Intel Core i7 Die
Posted on 10/01/2010 8:17:32 AM PDT by ShadowAce
Adding cores to the CPU has become the general recipe to ensure performance improvements in modern computers, even if we have heard before than the IT industry will face efficiency problems beyond 16 cores. New research published by MIT now suggests that the industry will be running into a soft wall when 48 cores are reached and new operating system architectures may be required.
Intel Core i7 Die
The number of cores in modern CPUs has grown much slower than we initially anticipated. The first mainstream quad-core processor (Intel Kentsfield), followed just 18 months after the release of the first dual-core processor (Intel Smithfield) in May 2005 and haven’t changed much since then. Six physical cores (and 12 threads) is the top of the range at Intel, while AMD has 12 cores available right now, but is talking about up to 16 cores in the not too distant future.
Intel has said in the past that, beyond 16 cores, it appears that much of the performance gain efficiency from the pure addition of cores may be gone and improving software that takes advantages of these cores may become much more important. That appears to be still true and we are actually seeing both processor makers buying themselves some time with the strategy of integrating GPUs into the processor package, which will provide a path to cost savings, but also a way to increase overall application speed as far as floating-point performance is concerned.
However, the question how many traditional CPU cores really make sense in a “many-core” environment remains. Dozens? Hundreds? Thousands?
MIT’s Frans Kaashoek has provided some clues and said that current operating systems, especially Linux can scale to take advantage of multiple cores with minor modifications to the underlying OS code. He and his team simulated a 48-core chip through an 8 x 6 core setup and monitored the performance change when cores were activated one by one. “At some point, the addition of extra cores began slowing the system down rather than speeding it up.” The explanation is that multiple cores often do redundant work and process the same data, which needs to be kept in the chip’s memory for that time. As long as the memory is used, it is not available for other tasks and a performance bottleneck is the result: When the number of cores increases, tasks that depend on the same data get split up into smaller and smaller chunks.
“The MIT researchers found that the separate cores were spending so much time ratcheting the [memory] counter up and down that they weren’t getting nearly enough work done,” the report states. However, the researchers also found that “slightly rewriting the Linux code so that each core kept a local count, which was only occasionally synchronized with those of the other cores, greatly improved the system’s overall performance.”
“The fact that that is the major scalability problem suggests that a lot of things already have been fixed. You could imagine much more important things to be problems, and they’re not. You’re down to simple reference counts.” Kaashoek said. “Our claim is not that our fixes are the ones that are going to make Linux more scalable,” Kaashoek says. “The Linux community is completely capable of solving these problems, and they will solve them. That’s our hypothesis. In fact, we don’t have to do the work. They’ll do it.”
But is there a limit? Remzi Arpaci-Dusseau, a professor of computer science at the University of Wisconsin, thinks so: “The big question in the community is, as the number of cores on a processor goes up, will we have to completely rethink how we build operating systems.”
According to Arpaci-Dusseau, if the number of cores on a chip gets “significantly beyond 48,” new architectures and operating systems may become necessary. However, that may not be the case within the next 5 to 8 years. He noted that finding the problems is the hard part. What that hints at for the rest of the community is that building techniques — whether they’re software techniques or hardware techniques or both — that help to identify these problems is going to be a rich new area as we go off into this multicore world.”
You add 48 cores and whaddaya get??
another day older and a blue screen of death
Saint Peter don’tcha call me ‘Cause-
I can’t go... my operating system has done hit a wall.
Only 48? Dang, I was hoping to get to 96.
48 cores? I still haven’t found any games, software, or applications I want that will use 4 cores fully.
48 cores? I still haven’t found any games, software, or applications I want that will use 4 cores fully.
The difference, of course, is that the cores were on separate machines, and separate CPUs. Each CPU had up to 4 cores.
Either redesign the CPUs memory management, or redesign the OS, I guess.
LOL! Very good!
Is this thread about that new Windows 7 POS?
I just blew $1200 on two laptops that won’t run ANY of my XP radio software programs?
Oh. Pr0n. Never mind.
Geezzeee…what are we really complaining about here.
I’ve been using Core2Quads, i3 and i5s with 64bit Win7 for some time now and they just rip right through everything I can throw at them; and i7s are even faster. Maybe they should focus on perfecting multi-distributed branch processing; although energy and heat are key issues.
Exactly. The fewer machines in a cluster, the less energy and heat produced.
That means more cores/CPU. Hence the discussion.
Download windows xp mode from microsoft
UNIX operating systems already have advanced beyond these limits.
Sun’s Solaris crossed this barrier 13 years ago, scaling to 64 cores. By 2004, it was scaling to 144 cores. Since 2008 it is was scaling to 256 cores 512 threads. Today IBM’s AIX is scaling to 256 cores and 1024 threads.
The memory management system for Solaris was changed to address very large memory with Solaris 8 in 2000. The multithreading model was changed to address large core counts with Solaris 9 in 2002.
AIX added some very strong reliability features needed for large core counts and large memory to AIX 5.3 in 2004. Sun added similar reliability features for large core counts and large memory to Solaris 10 in 2005.
What is really needed from this point forward are transactional memory management, preferably in hardware, faster cache coherency mechanisms, and perhaps a move from NUMA memory allocation to COMA memory systems.
A quick note- Sun, er.. I mean Oracle just introduced
a 16 core “T3 chip”- does 128 concurrent threads-
works great as a web server-has issues running high
transactional DataBases- Now try and deal with Larry
on lowering cost vs Intel Nehalem servers-
I’ve completely maxed by box out doing video production of textured 3-d models. That’s with 8 threads and 6GB on Fedora 11. This is the only thing I’ve found, though, that will even touch it, other than running multiple folding@home clients.
Ham stuff? There's lots of good Linux Ham tools.
No, it's about CPU cores. And it's "OS", not "POS". :)
> I just blew $1200 on two laptops that won’t run ANY of my XP radio software programs?
Sorry you're unhappy with your new machines. As others have commented, you can download "XP Mode" for Win7 from Microsoft (essentially a virtual machine of XP); or you might be able to downgrade Win7 to XP if you have an old copy of XP around (but beware of driver issues); or you can lose Windows entirely and load Linux.
My strong suggestion would be to make the leap to Win7 and see if you can get your programs in a version for it. Look for versions of the programs that are compiled for Win7, (or Vista). Although the cross-compatibility is not bad between NT5 (XP/2K) and NT6 (Win7/Vista), a lot of programs will run on one but not on the other.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.