Quote from: Mikorist on December 11, 2022, 07:58:18 PM

It won't work until numba -s shows

Code:

__CUDA Information__
Found 1 CUDA devices
id 0 b'GeForce GTX 970' [SUPPORTED]
compute capability: 5.2
pci device id: 0
pci bus id: 1

which will confirm whether you have a functioning CUDA or not.

well, it seems that my GPU is supported, cannot see any issue here:

Code:

$ numba -s

Quote

__CUDA Information__
CUDA Device Initialized : True
CUDA Driver Version : 11.8
CUDA Runtime Version : 11.8
CUDA NVIDIA Bindings Available : False
CUDA NVIDIA Bindings In Use : False
CUDA Detect Output:
Found 1 CUDA devices
id 0 b'NVIDIA GeForce RTX 3070 Laptop GPU' [SUPPORTED]
Compute Capability: 8.6
PCI Device ID: 0
PCI Bus ID: 1
UUID: GPU-27a2b515-798b-e33d-89f8-d679eec4ab47
Watchdog: Enabled
FP32/FP64 Performance Ratio: 32
Summary:
   1/1 devices are supported

CUDA Libraries Test Output:
Finding nvvm from System
   named libnvvm.so.4.0.0
   trying to open library...   ok
Finding cudart from System
   named libcudart.so.11.8.89
   trying to open library...   ok
Finding cudadevrt from System
   named libcudadevrt.a
Finding libdevice from System
   trying to open library...   ok

Quote from: Mikorist on December 11, 2022, 07:58:18 PM

Try to generate mandelbrot without GPU

https://numba.pydata.org/numba-doc/dev/user/examples.html#mandelbrot

0.3226363949943334 seconds with GPU
90 seconds with CPU

I get 0.21194690400443505 when running the original mandelbrot code and 2.2377483489981387 when commenting the "from numba import jit" and "@jit..." lines.