A New Scalable Parallel Algorithm for Fock Matrix Construction

Liu, Xing; Patel, Aftab; Chow, Edmond

doi:10.1109/ipdps.2014.97

Cited by 24 publications

(28 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All of these packages face similar challenges, including how to load-balance the computation, how to manage locality, and how to efficiently execute computation while providing an easy interface. They use either a tasking model for load-balancing computation with simple data layout [13,11,12], or a complex data layout with bulk synchronous communication [7]. A single programming model is used by these packages for all problems and at all run scales.…”

Section: Related Workmentioning

confidence: 99%

Cross-scale efficient tensor contractions for coupled cluster computations through multiple programming model backends

Ibrahim

Epifanovsky

Williams

et al. 2017

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

Coupled-cluster methods provide highly accurate models of molecular structure through explicit numerical calculation of tensors representing the correlation between electrons. These calculations are dominated by a sequence of tensor contractions, motivating the development of numerical libraries for such operations. While based on matrix-matrix multiplication, these libraries are specialized to exploit symmetries in the molecular structure and in electronic interactions, and thus reduce the size of the tensor representation and the complexity of contractions. The resulting algorithms are irregular and their parallelization has been previously achieved via the use of dynamic scheduling or specialized data decompositions. We introduce our efforts to extend the Libtensor framework to work in the distributed memory environment in a scalable and energy-efficient manner. We achieve up to 240× speedup compared with the optimized shared memory implementation of Libtensor. We attain scalability to hundreds of thousands of compute cores on three distributedmemory architectures, (Cray XC30 and XC40, and IBM Blue Gene/Q), and on a heterogeneous GPU-CPU system (Cray XK7). As the bottlenecks shift from being compute-bound DGEMM's to communication-bound collectives as the size of the molecular system scales, we adopt two radically different parallelization approaches for handling load-imbalance, tasking and bulk synchronous models. Nevertheless, we preserve a unified interface to both programming models to maintain the productivity of computational quantum chemists.

show abstract

Section: Related Workmentioning

confidence: 99%

Cross-scale efficient tensor contractions for coupled cluster computations through multiple programming model backends

Ibrahim

Epifanovsky

Williams

et al. 2017

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

show abstract

“…Second, there is a need for efficient atomic accumulate operations to update tiles of the global matrices without the explicit participation of the target process. Finally, dynamic load balancing in HF is usually controlled by either a single atomic counter [1], or many counters [6], [7], both of which require a fast onesided fetch-and-add implementation.…”

Section: B Pgas In Quantum Chemistrymentioning

confidence: 99%

“…Although individual two-electron integrals do not possess drastic differences in execution time, bundles of shell quartets can vary greatly in cost. It is necessary to designate shell quartets as task units in HF codes because it enables the reuse of intermediate quantities shared by basis functions within a quartet [13], [6]. The goal is to assign these task units to processors with minimal overhead and a schedule that reduces the makespan.…”

Section: E Load Balancing In Quantum Chemistrymentioning

confidence: 99%

A Hartree-Fock Application Using UPC++ and the New DArray Library

Ozog

Kamil

Hargrove

et al. 2016

2016 IEEE International Parallel and Distributed Processing Symposium (IPDPS)

View full text Add to dashboard Cite

Abstract-The Hartree-Fock (HF) method is the fundamental first step for incorporating quantum mechanics into manyelectron simulations of atoms and molecules, and it is an important component of computational chemistry toolkits like NWChem. The GTFock code is an HF implementation that, while it does not have all the features in NWChem, represents crucial algorithmic advances that reduce communication and improve load balance by doing an up-front static partitioning of tasks, followed by work stealing whenever necessary.To enable innovations in algorithms and exploit next generation exascale systems, it is crucial to support quantum chemistry codes using expressive and convenient programming models and runtime systems that are also efficient and scalable. This paper presents an HF implementation similar to GTFock using UPC++, a partitioned global address space model that includes flexible communication, asynchronous remote computation, and a powerful multidimensional array library. UPC++ offers runtime features that are useful for HF such as active messages, a rich calculus for array operations, hardwaresupported fetch-and-add, and functions for ensuring asynchronous runtime progress. We present a new distributed array abstraction, DArray, that is convenient for the kinds of randomaccess array updates and linear algebra operations on blockdistributed arrays with irregular data ownership. We analyze the performance of atomic fetch-and-add operations (relevant for load balancing) and runtime attentiveness, then compare various techniques and optimizations for each. Our optimized implementation of HF using UPC++ and the DArrays library shows up to 20% improvement over GTFock with Global Arrays at scales up to 24,000 cores.

show abstract

“…Their focus was on large heterogeneous clusters [26]. Foster et al presented scalable algorithms for distributing and constructing the Fock matrix in SCF problems on several massively parallel processing platforms [7].…”

Section: Related Workmentioning

confidence: 99%

Thread-level parallelization and optimization of NWChem for the Intel MIC architecture

Shan

Williams

Jong

et al. 2015

Proceedings of the Sixth International Workshop on Programming Models and Applications for Multicores and Manycores

View full text Add to dashboard Cite

In the multicore era it was possible to exploit the increase in on-chip parallelism by simply running multiple MPI processes per chip. Unfortunately, manycore processors' greatly increased thread-and data-level parallelism coupled with a reduced memory capacity demand an altogether different approach. In this paper we explore augmenting two NWChem modules, triples correction of the CCSD(T) and Fock matrix construction, with OpenMP in order that they might run efficiently on future manycore architectures. As the next NERSC machine will be a self-hosted Intel MIC (Xeon Phi) based supercomputer, we leverage an existing MIC testbed at NERSC to evaluate our experiments. In order to proxy the fact that future MIC machines will not have a host processor, we run all of our experiments in native mode. We found that while straightforward application of OpenMP to the deep loop nests associated with the tensor contractions of CCSD(T) was sufficient in attaining high performance, significant effort was required to safely and efficiently thread the TEXAS integral package when constructing the Fock matrix. Ultimately, our new MPI+OpenMP hybrid implementations attain up to 65× better performance for the triples part of the CCSD(T) due in large part to the fact that the limited on-card memory limits the existing MPI implementation to a single process per card. Additionally, we obtain up to 1.6× better performance on Fock matrix constructions when compared with the best MPI implementations running multiple processes per card.

show abstract

A New Scalable Parallel Algorithm for Fock Matrix Construction

Cited by 24 publications

References 26 publications

Cross-scale efficient tensor contractions for coupled cluster computations through multiple programming model backends

Cross-scale efficient tensor contractions for coupled cluster computations through multiple programming model backends

A Hartree-Fock Application Using UPC++ and the New DArray Library

Thread-level parallelization and optimization of NWChem for the Intel MIC architecture

Contact Info

Product

Resources

About