research
∙
04/27/2023
JaxPruner: A concise library for sparsity research
This paper introduces JaxPruner, an open-source JAX-based pruning and sp...
share
research
∙
10/07/2022
Demystifying Map Space Exploration for NPUs
Map Space Exploration is the problem of finding optimized mappings of a ...
research
∙
09/15/2022
Training Recipe for N:M Structured Sparsity with Decaying Pruning Mask
Sparsity has become one of the promising methods to compress and acceler...
research
∙
06/07/2022
A Formalism of DNN Accelerator Flexibility
The high efficiency of domain-specific hardware accelerators for machine...
research
∙
01/26/2022
DiGamma: Domain-aware Genetic Algorithm for HW-Mapping Co-optimization for DNN Accelerators
The design of DNN accelerators includes two key parts: HW resource confi...
research
∙
01/26/2022
DNNFuser: Generative Pre-Trained Transformer as a Generalized Mapper for Layer Fusion in DNN Accelerators
Dataflow/mapping decides the compute and energy efficiency of DNN accele...
research
∙
07/13/2021
FLAT: An Optimized Dataflow for Mitigating Attention Performance Bottlenecks
Attention mechanisms form the backbone of state-of-the-art machine learn...
research
∙
04/28/2021
Domain-specific Genetic Algorithm for Multi-tenant DNNAccelerator Scheduling
As Deep Learning continues to drive a variety of applications in datacen...
research
∙
03/18/2021
Extending Sparse Tensor Accelerators to Support Multiple Compression Formats
Sparsity, which occurs in both scientific applications and Deep Learning...
research
∙
09/04/2020
ConfuciuX: Autonomous Hardware Resource Assignment for DNN Accelerators using Reinforcement Learning
DNN accelerators provide efficiency by leveraging reuse of activations/w...
research
∙
06/06/2020
Conditional Neural Architecture Search
Designing resource-efficient Deep Neural Networks (DNNs) is critical to ...
research
∙
06/06/2020
Generative Design of Hardware-aware DNNs
To efficiently run DNNs on the edge/cloud, many new DNN inference accele...
research
∙
08/13/2019