pgaccelinfo does not list gpu device

Hi all,

I have a computer with a Quadro 2000.

I’m using Ubuntu 18.04. (I think the PGI compiler does not fully support this yet, but I’m hoping that’s a separate problem.)

nvidia-smi detects the GPU, while pgaccelinfo doesn’t.

Does anybody know what might be going wrong?

$ nvidia-smi
Wed Apr 24 12:06:09 2019       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 390.116                Driver Version: 390.116                   |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  Quadro 2000         Off  | 00000000:01:00.0  On |                  N/A |
| 30%   43C    P8    N/A /  N/A |    463MiB /   961MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
|    0      1255      G   /usr/lib/xorg/Xorg                            58MiB |
|    0      1374      G   /usr/bin/gnome-shell                          52MiB |
|    0      2020      G   /usr/lib/xorg/Xorg                           153MiB |
|    0      2180      G   /usr/bin/gnome-shell                         157MiB |
+-----------------------------------------------------------------------------+



$ # The deviceQuery example that came with CUDA
$ ./deviceQuery 
./deviceQuery Starting...

 CUDA Device Query (Runtime API) version (CUDART static linking)

Detected 1 CUDA Capable device(s)

Device 0: "Quadro 2000"
  CUDA Driver Version / Runtime Version          9.1 / 9.0
  CUDA Capability Major/Minor version number:    2.1
  Total amount of global memory:                 962 MBytes (1008205824 bytes)
MapSMtoCores for SM 2.1 is undefined.  Default to use 64 Cores/SM
MapSMtoCores for SM 2.1 is undefined.  Default to use 64 Cores/SM
  ( 4) Multiprocessors, ( 64) CUDA Cores/MP:     256 CUDA Cores
  GPU Max Clock rate:                            1251 MHz (1.25 GHz)
  Memory Clock rate:                             1304 Mhz
  Memory Bus Width:                              128-bit
  L2 Cache Size:                                 262144 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(65536), 2D=(65536, 65535), 3D=(2048, 2048, 2048)
  Maximum Layered 1D Texture Size, (num) layers  1D=(16384), 2048 layers
  Maximum Layered 2D Texture Size, (num) layers  2D=(16384, 16384), 2048 layers
  Total amount of constant memory:               65536 bytes
  Total amount of shared memory per block:       49152 bytes
  Total number of registers available per block: 32768
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  1536
  Maximum number of threads per block:           1024
  Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
  Max dimension size of a grid size    (x,y,z): (65535, 65535, 65535)
  Maximum memory pitch:                          2147483647 bytes
  Texture alignment:                             512 bytes
  Concurrent copy and kernel execution:          Yes with 1 copy engine(s)
  Run time limit on kernels:                     Yes
  Integrated GPU sharing Host Memory:            No
  Support host page-locked memory mapping:       Yes
  Alignment requirement for Surfaces:            Yes
  Device has ECC support:                        Disabled
  Device supports Unified Addressing (UVA):      Yes
  Device supports Compute Preemption:            No
  Supports Cooperative Kernel Launch:            No
  Supports MultiDevice Co-op Kernel Launch:      No
  Device PCI Domain ID / Bus ID / location ID:   0 / 1 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 9.1, CUDA Runtime Version = 9.0, NumDevs = 1
Result = PASS



$ pgaccelinfo

CUDA Driver Version:           9010
NVRM version:                  NVIDIA UNIX x86_64 Kernel Module  390.116  Sun Jan 27 07:21:36 PST 2019

Hi amarinph,

Which PGI version are you using?

Since NVIDIA dropped support for Fermi based cards (CC2.x), including Quadro 2000, last year, PGI also dropped support. Hence more recent PGI versions (18.5 or later) only support CC3.0 devices or later.

See: https://www.pgroup.com/resources/docs/18.10/x86/pgi-release-notes/index.htm#compute-cap

You’ll need to use an earlier version of the PGI compiler (such as 18.4) and compile with “-ta=tesla:cc20” or “-Mcuda=cc20”. Note access to archived PGI releases does require a Professional Edition license and not available to Community Edition users. I don’t see a Professional Edition license attached to your account, but maybe your university has one and get you access to PGI 18.4?

-Mat

Hi Mat,

Ah, I’m using PGI version 18.10. That’s probably why.

Looks like a preferable option may be to get a newer GPU, then. Thanks.

Amarin