SAFARI Live Seminar – PyGim: An Efficient Graph Neural Network Library for Real PIM Architecture
Title: PyGim: An Efficient Graph Neural Network Library for Real Processing-In-Memory Architecture
Speaker: Christina Giannoula, University of Toronto & incoming faculty at MPI-SWS
https://people.mpi-sws.org/~cgiannoula
Talk Details: https://safari.ethz.ch/safari-live-seminar-christina-giannoula-sept-23-2025/
Slides (pdf): https://safari.ethz.ch/wp-content/uploads/PyGIM_SAFARI_Live_Seminar_Sept2025_Clean.pdf
Abstract:
Graph Neural Networks (GNNs) are emerging ML models to analyze graph-structure data. Graph Neural Network (GNN) execution involves both compute-intensive and memory-intensive kernels, the latter dominates the total time, being significantly bottlenecked by data movement between memory and processors. Processing-In-Memory (PIM) systems can alleviate this data movement bottleneck by placing simple processors near or inside to memory arrays. In this talk, we will introduce PyGim, an efficient ML library that accelerates GNNs on real PIM systems. We propose intelligent parallelization techniques for memory-intensive kernels of GNNs tailored for real PIM systems, and develop handy Python API for them. We provide hybrid GNN execution, in which the compute-intensive and memory-intensive kernels are executed in processor-centric and memory-centric computing systems, respectively. We present an extensive evaluation of PyGim on a real-world PIM system with 1992 PIM cores using emerging GNN models, and we will demonstrate that it outperforms its state-of-the-art CPU counterpart on Intel Xeon by on average 3.04x, and achieves higher resource utilization than CPU and GPU systems. PyGim is open source at https://github.com/CMU-SAFARI/PyGim.
Bio: Christina Giannoula is an incoming Tenure-Track Faculty at the Max Planck Institute for Software Systems (MPI-SWS), where she will lead the SPIN research group. She is currently a Postdoctoral Researcher with the University of Toronto and received her Ph.D. degree from the School of Electrical and Computer Engineering, National Technical University of Athens, advised by Prof. Georgios Goumas, Prof. Nectarios Koziris, and Prof. Onur Mutlu. Christina is also an affiliated senior researcher at the SAFARI research group at ETH Zurich. Her research interests include the intersection of computer architecture, computer systems, and high-performance computing. Specifically, her research focuses on the hardware/software co-design of emerging applications, including graph processing, pointer-chasing data structures, machine learning workloads, and sparse linear algebra, with modern computing paradigms, such as large-scale multicore systems, disaggregated memory systems, and near-data processing architectures. She has several publications and awards for her research on the aforementioned topics.
Past SAFARI Live Seminars: https://safari.ethz.ch/safari-seminar-series/
Title: PyGim: An Efficient Graph Neural Network Library for Real Processing-In-Memory Architecture
Speaker: Christina Giannoula, University of Toronto & incoming faculty at MPI-SWS
https://people.mpi-sws.org/~cgiannoula
Talk Details: https://safari.ethz.ch/safari-live-seminar-christina-giannoula-sept-23-2025/
Slides (pdf): https://safari.ethz.ch/wp-content/uploads/PyGIM_SAFARI_Live_Seminar_Sept2025_Clean.pdf
Abstract:
Graph Neural Networks (GNNs) are emerging ML models to analyze graph-structure data. Graph Neural Network (GNN) execution involves both compute-intensive and memory-intensive kernels, the latter dominates the total time, being significantly bottlenecked by data movement between memory and processors. Processing-In-Memory (PIM) systems can alleviate this data movement bottleneck by placing simple processors near or inside to memory arrays. In this talk, we will introduce PyGim, an efficient ML library that accelerates GNNs on real PIM systems. We propose intelligent parallelization techniques for memory-intensive kernels of GNNs tailored for real PIM systems, and develop handy Python API for them. We provide hybrid GNN execution, in which the compute-intensive and memory-intensive kernels are executed in processor-centric and memory-centric computing systems, respectively. We present an extensive evaluation of PyGim on a real-world PIM system with 1992 PIM cores using emerging GNN models, and we will demonstrate that it outperforms its state-of-the-art CPU counterpart on Intel Xeon by on average 3.04x, and achieves higher resource utilization than CPU and GPU systems. PyGim is open source at https://github.com/CMU-SAFARI/PyGim.
Bio: Christina Giannoula is an incoming Tenure-Track Faculty at the Max Planck Institute for Software Systems (MPI-SWS), where she will lead the SPIN research group. She is currently a Postdoctoral Researcher with the University of Toronto and received her Ph.D. degree from the School of Electrical and Computer Engineering, National Technical University of Athens, advised by Prof. Georgios Goumas, Prof. Nectarios Koziris, and Prof. Onur Mutlu. Christina is also an affiliated senior researcher at the SAFARI research group at ETH Zurich. Her research interests include the intersection of computer architecture, computer systems, and high-performance computing. Specifically, her research focuses on the hardware/software co-design of emerging applications, including graph processing, pointer-chasing data structures, machine learning workloads, and sparse linear algebra, with modern computing paradigms, such as large-scale multicore systems, disaggregated memory systems, and near-data processing architectures. She has several publications and awards for her research on the aforementioned topics.
Past SAFARI Live Seminars: https://safari.ethz.ch/safari-seminar-series/
