HPM "zeros" were counted for the smallest possible null but complete program and one well-known program ("Hello world") using four languages. The program start up overhead is measureable but unseen. Various system load conditions (dedicated versus loaded systems) were measured using different hardware configurations. The resulting measures are neither intuitively obvious nor consistent at first glance.
We conclude that extensive HPM zeroing and scaling are needed for all languages and compilers, but a documented "zero" measurement is essential for future measurement interpretions. The "zero" point deserves special mention, because it is the starting point and easily obtained. Finally, simple output improvements are suggested.
About the speaker:
The NASA technical reviewer the the Joint NSF/DARPA/NASA Digital Libraries Initiative. Associate Editor for Publication and Software Reviews for the Journal of Scientific Programming (a quarterly). One of the moderators of comp.parallel. Research interests are in performance measurement and image processing of remtoely sensed images. Probably best known for the network concept of FAQs. Past President of the Bay Area ACM/SIGGRAPH. Steering Committee of the Hackers Conference. Member of the US Antartic Program. Honorary Glaciologist. Honorary Berkeley UNIX Wizard. Undergrad degree in mathematics from UCSB.
Contact information:
Eugene Miya
Applied Information Systems Division
NASA Ames Research Center
eugene@george.arc.nasa.gov