Skipformer: Evolving Beyond Blocks for Extensively Searching On-Device Language Models With Learnable Attention Window von Bodenham, Matthew, Kung, Jaeha

Volltext

On the Impact of Energy-Accuracy Tradeoff in a Digital Cellular Neural Network for Image Processing von Jaeha Kung, Duckhwan Kim, Mukhopadhyay, Saibal

Volltext

A Power-Aware Digital Multilayer Perceptron Accelerator with On-Chip Training Based on Approximate Computing von Duckhwan Kim, Jaeha Kung, Mukhopadhyay, Saibal

Volltext

Approximate LSTM Computing for Energy-Efficient Speech Recognition von Jo, Junseo, Kung, Jaeha, Lee, Youngjoo

Volltext

ReplaceNet: real-time replacement of a biological neural circuit with a hardware-assisted spiking neural network von Hwang, Sangwoo, Hwang, Yujin, Kim, Duhee, Lee, Junhee, Choe, Han Kyoung, Lee, Junghyup, Kang, Hongki, Kung, Jaeha

Volltext

Efficient Object Detection Using Embedded Binarized Neural Networks von Kung, Jaeha, Zhang, David, van der Wal, Gooitzen, Chai, Sek, Mukhopadhyay, Saibal

Volltext

Defending Against Flush+Reload Attack With DRAM Cache by Bypassing Shared SRAM Cache von Jang, Minwoo, Lee, Seungkyu, Kung, Jaeha, Kim, Daehoon

Volltext

Design and Analysis of Approximate Compressors for Balanced Error Accumulation in MAC Operator von Park, Gunho, Kung, Jaeha, Lee, Youngjoo

Volltext

One-Spike SNN: Single-Spike Phase Coding With Base Manipulation for ANN-to-SNN Conversion Loss Minimization von Hwang, Sangwoo, Kung, Jaeha

Volltext

Simplified Compressor and Encoder Designs for Low-Cost Approximate Radix-4 Booth Multiplier von Park, Gunho, Kung, Jaeha, Lee, Youngjoo

Volltext

Post-Silicon Estimation of Spatiotemporal Temperature Variations Using MIMO Thermal Filters von Jaeha Kung, Wen Yueh, Yalamanchili, Sudhakar, Mukhopadhyay, Saibal

Volltext

A Dual-Precision and Low-Power CNN Inference Engine Using a Heterogeneous Processing-in-Memory Architecture von Jung, Sangwoo, Lee, Jaehyun, Park, Dahoon, Lee, Youngjoo, Yoon, Jong-Hyeok, Kung, Jaeha

Volltext

FlexBlock: A Flexible DNN Training Accelerator with Multi-Mode Block Floating Point Support von Noh, Seock-Hwan, Koo, Jahyun, Lee, Seunghyun, Park, Jongse, Kung, Jaeha

Volltext

Implication of Optimizing NPU Dataflows on Neural Architecture Search for Mobile Devices von Lee, Jooyeon, Park, Junsang, Lee, Seunghyun, Kung, Jaeha

Volltext

Thermal signature: a simple yet accurate thermal index for floorplan optimization von Kung, Jaeha, Han, Inhak, Sapatnekar, Sachin, Shin, Youngsoo

Volltext

Adaptive Precision Cellular Nonlinear Network von Kung, Jaeha, Kim, Duckhwan, Mukhopadhyay, Saibal

Volltext

High-throughput Near-Memory Processing on CNNs with 3D HBM-like Memory von Park, Naebeom, Ryu, Sungju, Kung, Jaeha, Kim, Jae-Joon

Volltext

SEMS: Scalable Embedding Memory System for Accelerating Embedding-Based DNNs von Kim, Sejin, Kim, Jungwoo, Jang, Yongjoo, Kung, Jaeha, Lee, Sungjin

Volltext

Towards Scalable Analytics with Inference-Enabled Solid-State Drives von Kim, Minsub, Kung, Jaeha, Lee, Sungjin

Volltext

Deep Partitioned Training From Near-Storage Computing to DNN Accelerators von Jang, Yongjoo, Kim, Sejin, Kim, Daehoon, Lee, Sungjin, Kung, Jaeha

Volltext