Performance Engineering: A Must for Petaflops and Beyond
نویسندگان
چکیده
We discuss the need for a more principled approach to the management of the performance of applications for petascale platforms and outline some initial successes, related to the Blue Waters project.
منابع مشابه
A Curriculum for Petascale Computing
A group of faculty at Purdue is working to develop a curriculum for high performance computing and cyberinfrastructure [1]. Current curriculum efforts are focused on developing and delivering university courses in bioinformatics systems development, grid computing and cyberinfrastructure, algorithms, biomedical informatics, high performance computing systems, and scientific and information visu...
متن کاملThe PetaFlops Router: Harnessing FPGAs and Accelerators for High Performance Computing
The PetaFlops Router is a new approach to computing wherein network architecture and compute decisions are customized for a particular application. New FieldProgrammable Gate Array (FPGA) and router technologies including multi-gigabit transceivers and application specific blocks can provide vastly improved performance. The PetaFlops Router provides greatly improved data transfer rates, computa...
متن کاملPower Allocation and Task Scheduling on Multiprocessor Computers with Energy and Time Constraints
Performance-driven computer development has lasted for over six decades. Computers have been developed to achieve higher performance. As of June 2010, three supercomputers have achieved petaflops speed: Cray Jaguar (224,162 processors, 1.759 petaflops), Dawning Nebulae (120,640 processors, 1.271 petaflops), and IBM Roadrunner (122,400 processors, 1.042 petaflops) (1). According to Moore’s law o...
متن کاملDevelopment of an Efficient Hybrid Method for Motif Discovery in DNA Sequences
This work presents a hybrid method for motif discovery in DNA sequences. The proposed method called SPSO-Lk, borrows the concept of Chebyshev polynomials and uses the stochastic local search to improve the performance of the basic PSO algorithm as a motif finder. The Chebyshev polynomial concept encourages us to use a linear combination of previously discovered velocities beyond that proposed b...
متن کاملHigh-performance computing: clusters, constellations, MPPs, and future directions
Last year’s paper by Bell and Gray [1] examined past trends in high performance computing and asserted likely future directions based on market forces. While many of the insights drawn from this perspective have merit and suggest elements governing likely future directions for HPC, there are a number of points put forth that we feel require further discussion and, in certain cases, suggest alte...
متن کامل