Browsing by Keywords "Communication cost"
Now showing items 1-10 of 10
-
Addressing volume and latency overheads in 1d-parallel sparse matrix-vector multiplication
(Springer, 2017-08-09)The scalability of sparse matrix-vector multiplication (SpMV) on distributed memory systems depends on multiple factors that involve different communication cost metrics. The irregular sparsity pattern of the coefficient ... -
Cartesian partitioning models for 2D and 3D parallel SpGEMM algorithms
(IEEE, 2020)The focus is distributed-memory parallelization of sparse-general-matrix-multiplication (SpGEMM). Parallel SpGEMM algorithms are classified under one-dimensional (1D), 2D, and 3D categories denoting the number of dimensions ... -
Partitioning models for general medium-grain parallel sparse tensor decomposition
(IEEE, 2021)The focus of this article is efficient parallelization of the canonical polyadic decomposition algorithm utilizing the alternating least squares method for sparse tensors on distributed-memory architectures. We propose a ... -
Partitioning models for scaling parallel sparse matrix-matrix multiplication
(Association for Computing Machinery, 2018)We investigate outer-product--parallel, inner-product--parallel, and row-by-row-product--parallel formulations of sparse matrix-matrix multiplication (SpGEMM) on distributed memory architectures. For each of these three ... -
Recursive bipartitioning models for performance improvement in sparse matrix computations
(Bilkent University, 2017-08)Sparse matrix computations are among the most important building blocks of linear algebra and arise in many scienti c and engineering problems. Depending on the problem type, these computations may be in the form of ... -
A Recursive Hypergraph Bipartitioning Framework for Reducing Bandwidth and Latency Costs Simultaneously
(IEEE Computer Society, 2017)Intelligent partitioning models are commonly used for efficient parallelization of irregular applications on distributed systems. These models usually aim to minimize a single communication cost metric, which is either ... -
Reduce operations: send volume balancing while minimizing latency
(IEEE, 2020)Communication hypergraph model was proposed in a two-phase setting for encapsulating multiple communication cost metrics (bandwidth and latency), which are proven to be important in parallelizing irregular applications. ... -
Reducing communication overhead in sparse matrix and tensor computations
(Bilkent University, 2020-08)Encapsulating multiple communication cost metrics, i.e., bandwidth and latency, is proven to be important in reducing communication overhead in the parallelization of sparse and irregular applications. Communication ... -
Scalable unsupervised ML: Latency hiding in distributed sparse tensor decomposition
(IEEE Computer Society, 2022-11-01)Latency overhead in distributed-memory parallel CPD-ALS scales with the number of processors, limiting the scalability of computing CPD of large irregularly sparse tensors. This overhead comes in the form of sparse reduce ... -
Voltage island based heterogeneous NoC design through constraint programming
(Pergamon Press, 2014)This paper discusses heterogeneous Network-on-Chip (NoC) design from a Constraint Programming (CP) perspective and extends the formulation to solving Voltage-Frequency Island (VFI) problem. In general, VFI is a superior ...
