"A processor designed purely for speed, not for a compromise between speed and C support, would likely support large numbers of threads, have wide vector units, and have a much simpler memory model. Running C code on such a system would be problematic, so, given the large amount of legacy C code in the world, it would not likely be a commercial success."
@grainloom interesting. Never looked at this that way (mostly because I have no interest in layers so close to physical). Do they say what alternatives do should use instead?
@HalfTough in languages or in processors?
@grainloom mostly languages. Processors aren't my thing and since ther's so much c code everywhere I don't see switching would do me much good.
@HalfTough the author mentioned some research by Sun (RIP) and some other research chips (that I didn't look into) but I think that's it.
@HalfTough I think the only architecture they mentioned by name was SPARC.
@HalfTough on the language side.... Haskell???? and there was some talk about the JVM and the CLR, I think???
@HalfTough oh, forgot to mention, on the CPU side I heard something vague about the #Mill architecture being good for #fp but I don't know anything more about that.
