domains / families / science / optimize-for-gpu

optimize-for-gpu

separate

GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search, image-processing, graph, simulation, or file-I/O workloads; CuPy, cuDF, cuML, cuGraph, cuVS, cuCIM, KvikIO, Warp, Newton, Numba-CUDA, or RAFT questions; and profiling, memory-transfer, kernel, or multi-GPU bottlenecks. Also use when large data-parallel Python code is slow and GPU acceleration is a plausible option, even if the user does not name CUDA.

When to use

• CUDA/GPU optimization
• CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image workloads
• vector-search, image-processing, graph, simulation, or file-I/O workloads
• CuPy, cuDF, cuML, cuGraph, cuVS, cuCIM, KvikIO, Warp, Newton, Numba-CUDA, or RAFT questions
• profiling, memory-transfer, kernel, or multi-GPU bottlenecks
• large data-parallel Python code that is slow
• machine learning training, inference, hyperparameter tuning, preprocessing
• geospatial analysis, robotics, physics simulation

When not to use

• moving code out of PyTorch, JAX, TensorFlow, or another GPU-native framework merely to use one of these libraries
• using cuxfilter for new work
• using cuSpatial for new work

Skill page

Source