CMU-SAFARI / PyGimLinks
PyGim is the first runtime framework to efficiently execute Graph Neural Networks (GNNs) on real Processing-in-Memory systems. It provides a high-level Python interface, currently integrated with PyTorch, and supports various GNN models and real-world input graphs. Described by SIGMETRICS'25 by Giannoula et al. (https://arxiv.org/pdf/2402.16731)
☆27Updated 3 months ago
Alternatives and similar repositories for PyGim
Users that are interested in PyGim are comparing it to the libraries listed below
Sorting:
- MultiPIM: A Detailed and Configurable Multi-Stack Processing-In-Memory Simulator☆55Updated 4 years ago
- GNNear: Accelerating Full-Batch Training of Graph NeuralNetworks with Near-Memory Processing☆13Updated 2 years ago
- ☆65Updated 4 years ago
- PIM-DL: Expanding the Applicability of Commodity DRAM-PIMs for Deep Learning via Algorithm-System Co-Optimization☆31Updated last year
- This is a processing-in-memory simulator which models 3D-stacked memory within gem5. Also includes the workloads used for IMPICA (In-Memo…☆46Updated 8 years ago
- ☆20Updated 2 years ago
- The simulator for SPADA, an SpGEMM accelerator with adaptive dataflow☆38Updated 2 years ago
- A Cycle-level simulator for M2NDP☆29Updated 3 months ago
- ☆11Updated 3 years ago
- Examples of DPU programs using the UPMEM DPU SDK☆44Updated 6 months ago
- PIMeval simulator and PIMbench suite☆32Updated this week
- Sharing the codebase and steps for artifact evaluation/reproduction for MICRO 2024 paper☆9Updated 11 months ago
- ☆24Updated 8 months ago
- Source code for the evaluated benchmarks and proposed cache management technique, GRASP, in [Faldu et al., HPCA'20].☆18Updated 5 years ago
- ☆146Updated 6 months ago
- Scaling Graph Processing on HBM-enabled FPGAs with Heterogeneous Pipelines☆20Updated 2 years ago
- Artifact for paper "PIM is All You Need: A CXL-Enabled GPU-Free System for LLM Inference", ASPLOS 2025☆82Updated 3 months ago
- A PIM instrumentation, compilation, execution, simulation, and evaluation repository for BLIMP-style architectures.☆18Updated 3 years ago
- PIM-ML is a benchmark for training machine learning algorithms on the UPMEM architecture, which is the first publicly-available real-worl…☆24Updated 6 months ago
- The Artifact of NeoMem: Hardware/Software Co-Design for CXL-Native Memory Tiering☆54Updated 11 months ago
- 3D-FPIM: An Extreme Energy-Efficient DNN Acceleration System Using 3D NAND Flash-Based In-Situ PIM Unit (MICRO 2022)☆14Updated 2 years ago
- UPMEM LLM Framework allows profiling PyTorch layers and functions and simulate those layers/functions with a given hardware profile.☆33Updated 3 weeks ago
- STONNE Simulator integrated into SST Simulator☆20Updated last year
- ☆38Updated 2 months ago
- PrIM (Processing-In-Memory benchmarks) is the first benchmark suite for a real-world processing-in-memory (PIM) architecture. PrIM is dev…☆159Updated last year
- This repo is to collect the state-of-the-art GNN hardware acceleration paper☆54Updated 4 years ago
- SparseP is the first open-source Sparse Matrix Vector Multiplication (SpMV) software package for real-world Processing-In-Memory (PIM) ar…☆75Updated 3 years ago
- ☆25Updated last year
- SimplePIM is the first high-level programming framework for real-world processing-in-memory (PIM) architectures. Described in the PACT 20…☆27Updated last year
- ☆13Updated 5 years ago