Extending Block-Cyclic Tensors for Multi-GPU with NVIDIA cuTENSORMg

Originally published at: https://developer.nvidia.com/blog/extending-block-cyclic-tensors-for-multi-gpu-with-nvidia-cutensormg/

cuTENSOR is now able to distribute tensor contractions across multiple GPUs. This has been released as a new library called cuTENSORMg (multi-GPU).