News

Congratulations! We have a paper accepted to IEEE Custom Integrated Circuits Conference (CICC), 2022. “T-PIM: A 2.21-to-161.08TOPS/W Processing-In-Memory Accelerator for End-to-End On-Device Training” Jaehoon Heo, Junsoo Kim, Wontak Han, Sukbin Lim, Joo-Young Kim

Congratulations to our outstanding students Jaeuk Kim and Seungjae Moon, who were selected through a competitive process. In recognition of their academic achievement for the past years, they win 2021 Kwon Young-Se scholarship, awarded by KAIST department of electrical engineering.

Congratulations! We have a paper accepted to Architecture, Compiler, and System Support for Multi-model DNN Workloads (ACSMD) Workshop (MICRO Workshop), 2021. “A Heterogeneous Vector-Array Architecture with Resource Scheduling for Multi-User/Multi-DNN Workloads” Sungyeob Yoo, Jung-Hoon Kim, Joo-Young Kim https://research.facebook.com/arch-comp-sys-support-for-multi-model-dnn-workshop/

Hi Castlab. Three new master’s students(Sukbin, Seungjae, and Jaeuk) have joined Castlab since this 2021 fall semester. Sukbin, Seungjae, and Jaeuk are interested in Processing-in Memory (PIM) and AI chip design. [Sukbin] “HI, I’m a new M.S. student. As an undergraduate, I started having an interest in digital circuits and made a decision to enter […]

Congratulations! We have a paper accepted to IEEE 29th annual international symposium on Field-Programmable Custom Computing Machines(FCCM), 2021. “Accelerating Large-Scale Nearest Neighbor Search with Computational Storage Device” Ji-Hoon Kim, Yeo-Reum Park, Jaeyoung Do, Soo-Young Ji, and Joo-Young Kim https://ieeexplore.ieee.org/document/9444083

Hi Castlab. Two new masters students(Wontak on left, Junsoo on right) have joined Castlab since this 2021 spring semester. Wontak and Junsoo both are interested in AI chip design. [Junsoo] “Hello, I’m Junsoo Kim, a freshman in the CastLab master’s degree. I joined CastLab because I liked studying in computers and program coding, and wanted […]

Congratulations! We have a paper accepted to 58th IEEE Design Automation Conference (DAC), 2021. “FIXAR: A Fixed-Point Deep Reinforcement Learning Platform with Quantization-Aware Training and Adaptive Parallelism” Je Yang, Seongmin Hong, and Joo-Young Kim https://arxiv.org/abs/2102.12103

Congratulations! We have a paper accepted to IEEE Journal of Solid-State Circuits(JSSC), 2021. “Z-PIM: A Sparsity-Aware Processing-In-Memory Architecture with Fully-Variable Weight Bit-Precision for Energy-Efficient Deep Neural Networks” Ji-Hoon Kim, Juhyoung Lee, Jinsu Lee, Jaehoon Heo, Joo-Young Kim https://ieeexplore.ieee.org/document/9337169