Open nv160 opened 2 years ago
Hi,
could you share your setup to get PhoenixMiner ready with your A100 GPU. I have A100 in ubuntu 20.04. Driver and Cuda install: NVIDIA-SMI 515.65.01 Driver Version: 515.65.01 CUDA Version: 11.7
However the Phoenix miner shows me message:
Unable to enum CUDA GPUs: initialization error
No OpenCL platforms found
No available GPUs for mining. Please check your drivers and/or hardware.
Could you share your setup?
thanks
Hello,
I am using Nvidia A100 160gb GPU and just testing different mining software. (Don't predict that it's commercial product that I am using it personally -- as it's my own box that I have managed to get it)
its all pre-built like drivers, cuda-toolkit, docker and everything.
I am testing PhoenixMiner to test the speed which I am getting 174MH per card averagely 650MZ to 750MH with all cards. However, it is only utilising 5GB VRAM per card instead of using maximum or say atleast 10 to 15GB per card.
Here is the output of nvidia-smi command:
`+-----------------------------------------------------------------------------+ | NVIDIA-SMI 470.82.01 Driver Version: 470.82.01 CUDA Version: 11.4 | |-------------------------------+----------------------+----------------------+ | 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 NVIDIA A100-SXM... On | 00000000:01:00.0 Off | Off | | N/A 69C P0 279W / 275W | 5140MiB / 40536MiB | 100% Default | | | | Disabled | +-------------------------------+----------------------+----------------------+ | 1 NVIDIA A100-SXM... On | 00000000:47:00.0 Off | Off | | N/A 68C P0 274W / 275W | 5140MiB / 40536MiB | 100% Default | | | | Disabled | +-------------------------------+----------------------+----------------------+ | 2 NVIDIA A100-SXM... On | 00000000:81:00.0 Off | Off | | N/A 67C P0 279W / 275W | 5140MiB / 40536MiB | 100% Default | | | | Disabled | +-------------------------------+----------------------+----------------------+ | 3 NVIDIA DGX Display On | 00000000:C1:00.0 Off | N/A | | 34% 38C P8 N/A / 50W | 1MiB / 3911MiB | 0% Default | | | | N/A | +-------------------------------+----------------------+----------------------+ | 4 NVIDIA A100-SXM... On | 00000000:C2:00.0 Off | Off | | N/A 67C P0 274W / 275W | 5140MiB / 40536MiB | 100% Default | | | | Disabled | +-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=============================================================================| | 0 N/A N/A 111324 C ./PhoenixMiner 5137MiB | | 1 N/A N/A 111324 C ./PhoenixMiner 5137MiB | | 2 N/A N/A 111324 C ./PhoenixMiner 5137MiB | | 4 N/A N/A 111324 C ./PhoenixMiner 5137MiB | +-----------------------------------------------------------------------------+`
As you can see above memory usage is only 5137MiB per card but GPU-Utilisation shows 100%.
I don't know if it is the default behaviour or not, so thought to ask experts if they can help achieving more juices out of 160GB total GPUs.