My device 1 is showing an error that I've never seen. The same code is running on device 0. It won't keep, dies with no error, on device 1 (due to the ERR!).
Is this a hardware or software thing? What is it called besides 'ERR!'?
I ran the device query code similar to / available in many CUDA starter tutorials, and the output is normal. https://devblogs.nvidia.com/parallelforall/how-query-device-properties-and-handle-errors-cuda-cc/
my keel is:
uname -a
Linux manjaro 4.1.18-2-MANJARO #1 SMP PREEMPT Sat Feb 27 23:18:59 UTC 2016 x86_64 GNU/Linux
~$ nvidia-smi
Wed May 18 19:16:29 2016
+------------------------------------------------------+
| NVIDIA-SMI 361.28 Driver Version: 361.28 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 GeForce GTX 970 Off | 0000:01:00.0 Off | N/A |
| 23% 69C P2 140W / 170W | 1207MiB / 4092MiB | 99% Default |
+-------------------------------+----------------------+----------------------+
| 1 GeForce GTX 970 Off | 0000:02:00.0 Off | N/A |
|ERR! 58C P0 ERR! / 170W | 16MiB / 4092MiB | 1% Default |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 645 C /usr/local/bin/code-gpu-75 1190MiB |
+-----------------------------------------------------------------------------+
Recent Questions...
ما را در سایت Recent Questions دنبال میکنید
برچسب:
نویسنده: استخدام کار
بازدید: 227
تاريخ: پنجشنبه
30 ارديبهشت
1395 ساعت: 7:18