Article View: comp.sys.masscomp
Article #201Extended precision arithmetic in FPP's
From: Martin Francis Ryba
Date: Thu, 08 Jun 1989 07:51
Date: Thu, 08 Jun 1989 07:51
22 lines
1436 bytes
1436 bytes
To those who have problems with 64-bit reals: We've got a MC5500, (runs the 68000) and I notice that the FPP is limited to double precision real #'s. Meanwhile Motorola has gone ahead and now has FPP's (68881 I believe) that support something called extended precision (64 bits for fraction as opposed to 52), a 12-byte entity, that it says conforms to IEEE Binary Real Standard. Does this really exist and is accesible to the programmer? Is there a FPP unit that runs on a Masscomp that supports this? Please email any good ideas, since the kludges that I envision to get around this are *really* hairy. Marty Ryba Dept. of Physics, Princeton U. marty%puppsr@phoenix.princeton.edu (most mailers barf on puppsr direct) mfryba@phoenix.princeton.edu (always works) The MASSCOMP USERS' SOCIETY newsgroup is comp.sys.masscomp. Articles to: masscomp@soma.bcm.tmc.edu or uunet!soma.bcm.tmc.edu!masscomp Administrative stuff: masscomp-request@soma.bcm.tmc.edu Stan Barber, Moderator
Technical Details
Message-ID:
<1560@gazette.bcm.tmc.edu>Path:
arc1-ca.pugleaf.net!utzoo!utgpu!jarvis.csri.toronto.edu!rutgers!cs.utexas.edu!bcm!soma!masscomp-requestShow Full Headers
Complete Article Headers
Path: arc1-ca.pugleaf.net!utzoo!utgpu!jarvis.csri.toronto.edu!rutgers!cs.utexas.edu!bcm!soma!masscomp-request From: mfryba@phoenix.princeton.edu (Martin Francis Ryba) Newsgroups: comp.sys.masscomp Subject: Extended precision arithmetic in FPP's Message-ID: <1560@gazette.bcm.tmc.edu> Date: 8 Jun 89 07:51:24 GMT Sender: usenet@bcm.tmc.edu Lines: 22 Approved: masscomp@soma.neuro.bcm.tmc.edu Cc: mfryba@phoenix.princeton.edu Status: R