High-performance GPU SpMV kernels in Python/Numba CUDA. Achieves 96.6 GB/s (53% of cuSPARSE) with 5,432x speedup over CPU. Includes optimization analysis.
hpc linear-algebra cuda scientific-computing high-performance-computing gpu-acceleration numba spmv sparse-matrix gpu-programming cusparse python-cuda tesla-p100
-
Updated
Dec 27, 2025 - Python