Slashdot Mirror
Intel Next-Gen CPU Has Memory Controller and GPU
Many readers wrote in with news of Intel's revelations yesterday about its upcoming Penryn and Nehalem cores. Information has been trickling out about Penryn, but the big news concerns Nehalem — the "tock" to Penryn's "tick." Nehalem will be a scalable architecture with some products having on-board memory controller, "on-package" GPU, and up to 16 threads per chip. From Ars Technica's coverage: "...Intel's Pat Gelsinger also made a number of high-level disclosures about the successor to Penryn, the 45nm Nehalem core. Unlike Penryn, which is a shrink/derivative of Core 2 Duo (Merom), Nehalem is architected from the ground up for 45nm. This is a major new design, and Gelsinger revealed some truly tantalizing details about it. Nehalem has its roots in the four-issue Core 2 Duo architecture, but the direction that it will take Intel is apparent in Gelsinger's insistence that, 'we view Nehalem as the first true dynamically scalable microarchitecture.' What Gelsinger means by this is that Nehalem is not only designed to take Intel up to eight cores on a single die, but those cores are meant to be mixed and matched with varied amounts of cache and different features in order to produce processors that are tailored to specific market segments." More details, including Intel's slideware, appear at PC Perspectives and HotHardware.
It seems that AMD has lost, and I'm not trying to troll. It just seems that fortunes have truly reversed and that AMD is being beaten by 5 steps everywhere by AMD. Anybody have an opposing viewpoint? (Being an AMD fan, I am depressed.)
...they're taking AMD's on-die memory controller, AMD/ATi's on-die GPU and Sun's multi-thread handling and putting them on one chip?
Have Intel come up with anything genuinely new recently?
Goten Xiao
What do the Names mean? What is intel's naming scheme? Why do the select them that way?
And the next one will be faster, stronger and able to leap gigaflops in a single bound.
This is awesome. I'm just sitting here, waiting for more and more cores. While all the Windows/Office users whine that "it's dual-core, but there's only a 20% performance increase", I just set MAKEOPTS="-j3" (on my dual-core box) and watch things compile twice as fast. Add in the 6-12 MB of L2 cache these will have, and it's gonna rock. (my current laptop has 4 MB--that's as much RAM as my old 486 came with. (There. I got the irrelevant "when I was your age" comparison out of the way. (Yes, I know one of you had a computer whose RAM was as small as the L1 cache. Good for you.)))
ttuttle is a rankmaniac
Take your mod points, strike me down with all of your hatred...
*snicker*
My humor is probably your flamebait
doesn't the quality of onboard graphics suffer from being directly on the mobo? I know there's a thriving market for sub $70 dollar graphics cards that replace onboard graphics for the sake of better image quality. Wouldn't having it on chip make this worse? I'd love to have onboard graphics (especially if I could get good tv out with it ) to save on heat/noise, but the stuff I've seen has been pretty lame.
Hi! I make Firefox Plug-ins. Check 'em out @ https://addons.mozilla.org/en-US/firefox/addon/youtube-mp3-podcaster/
Intel has a lot of cash, and the ability to invest in expensive processes earlier than most. Certainly, earlier than AMD.
However, it's worth noting, that these are clearly AMD ideas.
* On die memory controller - AMD's idea - and it's been in use for quite a while now
* Embedded GPU - a rip off of the AMD fusion idea, announced shortly after the aquisition of AMD.
Intel is no longer leading as they have in yeas past - they are copying and looting their competition shamelessly. It appears that they are "leading" when point in fact it's simply not the case - had AMD not realeased the Athlon64 we would all still be using single processor NetBurst processors.
So it took Intel almost 9? years to integrate the Intel i740 GPU onto a CPU? I always wanted native DirectX 6.1 support right from the get-go!
Previewing comments are for sissies!
What will this mean if the GPU is integrated with the CPU?
Will we still need drivers? If we do, hopefully there will be open source versions since it is Intel and all.
I can't wait for the Frodo and Samwise chips
In the meantime, you can get an AMD X2 3600 (65nm Brisbane core) for around $85 now, and probably in the $60 range well before these new products hit. The high end is one thing, but who actually buys it? Very few. I don't know anyone that bought the latest FX when it came out, or an Opteron 185 when they hit, or even a Core2Duo Extreme. All this does is push the mid- to low-end products down, and a ~$65 dual core that overclocks like crazy (some are getting 3 GHz on stock volts on the 3600) would seem like the best price/performance to me.
AMD's not out because they don't control the high end. Remember, you can get the X2 3600 w/ a Biostar TForce 550 motherboard at Newegg for the same price as an E4300 CPU (no mobo), and that's the board folks are using to get it up to crazy clock speeds.
It seems that AMD has lost, and I'm not trying to troll. It just seems that fortunes have truly reversed and that AMD is being beaten by 5 steps everywhere by AMD. Anybody have an opposing viewpoint? (Being an AMD fan, I am depressed.)
Look at the title of this thread: Intel Next-Gen CPU Has Memory Controller and GPU.
The on-board memory controller was pretty much the defining architectural feature of the Opteron family of CPUs, especially as Opteron interacted with the HyperTransport bus. The Opteron architecture was introduced in April of 2003, and the HyperTransport architecture was introduced way back in April of 2001!!! As for the GPU, AMD purchased ATI in July of 2006 precisely so that they could integrate a GPU into their Opteron/Hypertransport package.
So from an intellectual property point of view, it's Intel that's furiously trying to claw their way back into the game.
But ultimately all of this will be decided by implementation - if AMD releases a first-rate implementation of their intellectual property, at a competitive price, then they'll be fine.
The first work machine I was on had a disk drive that held less than that!
By the time I started we had 10MB RL02 diskpacks, so it wasn't all that bad.
And a Whopping 64K extra memory on a 12" square board...
1. Putting a GPU on the processor immediately divides the market for it. Unless this is only going to be a laptop processor it probably won't sell well on desktops.
2. Hyperthreading only works well in an idle pipeline. The core 2 duo (like the AMD64) have fairly high IPC counts, and hence, low amount of bubbles (as compared to say the P4). And even on the P4 the benefit is marginal at best and in some cases it hurts performance.
The memory controller makes sense as it lowers the latency to memory.
if Intel wants to spend gates, why not put in more accelerators for things like the variants of the DCT used by MPEG, JPEG and MPEG audio? or how about crypto accelerators for things like AES and bignum math?
Tom
Someday, I'll have a real sig.
What will this mean if the GPU is integrated with the CPU?
It'll mean that if you want graphics performance that doesn't suck, you'll still need an external video card with dedicated VRAM, but for embedded systems, servers, and business laptops and desktops where Intel's ghastly GPUs are acceptable it'll be OK.
This will also probably make Microsoftwood happy, since it'll guarantee there's no open traces on the video card for you to use to pirate your HD movies on Vista.
I read the article as saying that the die was going to be modular so that a GPU or other type of unit (or two) could be added in place of one or (two) of the cores. This will give Intel the flexibility to use the same design across many different market segments. I expect the memory controller to similarly flexible. If so, this is a pretty innovative design.
I can see those being quite hot for servers, where running "many small" tasks is where the game is.
On a desktop PC you often need the focused application (say, some sort of graphical/audio editor, game, or just a very fancy flash web site even) to get most of the power of the CPU to render well.
If you split the speed potential in 16, would desktop users see actual speed benefit? They'll see increased responsiveness from the smoother multitasking of the more and more background tasks running on our everyday OS-es, but can a mostly single-task focused desktop usage really benefit?
How of course, we're witnessing ways to split concerns of a single task application into multiple threads: the new interface of Windows runs in a separate CPU thread and on the GPU, never mind if the app itself is single threaded or not. That's helping.
Still, serial programming is, and is going to be, prevalent for many many years to come, as most tasks a casual / consumer applications performs are inherently serial and not "paralelizable" or whatever that would be called.
My point being, I hope we'll still be getting *faster* threads, not just *more* threads. The situation now is that i's harder harder to communicate "hey we have only 1000 threads/cores unlike the competition which has 1 million, but we're faster!". It's just like AMD's tough position in the past, explaining their chips are faster despite having slower clock-rate.
1: Integrated sells very well on the desktop almost every single machine in your big box shops has integrated graphics. I am sure it is outsells machines with separate graphics cards in the desktop. Gamers are not the market.
2: I am skeptical about hyperthreading, but it all depends on the implementation. I don't think this is something they are pursuing just for marketing. They must have found a way to eek out even better loading of all execution units by doing this. I can't imagine this being done if it actually performs worse than hyperthreading in P4. We have to wait and see.
I sure hope they keep this crap out of the high-end desktop market CPUs. I would hate having to pay extra for a GPU I'm not going to use. The idea of having built in GPUs for gaming PCs is a bad one. Flexibility is key. I'm sure AMD and Intel know this, though.
Looks like you've got one of those new computers that runs faster based on originality. I bet those Lian Li cases really make it scream then!
OK, these new parallel chips aren't even out yet, and software has to get the hardware before SW can improve to exploit the HW. But the HW has all the momentum, as usual. SW for parallel computing is as rudimentary as a 16bit microprocessor.
What we need is new models of computing that programmers can use, not just new tools. Languages that specify purely sequential operations on specific virtual hardware (like scalar variables that merely represent specific allocated memory hardware), or metaphors for info management that computing killed in the last century ("file cabinets", trashcans of unique items and universal "documents" are going extinct) are like speaking Latin about quantum physics.
There's already a way forward. Compiler geeks should be incorporating features of VHDL and VeriLog, inherently parallel languages, into gcc. And better "languages", like flowchart diagrams and other modes of expressing info flow, that aren't constrained by the procedural roots of those HW synthesis old guard, should spring up on these new chips like mushrooms on dewy morning lawns.
The hardware is always ahead of the software - as instructions for hardware to do what it does, software cannot do more. But now the HW is growing capacity literally geometrically, even arguably exponentially, in power and complexity beyond our ability to even articulate what it should do within what it can. Let's see some better ways to talk the walk.
--
make install -not war
http://www.anandtech.com/cpuchipsets/intel/showdoc .aspx?i=2955 provides a much more detailed look at the new processor architectures coming from Intel. A little better than the PR blurb at ars'.
Quo usque tandem abutere, Nimbus, patientia nostra?
1. Yes there are many integrated graphics cards, but most gamers won't use them. There is a huge market for gamer PCs (hint: who do you think those FX processors are made for?)
2. Don't give Intel that much credit. The P4 *was* a gimmick. And don't think that add HTT is "free" at worst. It takes resources to manage the thread (e.g. stealing memory port access to fetch/execute opcodes for instance).
In the case of the P4 it made a little sense because the pipeline was mostly empty (re: it was a shitty design). In the core 2 duo case, the pipeline is less empty and there really just aren't useful bubbles to fill up with another thread.
Tom
Someday, I'll have a real sig.
It is interesting to note that Intel has now decided to put the memory controller on the die, after AMD showed the advantages of doing so.
However, I'm a little dismayed that Intel hasn't yet addressed the number one bottleneck for system throughput: the (shared) memory bus itself.
In the 90's, researchers at MIT were putting memory on the same die as the processor. These processors had unrestricted access to its own, internal RAM. There was no waiting on a relatively slow IDE drive or Ethernet card to complete a DMA transaction; no stalls during memory access, etc...
What is really needed is a redesign of the basic PC memory architecture. We really need dual ported RAM, so that a memory transfer to or from a peripheral doesn't take over the memory bus used by the processor. Having an onboard memory controller helps, but it doesn't address the fundamental issue that a 10 ms IDE DMA transfer effectively stalls the CPU for those 10 milliseconds. In this regard, the PC of today is no more efficient than the PC of 20 years ago.
The society for a thought-free internet welcomes you.
One stable and open socket technology. So you can pop custom hardware accelerators or FPGA chips in the additionnal sockets in a multi-CPU mother board.
Like AMD's AM2/AM2+/AM3 and hyper transport bus, with partners currently developping FPGA chips.
Not like intel who change controller with each chip generation, at least twice to screw the custommers (423 vs. 478) The Slot 1 used during the Pentium II / III / Copermine / Tualatin era was a good solution to keep 1 interface for the whole range.
Currently, Intel is in a situation where they lost a lot of valuable time and ressouece on the Pentium IV Netburst dead-end.
This has left time for AMD to catch up with nice technology, while Intel had to reboot from old technology (the P3 derived Pentium Mobile).
Now that Intel has slowly catched up (AMD64 intructions set, on-die memmory controller, on die specialized acceleretors), AMD won't be able to count on it to attract custommers.
What's left for AMD are 3rd praty developpers through their opening of socket/bus standart.
This is something that the Intel team won't be able so easily just by throwing money at it.
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
didn't Via test this idea a couple years ago? I even remember a plan of Via being talked about in MaximumPC a couple years ago to make a video chip socket on motherboards that's upgradeable instead of a card.
Why?
/. ?
I mean, of course sometimes it may feel petty or obnoxious, but I don't think GP's spelling correction was either. And if more people worried about spelling correctly and grammar, less corrections would be necessary. I don't know about you, but I appreciate reading well written text - maybe I should stop reading
^[:q!
From a market standpoint, yes AMD made the first in-roads with onchip mem controllers and now their integrated GPU (which they probably wouldn't be doing if not for purchasing a GPU manufacturer). From a technical standpoint, I don't think AMD really did anything others hadn't pondered already. It's not like examples of "integrated everythings" can't be found elsewhere.
On either side this isn't a huge engineering breakthrough. It's simply trying to gain more business. Not that there is anything wrong with that. I just don't feel Intel really "stole" AMD's thunder on this one. That's like saying Ford is now shipping a car with airbags, but Chevy did it first, so Ford is just stealing Chevy's "invention."
No sig for you!!
I just think it is too early to judge. Putting the Video on the die could offer sufficient performance benefits that only ultra high end graphics cards make sense. That is a small portion of the market.
:-)
On HT edition two. I have a skeptical wait and see attitude. Though I will probably buy a new computer in 2007 so it doesn't matter to me for a long time as I will probably squeeze 5 years out my next machine. So 2007 and 2012 are the years that interest me.
Redundant?
C'mon, modders, you can do better than that. Troll, Flamebait, Overrated, I'd understand; they're applicable. But redundant??
Besides, I was serious. When am I going to see some serious RAM on-chip?
110100 1101000 1101000 1100110 0 1101111 1101000 1100011 1
I get the sense that there's a huge difference in public opinion between AMD and Intel. Intel has boat loads more cash, so they can do a lot more marketing. When that happens, people think that AMD is worse off. I know AMD has been around with almost no marketing, but it might be time to start engaging, rather than relying on the techies (/.ers too) to spread the word. I don't know about you guys, but non-technical people sometimes don't like to hear the technical jargon, so they listen to the TV.
Timna was DRDRAM only cancelled low end intel chip with pentium3 CPU, a graphics and DRDRAM memory controller on die.
DRDRAM was never cheap enough for low end for intel to start selling those chips. And strategic failure of that project was probably one of the reasons intel didn't bring ondie memory controllers after that for a while.
And netburst had multithreading before Sun.
©God
This has been coming for a while, and shouldn't surprise anybody. I was expecting it to come from NVidia, though, which had been looking into putting a CPU on their graphics chips and cutting Intel/AMD out of the picture. Since they already had most of the transistor count, this made sense. They already had the nForce, which has just about everything but the CPU and RAM (GPU, network interface, disk interface, audio, etc) on one chip. But they never took the last step. Probably not because they couldn't do it technically.
We're obviously headed for the one-chip consumer PC. The standalone GPU chip market may not last. It's likely to go the way of the separate MMU chip, the separate FPU chip, and the separate network controller chip.
I've been a loyal AMD fanboy since the K6-2 came around...even though the performance is currently lower, I will likely stick with AMD for a while. I've had nothing but fantastic experiences with their products and support, and I will continue buying their stuff.
That said, it's good to hear Intel taking back the crown finally...AMD seemed to be slowing their innovation lately. Hopefully, this move by Intel will light the fire under the pants of AMD enough to get them to some major improvements again.
Living With a Nerd
Gentoo Linux - another day, another USE flag.
This news is just bullshit. AMD had a memory controller a long time ago.
Whilst I was writing a reply, I found out somebody else already found out.
Instead of doing a post all over, just read this.
In my experience, intel graphic chips and chipsets have always sucked in relation to performance AND functionality, it's nice they are integrating and this seems to be the direction most chip companies are heading (intel, amd, nvida, ati, etc..) but unless they have made some leaps in graphics capabilities recently I don't see any benefit of pairing their graphics with their CPUS, other than maybe the OLPC project.
Anyone want a car analogy for my viewpoint? No? Anyone? ok nvm...
Would anyone care to explain the essential difference between designing a chip and "architecting" it?
Now, it's time for Free CPUas in free beer that runs only free software!
China, in fact, is very fragile.
Yup.
"AMD has released their next generation of slow crap. With Intel breathing down their neck, can they survive for even the next few hours with such horrible products?"
vs
"Intel may release a product in the next 2-7 years. Can AMD survive?"
AMD has had on die memory controllers for how long now? Athlon 64 cornerstone was this feature. AMD has also developed and successfully integrated hypertransport in today's machines. AMD is also working on the same type of development, but they already has two key pieces already in place. Now with their acquisition of ATI i see them in a much better situation to implement this form of technology than intel. Intel can do it, but they have much more research to conduct and test before their chips will be ready. I believe AMD will quietly work on this, and drop it a year or so before intel. Then intel will be in the catchup phase again. This whole thing works in cycles, AMD and intel will constantly be swapping places on top of the mountain.
A lot of amd fanboys here. PErformance wise intels latest chips are winning versus amds chips. Without an integrated memory controller.
Now intel will have that also. This means that amds only advantage they will lose. AMD needs something huge to stay in the game.
Also baiscally this news sounds like Intels Version of the Cell processor.(they stated configurable cores that each core can be set to do something else.)
Actually, Intel put memory controller on die in 1997~2000 but never released the product. This was in response to the seg0 cost reduction effort that drove the http://www.pcworld.com/article/id,18726-page,1/art icle.html
But that was 10 years ago, so most of this audience wasn't even teenaged. Of course, embedded CPUs have been doing integration like this for 20+ years.
https://www.accountkiller.com/removal-requested
* Core2 is a wider processor, so there are more free functional units available.
* SMT can vary with implementations. For instance, IBM's Power6 basically gets the SMT promise.
* The P4 was designed to scale to 10+ GHz, but the designers expected too much from processing technology. As the dynamic power increases with frequency, and with power/heat becoming the bottleneck, the P4 wasn't able to achieve its promise. If it had, its HT implementation would have been fairly decent for the architecture.
"Open Source?" - Press any key to continue
Generally for a type of memory, the larger its capacity, the larger its latency becomes and the smaller the throughput you'll get from it. A memory hierarchy is sometimes seen as a solution to reduce memory system cost, but more fundamentally, as silicon technologies evolve, it also reflects an inherent characteristic of memories - either large or fast, you can't have it both ways.
People who dislike China tend to mention Tiananmen Square a lot, but they always forget the Tank Man is also a Chinese.
is moving parts. Eliminate moving parts and latency/loading/speedup time goes thru the roof. Fuck optical and magnetic storage.
I'd really like to see a pure solid state computer, tiny, where if you wanted to change your OS all you'd have to do is pop on an ESD strap, open up the computer, and plug in a different module.
Too bad nobody else is working towards this yet.
Still waiting on Serviscope_minor to wake up to fucking reality and realize that Jessica Price isn't going to fuck him.
Do you have any idea how large a 1GB dual-port stick of ram would be? It'd probably cost 2 to 3x as much to make
I realize that many people share your opinion, and that it is a valid point. However, I would add that it is people like you who hold back the desktop PC. When everything is about low cost, does it surprise anyone that the standards and hardware produced are optimized not for performance, but for low price?
One thing which impressed me about the designs of IBM mainframes and of the Apple computers (prior to Intel) was that they were absolutely beautiful from an architectural standpoint. When you have clients willing to pay a decent price for your computers, you can build them the way they should be built. (Of course, this is just my opinion).
Instead, we all buy PCs because they're cheaper, and then gripe about the low performance.
The society for a thought-free internet welcomes you.
Wheres my mobo that supports intel and amd chipsets?
where is it?
If you actually read the artical you will see the claims are rather vague. He says that the Nehalem may or may not have a memory control, but it depends and makes vague claims about a GPU (just because a GPU is on-core doesn't mean it going to be good, remember Intel already make crap on-motherboard GPUs).
Most of the rest of the artical is just speculation by Jon Stokes. It seems to me that Intel have no clear plan yet, and they don't really need to. They have clearly beaten AMD with the Conroe and it seems they will beat the Barcelona with the 45nm process.
You just emphasised the cost of doing so, while my post is basically saying the performance benefit of this approach is minimum.
People who dislike China tend to mention Tiananmen Square a lot, but they always forget the Tank Man is also a Chinese.