|
|
|
|
|
Cover Quote: November 2010
|
|
Researchers have been trying to tackle [parallel processing] problems since the 1960s. Many ideas have been tried, and just about as many have failed. One early vision was that the right computer language would make parallel programming straightforward. There have been hundreds—if not thousands—of attempts at developing such languages, including such long-gone examples as APL, Id, Linda, Occam, and SISAL. Some made parallel programming easier, but none has made it as fast, efficient, and flexible as traditional sequential programming. Nor has any become as popular as the languages invented primarily for sequential programming. [...] The most optimistic outcome, of course, is that someone figures out how to make dependable parallel software that works efficiently as the number of cores increases. That will provide the much-needed foundation for building the microprocessor hardware of the next 30 years. Even if the routine doubling every year or two of the number of transistors per chip were to stop—the dreaded end of Moore’s Law—innovative packaging might allow economical systems to be created from multiple chips, sustaining the performance gains that consumers have long enjoyed.
|
- David Patterson
The Trouble with Multicore, 2010
|
|
|
|
|
|