Milind Bhandarkar

Bio: Milind Bhandarkar is an academic researcher from University of Illinois at Urbana–Champaign. The author has contributed to research in topics: Load balancing (computing) & Component-based software engineering. The author has an hindex of 14, co-authored 25 publications receiving 2840 citations.

Adaptive Load Balancing for MPI Programs

Abstract: Parallel Computational Science and Engineering (CSE) applications often exhibit irregular structure and dynamic load patterns. Many such applications have been developed using MPI. Incorporating dynamic load balancing techniques at the application-level involves significant changes to the design and structure of applications. On the other hand, traditional run-time systems for MPI do not support dynamic load balancing. Object-based parallel programming languages, such as Charm++ support efficient dynamic load balancing using object migration. However, converting legacy MPI applications to such object-based paradigms is cumbersome. This paper describes an implementation of MPI, called Adaptive MPI (AMPI) that supports dynamic load balancing for MPI applications. Conversion from MPI to this platform is straightforward even for large legacy codes. We describe our positive experience in converting the component codes ROCFLO and ROCSOLID of a Rocket Simulation application to AMPI.

Converse: an interoperable framework for parallel programming

Abstract: Many different parallel languages and paradigms have been developed, each with its own advantages. To benefit from all of them, it should be possible to link together modules written in different parallel languages in a single application. Since the paradigms sometimes differ in fundamental ways, this is difficult to accomplish. This paper describes a framework, Converse, that supports such multi-lingual interoperability. The framework is meant to be inclusive, and has been verified to support the SPMD programming style, message-driven programming, parallel object-oriented programming, and thread-based paradigms. The framework aims at extracting the essential aspects of the runtime support into a set of core components, so that language-specific code does not have to pay overhead for features that it does not need.

Object-Based Adaptive Load Balancing for MPI Programs∗

Abstract: Parallel Computational Science and Engineering (CSE) applications often exhibit irregular structure and dynamic load patterns. Many such applications have been developed using procedural languages (e.g. Fortran) in message passing parallel programming paradigm (e.g. MPI) for distributed memory machines. Incorporating dynamic load balancing techniques at the application-level involves significant changes to the design and structure of applications. On the other hand, traditional run-time systems for MPI do not support dynamic load balancing. Object-based parallel programming languages, such as Charm++ support efficient dynamic load balancing using object migration for irregular and dynamic applications, as well as to deal with external factors that cause load imbalance. However, converting legacy MPI applications to such object-based paradigms is cumbersome. This paper describes an implementation of MPI, called Adaptive MPI (AMPI) that supports dynamic load balancing and multithreading for MPI applications. Our approach and implementation is based on the user-level migrating threads and load balancing capabilities provided by the Charm++ framework. Conversion from legacy codes to this platform is straightforward even for large legacy codes. We have converted the component codes ROCFLO and ROCSOLID of a Rocket Simulation application to AMPI. Our experience shows that with a minimal overhead and effort, one can incorporate dynamic load balancing capabilities in legacy Fortran-MPI codes.

Run-Time Support for Adaptive Load Balancing

Abstract: Many parallel scientific applications have dynamic and irregular computational structure. However, most such applications exhibit persistence of computational load and communication structure. This allows us to embed measurement-based automatic load balancing framework in run-time systems of parallel languages that are used to build such applications. In this paper, we describe such a framework built for the Converse [4] in teroperable runtime system. This framework is composed of mechanisms for recording application performance data, a mechanism for object migration, and interfaces for plug-in load balancing strategy objects. In terfaces for strategy objects allow easy implementation of novel load balancing strategies that could use application characteristics on the entire machine, or only a local neighborhood. We present the performance of a few strategies on a synthetic benchmark and also the impact of automatic load balancing on an actual application.

UCSF Chimera--a visualization system for exploratory research and analysis.

Abstract: The design, implementation, and capabilities of an extensible visualization system, UCSF Chimera, are discussed. Chimera is segmented into a core that provides basic services and visualization, and extensions that provide most higher level functionality. This architecture ensures that the extension mechanism satisfies the demands of outside developers who wish to incorporate new features. Two unusual extensions are presented: Multiscale, which adds the ability to visualize large-scale molecular assemblies such as viral coats, and Collaboratory, which allows researchers to share a Chimera session interactively despite being at separate locales. Other extensions include Multalign Viewer, for showing multiple sequence alignments and associated structures; ViewDock, for screening docked ligand orientations; Movie, for replaying molecular dynamics trajectories; and Volume Viewer, for display and analysis of volumetric data. A discussion of the usage of Chimera in real-world situations is given, along with anticipated future directions. Chimera includes full user documentation, is free to academic and nonprofit users, and is available for Microsoft Windows, Linux, Apple Mac OS X, SGI IRIX, and HP Tru64 Unix from http://www.cgl.ucsf.edu/chimera/.

Fast parallel algorithms for short-range molecular dynamics

Abstract: Three parallel algorithms for classical molecular dynamics are presented. The first assigns each processor a fixed subset of atoms; the second assigns each a fixed subset of inter-atomic forces to compute; the third assigns each a fixed spatial region. The algorithms are suitable for molecular dynamics models which can be difficult to parallelize efficiently—those with short-range forces where the neighbors of each atom change rapidly. They can be implemented on any distributed-memory parallel machine which allows for message-passing of data between independently executing processors. The algorithms are tested on a standard Lennard-Jones benchmark problem for system sizes ranging from 500 to 100,000,000 atoms on several parallel supercomputers--the nCUBE 2, Intel iPSC/860 and Paragon, and Cray T3D. Comparing the results to the fastest reported vectorized Cray Y-MP and C90 algorithm shows that the current generation of parallel machines is competitive with conventional vector supercomputers even for small problems. For large problems, the spatial algorithm achieves parallel efficiencies of 90% and a 1840-node Intel Paragon performs up to 165 faster than a single Cray C9O processor. Trade-offs between the three algorithms and guidelines for adapting them to more complex molecular dynamics simulations are also discussed.

Scalable molecular dynamics with NAMD

Abstract: NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD scales to hundreds of processors on high-end parallel platforms, as well as tens of processors on low-cost commodity clusters, and also runs on individual desktop and laptop computers. NAMD works with AMBER and CHARMM potential functions, parameters, and file formats. This article, directed to novices as well as experts, first introduces concepts and methods used in the NAMD program, describing the classical molecular dynamics force field, equations of motion, and integration methods along with the efficient electrostatics evaluation algorithms employed and temperature and pressure controls used. Features for steering the simulation across barriers and for calculating both alchemical and conformational free energy differences are presented. The motivations for and a roadmap to the internal design of NAMD, implemented in C++ and based on Charm++ parallel objects, are outlined. The factors affecting the serial and parallel performance of a simulation are discussed. Finally, typical NAMD use is illustrated with representative applications to a small, a medium, and a large biomolecular system, highlighting particular features of NAMD, for example, the Tcl scripting language. The article also provides a list of the key features of NAMD and discusses the benefits of combining NAMD with the molecular graphics/sequence analysis software VMD and the grid computing/collaboratory software BioCoRE. NAMD is distributed free of charge with source code at www.ks.uiuc.edu.

The Amber biomolecular simulation programs

Abstract: We describe the development, current features, and some directions for future development of the Amber package of computer programs. This package evolved from a program that was constructed in the late 1970s to do Assisted Model Building with Energy Refinement, and now contains a group of programs embodying a number of powerful tools of modern computational chemistry, focused on molecular dynamics and free energy calculations of proteins, nucleic acids, and carbohydrates.