The performance of multithreaded applications on multicore architectures
depends largely on locality and communication. However, most performance
analyses are architecture-dependent, and hence insights gleaned from an
application's behavior on one platform may not apply when the application is
run on another. In contrast, architecture-independent metrics allow a
program's performance to be analyzed across a range of architectures without
incurring the overhead of repeated profiling and analysis. We propose
multicore-aware reuse distance, which captures the inherent locality
properties of an application along with the impact of inter-thread data
interactions. We then show how statistical sampling and parallelization can
speed this analysis up by orders of magnitude with minimal loss of accuracy,
enabling the use of privatized O(1) data structures, reduced
synchronization, and sampling rates as low as one in a million.
Improving the Speed and Quality of Architectural Performance Evaluation

15.03.2012
Ημερομηνία : 15.03.2012
Ώρα : 12:00-13:00
Μέρος : STEP-C Aίθουσα Συναντήσεων, Κτίριο Β (1ος όροφος), ΙΤΕ, Ηράκλειο, Κρήτη
Φιλοξενείται από : Μπίλας Άγγελος
Vijay S. Pai [https://engineering.purdue.edu/~vpai] received his PhD from
Rice University in 2000. He joined the faculty of Purdue University in 2004
after serving as an assistant professor at Rice University and a senior
developer at iMimic Networking. He received the NSF CAREER award in 2003 and
the Wilfred "Duke" Hesselberth Award for Teaching Excellence in 2007. He was
a primary developer and maintainer of the publicly-available Rice Simulator
for ILP Multiprocessors (RSIM), and has advised the creation and free public
distribution of Spinach (network interface simulator), Toast (peer-to-peer
video-on-demand system), and SpeakAll! (augmented communication iPad app for
teachers of special-needs children).