Gunjae Koo

Korea University — South Korea

Computer Science · Physical Sciences

11h-index538citations43works0.82yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Parallel Computing and Optimization Techniques(26), Advanced Data Storage Technologies(20), Advanced Memory and Neural Computing(7), Security and Verification in Computing(6), Advanced Neural Network Applications(4)

Publications43 total

LOGFLEX: Flexible-bit Log Arithmetic Accelerator for Language Models on Edge
IEEE Micro·2026
HALO: Hybrid Systolic Arrays via Logical Partitioning for Acceleration of Complex-Valued Neural Networks
2025
Analysis of GEMV Kernel Computations by Address Mapping Approaches Based on GPU and PIM Architectures
Journal of KIISE·2025
MOST: Memory Oversubscription-Aware Scheduling for Tensor Migration on GPU Unified Storage
IEEE Computer Architecture Letters·2025· 2 cited
SSFFT: Energy-Efficient Selective Scaling for Fast Fourier Transform in Embedded GPUs
2025Open Access
SparsePIM: An Efficient HBM-Based PIM Architecture for Sparse Matrix-Vector Multiplications
2025
Hierarchical Traversal Stack Design Using Shared Memory for GPU Ray Tracing
2025
HyMM: A Hybrid Sparse-Dense Matrix Multiplication Accelerator for GCNs
2025
TM-Training: An Energy-Efficient Tiered Memory System for Deep Learning Training in NPUs
ACM Transactions on Storage·2025· 1 citedOpen Access
Beyond VABlock: Improving Transformer workloads through aggressive prefetching
Journal of Systems Architecture·2025
Cache Side-Channel Attacks Exploiting the RISC-V Coprocessor Interface on an SoC Platform
Journal of KIISE·2025
TLP Balancer: Predictive Thread Allocation for Multitenant Inference in Embedded GPUs
IEEE Embedded Systems Letters·2024
Coldmap: Extending SSD Lifetime Exploiting Multi-Page Mapping Information
2024· 1 cited
VitBit: Enhancing Embedded GPU Performance for AI Workloads through Register Operand Packing
2024· 1 citedOpen Access
Conflict-aware compiler for hierarchical register file on GPUs
Journal of Systems Architecture·2024
Adaptive Kernel Merge and Fusion for Multi-Tenant Inference in Embedded GPUs
IEEE Embedded Systems Letters·2024· 2 cited
Beyond Vablock: Improving Transformer Workloads Through Aggressive Prefetching
SSRN Electronic Journal·2024Open Access
SAVector: Vectored Systolic Arrays
IEEE Access·2024· 7 citedOpen Access
Warped-MC: An Efficient Memory Controller Scheme for Massively Parallel Processors
2023Open Access
Vizard: Passing Over Profiling-Based Detection by Manipulating Performance Counters
IEEE Access·2023· 1 citedOpen Access
page 1 of 3Next →

Frequent Co-authors

Yunho Oh(20), Myung Kuk Yoon(17), Murali Annavaram(13), Won Woo Ro(9), Hyeran Jeon(6), Sangun Choi(5), Jaebeom Jeon(5), Taeweon Suh(5), Phil Lee(4), Keun‐Soo Kim(4), J. H. Kim(4), Minseong Gil(4), Hung‐Wei Tseng(3), Jongmin Lee(3), Jaeyong Park(3), Eunbi Jeong(3), Kiran Kumar Matam(2), Seokin Hong(2), Jong Hyun Jeong(2), WooChul Jung(2)