I have a Tesla P100:
nvidia-smi
Thu Jun 13 11:01:28 2024
±--------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.104.05 Driver Version: 535.104.05 CUDA Version: 12.2 |
|-----------------------------------------±---------------------±---------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 Tesla P100-PCIE-16GB Off | 00000000:03:00.0 Off | 0 |
| N/A 41C P0 27W / 250W | 0MiB / 16384MiB | 0% Default |
| | | N/A |
±----------------------------------------±---------------------±---------------------+
| 1 Tesla P100-PCIE-16GB Off | 00000000:85:00.0 Off | 0 |
| N/A 44C P0 28W / 250W | 0MiB / 16384MiB | 1% Default |
| | | N/A |
±----------------------------------------±---------------------±---------------------+
±--------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
| No running processes found |
±--------------------------------------------------------------------------------------+
I have installed the CUDA Toolkit and I am having problems running the test busGrind in /usr/local/cuda/extras/demo_suite. All the test work, except the busGrind test:
flexe@leo02:/usr/local/cuda/extras/demo_suite$ ./busGrind
Device: 0, Tesla P100-PCIE-16GB, pciBusID: 3, pciDeviceID: 0, pciDomainID:0
Device: 1, Tesla P100-PCIE-16GB, pciBusID: 85, pciDeviceID: 0, pciDomainID:0
P2P Cliques:
Clique: 0 [0]
Clique: 1 [1]
Test Description: Bus bandwidth between the host and a single device
Cuda failure /dvs/p4/build/sw/rel/gpgpu/toolkit/r12.2/demo_suite/busGrind/busGrind_pthread.cu:216: ‘out of memory’
How I can solve this issue?