Feature-based spmv performance analysis on contemporary devices
P Mpakos, D Galanopoulos… - 2023 IEEE …, 2023 - ieeexplore.ieee.org
The SpMV kernel is characterized by high performance variation per input matrix and
computing platform. While GPUs were considered State-of-the-Art for SpMV, with the …
computing platform. While GPUs were considered State-of-the-Art for SpMV, with the …
An asynchronous and parallel row-wise compressed SpMV kernel on heterogeneous CPU-GPU architectures
H Tan - International Journal of Embedded Systems, 2022 - inderscienceonline.com
Sparse matrix vector multiplication (SpMV) is a fundamental and important algebra used
extensively in various fields, such as machine learning, data mining and numerical …
extensively in various fields, such as machine learning, data mining and numerical …
Open-Source SpMV Multiplication Hardware Accelerator for FPGA-Based HPC Systems
Abstract The Sparse Matrix Vector (SpMV) multiplication kernel is a key component of many
high-performance computing applications, but at the same time one of the most challenging …
high-performance computing applications, but at the same time one of the most challenging …
Open-Source SpMV Multiplication Hardware Accelerator for FPGA-Based HPC Systems
DN Pnevmatikatos, N Koziris - … Computing: Architectures, Tools …, 2024 - books.google.com
The Sparse Matrix Vector (SpMV) multiplication kernel is a key component of many high-
performance computing applications, but at the same time one of the most challenging to …
performance computing applications, but at the same time one of the most challenging to …