Analytical Energy Model Parametrized by Workload, Clock Frequency and Number of Active Cores for Share-Memory High-Performance Computing Applications
نویسندگان
چکیده
Energy consumption is crucial in high-performance computing (HPC), especially to enable the next exascale generation. Hence, modern systems implement various hardware and software features for power management. Nonetheless, due numerous different implementations, we can always push limits of achieve most efficient use our hardware. To be energy efficient, relies on dynamic voltage frequency scaling (DVFS), as well management (DPM). Yet, none have privileged information architecture application behavior, which may lead energy-inefficient operation. This study proposes analytical modeling behavior that used estimate energy-optimal configurations provide knowledgeable hints improve DVFS DPM techniques single-node HPC applications. Additionally, model parameters, such level parallelism power, insights into how modeled consumes energy, helpful energy-efficient development novel takes number active cores, operating frequencies, input size inputs estimation. We present 13 parallel applications employed determine several sizes. The results show up 70% could saved best scenario compared default Linux choice 14% average. also compare proposed with standard machine-learning concerning training overhead accuracy. approach generates about 10 times less same
منابع مشابه
High-performance Energy Minimization with Applications to Adiabatic Quantum Computing
Energy minimization of Ising spin-glasses has played a central role in statistical and solid-state physics, facilitating studies of phase transitions and magnetism. Recent proposals suggest using Ising spin-glasses for non-traditional computing as a way to harness the nature’s ability to find min-energy configurations, and to take advantage of quantum tunneling to boost combinatorial optimizati...
متن کاملComparative Energy and Delay of Energy Recovery and Square Wave Clock Flip-Flops for High-Performance and Low-Power Applications
Flip-flops are essential elements of a design from both delay and energy aspects. A significant fraction of the total power in highly synchronous systems 1s dissipated over clock networks. Hence, lowpower clocking schemes are promising approaches for future desfgns. Recently, there has been published several energy recovery flip-flops that enable energy recovery from the clock network, resultin...
متن کاملSynthetic Workload Generation for Cloud Computing Applications
We present techniques for characterization, modeling and generation of workloads for cloud computing applications. Methods for capturing the workloads of cloud computing applications in two different models benchmark application and workload models are described. We give the design and implementation of a synthetic workload generator that accepts the benchmark and workload model specifications ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Energies
سال: 2022
ISSN: ['1996-1073']
DOI: https://doi.org/10.3390/en15031213