I am using CUDA.jl to speed up double-precision simulations with large matrix computations and FFT (e.g. Split Step Fourier Method). I heard about Tensor Cores on NVIDIA GPUs and have the following questions: Tensor Core seems to target Machine Learning (in particular Neural Network) application…

Yes, see https://juliagpu.org/2020-10-02-cuda_2.0/#low--and-mixed-precision-operations .

NVIDIA Tensor Cores not useful for double-precision simulations?

Zhong_Pan November 17, 2020, 5:49pm 8

Great, many thanks!!

Topic		Replies	Views
How much faster is GPU compare to CPU GPU	16	26969	November 24, 2018
GPU compute & high precision general questions New to Julia gpu , cuda , opencl	19	3486	December 30, 2021
How to get started with GPU programming? OpenCL or CUDA? GPU	7	7299	August 29, 2017
Questions on a number of code acceleration techniques General Usage performance , hpc , parallel	11	1807	July 8, 2017
Performance comparison of Nvidia A100, V100, RTX2080Ti Performance gpu , cuda	17	5426	June 14, 2021