Convolution is most computationally intensive task of Convolutional Neural Network(CNN). It demands both computational power and memory storage of processing unit. There are different approaches to compute the solution of convolution. In this paper, matrix multiplication based convolution(ConvMM) approach is implemented and accelerated using concurrent resources of Graphics Processing Unit(GPU). CUDA computing language is used to implement this layer. Performance of this GPU-only convolutional layer is compared with its heterogeneous version. Further, flow of this GPU-only convolutional layer is optimized using Unified memory by eliminating overhead caused by extra memory transfers.

GPU-only unified ConvMM layer for neural classifiers / Rizvi, SYED TAHIR HUSSAIN; Cabodi, Gianpiero; Francini, Gianluca. - (2017). (Intervento presentato al convegno 4th International Conference on Control, Decision and Information Technologies) [10.1109/CoDIT.2017.8102649].

GPU-only unified ConvMM layer for neural classifiers

RIZVI, SYED TAHIR HUSSAIN;CABODI, Gianpiero;
2017

Abstract

Convolution is most computationally intensive task of Convolutional Neural Network(CNN). It demands both computational power and memory storage of processing unit. There are different approaches to compute the solution of convolution. In this paper, matrix multiplication based convolution(ConvMM) approach is implemented and accelerated using concurrent resources of Graphics Processing Unit(GPU). CUDA computing language is used to implement this layer. Performance of this GPU-only convolutional layer is compared with its heterogeneous version. Further, flow of this GPU-only convolutional layer is optimized using Unified memory by eliminating overhead caused by extra memory transfers.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2675423
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo