José-María Arnau

Computation Reuse in DNNs by Exploiting Input Similarity

Marc Riera, José-María Arnau, Antonio González · 2018 · 104 citations · Full text

Convolutional Neural Network, Deep Neural Networks, Computation Reuse +15

Neither more nor less: optimizing thread-level parallelism for GPGPUs

José-María Arnau, Joan-Manuel Parcerisa, Polychronis Xekalakis · 2013 · 89 citations · Full text

Gpu Architecture, Engineering, Gpu Benchmarking +13

Eliminating redundant fragment shader executions on a mobile GPU via hardware memoization

José-María Arnau, Joan-Manuel Parcerisa, Polychronis Xekalakis · ACM SIGARCH Computer Architecture News · 2014 · 54 citations

Engineering, Gpu Benchmarking, Hardware Memoization +17

TEAPOT

José-María Arnau, Joan-Manuel Parcerisa, Polychronis Xekalakis · 2013 · 41 citations · Full text

Gpu Architecture, Prior Gpu Simulators, Engineering +11

An ultra low-power hardware accelerator for automatic speech recognition

Reza Yazdani, Albert Segura, José-María Arnau et al. · 2016 · 36 citations · Full text

Asr Systems, Automatic Speech Recognition, Engineering +15