Yeah that seems reasonable. I’ve created another post which addresses the first part of this problem: how to call kernels vector-wise on a device matrix that update elements of a column vector. Once that is done I will update this thread.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Column-wise reduction on a CUDA.CuArray matrix | 0 | 1179 | August 16, 2020 | |
| CuArrays: error calling CuArray() (ERROR_INVALID_DEVICE) | 25 | 3919 | February 16, 2020 | |
| CuArray/CUDAnative argmin paradoxical performance | 2 | 874 | January 31, 2019 | |
| Julia with CuArray issue | 2 | 206 | July 1, 2024 | |
| Strange behavior of CuDeviceArrays | 7 | 934 | June 10, 2021 |