On Mon, 22 Apr 2002, Trei, Peter wrote: > So my suggestion is that while hardware accelaration of PRNGs may have > some usefulness, true RNGs need not have the same performance. I'd > rather see people work on making the true RNGs *trustworthy*, which is > a much more difficult problem.
Out of curiosity, does anyone know what kind of data rates one can get from the RNG built into those oh-so-commodity i8xx motherboards? I don't have one, else I would just go time a read loop. And has anyone ever done an analysis of the output? Last I heard (~2.5 years ago?) Intel was refusing to release the design for inspection. Has that changed since? -Jack