WebLog

NVIDIA CUDA Deep Neural Network library (cuDNN)

cuDNN is a GPU-accelerated library of primitives for deep neural networks. It provides highly tuned implementations of operations arising frequently in deep neural network (DNN) applications.

• Scaled dot-product attention
• Convolution, including cross-correlation
• Matrix multiplication
• Normalizations, softmax, and pooling
• Arithmetic, mathematical, relational, and logical pointwise operations

API layers are available for constructing these graphs: - Python frontend API - C++ frontend API - C backend API