Specialized computational chemistry packages have permanently reshaped the landscape of chemical and materials science by providing tools to support and guide experimental efforts and for the prediction of atomistic and electronic properties. In this regard, electronic structure packages have played a special role by using first-principle-driven methodologies to model complex chemical and materials processes. Over the past few decades, the rapid development of computing technologies and the tremendous increase in computational power have offered a unique chance to study complex transformations using sophisticated and predictive many-body techniques that describe correlated behavior of electrons in molecular and condensed phase systems at different levels of theory. In enabling these simulations, novel parallel algorithms have been able to take advantage of computational resources to address the polynomial scaling of electronic structure methods. In this paper, we briefly review the NWChem computational chemistry suite, including its history, design principles, parallel tools, current capabilities, outreach, and outlook.

Scalable heterogeneous computing systems, which are composed of a mix of compute devices, such as commodity multicore processors, graphics processors, reconfigurable processors, and others, are gaining attention as one approach to continuing performance improvement while managing the new challenge of energy efficiency. As these systems become more common, it is important to be able to compare and contrast architectural designs and programming systems in a fair and open forum. To this end, we have designed the Scalable HeterOgeneous Computing benchmark suite (SHOC). SHOC's initial focus is on systems containing graphics processing units (GPUs) and multi-core processors, and on the new OpenCL programming standard. SHOC is a spectrum of programs that test the performance and stability of these scalable heterogeneous computing systems. At the lowest level, SHOC uses microbenchmarks to assess architectural features of the system. At higher levels, SHOC uses application kernels to determine system-wide performance including many system features such as intranode and internode communication among devices. SHOC includes benchmark implementations in both OpenCL and CUDA in order to provide a comparison of these programming models.

This paper describes capabilities, evolution, performance, and applications of the Global Arrays (GA) toolkit. GA was created to provide application programmers with an inteface that allows them to distribute data while maintaining the type of global index space and programming syntax similar to that available when programming on a single processor. The goal of GA is to free the programmer from the low level management of communication and allow them to deal with their problems at the level at which they were originally formulated. At the same time, compatibility of GA with MPI enables the programmer to take advatage of the existing MPI software/libraries when available and appropriate. The variety of applications that have been implemented using Global Arrays attests to the attractiveness of using higher level abstractions to write parallel code.

This paper describes the Aggregate Remote Memory Copy Interface (ARMCI), a portable high performance remote memory access communication interface, developed oriinally under the U.S. Department of Energy (DOE) Advanced Computational Testing and Simulation Toolkit project and currently used and advanced as a part of the run-time layer of the DOE project, Programming Models for Scalble Parallel Computing. The paper discusses the model, addresses challenges of portable implementations, and demonstrates that ARMCI delivers high performance on a variety of platforms. Special emphasis is placed on the latency hiding mechanisms and ability to optimize noncotiguous data transfers.

This paper describes a novel methodology for implementing a common set of collective communication operations on clusters based on symmetric multiprocessor (SMP) nodes. Called Shared-Remote-Memory collectives, or SRM, our approach replaces the point-to-point message passing, traditionally used in implementation of collective message-passing operations, with a combination of shared and remote memory access (RMA) protocols that are used to implement semantics of the collective operations directly. Appropriate embedding of the communication graphs in a cluster maximizes the use of shared memory and reduces network communication. Substantial performance improvements are achieved over the highly optimized commercial IBM implementation and the opensource MPICH implementation of MPI across a wide range of message sizes on the IBM SP. For example, depending on the message size and number of processors, SRM implementation of broadcast, reduce, and barrier outperforms IBM MPI_Bcast by 27-84%, MPI_Reduce by 24-79%, and MPI_Barrier by 73% on 256 processors, respectively. Related WorkWith exception of our earlier paper devoted to barrier [17], to our knowledge, there is no published work that employs combined shared memory and RMA-based protocols for direct implementation of collective communication operations on SMP clusters. Multiple papers described issues and methods involved in implementation of pointto-point message passing on top of one-sided communication protocols e.g., [4] or shared memory e.g., [1,14]. A sizable number of papers on collective communications focused on aspects other than selection of communication protocols. Several previous efforts focused on designing algorithms and communication structures for collective communication operations. Banikazemi et al [2] discuss multicast operations on heterogeneous networks of workstations. Paper [5] describes degree-D trees and generalized Fibonacci trees in the context of message passing and discusses methods for pipelining and repeating a collective operation. Huse [6] compares different communication structures for collective operations.Sophisticated algorithms are available to determine nonbinomial optimal spanning trees. The interplay between cluster organizations and broadcast algorithms was investigated in [21]. Some studies [7,10] focused on