daveb@geac.UUCP (David Collier-Brown) (03/02/88)
In article <8332@eddie.MIT.EDU> jbs@eddie.MIT.EDU (Jeff Siegal) writes: [a discussion of edge-vectors, in C and elsewhere] >True, there is no answer that is going to address this problems short >of specialized hardware. I think it's pretty obvious that for >applications which primarily multiply, you want fast hardware support >for multiplication. Machines without such support are compromising >multiply performance for better performance at (hopefully) more common >operations like register loads and stores, comparisons, adds, etc. What support is there in modern architectures for indirection? Indirections used to be a well-loved page-thrasher in 7090-like architectures (albeit not on the IBM, which didn't page until years later). I know ICL was good at them in their CISC 29000 series, but what about "ordinary" C programs on "modern" RISC machines doing operations like the assignment in the header above? 1. How common are indirection instructions in 1.1 synthetic and 1.2 measured workloads? 2. How hard are they to deal with efficiently? --dave cb -- David Collier-Brown. {mnetor yunexus utgpu}!geac!daveb Geac Computers International Inc., | Computer Science loses its 350 Steelcase Road,Markham, Ontario, | memory (if not its mind) CANADA, L3R 1B3 (416) 475-0525 x3279 | every 6 months.