Tuesday, February 23rd 2010
AMD Starts Shipping 12-core and 8-core ''Magny Cours'' Opteron Processors
AMD has started shipping its 8-core and 12-core "Magny Cours" Opteron processors for sockets G34 (2P-4P+), and C32 (1P-2P). The processors mark entry of several new technologies for AMD, such as a multi-chip module (MCM) approach towards increasing the processor's resources without having to complicate chip design any further than improving on those of the Shanghai and Istanbul. The new Opteron chips further make use of third-generation HyperTransport interconnect technologies for 6.4 GT/s interconnect speeds between the processor and host, and between processors on multi-socket configurations. It also embraces the Registered DDR3 memory technology. Each processor addresses memory over up to four independent (unganged) memory channels. Technologies such as HT Assist improve inter-silicon bandwidth on the MCMs. The processors further benefit from 12 MB of L3 caches on board, and 512 KB of dedicated L2 caches per processor core.
In the company's blog, the Director of Product Marketing for Server/Workstation products, John Fruehe, writes "Production began last month and our OEM partners have been receiving production parts this month." The new processors come in G34/C32 packages (1974-pin land-grid array). There are two product lines: the 1P/2P capable (cheaper) Opteron 4000 series, and 2P to 4P capable Opteron 6000 series. There are a total of 18 SKUs AMD has planned some of these are listed as followed, with OEM prices in EUR:
Sources:
AMD Blogs, TechConnect Magazine
In the company's blog, the Director of Product Marketing for Server/Workstation products, John Fruehe, writes "Production began last month and our OEM partners have been receiving production parts this month." The new processors come in G34/C32 packages (1974-pin land-grid array). There are two product lines: the 1P/2P capable (cheaper) Opteron 4000 series, and 2P to 4P capable Opteron 6000 series. There are a total of 18 SKUs AMD has planned some of these are listed as followed, with OEM prices in EUR:
- Opteron 6128 (8 cores) | 1.5 GHz | 12MB L3 cache | 115W TDP - 253.49 Euro
- Opteron 6134 (8 cores) | 1.7 GHz | 12MB L3 cache | 115W TDP - 489 Euro
- Opteron 6136 (8 cores) | 2.4 GHz | 12MB L3 cache | 115W TDP - 692 Euro
- Opteron 6168 (12 cores) | 1.9 GHz | 12MB L3 cache | 115W TDP - 692 Euro
- Opteron 6172 (12 cores) | 2.1 GHz | 12MB L3 cache | 115W TDP - 917 Euro
- Opteron 6174 (12 cores) | 2.2 GHz | 12MB L3 cache | 115W TDP - 1,078 Euro
125 Comments on AMD Starts Shipping 12-core and 8-core ''Magny Cours'' Opteron Processors
I see the signs although they generally aren't anything to be worried about now on a quad-core; however, the more cores there are, the bigger the problem becomes. I don't want to imagine how much trouble it will be to multithread the code that handles multiple cores. The potential for errors, collisions, and other problems are exponentially increased.
These r useless for everyday users. Most games arent even coded to use 2 cores let alone 12
dual cores have been out for how long now and we still dont see universal acceptance of them by dev's... I <3 people who spew bs
one thing all you naysayers are forgetting, is that DX11 comes with multithreading as part of its basic design.. next gen games are going to use our spare threads quite well :)
And what Intel Crossfire issues? Your Crossfire issues do not stem from the Intel chipset, they stem from the shitty ATI drivers.
It's difficult to explain but multi-core doesn't have a very bright future. Everything about them multiplies complexity of operating systems to software. Until that is fixed on the hardware level, no one is going to be excited about more cores except Intel/AMD (because its cheap and easy) and consumers (because it's the new fad for incorrectly cataloguing performance like clockspeeds were up to Pentium 4/D).
Call me a pessimist but this trend is more harmful than helpful to developers and by extension, consumers.
Firstly these are for servers at the moment, as people were saying what used to take 12 cpus ( 4 cores each) can be done with 4 cpus.
That's space saving! ( aswell as cheaper eventually)
Also it means servers can process more incoming requests etc so online games could hold much more avatars in one area etc .
Also means if someone made a modified L4D server they could have 1000 or more zombies come at you at once rather then the typical 50 or so :P
Ontop of that imagine running several OS at once simultaneously, got a program that won't run on windows, no problem just switch to linux instantly.
You need to think outside your current thinking and see the potential.
Oh also your statement about computers not being able to recognise imagery is quickly becoming less and less true, hell hondas little robot can recognise chairs and cars etc, even recognise the model of the car if its been taught it.
With more powerful cpus with more cores it will be able to function even better.
Can use bunches of 10 cores to control individual body parts as well to give it much greater dexterity etc.
Seeing how effective massively parallel computing makes the human brain at such tasks, is teaching researchers that if we want our computers to perform increasingly "intelligent" and profound operations, we're going to have to step out of the box to take computing to the next level. We have to think beyond traditional methods, because they can only take us so far. At this point, the "next level" is massively parallel hardware. The ability of software to utilize it well will come as the technology matures.
In one line: Virtual servers in data centers, where one physical server with one or two physical CPUs can be used to rent 12 web-servers, each suiting the customer's needs.
Intel/AMD is trying to cater to one crowd (enterprise) while consumers get shafted because workstation/home computers are well-rounded machines and not task oriented. Your GPU will be crying for mercy long before your CPU. And still, there is little one fast core couldn't do than 100 slow cores. Personally, I think mainstream processors should have no more than four cores. The focus needs to be on core performance. If, as I stated earlier, that takes symmetrical core design, so be it. The point is: most users with quad cores rarely see their CPU usage over 50% if not 25% doing anything they do on a day to day basis. Unless you are talking about virtualization, that doesn't work: resource collisions. I'm looking 10-50 years out here. The prognosis starts getting grim in about 6 years when die shrinks are no longer possible. From there, it's nothing but question marks. Nothing revolutionary has happened in computing since the 1970s. We're still using the same old techniques with different materials. Which demonstrates the brain is falling behind. We can build processors faster, not brains (at least not yet). It is still inefficient because images don't translate well to binary but that's the nature of the beast. Only if the process is not linear. If step b requires the result from a, step c requires the result from b, step d require the result from c, and so on, it is doomed to forever be slow in the foreseeable future. That is what most concerns me (aside from manufacture process). A 486 could handle that with lots of room to spare. Computer controlled robots have been in use a long time. Oh, so you want some nameless corporation 1,000 miles from where you live to know everything you did and are doing? That's the Google wet-dream there. They would know everything about you from how much is in your checking account to which sites you frequent, to all your passwords and user names, to your application usage, to everything that would exist in your "personal computer." Cloudcomputing/virtualization is the epitome of data-mining. Google already knows every single search you made in the past six months with their search engine.
Corporations want this. It is vital we not give it to them. Knowledge is power.
If you want to fight the concept, go build a better system that doesn't utilize it. Otherwise, take a look around. Multi-core CPUs, multi-CPU systems, Crossfire and SLI, RAID ... running components in parallel isn't perfectly efficient, but guess what: neither is anything else.
Sure, maybe there's overhead, and maybe more than we'd like (although that's improving), but as a car guy [I gather] you should understand very well that sometimes you have to take a loss to make bigger gains (unless you don't believe in forced induction either?).
That's not due to its motors its has it doesn't have the processing power to run !
Unlike humans that build up muscle memory and automatic responses a machine has to think about moving, so once its phsyical speed starts building up it becomes more and more difficult.
Where as having a CPU core for each sensor it has it will be able to adjust things all that much quicker.
( thus move quickly)
Same reason the thing falls arse over tit when climbing stair cases sometimes :p