TESLA M40 24GB

[JasonAaronLawrence]

are these still supported? finally got through all the driver kinks, gota cuda and opencl going and power cables working and the log indicates:

Code: Select all

17:43:06:W :OpenCL not supported: clGetPlatformIDs() returned -1001
17:43:06:W :CUDA not supported: cuInit() returned 999
17:43:06:I3:gpus = {
17:43:06:I3: "gpu:03:00:00": {"vendor": 4318, "device": 6141, "type": "nvidia", "supported": false, "description": "GM200GL [Tesla M40] 6844 "},
17:43:06:I3: "gpu:131:00:00": {"vendor": 4318, "device": 6141, "type": "nvidia", "supported": false, "description": "GM200GL [Tesla M40] 6844 "}
17:43:06:I3:}

jason@tercerus:/var/lib/fah-client$ nvidia-smi Tue Jan 7 17:55:19 2025 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 565.57.01 Driver Version: 565.57.01 CUDA Version: 12.7 | |-----------------------------------------+------------------------+----------------------+ | 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 M40 24GB On | 00000000:03:00.0 Off | 0 | | N/A 20C P8 15W / 250W | 0MiB / 23040MiB | 0% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ | 1 Tesla M40 24GB On | 00000000:83:00.0 Off | 0 | | N/A 21C P8 16W / 250W | 0MiB / 23040MiB | 0% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | No running processes found | +-----------------------------------------------------------------------------------------+

[Joe_H]

Yes, as a Maxwell based card the Tesla M40 is still supported. But getting Linux, the Nvidia drivers, and F@h all working together can be a pain at times. In this case for whatever reason the F@h client app is not detecting the CUDA and OpenCL support installed on your system. It could be a permissions problem or a path problem. Someone more familiar with the Linux installation issues may give you some ideas on what additional needs to be done to get this working for you

Additional pieces of information that may help is which version of the F@h software you have installed and which Linux version you are using. You may also find some more information in topics posted to this sub-forum - viewforum.php?f=80.

[JasonAaronLawrence]

thanks...that sent me on a search. i verified the packages required were installed, then noted the install order. i reinstalled the fah-client from .deb and the cards were recognized and ran wu's.

This is ubuntu server 24.04
fah-client v8.3.18