As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
Power consumption is a critical consideration in high performance computing systems and it's becoming the limiting factor to build and operate Petascale and Exascale systems. When studying the power consumption of existing systems running HPC workloads, we find power, energy and performance are closely related leading to the possibility to optimize energy without sacrificing (much or at all) performance.
This paper starts by analyzing the power consumption of different HPC workloads at various levels of the server (processor, memory, io) across different blade systems using different processor micro-architectures (IBM Power6 blades, Intel Hapertown and Nehalem blades). It proposes a model to predict the power consumption of real workloads based on their performance characteristics measured by hardware performance counters (HPM). It shows the power estimation model achieves less than 2% error versus actual measurements. It shows the impact of over clocking and down clocking processor frequency on both power, performance and energy on the same set of HPC workloads and platforms as above.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.