A processing unit in an NVIDIA GPU that accelerates AI neural network processing and high-performance computing (HPC). Tensor cores compute values on matrices in parallel. A new matrix is created from two matrices by quickly multiplying and adding 16- or 32-bit floating point values in parallel. See
TF32.
Tensor vs. CUDA
Although CUDA cores have been used in AI applications, Tensor cores were designed for AI deep learning, and both CUDA and Tensor cores are found in NVIDIA GPUs. See
CUDA core,
matrix multiplication,
GPU,
TPU,
neural network,
Tensor Processing Unit and
Tensor chip.