The primary operation in DNNs is the dot product of quantized input
acti...
Quantization is commonly used in Deep Neural Networks (DNNs) to reduce t...
Autonomous Driving (AD) systems extensively manipulate 3D point clouds f...
Binary Neural Networks (BNNs) are showing tremendous success on realisti...
In real-time rendering, a 3D scene is modelled with meshes of triangles ...
Recurrent Neural Networks (RNNs) are a key technology for applications s...
Deep Neural Networks (DNNs) are widely used in many applications domains...
The outstanding accuracy achieved by modern Automatic Speech Recognition...
Data-intensive workloads and applications, such as machine learning (ML)...
Deep Neural Networks (DNNs) have achieved tremendous success for cogniti...
Hardware/Software (HW/SW) co-designed processors provide a promising sol...
With computers getting more and more powerful and integrated in our dail...
Recurrent Neural Network (RNN) inference exhibits low hardware utilizati...
GPGPU architectures have become established as the dominant parallelizat...
The use of low numerical precision is a fundamental optimization include...
The effectiveness of LSTM neural networks for popular tasks such as Auto...
DNN pruning reduces memory footprint and computational work of DNN-based...
GPUs are one of the most energy-consuming components for real-time rende...
This paper presents an overview of the main trends in processor architec...
Recurrent Neural Networks (RNNs) are a key technology for emerging
appli...