Abstract
As computation intensive scientific applications rely on high performance computing (HPC), energy consumption is a challenging issue. Reducing energy consumption is a major design constraint for modern heterogeneous computing systems. Conventional energy efficient scheduling strategies developed on distributed systems do not sufficiently exploit the system elasticity and adaptability for maximum energy savings. The conventional scheduling algorithm, dynamic power management (DPM) or dynamic voltage and frequency scaling (DVFS) do not simultaneously take account of energy usage and optimal system performance. In this paper, a novel scheduling strategy on DVFS enabled HPC clusters is proposed.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have