18 Apr
2013
18 Apr
'13
12:28 p.m.
hi mathias,
Unfortunately the concurrency/parallelism group has decided that they do not want C++ to provide types representing SIMD registers. I'm afraid I don't quite understand the rationale for such a refusal; proposing more high-level constructs similar to valarray (or to our own library NT2) was suggested, but that's obviously a more complex and limited API, not a basic building block to program portably a specific processor unit.
hmm ... that's quite unfortunate ... a memory-based interface like valarray just does not compose and is pretty useless for many use cases ... would be quite interested to hear the reasons for the refusal, do you have any details? cheers, tim