About us
Our mission at the Parallel System Architecture Laboratory is to pioneer cutting-edge computer architectures and systems that maximize performance and efficiency. We target a wide range of systems, from high-performance servers to low-power edge devices, with a particular focus on parallel and scalable designs. We achieve the goal through innovative design and optimization approaches that span hardware and software layers.
[2024, Oct.]
Our paper, "ONNXim: A Fast, Cycle-level Multi-core NPU Simulator," has been accepted for publication in IEEE Computer Architecture Letters (CAL). Congratulations!
[2024 Sep.]
Our paper, "Non-Invasive, Memory Access-Triggered Near-Data Processing for DNN Training Acceleration on GPUs," has been accepted for publication in IEEE Access. Congratulations!
[2024 Jul.]
Our paper, "Low-overhead General-purpose Near-Data Processing in CXL Memory Expanders," has been accepted to MICRO'24. Congratulations!
[2024 Jun.]
Our fast and detailed multi-core NPU simulator, called ONNXim, is released (link).
[2023 Oct.]
Our paper, "Bandwidth-Effective DRAM Cache for GPUs with Storage-Class Memory," has been accepted to HPCA'24. Congratulations!
[2023 Sep.]
Jinhoon Bae and Okkyun Woo have joined our team. Welcome!
News
