| | |
Summary: A First-Order Fine-Grained Multithreaded Throughput Model
Xi E. Chen Tor M. Aamodt
Department of Electrical and Computer Engineering
University of British Columbia, Vancouver, BC, CANADA
{xichen, aamodt}@ece.ubc.ca
Abstract
Analytical modeling is an alternative to detailed perfor-
mance simulation with the potential to shorten the devel-
opment cycle and provide additional insights. This paper
proposes analytical models for predicting the cache con-
tention and throughput of heavily multithreaded architec-
tures such as Sun Microsystems' Niagara. First, it pro-
poses a novel probabilistic model to accurately predict
the number of extra cache misses due to cache contention
for significantly larger numbers of threads than possible
with prior analytical cache contention models. Then it
presents a Markov chain model for analytically estimating
the throughput of multicore, fine-grained multithreaded ar-
chitectures. The Markov model uses the number of stalled
threads as the states and calculates transition probabili-
|
