Re: Someone has repealed Amdahl's law?
The first step to solve a problem is to truly understand it. Once you have understood it, you might be able to reformulate it in such a way as to maximize the parallelization opportunities. If this does not happen then perhaps 1) the problem is inherently difficult to parallelize or 2) you are simply not good enough. I know which one it is for me, which is why I'm looking forward to watching this presentation.