2 papers
cs.AR2025
Squire: A General-Purpose Accelerator to Exploit Fine-Grain Parallelism on Dependency-Bound Kernels
Rubén Langarita, Jesús Alastruey-Benedé, Pablo Ibáñez-MarÃn +3
Multiple HPC applications are often bottlenecked by compute-intensive kernels implementing complex dependency patterns (data-dependency bound). Traditional general-purpose accelera…
cs.AR2024
SpChar: Characterizing the Sparse Puzzle via Decision Trees
Francesco Sgherzi, Marco Siracusa, Ivan Fernandez +2
Sparse matrix computation is crucial in various modern applications, including large-scale graph analytics, deep learning, and recommender systems. The performance of sparse kernel…