We present a novel approach for accurate character-
ization of workloads. Workloads are generally de-
scribed with statistical models and are based on the
analysis of resource requests measurements of a run-
ning program. In this paper we propose to con-
sider the sequence of virtual memory references gen-
erated from a program during its execution as a tem-
poral series, and to use spectral analysis principles
to process the sequence. However, the sequence is
time-varying, so we employed processing approaches
based on Ergodic Continuous Hidden Markov Mod-
els (ECHMMs) which extend conventional stationary
spectral analysis approaches to the analysis of time-
varying sequences.
In this work, we describe two applications of the
proposed approach: the on-line classication of a run-
ning process and the generation of synthetic traces of
a given workload. The rst step was to show that
ECHMMs accurately describe virtual memory se-
quences; to this goal a dierent ECHMM was trained
for each sequence and the related run-time average
process classication accuracy, evaluated using trace
driven simulations over a wide range of traces of
SPEC2000, was about 82%. Then, a single ECHMM
was trained using all the sequences obtained from a
given running application; again, the classication
accuracy has been evaluated using the same traces
and it resulted about 76%. As regards the synthetic
trace generation, a single ECHMM characterizing a
given application has been used as a stochastic gen-
erator to produce benchmarks for spanning a large
application space.
