The artificial intelligence community has long struggled with a fundamental challenge of making AI systems transparent and understandable. As large language models become increasingly powerful, ...

Brain-inspired chips can slash AI energy use by as much as 100-fold, but the road to mainstream deployment is far from guaranteed.

We illustrate the OpenH programming model and library API using two hybrid parallel applications based on matrix multiplication and 2D fast Fourier transform for the most general case of a hybrid ...

With the widespread use of heterogeneous computing platforms in the AI field, neural network models on heterogeneous computing platforms are experiencing problems such as low execution efficiency and ...