cufinufft

cufinufft copied to clipboard

Running on AMD

7

Hello, Are you aware of any attempts to hipify this library on AMD GPUS using HIP? Cristian

csccva

We currently constrain ourselves to 49k of shmem -- AFAIK this is a constraint that is not really applicable anymore. We should experiment with changing this. Noted at #156

blackwer

Just lodging the request that we build some MATLAB/octave wrappers some day soon. Calling this from MATLAB would be really cool, as a drop-in replacement for FINUFFT.

ahbarnett

Add type 3 for 3D

13

For a project, we require a type 3 transform on GPU. Since this feature is still missing, I've implemented it for the 3D case. This was mainly done by porting...

AdhocMan

Thrust `max_element` header change

1

Building the latest master with the compilers below gave an error regarding a missing header. Reporting this for posterity; already worked around. One line fix is below. ``` nvcc -DSINGLE...

garrettwrong

Hmm, having to PR to master is annoying for docs :)

ahbarnett

Add support for AMD GPUs via HIP

9

This is work in progress branch to add support for AMD GPUs via [HIP](https://rocmdocs.amd.com/en/latest/Programming_Guides/HIP-GUIDE.html), a very nearly CUDA-compatible API by AMD. While this isn't ready to go yet, it's far...

elliottslaughter

Windows version

7

Hi, I was wondering if cuFINUFFT is platform neutral. If not, do you plan to develop a Windows version? Thanks, Yuan

ApplestarGY

Issue with interpolation only option with python wrapper

1

Hello, I encountered the issue, when I select a gpu_spreadinterponly (I want to only interpolate, I do not need the FFT at this moment). I use this simple code to...

headmeister

Implementing 1.25 upsampling factor with precomputed Horner kernel

3

Hi all, Thank you very much for everyone's work on this library. What would be required to implement the upsampling ratio sigma of 1.25 in a similar way to the...

AaronGhost