HHHyungkyu Ham

Hyungkyu Ham

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hyungkyu Ham has a total of 28 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Exploring High-Bandwidth Flash for Modern LLM Inference: Opportunities and Challenges

    by Dowon Son, Yonggon Park, Hyunuk Cho, Hyungkyu Ham, Onur Mutlu, Sungjin Lee, Gwangsun Kim, Jisung Park


  • Open Access

    PyTorchSim: A Comprehensive, Fast, and Accurate NPU Simulation Framework

    by Wonhyuk Yang, Yunseon Shin, Okkyun Woo, Geonwoo Park, Hyungkyu Ham, Jeehoon Kang, Jongse Park, Gwangsun Kim


  • ONNXim: A Fast, Cycle-Level Multi-Core NPU Simulator

    by Hyungkyu Ham, Wonhyuk Yang, Yunseon Shin, Okkyun Woo, Guseul Heo, Sangyeop Lee, Jongse Park, Gwangsun Kim

    As DNNs (Deep Neural Networks) demand increasingly higher compute and memory requirements, designing efficient and performant NPUs (Neural Processing Units) has become more important. However, existing architectural NPU simulators lack support for high-speed simulation, multi-core modeling, multi-tenant scenarios, detailed DRAM/NoC modeling, and/or different deep learning frameworks. To address these limitations, this work proposes ONNXim , a fast cycle-level simulator for multi-core NPUs in DNN serving systems. For ease of simulation, it takes DNN models in the ONNX graph format generated from various deep learning frameworks. In addition, based on the observation that typical NPU cores process tensor tiles from SRAM with deterministic compute latency, we model computation accurately with an event-driven approach, avoiding the overhead of modeling cycle-level activities. ONNXim also preserves dependencies between compute and tile DMAs. Meanwhile, the DRAM and NoC are modeled in cycle-level to properly model contention among multiple cores that can execute different DNN models for multi-tenancy. Consequently, ONNXim is significantly faster than existing simulators (e.g., by up to 365× over Accel-sim) and enables various case studies, such as multi-tenant NPUs, that were previously impractical due to slow speed and/or lack of functionalities. ONNXim is publicly available at https://github.com/PSAL-POSTECH/ONNXim .


  • Open Access

    Non-Invasive, Memory Access-Triggered Near-Data Processing for DNN Training Acceleration on GPUs

    by Hyungkyu Ham, Hyunuk Cho, Minjae Kim, Jueon Park, Jeongmin Hong, Hyojin Sung, Eunhyeok Park, Euicheol Lim, Gwangsun Kim

    To address the off-chip bandwidth (BW) and memory capacity challenges of GPUs in DNN training, we propose a memory access-triggered near-data processing mat NDP architecture that offloads memory- and communication-bound operations. With mat NDP, normal memory accesses also serve as implicit NDP requests to enable NDP in a non-invasive manner without modifying core-side ISA/microarchitecture/SW, for practical NDP. In addition, mat NDP enables on-the-fly NDP where the data already supplied in normal memory requests for compute-bound operations are also simultaneously used for NDP; thus, matNDP can overlap even dependent kernels while also reducing memory traffic. Moreover, with the overlap, memory bandwidth (BW) underutilized by GPU cores can be used by NDP units to improve performance even under the same total memory BW. The matNDP units can be deployed to heterogeneous memory devices in a system. First, we deploy them near GPU’s memory controllers. Secondly, our NDP units are deployed in memory expanders connected to multiple GPUs to create an NDP-enabled memory eXpander Network (NDPXNet) . It can entirely offload gradient reduction and optimizer in data-parallel training, achieving additional speedups while eliminating redundancy in memory usage and optimizer execution. As a result, we 1) enable NDP without core HW/SW changes, 2) overlap the execution of dependent layers, and 3) offload both memory- and communicationbound operations from GPUs in DNN training. Through our deep learning compiler support, NDP kernels can be generated automatically without any model code modification. Consequently, mat NDP can improve training throughput by up to 2.73× and reduce energy by up to 41.4%.


  • Top Cited Papers
    Open Access

    NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing

    by Guseul Heo, Sangyeop Lee, Jaehong Cho, Hyunmin Choi, Sanghyeon Lee, Hyungkyu Ham, Gwangsun Kim, Divya Mahajan, Jongse Park

    Modern transformer-based Large Language Models (LLMs) are constructed with a series of decoder blocks. Each block comprises three key components: (1) QKV generation, (2) multi-head attention, and (3) feed-forward networks. In batched processing, QKV generation and feed-forward networks involve compute-intensive matrix-matrix multiplications (GEMM), while multi-head attention requires bandwidth-heavy matrix-vector multiplications (GEMV). Machine learning accelerators like TPUs or NPUs are proficient in handling GEMM but are less efficient for GEMV computations. Conversely, Processing-in-Memory (PIM) technology is tailored for efficient GEMV computation, while it lacks the computational power to handle GEMM effectively. Inspired by this insight, we propose NeuPIMs, a heterogeneous acceleration system that jointly exploits a conventional GEMM-focused NPU and GEMV-optimized PIM devices. The main challenge in efficiently integrating NPU and PIM lies in enabling concurrent operations on both platforms, each addressing a specific kernel type. First, existing PIMs typically operate in a "blocked" mode, allowing only either NPU or PIM to be active at any given time. Second, the inherent dependencies between GEMM and GEMV in LLMs restrict their parallel processing. To tackle these challenges, NeuPIMs is equipped with dual row buffers in each bank, facilitating the simultaneous management of memory read/write operations and PIM commands. Further, NeuPIMs employs a runtime sub-batch interleaving technique to maximize concurrent execution, leveraging batch parallelism to allow two independent sub-batches to be pipelined within a single NeuPIMs device. Our evaluation demonstrates that compared to GPU-only, NPU-only, and a naïve NPU+PIM integrated acceleration approaches, NeuPIMs achieves 3×, 2.4× and 1.6× throughput improvement, respectively.


  • Near-Data Processing in Memory Expander for DNN Acceleration on GPUs

    by Hyungkyu Ham, Hyunuk Cho, Minjae Kim, Jueon Park, Jeongmin Hong, Hyojin Sung, Eunhyeok Park, Euicheol Lim, Gwangsun Kim

    We propose a near-data processing (NDP) architecture that exploits a memory expander with byte-addressable memory-semantic interconnect to accelerate memory-bound operations in deep neural networks (DNNs). Our architecture can execute NDP operations on the memory traffic from the GPU on-the-fly by employing bump-in-the-wire NDP logic between the off-chip link and memory controller. In addition, the memory-bound operations executed on the NDP unit can be effectively overlapped with compute-intensive operations executed on a GPU, even if the two operations have a dependency. Furthermore, the NDP offloading can be automatically done by the compiler without any code modification by deep learning practitioners. Our approach can achieve a 51% speedup for training VGG-16 with batch normalization.