Byeongho Kim

MVP: An Efficient CNN Accelerator with Matrix, Vector, and Processing-Near-Memory Units

Jung Ho Ahn, Sunjung Lee, Wonkyung Jung, 2022, ACM Trans. Design Autom. Electr. Syst..

Restructuring Batch Normalization to Accelerate CNN Training pdf

Jung Ho Ahn, Wonjong Rhee, Daejin Jung, 2018, SysML.

Accelerating Transformer Networks through Recomposing Softmax Layers

Jung Ho Ahn, Jaewan Choi, Byeongho Kim, 2022, 2022 IEEE International Symposium on Workload Characterization (IISWC).

TRiM: Enhancing Processor-Memory Interfaces with Scalable Tensor Reduction in Memory

Jung Ho Ahn, Minsoo Rhu, Eojin Lee, 2021, MICRO.

TRiM: Tensor Reduction in Memory

Jung Ho Ahn, Jaehyun Park, Minsoo Rhu, 2021, IEEE Computer Architecture Letters.

MViD: Sparse Matrix-Vector Multiplication in Mobile DRAM for Accelerating Recurrent Neural Networks

Jung Ho Ahn, Jaehyun Park, Jongwook Chung, 2020, IEEE Transactions on Computers.

CLAY: CXL-based Scalable NDP Architecture Accelerating Embedding Layers

Byeongho Kim, Jaehyun Park, Eojin Lee, 2024, ICS.