scholarly journals Power, Performance, and Thermal Management for High-Performance Systems

2007 ◽  
Author(s):  
Heather Hanson ◽  
Stephen W. Keckler ◽  
Karthick Rajamani ◽  
Soraya Ghiasi ◽  
Freeman Rawson ◽  
...  
Keyword(s):  
Thermal Management ◽  
High Performance ◽  
Power Performance ◽  
High Performance Systems

Advanced Packaging and Thermal Management of High-Power DC-DC Converters

2019 ◽  
Author(s):  
Sevket U. Yuruker ◽  
Raphael K. Mandel ◽  
Patrick McCluskey ◽  
Michael M. Ohadi ◽  
Shiladri Chakraborty ◽  
...  
Keyword(s):  
Thermal Management ◽  
High Power ◽  
High Performance ◽  
Magnetic Core ◽  
Dual Active Bridge ◽  
Thermally Conductive ◽  
Significant Area ◽  
Unique Shape ◽  
Advanced Packaging ◽  
High Performance Systems

Abstract Thermal management of high-power electronics is often a major obstacle in achieving improved packaging density. Emergence of SiC devices allows higher voltage and temperature limits, but thermal management is still a bottleneck in achieving compact, reliable and high-performance systems. This study introduces the design of an advanced packaging configuration of a dual-active-bridge 10 kW DC-DC converter module with 97% efficiency and ∼1.5 × 104 kW/m3 power density based on preliminary modeling analysis. The proposed packaging scheme allows for significant volume reduction and considerably lighter weight at greater power levels than commercially available converter modules. We introduce an improved placement of high power/high frequency MOSFET switches on the board that enables double-sided cooling, where the dissipated heat is removed from both sides of the switches via manifold-microchannel cooler modules. The cooler modules are additively manufactured monolithic structures made out of a thermally and electrically conductive material, which in turn allows them to double function as electrical terminals for the switches. Their unique shape minimizes footprint utilization on the board while still providing significant area enhancement over the heat dissipating chips’ footprint. Moreover, thermal management of other components with significant heat flux, such as the transformer coils and magnetic core are also accomplished via dielectric liquid cooling with electrically insulating but thermally conductive 3D printed coolers. The overall circuit diagram, assembly configuration and flow routing within the system are demonstrated. The advantages of the proposed design over commercially available modules are discussed in detail.

Energy Profiling and Analysis of the HPC Challenge Benchmarks

2009 ◽  
Vol 23 (3) ◽  
pp. 265-276 ◽  
Author(s):  
Shuaiwen Song ◽  
Rong Ge ◽  
Xizhou Feng ◽  
Kirk W. Cameron
Keyword(s):  
Power Consumption ◽  
High Performance ◽  
System Size ◽  
Power Performance ◽  
Performance Profiling ◽  
Energy Profiles ◽  
Depth Analysis ◽  
High Performance Systems ◽  
Access Patterns ◽  
Power And Energy

Future high performance systems must use energy efficiently to achieve petaFLOPS computational speeds and beyond. To address this challenge, we must first understand the power and energy characteristics of high performance computing applications. In this paper, we use a power-performance profiling framework called Power-Pack to study the power and energy profiles of the HPC Challenge benchmarks. We present detailed experimental results along with in-depth analysis of how each benchmark's workload characteristics affect power consumption and energy efficiency. This paper summarizes various findings using the HPC Challenge benchmarks, including but not limited to: 1) identifying application power profiles by function and component in a high performance cluster; 2) correlating applications' memory access patterns to power consumption for these benchmarks; and 3) exploring how energy consumption scales with system size and workload.

Extending PowerPack for Profiling and Analysis of High-Performance Accelerator-Based Systems

2014 ◽  
Vol 24 (04) ◽  
pp. 1442001
Author(s):  
Bo Li ◽  
Hung-Ching Chang ◽  
Shuaiwen Song ◽  
Chun-Yi Su ◽  
Timmy Meyer ◽  
...  
Keyword(s):  
High Performance ◽  
Energy Use ◽  
Individual Component ◽  
Experimental Studies ◽  
Xeon Phi ◽  
Hardware Support ◽  
Power Performance ◽  
Host Processor ◽  
High Performance Systems ◽  
Power And Energy

Accelerators offer a substantial increase in efficiency for high-performance systems offering speedups for computational applications that leverage hardware support for highly-parallel codes. However, the power use of some accelerators exceeds 200 watts at idle which means use at exascale comes at a significant increase in power at a time when we face a power ceiling of about 20 megawatts. Despite the growing domination of accelerator-based systems in the Top500 and Green500 lists of fastest and most efficient supercomputers, there are few detailed studies comparing the power and energy use of common accelerators. In this work, we conduct detailed experimental studies of the power usage and distribution of Xeon-Phi-based systems in comparison to the NVIDIA Tesla and an Intel Sandy Bridge multicore host processor. In contrast to previous work, we focus on separating individual component power and correlating power use to code behavior. Our results help explain the causes of power-performance scalability for a set of HPC applications.

МЕТОДЫ ДОСТИЖЕНИЯ МАКСИМАЛЬНОЙ ЭФФЕКТИВНОСТИ ПЛАТФОРМЫ ПРОТОТИПИРОВАНИЯ ВЫСОКОПРОИЗВОДИТЕЛЬНЫХ СИСТЕМ НА КРИСТАЛЛЕ НА ЗАДАЧАХ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА

2020 ◽  
Vol 96 (3s) ◽  
pp. 585-588
Author(s):  
С.Е. Фролова ◽  
Е.С. Янакова
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Computer Vision ◽  
High Performance ◽  
Systems On Chip ◽  
High Performance Systems ◽  
On Chip ◽  
Network Technologies ◽  
Neural Network Technologies

Предлагаются методы построения платформ прототипирования высокопроизводительных систем на кристалле для задач искусственного интеллекта. Изложены требования к платформам подобного класса и принципы изменения проекта СнК для имплементации в прототип. Рассматриваются методы отладки проектов на платформе прототипирования. Приведены результаты работ алгоритмов компьютерного зрения с использованием нейросетевых технологий на FPGA-прототипе семантических ядер ELcore. Methods have been proposed for building prototyping platforms for high-performance systems-on-chip for artificial intelligence tasks. The requirements for platforms of this class and the principles for changing the design of the SoC for implementation in the prototype have been described as well as methods of debugging projects on the prototyping platform. The results of the work of computer vision algorithms using neural network technologies on the FPGA prototype of the ELcore semantic cores have been presented.

scholarly journals High-performance chemical- and light-inducible recombinases in mammalian cells and mice

2019 ◽  
Vol 10 (1) ◽  
Author(s):  
Benjamin H. Weinberg ◽  
Jang Hwan Cho ◽  
Yash Agarwal ◽  
N. T. Hang Pham ◽  
Leidy D. Caraballo ◽  
...  
Keyword(s):  
Gene Expression ◽  
Mammalian Cells ◽  
High Performance ◽  
Genome Engineering ◽  
Genetic Circuits ◽  
Control Of Gene Expression ◽  
Expression Control ◽  
Gene Expression Control ◽  
High Performance Systems ◽  
Spatiotemporal Control

Abstract Site-specific DNA recombinases are important genome engineering tools. Chemical- and light-inducible recombinases, in particular, enable spatiotemporal control of gene expression. However, inducible recombinases are scarce due to the challenge of engineering high performance systems, thus constraining the sophistication of genetic circuits and animal models that can be created. Here we present a library of >20 orthogonal inducible split recombinases that can be activated by small molecules, light and temperature in mammalian cells and mice. Furthermore, we engineer inducible split Cre systems with better performance than existing systems. Using our orthogonal inducible recombinases, we create a genetic switchboard that can independently regulate the expression of 3 different cytokines in the same cell, a tripartite inducible Flp, and a 4-input AND gate. We quantitatively characterize the inducible recombinases for benchmarking their performances, including computation of distinguishability of outputs. This library expands capabilities for multiplexed mammalian gene expression control.

Optimal Flow Control and Single Split Architecture Exploration for Fluid-Based Thermal Management

2018 ◽  
Author(s):  
Satya R. T. Peddada ◽  
Daniel R. Herber ◽  
Herschel C. Pangborn ◽  
Andrew G. Alleyne ◽  
James T. Allison
Keyword(s):  
Flow Control ◽  
Thermal Management ◽  
High Performance ◽  
Dynamic Models ◽  
Cooling System ◽  
Rooted Tree ◽  
Modeling Framework ◽  
System Architectures ◽  
Tree Graphs ◽  
Heat Loads

High-performance cooling is often necessary for thermal management of high power density systems. Both human intuition and vast experience may not be adequate to identify optimal thermal management designs as systems increase in size and complexity. This paper presents a design framework supporting comprehensive exploration of a class of single phase fluid-based cooling architectures. The candidate cooling system architectures are represented using labeled rooted tree graphs. Dynamic models are automatically generated from these trees using a graph-based thermal modeling framework. Optimal performance is determined by solving an appropriate fluid flow control problem, handling temperature constraints in the presence of exogenous heat loads. Rigorous case studies are performed in simulation, with components having variable sets of heat loads and temperature constraints. Results include optimization of thermal endurance for an enumerated set of 4,051 architectures. In addition, cooling system architectures capable of steady-state operation under a given loading are identified.

Sign in / Sign up

Export Citation Format

Share Document