Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP Path: utzoo!mnetor!uunet!husc6!cmcl2!rutgers!princeton!udel!mminnich From: mminnich@udel.EDU (Mike Minnich) Newsgroups: comp.protocols.tcp-ip Subject: Re: TCP performance limitations Message-ID: <564@louie.udel.EDU> Date: Tue, 6-Oct-87 11:21:54 EDT Article-I.D.: louie.564 Posted: Tue Oct 6 11:21:54 1987 Date-Received: Fri, 9-Oct-87 05:59:59 EDT References: <8710051601.AA14825@ucbvax.Berkeley.EDU> Organization: University of Delaware Lines: 19 In article <8710051601.AA14825@ucbvax.Berkeley.EDU>, MAB@CORNELLC.BITNET (Mark Bodenstein) writes: > Could you provide more detail on how you unrolled this loop? > > (The complication being that the length of the loop is determined by > the length of the data. Some alternatives I can think of would be: > > 2. to unroll the loop for each possible data length, and chose and > execute the appropriate unrolled loop > A simple technique that has worked well for me in the past is to unroll the loop for the longest possible length and then compute a jump into the unrolled loop based on the length of the data to be checksummed/copied/etc. Only one version of the unrolled loop is needed in this case. mike -- Mike Minnich