Scalable Multi-Node Multi-GPU Datalog Engine with Energy-Aware Profiling
Scalable Multi-Node Multi-GPU Datalog Engine with Energy-Aware Profiling
Shovon, A. R.,Kumar, S.
- Location: St. Louis, MO
- PDF: sc_2025_shovon_final.pdf
Conclusion• First ever Datalog engine designed for multinode multi-GPU HPC systems outperforming state-of-the-art engines• Introduces novel GPU-Aware communication for scalable recursive query evaluation• Supports recursive aggregation for Datalog rules using high-throughput GPU kernels• Power profiling of GPU-based Datalog engines
Citation: Shovon, A. R., Kumar, S., Scalable Multi-Node Multi-GPU Datalog Engine with Energy-Aware Profiling, Supercomputing 2025 (SC25), St. Louis, MO, 2025-11-16.