Abstract
Back in 1973, floating-point additions and loads from cache took perhaps 0.3 microseconds, floating-point multiplications perhaps 1 and loads from memory perhaps 2. A machine might have 4 KB of cache for 2 MB of memory, and a cache hit ratio of 90% allowed the machine to run at near-peak performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer Science+Business Media New York
About this chapter
Cite this chapter
Maclaren, N. (1999). From Flops to Udaps: Algorithms, Benchmarking and Tuning. In: Allan, R.J., Guest, M.F., Simpson, A.D., Henty, D.S., Nicole, D.A. (eds) High-Performance Computing. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-4873-7_6
Download citation
DOI: https://doi.org/10.1007/978-1-4615-4873-7_6
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-7211-0
Online ISBN: 978-1-4615-4873-7
eBook Packages: Springer Book Archive