Congratulations! We have a paper accepted to Communications of the ACM, 2023 ” South Korea’s Nationwide Effort for AI Semiconductor Industry ” Ji-Hoon Kim, Sungyeob Yoo, and Joo-Young Kim
Read MoreCongratulations! We have a paper accepted to IEEE European Solid-State Circuits Conference (ESSCIRC), 2023 ” JNPU: A 1.04TFLOPS Joint-DNN Training Processor with Speculative Cyclic Quantization and Triple Heterogeneity on Microarchitecture / Precision / Dataflow ” Je Yang, Sukbin Lim, Sukjin Lee, Jae-Young Kim and Joo-Young Kim
Read MoreCongratulations! We have a paper accepted to the International Conference on Symposium on VLSI Technology and Circuits (VLSI), 2023. “SP-PIM: A 22.41TFLOPS/W, 8.81Epochs/Sec Super-Pipelined Processing-In-Memory Accelerator with Local Error Prediction for On-Device Learning” *Jung-Hoon Kim, *Jaehoon Heo, Wontak Han, Jaeuk Kim and Joo-Young Kim (*equal contribution)
Read MoreWe are thrilled to announce that our very own Professor Joo-Young Kim has recently been promoted to Associate Professor and has become a distinguished lecturer for the Solid-State Circuits Society (SSCS).link: https://lnkd.in/gek5jiV We are so proud to have such a talented and dedicated professor leading our lab, and we couldn’t be happier to share this exciting news with […]
Read MoreCongratulations! We have a paper got a ‘Gold Prize’ to the 29th Samsung Humantech Paper Award. The Gold Award is a prize given only to the first-place winner in each division. “JNPU: A 1.04 TFLOPS Joint-DNN Training Processor with Speculative Quantization and Triple Heterogeneity” (research section: Circuit Design) Je Yang, Jae-Young Kim, Sukbin Lim, Sukjin […]
Read MoreCongratulations! We have a paper got a ‘Gold Prize’ to the 29th Samsung Humantech Paper Award. The Gold Award is a prize given only to the first-place winner in each division. “JNPU: A 1.04 TFLOPS Joint-DNN Training Processor with Speculative Quantization and Triple Heterogeneity” (research section: Circuit Design) Je Yang, Jae-Young Kim, Sukbin Lim, Sukjin […]
Read MoreHi Castlab. One new Ph.D student(Seungjae) and five new master’s students(Seri, Junyoung, Jinho, Jieon, Sungwoong) have joined Castlab since this 2023 spring semester. Seungjae, Seri, Junyoung, Jinho, Jieon, and Sungwoong are interested in a software-hardware co-design approach in AI accelerator and processing in/near memory. [Seungjae] “Hello, I’m Seungjae Yoo, a new Ph.D. student at CastLab. I’m delighted to […]
Read MoreCongratulations! We have a paper accepted to IEEE Custom Integrated Circuits Conference (CICC), 2023 ” A 26.55TOPS/W Explainable AI Processor with Dynamic Workload Allocation and Heat Map Compression/Pruning ” Junsoo Kim, Geonwoo Ko, Ji-Hoon Kim, Changha Lee, Taewoo Kim, Chan-Hyun Yoon, Joo-Young Kim
Read More