research
∙
07/07/2023
ITA: An Energy-Efficient Attention and Softmax Accelerator for Quantized Transformers
Transformer networks have emerged as the state-of-the-art approach for n...
share
research
∙
05/15/2023
Marsellus: A Heterogeneous RISC-V AI-IoT End-Node SoC with 2-to-8b DNN Acceleration and 30
Emerging Artificial Intelligence-enabled Internet-of-Things (AI-IoT) Sys...
research
∙
09/02/2022
Soft Tiles: Capturing Physical Implementation Flexibility for Tightly-Coupled Parallel Processing Clusters
Modern high-performance computing architectures (Multicore, GPU, Manycor...
research
∙
07/07/2022
MiniFloat-NN and ExSdotp: An ISA Extension and a Modular Open Hardware Unit for Low-Precision Training on RISC-V cores
Low-precision formats have recently driven major breakthroughs in neural...
research
∙
02/14/2022
Vau da muntanialas: Energy-efficient multi-die scalable acceleration of RNN inference
Recurrent neural networks such as Long Short-Term Memories (LSTMs) learn...
research
∙
11/15/2017