GRACOS: Scalable and Load Balanced P3M Cosmological N-body Code

Alexander Shirokov; Edmund Bertschinger

Home/Archive/arXiv

arXiv · astro-ph/0505087

GRACOS: Scalable and Load Balanced P3M Cosmological N-body Code

Alexander Shirokov·Edmund Bertschinger

View original source ↗Read source document ↗Export metadata ↓

Abstract

We present a parallel implementation of the particle-particle/particle-mesh (P3M) algorithm for distributed memory clusters. The GRACOS (GRAvitational COSmology) code uses a hybrid method for both computation and domain decomposition. Long-range forces are computed using a Fourier transform gravity solver on a regular mesh; the mesh is distributed across parallel processes using a static one-dimensional slab domain decomposition. Short-range forces are computed by direct summation of close pairs; particles are distributed using a dynamic domain decomposition based on a space-filling Hilbert curve. A nearly-optimal method was devised to dynamically repartition the particle distribution so as to maintain load balance even for extremely inhomogeneous mass distributions. Tests using $800^3$ simulations on a 40-processor beowulf cluster showed good load balance and scalability up to 80 processes. We discuss the limits on scalability imposed by communication and extreme clustering and suggest how they may be removed by extending our algorithm to include adaptive mesh refinement.

Explore related subjects

astro-ph

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Alexander Shirokov, Edmund Bertschinger. 2005-05-05. GRACOS: Scalable and Load Balanced P3M Cosmological N-body Code. https://arxiv.org/abs/astro-ph/0505087

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2022

MOND: A consequence of the geometric Leibniz Clock

Leibniz considered the notion of the 'empty physical space' to be a meaningless abstraction, and he held firmly to the view that the only significant thing was the set of relationships between 'objects', whatever these 'objects' might be. Similarly, he was equally clear in expressing his views about Newton's universal time, which he also considered to be a meaningless abstraction. In effect, for him, time was no more than a synonym for ordered change within a material system. The process of giving quantitative realization to this duality of non-Newtonian ideas forms the core of this work. A primary result arising is that every gravitating particle is no more than a clock - the geometric Leibniz Clock - which provides all the basic things: it conserves energy and angular momentum and satisfies the Weak Equivalence Principle. When the Clock is applied to model the concept of a galactic object within which all motions are circular, the characteristic properties of the MOND galaxy (asymptotic flatness, a critical acceleration scale, the baryonic Tully-Fisher relationship) are quantitatively reproduced in the resulting Leibniz galaxy. In short, the characteristic essence of MOND has its source in the geometric Leibniz Clock.

astro-ph↗

arXiv2020

Cosmic Variance and Its Effect on the Luminosity Function Determination in Deep High z Surveys

We study cosmic variance in deep high redshift surveys and its influence on the determination of the luminosity function for high redshift galaxies. For several survey geometries relevant for HST and JWST instruments, we characterize the distribution of the galaxy number counts. This is obtained by means of analytic estimates via the two point correlation function in extended Press-Schechter theory as well as by using synthetic catalogs extracted from N-body cosmological simulations of structure formation. We adopt a simple luminosity - dark halo mass relation to investigate the environment effects on the fitting of the luminosity function. We show that in addition to variations of the normalization of the luminosity function, a steepening of its slope is also expected in underdense fields, similarly to what is observed within voids in the local universe. Therefore, to avoid introducing artificial biases, caution must be taken when attempting to correct for field underdensity, such as in the case of HST UDF i-dropout sample, which exhibits a deficit of bright counts with respect to the average counts in GOODS. A public version of the cosmic variance calculator based on the two point correlation function integration is made available on the web.

astro-ph↗

arXiv2020

Receiver control for the Submillimeter Array

Efficient operation of a submillimeter interferometer requires remote (preferably automated) control of mechanically tuned local oscillators, phase-lock loops, mixers, optics, calibration vanes and cryostats. The present control system for these aspects of the Submillimeter Array (SMA) will be described. Distributed processing forms the underlying architecture and the software is split between hardware platforms in a leader/follower arrangement. In each antenna cabin, a serial network of up to ten independent 80C196 microcontroller boards attaches to the real-time PowerPC computer (running LynxOS). A multi-threaded, gcc-compiled leader program on the PowerPC accepts top-level requests via remote procedure calls (RPC), subsequently dispatches tuning commands to the relevant follower microcontrollers, and regularly reports the system status to optical-fiber-based reflective memory for common access by the telescope monitor and error reporting system. All serial communication occurs asynchronously via encoded, variable-length packets. The microcontrollers respond to the requested commands and queries by accessing non-volatile, rewriteable lookup-tables (when appropriate) and executing embedded software that operates additional electronic devices (DACs, ADCs, etc.). Since various receiver hardware components require linear or rotary motion, each microcontroller also implements a position servo via a one-millisecond interrupt service routine which drives a DC-motor/encoder combination that remains standard across each subsystem.

astro-ph↗