A Heterogeneous Vector-Array Architecture with Resource Scheduling for Multi-User/Multi-DNN Workloads

Paper Link: https://scontent.ficn2-2.fna.fbcdn.net/v/t39.8562-6/264678175_638181700547693_1020667141522086569_n.pdf?_nc_cat=106&ccb=1-6&_nc_sid=ad8a9d&_nc_ohc=0P4Do9N_VNEAX9wOvd8&_nc_ht=scontent.ficn2-2.fna&oh=00_AT87Z_o7_qAQ3WSO4GSsYM2uHTuzprjDtKzYuzRpHiwevg&oe=627F6F18

Accelerating Large-Scale Nearest Neighbor Search with Computational Storage Device

Paper Link: https://ieeexplore.ieee.org/document/9444083

FIXAR: A Fixed-Point Deep Reinforcement Learning Platform with Quantization-Aware Training and Adaptive Parallelism

Paper Link: https://ieeexplore.ieee.org/document/9586213

Z-PIM: A Sparsity-Aware Processing-In-Memory Architecture with Fully-Variable Weight Bit-Precision for Energy-Efficient Deep Neural Networks

Paper Link: https://ieeexplore.ieee.org/document/9337169