Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!yale!think.com!linus!linus!linus!bs From: bs@linus.mitre.org (Robert D. Silverman) Newsgroups: comp.arch Subject: Re: standard extensions Message-ID: <1991Feb26.171338.8362@linus.mitre.org> Date: 26 Feb 91 17:13:38 GMT References: <1991Feb25.135057.23667@linus.mitre.org> <1991Feb25.201406.18643@bingvaxu.cc.binghamton.edu> Sender: news@linus.mitre.org (News Service) Organization: The MITRE Corporation, Bedford, MA 01730 Lines: 20 Nntp-Posting-Host: linus.mitre.org In article <1991Feb25.201406.18643@bingvaxu.cc.binghamton.edu> kym@bingvaxu.cc.binghamton.edu (R. Kym Horsell) writes: :To summarize: I don't think provision of a combined divide/remainder :(or divide/modulus for that matter) instruction will necessarily :speed up the total running time of any real programs appreciably :(i.e. more than, say, 10%). Perhaps Bob Silverman could illustrate :some circumstance which contradicts this? You miss the point. There ARE many processors that provide double length multiply and divide with remainder instructions. Most current HLL's have no way of generating code that will access these instructions. Furthermore, there ARE codes which can show much more than a 10% gain by having such instructions. Most are number-theoretic or cryptographic or group-theoretic in nature. -- Bob Silverman #include Mitre Corporation, Bedford, MA 01730 "You can lead a horse's ass to knowledge, but you can't make him think" Brought to you by Super Global Mega Corp .com