Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!utgpu!water!watnot!watmath!clyde!cbatt!ucbvax!JHUNIX.BITNET!ins_ajbh
From: ins_ajbh@JHUNIX.BITNET.UUCP
Newsgroups: mod.computers.vax
Subject: Hidden floating point use?
Message-ID: <8703140320.AA08495@ucbvax.Berkeley.EDU>
Date: Thu, 12-Mar-87 14:37:09 EST
Article-I.D.: ucbvax.8703140320.AA08495
Posted: Thu Mar 12 14:37:09 1987
Date-Received: Sat, 14-Mar-87 15:33:08 EST
Sender: daemon@ucbvax.BERKELEY.EDU
Distribution: world
Organization: The ARPA Internet
Lines: 9
Approved: info-vax@sri-kl.arpa

Does an assembler instruction of the following form

 MOV      (R0)[R1], R3

kick in the floating point hardware on a 785? R0 points to a
array of longwords. The reason for the question is that I have a
program that runs much faster on a machine with FPA than on a
machine without FPA but has no obvious floating instructions. I could
see it evaluating "Address(R0) + 4*R1" this way.