4 papers
A Lightweight, Compiler-Assisted Register File Cache for GPGPU
Mojtaba Abaie Shoushtary, Jose Maria Arnau, Jordi Tubella Murgadas +1
Modern GPUs require an enormous register file (RF) to store the context of thousands of active threads. It consumes considerable energy and contains multiple large banks to provide…
CREW: Computation Reuse and Efficient Weight Storage for Hardware-accelerated MLPs and RNNs
Marc Riera, Jose-Maria Arnau, Antonio Gonzalez
Deep Neural Networks (DNNs) have achieved tremendous success for cognitive applications. The core operation in a DNN is the dot product between quantized inputs and weights. Prior…
E-BATCH: Energy-Efficient and High-Throughput RNN Batching
Franyell Silfa, Jose Maria Arnau, Antonio Gonzalez
Recurrent Neural Network (RNN) inference exhibits low hardware utilization due to the strict data dependencies across time-steps. Batching multiple requests can increase throughput…
SHARP: An Adaptable, Energy-Efficient Accelerator for Recurrent Neural Network
Reza Yazdani, Olatunji Ruwase, Minjia Zhang +3
The effectiveness of Recurrent Neural Networks (RNNs) for tasks such as Automatic Speech Recognition has fostered interest in RNN inference acceleration. Due to the recurrent natur…