ismember with 'rows' option fails on GPU

2 次查看（过去 30 天）
Wasim Aftab
Wasim Aftab 2018-3-12
编辑： Matt J 2018-7-2
Hi, when I run the command
[Lia, Locb] = ismember(gpuArray(Ent_Pair_Pos), gpuArray(Ent_Pair_Dmel), 'rows')
I get this error
Error using gpuArray/ismember
Failed to initialize GPU BLAS library.
I am using MATLAB Version: 9.0.0.341360 (R2016a) on Ubuntu 14.04. I am attaching data files here. Any idea regarding the error?
Thanks in advance
  2 个评论
Joss Knight
Joss Knight 2018-3-14
Well, it works for me. It looks like a driver problem. You should try installing the latest NVIDIA drivers.
Wasim Aftab
Wasim Aftab 2018-7-2
编辑：Matt J 2018-7-2
Hi Joss, Its not working with 'rows' option.
CUDADevice with properties:
Name: 'GeForce GTX TITAN X'
Index: 1
ComputeCapability: '5.2'
SupportsDouble: 1
DriverVersion: 9
ToolkitVersion: 8
MaxThreadsPerBlock: 1024
MaxShmemPerBlock: 49152
MaxThreadBlockSize: [1024 1024 64]
MaxGridSize: [2147483647 65535 65535]
SIMDWidth: 32
TotalMemory: 12794789888
AvailableMemory: 11489981880
MultiprocessorCount: 24
ClockRateKHz: 1076000
ComputeMode: 'Default'
GPUOverlapsTransfers: 1
KernelExecutionTimeout: 1
CanMapHostMemory: 1
DeviceSupported: 1
DeviceSelected: 1
Mon Jul 2 15:26:34 2018
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 384.130 Driver Version: 384.130 |
|-------------------------------+----------------------+----------------------+
| 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 TIT... Off | 00000000:01:00.0 On | N/A |
| 22% 49C P8 17W / 250W | 1254MiB / 12202MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 1457 G /usr/bin/X 362MiB |
| 0 2701 G compiz 182MiB |
| 0 5901 C /opt/anaconda3/bin/python 473MiB |
| 0 6615 C+G .../local/MATLAB/R2017b/bin/glnxa64/MATLAB 222MiB |
+-----------------------------------------------------------------------------+

请先登录，再进行评论。

请先登录，再回答此问题。

回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 GPU Computing 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by