-
Currently, `device` is an input parameter as **global** variable. When `device=gpu`, all the calculation will be done on GPUs.
However, "the machine has GPUs" does not need "every module calculates on…
-
**Hardware**
- CPU: Intel Core i5-9400F
- RAM: 16 GB
- GPU: GTX 1070
- SDR: Remote MiriSDR
**Software**
- Operating System: Windows 11 x64
- SDR++: Oct 14 2024 (self-compiled, but i didn't se…
-
### Description
I tried to run `tests/fft_test.py::FftTest::testFftfreq5` on g5.24xlarge instance which has 4 GPU devices.
The test works fine if executed individually
```
pytest -s -v tests/fft…
-
GAMER currently only supports computing FFT on CPUs. It will be great to support multi-GPU, multi-node FFT using `cuFFTMp`.
- [Blog](https://developer.nvidia.com/blog/multinode-multi-gpu-using-nvidia…
-
**Describe the proposal**
Now that `amrex::FFT` exists, we can do the FFT to generate Gaussian random fields (e.g., for turbulence initial conditions and driving) directly on the GPU.
**Describe alte…
-
Hi,
First let me say that I have been quite happy with the performance of deconwolf. I have tested it using sets of RNA FISH images with great results. I think it works better (and faster) than th…
-
### 🐛 Describe the bug
When running the following function in my code, it reports an error:
The code is:
```
import torch
import torch.nn as nn
import torch.fft
import torch.cuda
...
de…
-
For even faster convolution, can we augment fftw with pyvkfft?
https://github.com/vincefn/pyvkfft
https://pyvkfft.readthedocs.io/en/latest/
-
### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
Yes
### Source
source
### TensorFlow version
tf2.17.0 tf2.16.1
### Custom code
Yes
### OS platform and distributio…
-
### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
Yes
### Source
source
### TensorFlow version
tf2.17.0 tf2.16.1
### Custom code
Yes
### OS platform and distributio…