| HappySqurriel said: Regardless of which approach you take you will find that a major problem will be preventing the SPEs from being idle ... Even if you optimize most of your code to take advantage of the SPEs most of the time you will only be using one or two of the SPEs, and when you are using most (or all) of the SPEs one will likely be overloaded while another is starved for work. |
Yes,such problems are very common. It is much easier to talk about the advantages of parallel programs, but when you have to write one, you have to recognize, that these parallel systems can only work efficiently if they are synchronized to each other. This makes them so tricky, together with their debugging problems, which makes the development quite expensive.
So in many cases it is simply cheaper to use only one system instead of a parallel system.
