Revision as of 15:04, 2 May 2016 edit Int512 (talk \| contribs) 19 edits remove incorrect statistics, x86 and x86-64 is much more complicated than "read size = general purpose register size" and would be too much detail ← Previous edit		Revision as of 19:24, 4 May 2016 edit undo Cyberbot II (talk \| contribs) Bots, Pending changes reviewers 469,753 edits Rescuing 1 sources. #IABot Next edit →
Line 57: ==Implementations== Octuple precision is rarely implemented since usage of it is extremely rare. [[Apple Inc.]] had an implementation of addition, subtraction and multiplication of octuple-precision numbers with a 224-bit [[two's complement]] significand and a 32-bit exponent.<ref>{{cite web \| url=~~https://web.archive.org/web/20060728140052/~~http://images.apple.com/ca/acg/pdf/oct3a.pdf \| title=Octuple-precision floating point on Apple G4 (archived copy on web.archive.org) \| author1=R. Crandall \| author2=J. Papadopoulos \| date=8 May 2002 \|deadurl=unfit \|archiveurl=https://web.archive.org/web/20060728140052/http://images.apple.com/ca/acg/pdf/oct3a.pdf \|archivedate=July 28, 2006 }}</ref> One can use general [[arbitrary-precision arithmetic]] libraries to obtain octuple (or higher) precision, but specialized octuple-precision implementations may achieve higher performance. === Hardware support ===

Octuple-precision floating-point format: Difference between revisions