Path: utzoo!utgpu!news-server.csri.toronto.edu!clyde.concordia.ca!uunet!samsung!usc!snorkelwacker!paperboy!meissner From: meissner@osf.org (Michael Meissner) Newsgroups: comp.unix.wizards Subject: Re: fastest way to copy hunks of memory Message-ID: Date: 7 May 90 15:18:15 GMT References: <3296@auspex.auspex.com> <11311@cbmvax.commodore.com> Sender: news@OSF.ORG Organization: Open Software Foundation Lines: 22 In-reply-to: ag@cbmvax.commodore.com's message of 4 May 90 01:53:26 GMT In article <11311@cbmvax.commodore.com> ag@cbmvax.commodore.com (Keith Gabryelski) writes: | In article <3296@auspex.auspex.com> guy@auspex.auspex.com (Guy Harris) writes: | >I don't think S5 has "bcopy()" until, possibly, S5R4. | | A lot of vendors added bcopy() to S5R3 when they hacked in TCP/IP | support, just for ease of porting. | | S5R4 has support for bcopy() in libucb.a. | | Pax, Keith But of course, the question still is which routine has your vendor spent time optimizing, and for which is it just a byte-by-byte copy? The answers are different for each vendor (some unfortunately don't optimize any of them, even if they provide both). -- Michael Meissner email: meissner@osf.org phone: 617-621-8861 Open Software Foundation, 11 Cambridge Center, Cambridge, MA Catproof is an oxymoron, Childproof is nearly so