We aim here to leverage supervised learning to enable large-scale analysis of performance
logs, in order to accurately classify code runs and understand the importance of different …

A hive plot is a network layout algorithm that uses a parallel coordinate plot in which axes
are radially arranged and node position is based on structural properties of that node [8]. We …

The Department of Energy (DOE) has the responsibility to address the energy,
environmental, and nuclear security challenges that face our nation. Much of DOE's …

Communication patterns extracted from parallel programs can provide a valuable source of
information for parallel pattern detection, application auto-tuning, and runtime workload …

This paper presents a workload classification framework that discriminates illicit computation
from authorized workloads on GPU-accelerated HPC systems. As such heterogeneous …

High Performance Computing (HPC) is a field concerned with solving large-scale problems
in science and engineering. However, the computational infrastructure of HPC systems can …

Detecting illicit workloads on High Performance Computing (HPC) systems is an important
task. Such workloads might indicate a user account is being misused, for example to run …

A critical factor for developing robust shared-memory applications is the efficient use of the
cache and the communication between threads. Inappropriate data structures, algorithm …

This paper presents a workload classification framework that accurately discriminates illicit
computation from authorized workloads on GPU-accelerated HPC systems at runtime. As …

Monitoring users on large computing platforms such as high performance computing (HPC)
and cloud computing systems is non-trivial. Utilities such as process viewers provide limited …