Lec8Perf

# To study parallel programs performance we often use

This preview shows page 1. Sign up to view the full content.

This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: formance or x: #processors, y: performance. To study (parallel) program’s performance, we often use plotting tools n༆  gnuplot, excel, matlab … (in these slides: excel) Let’s look at increasing functions first. Example: 3 data sets f, g and h n f(n) g(n) h(n) 1 2 9 2 2 12 18 6 3 36 35 24 4 80 68 68 5 150 131 162 180" 160" 140" 120" 100" f" g" 80" h" 60" What kinds of functions are f, g and h? •  exponential? which base? •  polynomial? which order? 40" 20" 0" 1" 2" 3" 4" 5" Hard / impossible to infer 2 Why are functions hard to infer? n༆  Two problems: ¨༊ Very small domain (here 1..5) n༆  Try to get a large data domain ¨༊ Interpreting n༆  All super-linear functions from plots is hard polynomials and exponentials swoop up Larger domain n f(n) g(n) h(n) 1 2 9 2 2 12 18 6 3 36 35 24 4 80 68 68 5 150 131 162 7 400 520 624 10 1100 4106 2510 12 1872 16396 5196 18000" 16000"...
View Full Document

## This note was uploaded on 02/12/2014 for the course CS 475 taught by Professor Staff during the Fall '08 term at Colorado State.

Ask a homework question - tutors are online