Path: utzoo!utgpu!news-server.csri.toronto.edu!rutgers!usc!jarthur!nntp-server.caltech.edu!nntp-server.caltech.edu!ph
From: ph@ama-1.ama.caltech.edu (Paul Hardy)
Newsgroups: comp.sys.mips
Subject: MIPS FP assembler
Message-ID: <PH.90Dec5142027@ama-1.ama.caltech.edu>
Date: 5 Dec 90 22:20:27 GMT
Sender: news@nntp-server.caltech.edu
Distribution: comp
Organization: California Institute of Technology
Lines: 7
Nntp-Posting-Host: ama.caltech.edu


I re-ordered my matrix multiply subroutine to perform an add.s right after
a mul.s, and I'm now sustaining over 6 MFLOPS on a DECstation 3100 (a machine
which Digital Review rated at 3.2 LINPACK MFLOPS, and DEC rated at 3.7!)
Thanks again to Mark and Chris at MIPS for their advice (well taken).

                                   --Paul