M. Asunción Castaño
YOU?
Author Swipe
View article: Convolutional neural nets for estimating the run time and energy consumption of the sparse matrix-vector product
Convolutional neural nets for estimating the run time and energy consumption of the sparse matrix-vector product Open
Modeling the performance and energy consumption of the sparse matrix-vector product (SpMV) is essential to perform off-line analysis and, for example, choose a target computer architecture that delivers the best performance-energy consumpt…
View article: Block-wise sparse matrix-vector product dataset and convolutional neural nets for estimating the run time and energy consumption of the sparse matrix-vector product
Block-wise sparse matrix-vector product dataset and convolutional neural nets for estimating the run time and energy consumption of the sparse matrix-vector product Open
Introduction SpMV-CNN is a set of Convolutional Neural Networks (CNNs) that provide accurate estimations of the performance and energy consumption of the SpMV kernel. The proposed CNN-based models use a bl…
View article: Block-wise sparse matrix-vector product dataset and convolutional neural nets for estimating the run time and energy consumption of the sparse matrix-vector product
Block-wise sparse matrix-vector product dataset and convolutional neural nets for estimating the run time and energy consumption of the sparse matrix-vector product Open
Introduction SpMV-CNN is a set of Convolutional Neural Networks (CNNs) that provide accurate estimations of the performance and energy consumption of the SpMV kernel. The proposed CNN-based models use a bl…
View article: Performance modeling of the sparse matrix–vector product via convolutional neural networks
Performance modeling of the sparse matrix–vector product via convolutional neural networks Open
View article: Game-based learning supported by audience response tools: game proposals and preliminary assessment
Game-based learning supported by audience response tools: game proposals and preliminary assessment Open
The so-called game-based learning strategies are based on introducing games in the classrooms to improve aspects such as student performance, concentration and effort. Currently, they provide a very useful resource to increase the motivati…
View article: Adapting concurrency throttling and voltage–frequency scaling for dense eigensolvers
Adapting concurrency throttling and voltage–frequency scaling for dense eigensolvers Open
We analyze power dissipation and energy consumption during the execution\n\t\t\t\t of high-performance dense linear algebra kernels on multi-core processors. On top of\n\t\t\t\t this analysis, we propose and evaluate several strategies to …