Calculate data flows on GPU (ILGPU)

Nico Gerbrand
Employee




With machine learning, for example Tensorflow, it is possible to perform calculations on a CPU or GPU. Powerful GPUs are often used for this in order to achieve a significant performance gain.
Idea: Calculating data flows in Board using a GPU.
I could imagine that this is possible using ILGPU. ILGPU is a new JIT (just-in-time) compiler for high-performance GPU programs (also known as kernels) written in .Net-based languages. ILGPU is completely written in C# without any native dependencies which allows you to write GPU programs that are truly portable.
Tagged:
6