ABNN
            <sup>2</sup>

Shen, Liyan; Dong, Ye; Fang, Binxing; Shi, Jinqiao; Wang, Xuebin; Pan, Shengli; Shi, Ruisheng

doi:10.1145/3489517.3530680

Cited by 8 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ubiquitous matrix multiplication operation is an essential component of many problems arising in combinatorial and scientific computing. It is considered an intermediate step in a myriad of scientific, graph, and engineering applications including computer graphics, network theory, algebraic multigrid solvers, triangle counting, multisource breadth-first searching, shortest path problems, colored intersecting, subgraph matching, and quantized neural networks [1][2][3][4][5][6]. The data structures for storing large matrices optimize the memory used for storage and the performance of the multiplication operation.…”

Section: Introductionmentioning

confidence: 99%

GPU Algorithms for Structured Sparse Matrix Multiplication with Diagonal Storage Schemes

Haque,

Parvez,

Hossain

2024

Algorithms

View full text Add to dashboard Cite

Matrix–matrix multiplication is of singular importance in linear algebra operations with a multitude of applications in scientific and engineering computing. Data structures for storing matrix elements are designed to minimize overhead information as well as to optimize the operation count. In this study, we utilize the notion of the compact diagonal storage method (CDM), which builds upon the previously developed diagonal storage—an orientation-independent uniform scheme to store the nonzero elements of a range of matrices. This study exploits both these storage schemes and presents efficient GPU-accelerated parallel implementations of matrix multiplication when the input matrices are banded and/or structured sparse. We exploit the data layouts in the diagonal storage schemes to expose a substantial amount of fine-grained parallelism and effectively utilize the GPU shared memory to improve the locality of data access for numerical calculations. Results from an extensive set of numerical experiments with the aforementioned types of matrices demonstrate orders-of-magnitude speedups compared with the sequential performance.

show abstract

Section: Introductionmentioning

confidence: 99%

GPU Algorithms for Structured Sparse Matrix Multiplication with Diagonal Storage Schemes

Haque,

Parvez,

Hossain

2024

Algorithms

View full text Add to dashboard Cite

show abstract

MOTUS: How Quantized Parameters Improve Protection of Model and Its Inference Input

Kitai

Yanai

Iwahana

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference

Kundu

Zhang

Chen

et al. 2023

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

ABNN ²

Cited by 8 publications

References 11 publications

GPU Algorithms for Structured Sparse Matrix Multiplication with Diagonal Storage Schemes

GPU Algorithms for Structured Sparse Matrix Multiplication with Diagonal Storage Schemes

MOTUS: How Quantized Parameters Improve Protection of Model and Its Inference Input

Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference

Contact Info

Product

Resources

About

ABNN 2

Cited by 8 publications

References 11 publications

GPU Algorithms for Structured Sparse Matrix Multiplication with Diagonal Storage Schemes

GPU Algorithms for Structured Sparse Matrix Multiplication with Diagonal Storage Schemes

MOTUS: How Quantized Parameters Improve Protection of Model and Its Inference Input

Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference

Contact Info

Product

Resources

About

ABNN ²