Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP Path: utzoo!mnetor!uunet!seismo!mimsy!chris From: chris@mimsy.UUCP (Chris Torek) Newsgroups: comp.lang.c,comp.unix.wizards Subject: Vax arithmetic (was Re: pointer alignment) Message-ID: <7559@mimsy.UUCP> Date: Thu, 16-Jul-87 10:05:08 EDT Article-I.D.: mimsy.7559 Posted: Thu Jul 16 10:05:08 1987 Date-Received: Sat, 18-Jul-87 08:35:04 EDT References: <493@its63b.ed.ac.uk> <6061@brl-smoke.ARPA> <3812@spool.WISC.EDU> <6706@steinmetz.steinmetz.UUCP> Organization: U of Maryland, Dept. of Computer Science, Coll. Pk., MD 20742 Lines: 15 Xref: mnetor comp.lang.c:3099 comp.unix.wizards:3272 In article <6706@steinmetz.steinmetz.UUCP> davidsen@steinmetz.steinmetz.UUCP (William E. Davidsen Jr) writes: >[ I thought you mentioned that the 32 bit size was hardware supported. >On many machines the short math is faster than long (ie. vax, 68000). ] On the Vax, the short math is exactly as fast (or as slow) as the long, at least in register-to-register operations, according to an ancient set of 780 `timings' that once appeared on the net. The 4BSD compilers will not put `short' or `char' variables in registers, and memory references are slower than register references; hence 32 bit arithmetic is often faster than 16 or 8 bit arithmetic on a Vax. -- In-Real-Life: Chris Torek, Univ of MD Comp Sci Dept (+1 301 454 7690) Domain: chris@mimsy.umd.edu Path: seismo!mimsy!chris