Highlight: Efficient and flexible dnn acceleration with hierarchical structured sparsity

YN Wu, PA Tsai, S Muralidharan, A Parashar… - Proceedings of the 56th …, 2023 - dl.acm.org
Due to complex interactions among various deep neural network (DNN) optimization
techniques, modern DNNs can have weights and activations that are dense or sparse with …

CiMLoop: A flexible, accurate, and fast compute-in-memory modeling tool

T Andrulis, JS Emer, V Sze - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
Compute-In-Memory (CiM) is a promising solution to accelerate Deep Neural Networks
(DNNs) as it can avoid energy-intensive DNN weight movement and use memory arrays to …

Mind the gap: Attainable data movement and operational intensity bounds for tensor algorithms

Q Huang, PA Tsai, JS Emer… - 2024 ACM/IEEE 51st …, 2024 - ieeexplore.ieee.org
The architectural design-space exploration (or DSE) process-whether manual or automated-
benefits greatly from knowing the limits of the metrics of interest in advance. Data movement …

Demystifying map space exploration for npus

SC Kao, A Parashar, PA Tsai… - 2022 IEEE International …, 2022 - ieeexplore.ieee.org
Map Space Exploration is the problem of finding optimized map**s of a Deep Neural
Network (DNN) model on an accelerator. It is known to be extremely computationally …

Architecture-level modeling of photonic deep neural network accelerators

T Andrulis, GI Chaudhry… - … Analysis of Systems …, 2024 - ieeexplore.ieee.org
Photonics is a promising technology to accelerate Deep Neural Networks as it can use
optical interconnects to reduce data movement energy and it enables low-energy, high …

Ceiba: An Efficient and Scalable DNN Scheduler for Spatial Accelerators

F Wang, M Shen, Y Lu, N ** Framework for Processing In-Memory Neural Network Acceleration
X Wang, M Zhou, T Rosing - IEEE Transactions on Computer …, 2024 - ieeexplore.ieee.org
Processing in-memory (PIM) is promising to accelerate neural networks (NNs) because it
minimizes data movement and provides large computational parallelism. Similar to machine …

DNNOPT: A Framework for Efficiently Selecting On-chip Memory Loop Optimizations of DNN Accelerators

P Ranawaka, MW Azhar, P Stenstrom - Proceedings of the 21st ACM …, 2024 - dl.acm.org
Deep neural network (DNN) accelerators suffer from poor utilization of on-chip memory
which potentially reduces performance and energy efficiency. Loop reordering and blocking …