The AOCL Data Analytics Library (AOCL-DA) provides optimized building blocks for data analysis and machine learning. It is written with a C-compatible interface to make it as seamless as possible to ...
High performance: close to roofline fp16 TensorCore (NVIDIA GPU) / MatrixCore (AMD GPU) performance on major models, including ResNet, MaskRCNN, BERT, VisionTransformer, Stable Diffusion, etc. Unified ...