19 citations · 62 across the 13 of their papers we have counts for
14 papers
PipeOrgan: Efficient Inter-operation Pipelining with Flexible Spatial Organization and Interconnects
Raveesh Garg, Hyoukjun Kwon, Eric Qin +3
Because of the recent trends in Deep Neural Networks (DNN) models being memory-bound, inter-operator pipelining for DNN accelerators is emerging as a promising optimization. Inter-…
Characterizing the Accuracy -- Efficiency Trade-off of Low-rank Decomposition in Language Models
Chakshu Moar, Faraz Tahmasebi, Michael Pellauer +1
Recent large language models (LLMs) employ billions of parameters to enable broad problem-solving capabilities. Such language models also tend to be memory-bound because of the dom…
DREAM: A Dynamic Scheduler for Dynamic Real-time Multi-model ML Workloads
Seah Kim, Hyoukjun Kwon, Jinook Song +4
Emerging real-time multi-model ML (RTMM) workloads such as AR/VR and drone control involve dynamic behaviors in various granularity; task, model, and layers within a model. Such dy…
XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaverse
Hyoukjun Kwon, Krishnakumar Nair, Jamin Seo +15
Real-time multi-task multi-model (MTMM) workloads, a new form of deep learning inference workloads, are emerging for applications areas like extended reality (XR) to support metave…
A Formalism of DNN Accelerator Flexibility
Sheng-Chun Kao, Hyoukjun Kwon, Michael Pellauer +2
The high efficiency of domain-specific hardware accelerators for machine learning (ML) has come from specialization, with the trade-off of less configurability/ flexibility. There…
Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation
Jiaqi Gu, Hyoukjun Kwon, Dilin Wang +6
Vision Transformers (ViTs) have emerged with superior performance on computer vision tasks compared to convolutional neural network (CNN)-based models. However, ViTs are mainly des…
Evaluating Spatial Accelerator Architectures with Tiled Matrix-Matrix Multiplication
Gordon E. Moon, Hyoukjun Kwon, Geonhwa Jeong +3
There is a growing interest in custom spatial accelerators for machine learning applications. These accelerators employ a spatial array of processing elements (PEs) interacting via…
Extending Sparse Tensor Accelerators to Support Multiple Compression Formats
Eric Qin, Geonhwa Jeong, William Won +7
Sparsity, which occurs in both scientific applications and Deep Learning (DL) models, has been a key target of optimization within recent ASIC accelerators due to the potential mem…
Dataflow-Architecture Co-Design for 2.5D DNN Accelerators using Wireless Network-on-Package
Robert Guirado, Hyoukjun Kwon, Sergi Abadal +2
Deep neural network (DNN) models continue to grow in size and complexity, demanding higher computational power to enable real-time inference. To efficiently deliver such computatio…
Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks
Lei Yang, Zheyu Yan, Meng Li +6
Neural Architecture Search (NAS) has demonstrated its power on various AI accelerating platforms such as Field Programmable Gate Arrays (FPGAs) and Graphic Processing Units (GPUs).…
Marvel: A Data-centric Compiler for DNN Operators on Spatial Accelerators
Prasanth Chatarasi, Hyoukjun Kwon, Natesh Raina +6
The efficiency of a spatial DNN accelerator depends heavily on the compiler and its cost model ability to generate optimized mappings for various operators of DNN models on to the…
Understanding the Impact of On-chip Communication on DNN Accelerator Performance
Robert Guirado, Hyoukjun Kwon, Eduard Alarcón +2
Deep Neural Networks have flourished at an unprecedented pace in recent years. They have achieved outstanding accuracy in fields such as computer vision, natural language processin…
Heterogeneous Dataflow Accelerators for Multi-DNN Workloads
Hyoukjun Kwon, Liangzhen Lai, Michael Pellauer +3
Emerging AI-enabled applications such as augmented/virtual reality (AR/VR) leverage multiple deep neural network (DNN) models for sub-tasks such as object detection, hand tracking,…
Understanding Reuse, Performance, and Hardware Cost of DNN Dataflows: A Data-Centric Approach Using MAESTRO
Hyoukjun Kwon, Prasanth Chatarasi, Michael Pellauer +3
The data partitioning and scheduling strategies used by DNN accelerators to leverage reuse and perform staging are known as dataflow, and they directly impact the performance and e…