Index for cjcoats.github.io


Optimizing Environmental Models for Microprocessor Based Systems — The Easy Stuff
Computational efficiency is environmental models is affected greatly by two things: (1) that computer memory is far slower than the processors, and filtered through a "cache" system; and (2) that the processors are deeply pipelined and superscalar, attempting to run many instructions (in various stages of completion) at one time.

This started as a presentation for US EPA's Office of Research and Development in 2002 when the author was at MCNC—North Carolina Supercomputing Center, and has been updated from time to time since. It is amazing just how well the lessons of that time have held up—the only thing is that the tendencies noted in 2002 have become even stronger over time—main memory (and even caches) is even slower relative to processor-cores, for example

The Models-3 I/O API
The Models-3/EDSS Input/Output Applications Programming Interface (I/O API) provides the environmental model developer with an easy-to-learn, easy-to-use programming library for data storage and access, available from both Fortran and C. The I/O API provides a variety of data structure types for organizing the data, and a set of access routines which offer selective direct access to the data in terms meaningful to the modeler, as well as robust error checking and reporting "behind the scenes".

For example,

Read layer 1 of variable 'OZONE' from 'CONCFILE' for 5:00 PM GMT on July 19, 2018 and put the result into array A.
is the direct English translation of a typical I/O API READ3() call.

I/O API Home Page

I/O API Programmers Manual

PAVE-3.0
The Package for Analysis and Visualization of Environmental data (PAVE) is a flexible tool to visualize multivariate gridded environmental datasets. PAVE Version 3.0 is a new release, restructured as a stand-alone application, with major optimizations (after the fashion of Optimizing Environmental Models, above), with Linux "medium memory-model support", so that file size, etc., is essentially limited by available RAM and inherent netCDF limitations,

PAVE Users Guide

PAVE Frequently Asked Questions