I get ~ 17 cpd with my GTX 1080Ti, nice =)
I'm trying xpmclient on a g3.4xlarge instance of AWS: 1 GPU (product: GM204GL [Tesla M60]) with 8GiB and 16vCPUs (
https://aws.amazon.com/blogs/aws/new-next-generation-gpu-powered-ec2-instances-g3/).
I've got only ~6cpd =(
Here is the result of a nvidia-smi
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 384.98 Driver Version: 384.98 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 Tesla M60 Off | 00000000:00:1E.0 Off | 0 |
| N/A 56C P0 122W / 150W | 1115MiB / 7613MiB | 100% Default |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 4795 C ./xpmclient 1104MiB |
+-----------------------------------------------------------------------------+
Is it possible to use all GPU memory ? (It only uses 1115Mib of the 7613 available...)
Could it boost the cpd ?
[I've got the same result on a p2.xlarge aws instance.]
Thanks
Show Posts
