AMD's upcoming Phenom desktop processor family will include CPUs with three processing cores, the chip maker announced last night. Now that dual-core products are commonplace and four-core chips becoming more so, why not tri-core too? AMD didn't provide any details of the Phenom series members' speeds and feeds, but it did …
So AMD should compete with a 5-core CPU?
I'll get my coat.
Nice strategy, but price..?
The CPUs are literally going to have to be dirt cheap to win. Core 2 quad 6600 is already inexpensive, so the AMD offering will have to match the price of a Core 2 Duo or have an extremely small price premium..
"here at the Intel Development Forum, company CEO Paul Otellini will today speak on the subject of "extreme to the mainstream"."
Surely that was an album by Vanilla Ice.
My hat, it has three corners..
tri core? triangular chips? I dont think so...
Why do I suspect that these will be duff or crippled Quads...
doesn't make sense to design a different shaped silicon when you could just copy what you've got, unless they are moving cache around... show us some pics...
Three Dollar Bill
...that's what springs to mnd when I think about a three core cpu.
CPU Intensive tasks like [b]Games[/b]
"but there's no doubt that three cores provide more processing resources than two, to the benefit of anyone running CPU-intensive tasks like games,"
Have you guys been living under a rock. Games that can take advantage of multiple cores can be counted on your clawed vulture feet. There's the argument that a 2nd core takes care of all the background windows processes, but there is no argument for tri or quad core processors being superior to dual for games purposes.
Benchmarks actually show quad cores being slower than dual, probably due to syncronisation overhead when only one core is being heavily utilised, and the same will probably apply to 3 cores.
AMD advantage, Intel advantage
AMD has better computer scientists and electrical engineers on its team. That's great! For a given process, their chips will outperform Intel's.
Unfortunately for AMD, Intel has far better physicists working on process engineering. They're always at least one step ahead of AMD on that front, and that's starting to pay real dividends now that the Intel EEs, who up until recently were depending on Intel physicists to continue to push up clock speeds as a substitute for any further electrical design improvements, have started to actually come up with new designs (or at least successfully copy AMD's good designs).
Moral of the story, don't ignore the physicists. This message brought to you by a physicist.
More cores = so what...
At Intel four cores = 2x two cores as opposed to AMD where four is four.
Not that it matters in Windows, even with Vista.
Multiprocessing in the desktop world means bog down the first core/processor and use the other when a thread can become available off of the first core/processor. True there are applications that run on Windows that know about multiprocessing but even they can only do that for certain processes and then only when conditions are met.
I would suspect that if the consumer sees a performance increase it is not because of the extra cores but because of larger more efficient caches and core design.
More Cores, More Sense
3 cores would be perfect:
1 core dedicated to antivirus/firewall.
1 core dedicated DRM overhead.
1 core left for user tasks (displaying pr0n).
"Why do I suspect that these will be duff or crippled Quads..."
Because, clearly, you read the damn article.
We all know that clock isn't everything - not anymore. But to a given CPU higher clock = higher speed.
Phenon can disable it's cores one by one - wich means that even if the 3 core are, in fact, a defective 4 core, it will run cooler.
Now, the magic: Very few desktop tasks would see an improvement beeing run on a 4 core. There's a good chance that they will be slower - due to the overhead os the core's comunnication.
How about, then, a higher clock 3 core? Less cores running = less heat. AMD is using 65 nm, and Intel is going to 45. Who knows? A 3 core at 3 GHz may be faster (on the typical desktop) than a 4 core at 3 GHz. It all depends of the software and overhead of keeping 4 cores in sync. :)
A question: If AMD can make a 3 core, would be a 6 core feasible? A 5 core? A 7 core? It would allow them to address different kinds of load...
why more cores?
The analogy to a core for DRM, 1 for apps, 1 for antivirus isn't too far off...
Having tested multicores for quite a while now, even single threaded apps can see a great improvement when run with an SMP OS. Each new process started will be placed on the least busy core, and while a core is tied up doing I/O other processes that aren't awaiting I/O can run at full speed.
Classic tightly coupled SMP tests show a significant roll off after 8 processors without SMP aware apps, but up to there you get almost a multiplier effect for each new added core so long as memory and I/O bottlenecks are avoided.
This *does* depend on your OS being good at multiprocessing.
Nice , now with these babies and multiple motherboards , I can cheaply assemble and create a very cheap low cost desktop version of the mid nineties super computers , now that rocks !
Number of the Beast
So, now AMD has a chance of making a 6-core chip (two 3-cores in the same package), and by extension, they should naturally look into making a 6x6x6 platform for devilishly fast performance.
3 cores faster than 4?
@Steve: The fur-core benchmarks are all on systems where there are two dual-core processors in two sockets or two dual-core processors on one chip but still using the frontside bus. Three or four cores with a single crossbar (as AMD uses and Intel is rumored to use soon) could be much faster. I'll wait for benchmarks of actual systems to find out for sure.
- Facebook offshores HUGE WAD OF CASH to Caymans - via Ireland
- Microsoft teams up with Feds, Europol in ZeroAccess botnet zombie hunt
- Justin Bieber BEGGED for a $200k RIM JOB – and got REJECTED
- Review Bigger on the inside: WD’s Tardis-like Black² Dual Drive laptop disk
- Inside Steve Ballmer’s fondleslab rear-guard action