Haspmv: Heterogeneity-aware sparse matrix-vector multiplication on modern asymmetric multicore processors
Sparse matrix-vector multiplication (SpMV) is a fundamental routine in computational
science and engineering. Its optimization methods on various homogeneous parallel …
science and engineering. Its optimization methods on various homogeneous parallel …
Amgt: Algebraic multigrid solver on tensor cores
Algebraic multigrid (AMG) methods are particularly efficient to solve a wide range of sparse
linear systems, due to their good flexibility and adaptability. Even though modern parallel …
linear systems, due to their good flexibility and adaptability. Even though modern parallel …
Two-Face: Combining Collective and One-Sided Communication for Efficient Distributed SpMM
Sparse matrix dense matrix multiplication (SpMM) is commonly used in applications ranging
from scientific computing to graph neural networks. Typically, when SpMM is executed in a …
from scientific computing to graph neural networks. Typically, when SpMM is executed in a …
Generating Data Locality to Accelerate Sparse Matrix-Matrix Multiplication on CPUs
J Wolfson-Pou, J Laukemann, F Petrini - arXiv preprint arXiv:2501.07056, 2025 - arxiv.org
Sparse GEneral Matrix-matrix Multiplication (SpGEMM) is a critical operation in many
applications. Current multithreaded implementations are based on Gustavson's algorithm …
applications. Current multithreaded implementations are based on Gustavson's algorithm …
SaSpGEMM: Sorting-Avoiding Sparse General Matrix-Matrix Multiplication on Multi-Core Processors
We propose the SaSpGEMM: a parallel sparse general matrix-matrix multiplication
(SpGEMM) to avoid the overhead of sorting. The typical workflow of SpGEMM contains: size …
(SpGEMM) to avoid the overhead of sorting. The typical workflow of SpGEMM contains: size …
[PDF][PDF] Two-Face: Combining Collective and One-Sided Communication for E cient Distributed SpMM
Sparse matrix dense matrix multiplication (SpMM) is commonly used in applications ranging
from scienti c computing to graph neural networks. Typically, when SpMM is executed in a …
from scienti c computing to graph neural networks. Typically, when SpMM is executed in a …
A hybrid communication pattern and algorithm for distributed sparse-times-dense matrix multiplication
C Block - 2024 - ideals.illinois.edu
Sparse matrix dense matrix multiplication (SpMM) is commonly used in applications ranging
from scientific computing to graph neural networks. Typically, when SpMM is executed in a …
from scientific computing to graph neural networks. Typically, when SpMM is executed in a …
LibAMM: Empirical Insights into Approximate Computing for Accelerating Matrix Multiplication
X Zeng, W Jiang, S Zhang - The Thirty-eight Conference on Neural … - openreview.net
Matrix multiplication (MM) is pivotal in fields from deep learning to scientific computing,
driving the quest for improved computational efficiency. Accelerating MM encompasses …
driving the quest for improved computational efficiency. Accelerating MM encompasses …