Search Results - "communication avoiding algorithms"

A massively parallel tensor contraction framework for coupled-cluster computations by Solomonik, Edgar, Matthews, Devin, Hammond, Jeff R., Stanton, John F., Demmel, James

“…Precise calculation of molecular electronic wavefunctions by methods such as coupled-cluster requires the computation of tensor contractions, the cost of which…”
Get full text

Multiscale high-order/low-order (HOLO) algorithms and applications by Chacón, L., Chen, G., Knoll, D.A., Newman, C., Park, H., Taitano, W., Willert, J.A., Womeldorff, G.

“…We review the state of the art in the formulation, implementation, and performance of so-called high-order/low-order (HOLO) algorithms for challenging…”
Get full text

Communication Avoiding Block Low-Rank Parallel Multifrontal Triangular Solve with Many Right-Hand Sides by Amestoy, Patrick, Boiteau, Olivier, Buttari, Alfredo, Gerest, Matthieu, Jézéquel, Fabienne, L’Excellent, Jean-Yves, Mary, Theo

“…Block low-rank (BLR) compression can significantly reduce the memory and time costs of parallel sparse direct solvers. In this paper, we investigate the…”
Get full text

Parallel Fast Multipole Method accelerated FFT on HPC clusters by Mehta, Chahak, Karthi, Amarnath, Jetly, Vishrut, Chaudhury, Bhaskar

“…With increasing sizes of distributed systems, there comes an increased risk of communication bottlenecks. In the past decade there has been a growing interest…”
Get full text

Multiscale high-order/low-order (HOLO) algorithms and applications by Chacon, Luis, Chen, Guangye, Knoll, Dana Alan, Newman, Christopher Kyle, Park, HyeongKae, Taitano, William, Willert, Jeff A., Womeldorff, Geoffrey Alan

“…Here, we review the state of the art in the formulation, implementation, and performance of so-called high-order/low-order (HOLO) algorithms for challenging…”
Get full text

Communication-Avoiding Recursive Aggregation by Sun, Yihao, Kumar, Sidharth, Gilray, Thomas, Micinski, Kristopher

“…Recursive aggregation has been of considerable interest due to its unifying a wide range of deductive-analytic workloads, including social-media mining and…”
Get full text

Translational process: Mathematical software perspective by Dongarra, Jack, Gates, Mark, Luszczek, Piotr, Tomov, Stanimire

“…Each successive generation of computer architecture has brought new challenges to achieving high performance mathematical solvers, necessitating development…”
Get full text

Accelerating solutions of one-dimensional unsteady PDEs with GPU-based swept time–space decomposition by Magee, Daniel J., Niemeyer, Kyle E.

“…•A GPU implementation of the swept time–space decomposition rule is presented.•Three versions of the scheme are considered.•The shared-memory implementation…”
Get full text

Reconstructing Householder vectors from Tall-Skinny QR by Ballard, G., Demmel, J., Grigori, L., Jacquelin, M., Knight, N., Nguyen, H.D.

“…The Tall-Skinny QR (TSQR) algorithm is more communication efficient than the standard Householder algorithm for QR decomposition of matrices with many more…”
Get full text

Applying the swept rule for solving explicit partial differential equations on heterogeneous computing systems by Magee, Daniel J., Walker, Anthony S., Niemeyer, Kyle E.

“…Applications that exploit the architectural details of high-performance computing (HPC) systems have become increasingly invaluable in academia and industry…”
Get full text

Reducing Communication in Graph Neural Network Training by Tripathy, Alok, Yelick, Katherine, Buluc, Aydin

“…Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse connectivity information of the data. GNNs represent this…”
Get full text

Communication-Avoiding Symmetric-Indefinite Factorization by Ballard, Grey, Becker, Dulceneia, Demmel, James, Dongarra, Jack, Druinsky, Alex, Peled, Inon, Schwartz, Oded, Toledo, Sivan, Yamazaki, Ichitaro

“…We describe and analyze a novel symmetric triangular factorization algorithm. The algorithm is essentially a block version of Aasen's triangular…”
Get full text

A Class of Communication-avoiding Algorithms for Solving General Dense Linear Systems on CPU/GPU Parallel Machines by Baboulin, Marc, Donfack, Simplice, Dongarra, Jack, Grigori, Laura, Rémy, Adrien, Tomov, Stanimire

“…We study several solvers for the solution of general linear systems where the main objective is to reduce the communication overhead due to pivoting. We first…”
Get full text

Cyclops Tensor Framework: Reducing Communication and Eliminating Load Imbalance in Massively Parallel Contractions by Solomonik, Edgar, Matthews, Devin, Hammond, Jeff R., Demmel, James

“…Cyclops (cyclic-operations) Tensor Framework (CTF) 1 is a distributed library for tensor contractions. CTF aims to scale high-dimensional tensor contractions…”
Get full text

Distributed-Memory Sparse Kernels for Machine Learning by Bharadwaj, Vivek, Buluc, Aydin, Demmel, James

“…Sampled Dense Times Dense Matrix Multiplication (SDDMM) and Sparse Times Dense Matrix Multiplication (SpMM) appear in diverse settings, such as collaborative…”
Get full text

Communication-Avoiding Parallel Sparse-Dense Matrix-Matrix Multiplication by Koanantakool, Penporn, Azad, Ariful, Buluc, Aydin, Morozov, Dmitriy, Sang-Yun Oh, Oliker, Leonid, Yelick, Katherine

“…Multiplication of a sparse matrix with a dense matrix is a building block of an increasing number of applications in many areas such as machine learning and…”
Get full text

Event-Triggered Communication in Parallel Computing by Ghosh, Soumyadip, Saha, Kamal K., Gupta, Vijay, Tryggvason, Gretar

“…Communication overhead in parallel systems can be a significant bottleneck in scaling up parallel computation. In this paper, we propose event-triggered…”
Get full text

Write-Avoiding Algorithms by Carson, Erin, Demmel, James, Grigori, Laura, Knight, Nicholas, Koanantakool, Penporn, Schwartz, Oded, Simhadri, Harsha Vardhan

“…Communication, i.e., moving data between levels of a memory hierarchy or between processors over a network, is much more expensive (in time or energy) than…”
Get full text

Minimizing Communication in All-Pairs Shortest Paths by Solomonik, Edgar, Buluç, Aydın, Demmel, James

“…We consider distributed memory algorithms for the all-pairs shortest paths (APSP) problem. Scaling the APSP problem to high concurrencies requires both…”
Get full text

Recent Developments in Iterative Methods for Reducing Synchronization by Zou, Qinmeng, Magoules, Frederic

“…On modern parallel architectures, the cost of synchronization among processors can often dominate the cost of floating-point computation. Several modifications…”
Get full text