Good tutorial for understanding the basics of CUDA: https://www.pyspur.dev/blog/introduction_cuda_programming. It also links to NVIDIA’s simple tutorial. Implemented a simple float16 addition kernel in CUDA at https://github.com/cmdr2/study/blob/main/ml/cuda/half_add.cu. Compile it using nvcc -o half_add half_add.cu.
Continued to test and fix issues in sdkit, after the change to support DirectML. The change is fairly intrusive, since it removes direct references to torch.cuda with a layer of abstraction. Fixed a few regressions, and it now passes all the regression tests for CPU and CUDA support (i.e. existing users). Will test for DirectML next, although it will fail (with out-of-memory) for anything but the simplest tests (since DirectML is quirky with memory allocation).