fraction of people that are the utmost enthusiasts. They care about every last aspect of that processor and they want to want to push it to the limits. They are tinkerers, they don't mind buying a handful of processors to blow 'em up just to see what they can do, and to make their own living, be it working in Taiwan for the ODMs who make motherboards, or be it in other capacities in the media to submit their opinions on Intel's top end parts."

"We love the boutique nature of it," continued Stude, "because the people in that seat typically have very interesting compute perspectives that influence the decisions that others make. So, if you're very overclockable, you have a very influential position...so we do the best we can to feed this community our best story and we'll continue to that."

While there's no doubt AMD CPUs offer excellent value for money (we used one to great effect in our budget PC build), they still lag behind Intel when it comes to outright performance and performance per watt; to stay in the PC market, AMD has a much tougher job ahead of it then its rival.

"From an engineering perspective, performance per watt becomes the limiting factor in a lot of situations so there's no doubt that we need to do a better job," says AMD"s Huddy. "It's very clear that Intel and Nvidia, and everyone that competes in the silicon market has to be more aware of this. If you go back 10 and in particular 20 years ago, performance per watt, wasn't a big issue, but it increasingly is, and we aim to do better. I have absolutely no doubt about that. There's a lot of attention being paid to that. There are limits over how much we control our own destiny, but particularly for us where we use companies such as TSMC as others do, then those companies work with the same constraints as us and we should be able to just match them."

"From an engineering perspective, performance per watt becomes the limiting factor in a lot of situations so there's no doubt that we need to do a better job." - AMD

AMD Bets On Mantle

The future for AMD may lie in more than just hardware too. Mantle--its competitor API to OpenGL and Direct X--allows console-like low-level access to the CPU and GPU, and it's clear from speaking to the company that it has a lot of hopes pinned on the technology, even if Microsoft's upcoming Direct X 12 promises to do something very similar.

"It's very clear people have seen there's an artificial limitation that really needs to be fixed, and it's not just about giving you more gigahertz on your CPU," says AMD's Huddy. "We can be extremely proud of Mantle, getting the CPU out of the way when there was an artificial bottleneck. There's no doubt that people will use the extra CPU horsepower for good stuff, and we're seeing that in the demos that we're already able to show. However, let's not get hung up on gigahertz, sometimes it's smarts that get you there, and if you're looking for the fastest throughput API on the planet, then you'd have to say it is Mantle, and you'd have to say 'okay, now I get why AMD is leading the way', don't just count the CPU gigahertz, but look at the technology innovation that we're coming up with."

"Amusingly, and I don't know how relevant it is, you can make your own decision on that, for me it's entertaining: one of the companies that approached us [about Mantle] was Intel, and we said to Intel, 'You know what, can you give us some time, to fully stabilise this because this has to be future proof, but we'll publish the API spec before the end of the year.’ And if Intel want to do their own Mantle driver and want to contribute to that they can build their own. We're trying to build a better future."

For more on AMD's Mantle, and why the company thinks Nvidia is doing "something exceedingly worrisome" with Gameworks technology, check back later in the week for our look at the developing war between PC graphics most prolific companies.

Written By

Discussion

231 comments
Tuckpoint
Tuckpoint

With as much complaining as I do about the quality of the articles on this site, I think it only right that I applaud the good examples.  Good read, Mark, thank you.

taker254isback
taker254isback

How about a DUAL INTEGER CORE on a BIGGER die fed off by a Bulldozer/Piledriver type module? Like a Pentium G3258 cores built into the FX8350's 4 modules.

blackeagle84
blackeagle84

Intel is going down hill, their Baytrail is a real POS and their Cherry trail, being 14nm gate size, is hitting a brick wall due to low yield from the fab. The only edge Intel has for now, is their fab, they are only surviving because of 1. The only 10nm Fab in the world, 2. server market.

wowwow27
wowwow27

the icore's have been around forever it seems (in cpu years).  I'm actually surprised we don't see something like a full scale desktop with arm processors.

TotalWarHero
TotalWarHero

Just wanted to drop by to say this is excellent journalism.  Well sourced, well thought out article that is too rare these days not just on Gamespot but the internet abroad.  Great work Mark!

rhymesmatter
rhymesmatter

I have an 8 Core Vishera OCed to 4.60 ( i was lazy to juice it up to it's limit) from the stock 3.50 ! Performance wise Intel is still beating my ass to a pulp but there is a huge difference to that : People (like me) that bet on value for money 8core system will rip their rewards post Xmas when good ol' Nvidia and ATI will be FORCED to give us drivers " optimized for 8 cores" and then you'll see the huge gap between 8 cores of the cheaper piledriver based than the expensive 4core i7 ( current gen) Pretty much what happened with the jump from 2 to 4 cores when ppl were mocking the mates that were investing to 4cores because dual cores were dishing out more frames (due to games being optimized for those rather than 4cores) and overnight optimized drivers came out and they were biting their lips!

Consoles wear 8cores and let's face it , 80% of games are heavily manufactured based on consoles or even worse PORTED from them! It's only a matter of time before full optimization for 8 cores come and then i will smile grandly for my trusty AMD !
Having that said the day that Intel 8 core releases (and if they make it accessible value-wise which i doubt) then we will be back to the same situation: Intel beating the crap out of AMD on CPUs

omNOMinator
omNOMinator

The growth in performance from ARM and Imagination Technologies' chips is so much faster than that of Intel of AMD. Both companies claim the next generation of their technology coming next year will be on par with the PlayStation 4 (my dad works at ImgTech as a senior design engineer).

And so, quite soon AMD and Intel will be pushed out of the market by ARM/Imagination due to the massive increase in efficiency that they provide in terms of space, power, heat dissipation etc. 

In other words, computers are getting smaller and cooler and Intel are way behind.

Amaregas
Amaregas

We are more software limited than hardware

ktseymour
ktseymour

I know the author knows this but , Intel did not win the cpu war . Intel won the dirty under handed business war and set back tech and cpu tech in general for decades. If the so called Free Market truly was free this would be a different story.

I wont support or buy Intel , they are the perfect picture of the person who couldn't compete , and cheated. On the surface these people or companies look like smart and savvy business winners, but the truth is much more scummy then 99% of people know. The real story is Intel was really good at strong arming the retail chain ,and partners, and back ally deals then actually competing on fair ground.

Sad fact,most successful people or companies don't get to the top because they were smarter or better. Business and life are dirty, and you don't get to the top Hallmark/ABC special style. You get there by being a son of a b*%ch!

skopas
skopas

...It's funny how the article starts with saying Intel this and that.  But when you think about it, it's a debatable situation.  Intel would win this hands down if they kept the prices in reasonable range.  AMD on the other thinks smarter.  They're cpu's are a bit slower but with that the prices are incredibly affordable. Take the FX-6300 6 core it's over clocked to 4.1 ghtz right out the box for $100 bucks, and its a black edition so you can continue feeding the beast. With all that and enjoy doing everything a Intel processor does be it games or apps.  Overall Intel and AMD need to put they're heads together to keep the PC genre alive and kicking for the years to come.  But a little competition never hurt no one and makes us the consumers the winners.

saturatedbutter
saturatedbutter

Make the CPU hexagon shaped instead of square. Hexagons are futuristic and advanced.


I know this because video games.

leandrro
leandrro

CPUs are not about who produces the fastest processor, anyone can produce a monster for $10.000 that will beat anything

its also not only about power consumption, a i3 and a athlon 740k; also a i5 and a fx-6300 have both about the same performance and TDP

the real winner is the one that is able to sell the fastest processor for the lowest price, this means they have the lead on that technology and are able to produce with less cost

AMD dominates low and mid-end market, intel gets the high-end but not by much 

firsTraveler
firsTraveler

How about adding that new IBM brain chip?  Maybe games could have not-horrid ai.

sammoth
sammoth

I have to give everyone who posted here kudos for being level headed. It's such a good article by Gamespot and takes us PC enthusiast away from the long drawn out console wars on this site.

Great post everyone nice to see some intellectual debates than pointless dribble.

Gegglington
Gegglington

good article i dunno why i choose amd over intel same as i always buy nvidia gfx cards one of those things i guess ive stuck with. my last intel pc rig i had was a pentium 2 single core 0.60 mhz it was the dogs danglies back in the day :)

wexorian
wexorian

In few day's intl going to announce next generation CPU, new standarts inc.

Great article good job 

BehemothBlade
BehemothBlade

AMD boasts HSA in their Kaveri APUs.

But the thing is, softwares are not optimized to take advantage of that yet.

Cronyk
Cronyk

They say "the biggest problem is feeding the beast" (talking about RAM) but end the discussion only a few lines later. Would've liked to learn more about this factor. For example, whats the difference between faster RAM and simply more ram? Is it the same silicon heat restraints keeping RAM from getting faster?

intotheminx
intotheminx

I believe the future of gaming is integrated graphics. The Iris Pro 5200 for Intel was a big step in the right direction. It is capable of 1080p gaming in a lot of cases, but isn't quite there yet. Hopefully the Iris Pro 6200 will see a 30%-40% boost in performance. That would make it capable to play a game like Crysis 3 at a 1080p resolution. If you've never built a PC before it can be a daunting task to select the proper parts. AMD and Intel need to up their igpu to a mid level range so people can stop worrying about GPU's and such and have the ability to just buy a Desktop. A strong igpu in a pre built desktop for a reasonable price could boost sales imo.

valkyr_anubis
valkyr_anubis

I personally find it very amusing and interesting to consider the whole situation of Intel's and AMD's CPU development and what paths they might choose in the future. Kinda funny to think of it, when I got my first own PC, it had a AMD Athlon 64 3200+ CPU and most of the time I used this CPU for games like UT2004 and Doom 3. However, today I got Intel Core i5 3450 and to compare these CPUs is pure madness somehow. I mean, the time difference is only something like 8 years (release), but if you consider the technology, they achieved so very much and they done a good job. Of course, there are many other CPUs on market, which are much better and faster than my own one, but I'm happy with it.


What I wonder about is, if the developer can get a better CPU optimization done. I don't play all current games, not even a hand full, but it is kinda interesting to see, how a application uses your CPU cores. However at this point, you also have to pay attention to the fact, that it is not that piece of cake to get this done. I remember talking about this at school and we only scratched the tip of the iceberg. Interesting indeed, but also pretty complicated, but it is not something you can force. It takes time. Looking forward to see how this thing turns out in case of 6 core and even 8 core CPUs. Having a 6 or 8 core CPU is indeed very much fun, but does any game really require this? I'm not really sure about this!


In the end, I'm really looking forward to the future. Let's see how DX12 turns out, more use of Mantle, which next step CPU development might take, etc. Despite that, I never really got the point of this Nvidia Gameworks business and why AMD is worried about it to be something negative. How many games use this Nvidia Gameworks? Not that many, aye.



suppaphly42
suppaphly42

so about ten years ago intel was playing around with using diamonds instead of silicon because it can endure 2-4 times the heat and get speeds in the range of 81ghz.

now here we are 10 years later and still no diamond based cpus  if they wish to keep moores law intact then should they not be pursuing this.

ArabrockermanX
ArabrockermanX

I just want IBM CPU's to join the home PC market then we'll have an actual competition and cheaper prices. Currently it is like Intel and AMD decide to to really compete against each other(1 takes the high ground other takes the low ground)...

wowwow27
wowwow27

@Amaregas that won't stop em' from making you feel like you need to go out and buy new hardware for the latest releases.  (I'm still using a q6600 desktop for my design work).

brockelley
brockelley

@ktseymour Exactly, Moore lived in a time when technological advancements meant saving millions more lives; nowadays, the only thing that matters is padding the bottom line.


Just like the constitution needs serious work, so do our dogmatic rules that frame the human condition as constant.

kolz4ever
kolz4ever

@ktseymour So then basically they won the cpu war.. Cry some more noob while us intel people will always have the better cpu. ;)

Zhyr_
Zhyr_

@skopas It's kinda bugged me for ages that AMD claims 6-8 cores when they're not true cores. Intel could claim 8 cores just as easily instead of hyperthreading. 

"Its Bulldozer CPU architecture (which all of its recent processors are based on modified versions of) tried to both ramp up clock speeds by lengthening the CPU’s pipeline, increasing latency (an approach not too dissimilar to the disastrous Prescott Pentium 4 from Intel), and by increasing the number of cores by sharing resources like the scheduler and floating point unit, rather than by duplicating them like in a standard multicore CPU"

wowwow27
wowwow27

@saturatedbutter they would have to go in all three dimensions if they decided to take that route, like a crystal, whats up?

suppaphly42
suppaphly42

@leandrro well the 4770k and 4790k are not that pricey and bang for your buck are not bad either so yeah things are close but intel still leads but as you said not by much.

 but then things are getting to the point where we need a complete flip on its head innovation in order to regain the jumps of the late 90's early 2000's 

brockelley
brockelley

@firsTraveler idk, a few user created mods I've seen make NPCs rather difficult, rather intelligent.

DanGleeSack
DanGleeSack

@xantufrog It is very cool. I might be perusing a masters in neural engineering once I finish up my undergrad as I have always been interested in how the brain works and related biochem too. 'Smart drugs' do seem to be shaping up better as well, at-least for healing damaged brains. Our brains are essentially electrical circuits that are driven by the electric (action) potential created by calcium/potassium/sodium/chloride transfer. It applies voltage in the same way (on or off) to interact at synapses. Charge builds up on either the inside or outside of cell membranes to drive the interaction in the way it wants to. Ions are at the heart of our brains, the same way the transistors in our electronics are driven by the ions within the doped substrates. Very simplified, but I think that is the basic concept of how they work. 


I looked at your article, it was interesting. The 70mW power consumption comes from the power that our brain cells (simplified) generate in real life, about 60-80mW. It is still a silicon based chip however, but it is a good step into pushing the most we can out of the technology while we are working on completely new ways.

Look up DNA computation and quantum computing as well, they both have the power to do computations fully parallel (as they are 3D concepts/structures). I believe they actually used salmon DNA integrated with a silicon chip so far. This means that they will be magnitudes more powerful and even smaller than anything we have today. It can also easier make integration with say prosthetics or implants a lot better. Most importantly, they will be powerful enough to perhaps begin to model how our brain works. Even our best supercomputers can only run a basic simulation for a very short period of time, from the last I had read about it.

suppaphly42
suppaphly42

@Gegglington thats funny that you would choose and amd cpu but not an amd gpu one would think they would work well together, and a bit less well when not paired up but i guess they don't ;)

suppaphly42
suppaphly42

@Cronyk my guess is not yet as gddr5 ram is in the 5000+ mhz range and ddr3 is in the 3000+ mhz range so i'm guessing it is a problem with getting a memory controller on the die that small that can handle it but then i don't know that much about this stuff and if someone knows for sure i would like to know

Tabarnaque
Tabarnaque

@intotheminx The GPU is about the only part gamers look at when choosing a prebuilt, no one is annoyed to look  a graphic card, it's part of life, and shoving two huge blocks of fans and computer chips together in SLI or Crossfire is part of the fun when building, if everything is integrated, there is no more choice, well like a prebuilt, but building your PC the entry test to the Master Race.

DanGleeSack
DanGleeSack

@intotheminx That is a tall order. Games are pushing a lot of pixels around now, just wait till 4K starts to hit mainstream. The dedicated GPU allows a much more doable process as it has its own bank of fast and dedicated memory and the ability to perform calculations internally parallel and independent of the CPU clock. This frees up a lot of your CPU for the number crunching, while letting the GPU handle rendering and maybe some physics. I really don't see integrated graphics ever being anything past something just to let people be able to use a desktop for non-gaming purposes. Even if we could reach GPU levels now on a small integrated chip, it would still never be as good as what we could achieve in a GPU.

DanGleeSack
DanGleeSack

@suppaphly42 They are very expensive and the diamond has to be very very very chemically pure so it can be doped correctly to create a p-type substrate. The issue is also creating an n-type substrate to form the transistors, as you need both types of doping to create the potential. You also have to be careful with the radiant heat frying everything else on your motherboard. We have pretty much pushed our silicon MOSFETs to their physical limits so they are working more with stacking and better architecture.


Not sure how well we can create synthetic diamonds, but if that improves, this might become more commonplace, along with diamond coatings to create stronger and lower friction parts.

DanGleeSack
DanGleeSack

@suppaphly42 @Cronyk Well its too complicated to really give you a good answer here but I'll try. Memory is the ability to store data as bits (1s or 0s; ON or OFF). Bits can be moved(shifted) in either serial (one after another) or parallel methods (a group at a time). Memory is also not just the storage of the bits, but the ability to read/write the bits using decoders/refresh counters/data selectors/registers/buffers/ect. depending on your type of memory. Your CPU has a clock rate, which is what times the transfer of bits around; it is the brain of your computer while the motherboard is the body. All your components are tied to this in a sense, even if they are faster the data is not read until the proper cycle, that is partly why faster CPUs can perform more calculations. I'd be writing a textbook if I went into what everything was, but they are things you can look up if you are interested. My Digital Fundamentals by Floyd book served me pretty well in my courses if you can find it online or in a library. 

It is mainly the architecture of how memory works; there are different types of RAM, that work in different ways. There is asynchronous and synchronous static ram and then there is dynamic ram with many subsets, there is there is solid state memory, there is High Density RAM. These use either transistors/capacitors or flip-flops (a Boolean logic gate setup). There are even newer developments such as purely silicon based RAM or even organic DNA based memory. Can't go into it here, and I wouldn't even be able to necessarily tell you everything so these are just things to try to look up on your own. If you can find the logic diagrams and schematics it might help. Don't worry you don't need to be an engineer to get at least a basic understanding.


Anyways, more RAM only gives you the ability to store more bits, while faster RAM means that read/write speeds might be higher or it has a more efficient architecture; such as having a cache that stores frequently accessed data or tries to generate future dependencies/calculations based upon what is happening at the moment (pre-fetching). Sure you can just keep stacking more RAM on, but it depends on 1) if your OS will address that much 2) if you program is coded to request that much from the OS and 3) the physical limitations in the form of clock timing, internal latency, and the speed of the actual wiring/components 4) any others I'm forgetting right now. Just shoving in more really accomplishes nothing tangible at this point; so they are working on making faster and more efficient designs.


Your PC is most likely using DDR SDRAM, double date rate synchronous dynamic random access memory. 

The double data rate part means that it transfers on both the rising and falling edge of the clock cycle (picture a line that starts at 0 and goes to 1, rises up, goes over a unit, then down and continues the line; this pattern is repeated in the same frequency as your CPU; this is the clock cycle). This means it address memory at two times per clock cycle 

The synchronous part means that it is timed to read/write at the same cycles as your CPU clock. This means you don't have to have extra buffers to feed data in the correct order and at the time that it will actually be read.

The dynamic part means that this form uses a transistor and a capacitor sequence to store electrical charge. The transistor acts as a gate while the capacitor is like a little bucket to hold an electron. If it is 'full' it sores a '1', if it is 'empty' it stores a '0'. This charge decreases over time (milliseconds), so it must be refreshed every once and while to keep the stored bit value correct. This means you need your CPU or a memory controller in the chip to keep recharging every capacitor with a '1'.


Some have features such as error correction which takes extra space to check values essentially. 


So in the end, silicon is partly responsible for the speeds (as it is in the transistors), but there is a lot more going on as well that determines efficiency. I say efficiency over speed, because more speed in computers isn't necessarily beneficial on its own. It also depends on the other components and coding (OS and micro-coding) as well. This is why people talk of CPU bottleneck (overblown on this forum). Once we more to a new form of RAM to use, things will get a lot faster, although motherboards will have to change as well. Sorry if this is a little disjointed or not fully correct, it was done quickly, but its a s

tr4newreck
tr4newreck

@DanGleeSack aren't artificial diamonds too perfect, a discerning feature, and dead giveaway for a jeweler.


and they are made en masse, many industries require either pieces, or dust of diamond, for cutting and drilling tools/equipment


but  the heat wash issue seems like a damning problem

suppaphly42
suppaphly42

@DanGleeSack @suppaphly42 so i looked up all of that before i made that post and you are right on all points but one.

there are a few  companies who make diamonds and with the right infrastructure they could be on par in price with silicon now i don't know how much adding the dope will cost and that might be the problem. 

thank you for responding  

mbloof
mbloof

@DanGleeSack @suppaphly42 @Cronyk  Put simply, a "CPU" (central processing unit) requires instructions and data to work with. Both of which need to be "read" into the CPU and at some point the data needs to written out and ether used or stored somewhere.


Since almost forever a CPU can execute instructions in less time than it takes to read both the instructions and the data and write the result back out.


All the CPU vendors have gone to great lengths in the past to make their parts "process" information as quickly as possible however getting that information to/from your screen, USB port, SDD/HDD or even the (mostly) computers main memory has become problematic.


Modern computers have ginormous amounts of Random Access Memory (RAM). Much of it is used to cache information coming to/from even slower devices such as HHD's and even modern SSD's however even with 16, 32 or even 64GB of RAM for storing entire applications and all the data a "bottle neck" will always form at the weakest link - namely in modern times between the CPU and main memory.


When DDR4 is pushed into the main stream it will help a bit but unless CPU makers start including ginormous GDDR5/GDDR6 on die "cache" to help feed data and instructions to the CPU's there's not much sense in making the CPU's faster.

suppaphly42
suppaphly42

@DanGleeSack @suppaphly42 @Cronyk whoa that is a lot to read and i did read all of it. that was very insightful and addressed, many of the things i did not know what they meant some i did know. as i am interested in this stuff as a hobby i will look into what you suggested. my thanks  

 i myself have been wrestling with whether i should keep my 2400mhz ram at its stock speed or drop it to 1866 and get a better cas latency, it is for mostly gaming and i got it before i found out the 1600mhz is ideal for gaming. latter i saw some benchmarks the suggested that 1866 was better so i thought that 1866 with a lower cas latency  would be better since you have way more knowledge in this field then me maybe you can tell me if what i have found is correct        

DanGleeSack
DanGleeSack

@tr4newreck Yeah I believe that is an issue for cosmetic reasons, it looks too artificial, although now even some jewelers are having a hard time because they can approximate the natural conditions better and use different components. 


You would still need the diamond dust I'm sure for the transistors, but that shouldn't be too big of a problem. Synthetic diamonds are softer than real diamond, so a diamond drill and/or heat should be able to grind them down no problem while keeping impurities to a minimum. 


Again the real issue comes down to the composition of the material; it has to be almost an 100% pure element so that you can reliably dope (introduce impurities, in the form of another pure element, to allow for free and bound electrons) the substrates. It is that potential that allows current to flow with applied voltage. Unaccounted for impurities can potentially harm sensitive electronics that must operate within a finite range of voltage/current/heat.

DanGleeSack
DanGleeSack

@suppaphly42 No problem, I'm studying for an engineering and physics duel degree, so figured I'd give my 2 cents. Had a class on transistors/semi-conductor physics and it really only went into silicon based components due to time. That's cool what you found, maybe there is good hope in new technology coming public

DanGleeSack
DanGleeSack

@suppaphly42 @Cronyk I can't really say how much that would actually help. The lower lagtency is usually desirable, but it is always a crapshoot to how much tangible benefit it will have compared to the higher speed. With lagtency, you are probably only talking nanoseconds or less here. If it is the slowest component of your PC by a noticeable margin, than sure it will definitely help, otherwise probably won't make a difference. I'm guessing that increasing RAM frequency and/or decreasing lagtency really won't have a huge impact for your overall system anyways at this point.

Say your 2400mhz has a cas 9 lagtency, that means it operates at 2400 million cycles per second, while the cas 9 means that it takes 9 of those cycles before each operation is started after one is completed. That gives you 9/2400, or 0.00375ms of lag.


You go down to 1866mhz with say a cas 6 lagtency. That gives you 6/1866, or 0.00322. Smaller by 0.00053ms, or a 14.13% decrease from 0.00375ms. So, this would be an increase in performance. You have to be careful tightening up your timings after under clocking, it could result in instability or not being able to boot. This can be fixed, but messing with voltages has the ability to fry your hardware, it has small ranges to work with dealing with transistors/heat tolerances and all. In fact your hardware most likely goes bad from heat damage that irreversibly harms the silicon/doping or even melting the casings/connections if you are unlucky enough.

Plug in your equipment into the fractions and you can see what you end up with. I'd say if you have the time just drop it down and test the results firsthand, that is usually the best way to do things. You can design things and calculate them theoretically, but real world application always throws a wrench into it. 

Would I personally do it? No, probably won't make a difference for the effort you're putting into it. If you want to, by all means, shouldn't ****(always a change to though)**** hurt anything. I haven't overclocked my system, it works good enough for me since I was able to find good parts for pretty cheap, so I am only answering based on what I have had some experience with from an engineering perspective. I'd look on an overclocking or gaming forum too if you feel uncomfortable about it.

suppaphly42
suppaphly42

@DanGleeSack @suppaphly42 @Cronyk 

thanks again.

 i bought a maximus 6 formula mobo a 4770k i'm going to get a liquid cooler, the reason i got this stuff is was to learn how to OC with gear that would make it as safe and easy as it can be, baby steps right.

 i have spent months reading about how to do it,  what can go wrong and why, and the only reason i have not tried it yet is a massive expense cleaned me out of money, so thing are tight right now, and i can't get the new cooler which is one of the more important parts as far as safety goes.

now that i see the math that is not much of a jump but that said its the total of all the tweaks that may add up to a more noticeable improvement like get the ram running better get the cpu turn up to its safe and stable max, which from what i have read will make the most out of the ram tweaks, then see if my gpu can go a bit higher (i know that there is not much room to play with in gpus) now when you take all that into consideration it should add up to a marked improvement    

won't know till i try