Nyx: A Massively Parallel AMR Code for Computational Cosmology

نویسندگان

چکیده

Author(s): Sexton, Jean; Lukic, Zarija; Almgren, Ann; Daley, Chris; Friesen, Brian; Myers, Andrew; Zhang, Weiqun

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Towards a New Massively Parallel Computational Model for Logic Programming

The semantics of logic programs is commonly deened as the least xed point of an appropriate meaning operator. In case of normal programs, however, some undesired results do occur and it has recently been suggested to apply metric methods in order to overcome these problems. We show in this paper that these metric methods can be directly implemented by recurrent connectionist networks giving ris...

متن کامل

Towards a New Massively Parallel Computational Model for Logic Programming

The semantics of logic programs is commonly deened as the least xed point of an appropriate meaning operator. In case of normal programs, however, some undesired results do occur and it has recently been suggested to apply metric methods in order to overcome these problems. We show in this paper that these metric methods can be directly implemented by recurrent connectionist networks giving ris...

متن کامل

Vectorization of astrophysical code for massively parallel supercomputers

We describe a new version of our AstroPhi code for the simulation of astrophysical objects dynamics and other physical processes on hybrid supercomputers equipped with Intel Xeon Phi accelerators. The new version of the AstroPhi code was rewritten in accordance with co-design technique. Thus, we used the latest knowledge about the last Intel Xeon Phi generation during code development. The most...

متن کامل

The Challenges of Efficient Code-Generation for Massively Parallel Architectures

Overcoming the memory wall [15] may be achieved by increasing the bandwidth and reducing the latency of the processor to memory connection, for example by implementing Cellular architectures, such as the IBM Cyclops. Such massively parallel architectures have sophisticated memory models. In this paper we used DIMES (the Delaware Iterative Multiprocessor Emulation System), developed by CAPSL at ...

متن کامل

ذخیره 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: Journal of open source software

سال: 2021

ISSN: ['2475-9066']

DOI: https://doi.org/10.21105/joss.03068