State of the art sorting and segmented sorting, including OneSweep. Implemented in CUDA, D3D12, and Unity style compute shaders. Theoretically portable to all wave/warp/subgroup sizes.
Lecture-215 - Rotting Oranges Lecture-216 - Minimum Time to Collect All Apples in a Tree Lecture-217 - Most Stones Removed with Same Row or Column Lecture-218 - Accounts Merge Lecture-219 - Cycle ...