List view
Support for features introduced with CUDA 12.9
No due date•0/2 issues closedSupport settings and features introduced in CUDA release 12.8 (over those already available in 12.6.x)
No due date•1/3 issues closed- No due date•3/6 issues closed
- No due date•0/1 issues closed
- No due date•0/1 issues closed
CUDA 12.3 adds the following relevant features: * CUDA Graphs: * Graph edge data, allowing modified dependencies between nodes. Programmatic Dependent Launch may now be described natively in CUDA Graphs. * Launch completion events: * Allows a dependency on scheduling, but not completion, of all blocks in a kernel, enabling tighter control of scheduling. * Added a driver API to return the name of a kernel function. * Added an API to libnvJitLink to return the nvJitLink version. * Added support for reading kernel parameters in device functions. * Enable querying the return type of __device__ lambdas with trailing return type. Fixes uncommon failures when using device-side lambdas. ... plus some NVML features.
No due date•1/4 issues closed- No due date•0/1 issues closed
- No due date•5/10 issues closed
- No due date•2/2 issues closed
Support all CUDA API elements/features introduced in CUDA 11.* versions (currently 11.0 - 11.5)
No due date•7/11 issues closedSupport all CUDA API elements/features introduced in the CUDA 7.* versions (7.0, 7.5)
No due date•2/2 issues closedSupport all CUDA API elements/features introduced in CUDA 10.* versions (10.0, 10.1, 10.2).
No due date•8/9 issues closedThe example programs covering the different modules/parts of the API wrappers cover all functions, i.e. call them in non-dead branches obtaining non-trivial results (if applicable).
No due date•0/1 issues closedAt this milestone, the API wrappers will cover all non-3d-graphics, non-multidimensional parts of the Runtime API of CUDA version 9.2.
No due date•8/9 issues closed