Report: Roadblock Ahead for Multi-Core Processors

Respital

Active Member
Source: http://www.maximumpc.com/article/news/report_roadblock_ahead_multicore_processors

In case you haven't noticed, multi-core processing has taken hold and the race is on to cram more cores onto a single die. But assuming developers can keep up, at some point, chip manufacturers are going to have address a potential major problem that could make adding more cores a useless endeavor. More specifically, a "memory wall" looms large in the not too distant future that, as Jon Stokes from ArsTechnica puts it, could make more than 16 cores pointless.

The problem stems from memory bandwidth not being able to keep pace with faster processors, whether those speed bumps come from a faster frequency or more cores. Put simply, memory is creating a bottleneck and can't feed the processor fast enough, a problem that has existed for some time. Intel and AMD have been able to mask the problem by adding more cache, but doing so doesn't overcome the memory wall, which looks poised to really rear its ugly head as more cores are piled on to new chip packages.

"Engineers at Sandia National Laboratories, in New Mexico, have simulated future high-performance computers containing the 8-core, 16‑core, and 32-core microprocessors that chip makers say are the future of the industry," writes Samuel K. Moore at IEEE Spectrum Online. "The results are distressing. Because of limited memory bandwidth and memory-management schemes that are poorly suited to supercomputers, the performance of these machines would level off or even decline with more cores."

According to the simulation, performance gains level out at 8-cores, with 16-core chips performing no better than a dual-core processor. As the core count increases, the performance starts to decline sharply.

One solution Sandia has proposed is to stack memory chips on top of the processor, something both Intel and IBM have been working on. Some might also remember reading about multi-core memory, a new memory architecture developed by cryptographer Joseph Ashwood. But no matter what the eventual solution, someone's going to have to come with something relatively fast. Sixteen core chips might not be as far off as you think, and the memory wall isn't going to crumble on its own.
Signs.png

Maybe someone could shed some light on this topic, i haven't heard about this before. But if nothing above octo is going to show performance increase it's going to be all about the bragging rights. :P
 
When moving up from a 2.2ghz single core cpu on the prior build to the 3ghz. dual core model now in the one thing that saw the most notice was simply moving up from 2.2 to 3.1ghz without any ocing and the fact that the new build was seeing a dual core cpu. The memory change also helped going from DDR400 upto DDR2 800.

When increasing the amount of cores you also generate the need for a wider bandwidth for memory as the article was pointing out there. I wouldn't expect to be seeing 16 core cpus any time soon however since quads haven't even been out for only a few years now with dual core models a relatively short period before that a new platform for cpus will be the final answer over simply adding in more cores.
 
I agree with the article, 16-core CPU's aren't far off if this trend continues. Quad cores have been out for what, 1-2 years? Intel is already saying that at some point in 2009 they will release Core i7's with 8-cores, so potentially in 2010-2011 we could see 16-core CPU's.
 
Too many cores and too many problems is simply where the article is going there. The second article there points to Intel now trying to work sideways since AMD had the lead with seeing more work done per clock cycle years back. It sounds more like role reversal lately with AMD now focusing on clock speed for the next line of Phenom IIs coming out. :P
 
Back
Top