Basic HTML version of Foils prepared October 2 1998

Foil 17 JGF Proposed FP Execution Modes

From Java Grande (a.k.a. Java for High Performance Computing) in a Nutshell Sun MicroSystems Java Day at MIT (Marriot Hotel Cambridge MA) -- Sept 25 1998. by Geoffrey C. Fox
1 Language Chip Architecture
2 Modifier x86 PowerPC SPARC
3
4 strictfp Java 1.0 (no double Java 1.0 Java 1.0
5 rounding on underflow) (no fused mac)
6 default i.e. larger exponent range fused mac can Java 1.0
7 no modifier allowed be used
8 associativefp many optimizations allowed on all platforms
9 Current default is essentially strictfp although not always implemented precisely
10 mac is fused hardware multiply-add (a*b+c)
11 strictfp is a little more than 2 times slower than default on INTEL x86 for a vector dot product
in Table To:

© Northeast Parallel Architectures Center, Syracuse University, npac@npac.syr.edu

If you have any comments about this server, send e-mail to webmaster@npac.syr.edu.

Page produced by wwwfoil on Sat Nov 28 1998