Download Latest Version Version 0.8.1 CUDA 12.x compatibility improvements _ minor fixes source code.tar.gz (630.3 kB)
Email in envelope

Get an email when there's a new version of CUDA API Wrappers

Home / v0.7.0
Name Modified Size InfoDownloads / Week
Parent folder
README.md 2024-06-06 1.4 kB
Version 0.7.0_ Graph support source code.tar.gz 2024-06-06 369.2 kB
Version 0.7.0_ Graph support source code.zip 2024-06-06 488.9 kB
Totals: 3 Items   859.5 kB 0

Changes since v0.6.9:

Graph support

The wrappers library now supports the creation and manipulation of CUDA graphs - meriting a version number bump.

One can now:

  • Construct graphs (= graph templates) directly
  • Capture graphs (= graph templates) on streams
  • Instantitate and launch graph templates

... all using a more convenient interface, similar to non-graph CUDA-API calls. Two examples of this kind of code have been added, both adaptations of NVIDIA CUDA samples:

The main class templates are: template_t, node_t, typed_node_t, instance_t - all in namespace cuda::graph.

Most, but not all, graph capabilities are supported.

Other minor changes

  • [#649]: Respect deprecation of shared memory bank size setting as of CUDA 12.3
  • Avoiding more MSVC compilation warnings
Source: README.md, updated 2024-06-06