CUDA 13.2
CUDA 13.2 is the latest release of NVIDIA's parallel computing platform and application programming interface (API) model, designed to leverage the power of NVIDIA GPUs for high-performance computing tasks. This version introduces significant enhancements, including full support for CUDA Tile on various GPU architectures and advanced features in cuTile Python, aiming to simplify GPU programming and improve developer productivity.
CUDA 13.2 is the latest release of NVIDIA's parallel computing platform and application programming interface (API) model, designed to leverage the power of NVIDIA GPUs for high-performance computing tasks. This version introduces significant enhancements, including full support for CUDA Tile on various GPU architectures and advanced features in cuTile Python, aiming to simplify GPU programming and improve developer productivity.
- 01Full support for CUDA Tile on compute capability 8.X (Ampere, Ada), 10.X, and 12.X (Blackwell) architectures
- 02Enhanced cuTile Python with recursive functions, closures, custom reductions, type-annotated assignments, and improved array slicing
- 03New `cudaMemcpyWithAttributesAsync` and `cudaMemcpy3DWithAttributesAsync` APIs for flexible memory transfers
- 04Per-context local memory footprint reduction in Windows WDDM mode for better memory efficiency
- 05Shift in default Windows GPU driver mode from TCC to MCDM for improved compatibility and feature access