Tensor core

Hardware

With the exception of the shader-core version implemented in Control, DLSS is only available on GeForce RTX 20, GeForce RTX 30, GeForce RTX 40, GeForce RTX 50, and Quadro RTX series of video cards, using dedicated AI accelerators called Tensor Cores. Tensor Cores are available since the Nvidia VoltaGPUmicroarchitecture, which was first used on the Tesla V100 line of products. They are used for doing fused multiply-add (FMA) operations that are used extensively in neural network calculations for applying a large series of multiplications on weights, followed by the addition of a bias. Tensor cores can operate on FP16, INT8, INT4, and INT1 data types. Each core can do 1024 bits of FMA operations per clock, so 1024 INT1, 256 INT4, 128 INT8, and 64 FP16 operations per clock per tensor core, and most Turing GPUs have a few hundred tensor cores. The Tensor Cores use CUDAWarp-Level Primitives on 32 parallel threads to take advantage of their parallel architecture. A Warp is a set of 32 threads which are configured to execute the same instruction. Since Windows 10 version 1903, Microsoft provided DirectML as one part of DirectX to support Tensor Cores.