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
GPU compute & high precision general questions New to Julia gpu , cuda , opencl	19	3565	December 30, 2021
How much faster is GPU compare to CPU GPU	16	27301	November 24, 2018
Why is my GPU kernel an order of magnitude slower than my CPU function? GPU question	8	450	June 4, 2025
Performance comparison of Nvidia A100, V100, RTX2080Ti Performance gpu , cuda	17	5582	June 14, 2021
Why the Floating-Point Calculation Efficiency of CUDA.jl Does Not Reach the Official Theoretical Value GPU	1	135	February 2, 2025