bandwidthTest crashes bandwidthTest crashes when run

Accelerated Computing CUDA CUDA Programming and Performance
1

Hi,

I recently configured a fedora 10 linux gpu system for research into gpu computing. The system has a NVIDIA Tesla C1060 and GeForce 9500 GT processor. I ran the tests suggested in the CUDA computing guide to see if things were configured right. I found a couple of strange things.

  1. deviceQuery returned no GPUs
  2. deviceQuryDrv returned 2 GPUS.

However when I run bandwidth test it crashes as follows;

[kadambi@janaka release]$ ./bandwidthTest
Running on…
device 0:��~Z�
Quick Mode
Host to Device Bandwidth for Pageable memory
Segmentation fault

device Query OUTPUTS:

[kadambi@janaka release]$ ./deviceQuery
CUDA Device Query (Runtime API) version (CUDART static linking)
There is no device supporting CUDA

Test PASSED

Press ENTER to exit…

[kadambi@janaka release]$ ./deviceQueryDrv
CUDA Device Query (Driver API) statically linked version
There are 2 devices supporting CUDA

Device 0: “Tesla C1060”
CUDA Driver Version: 2.20
CUDA Capability Major revision number: 1
CUDA Capability Minor revision number: 3
Total amount of global memory: 4294705152 bytes
Number of multiprocessors: 30
Number of cores: 240
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 16384 bytes
Total number of registers available per block: 16384
Warp size: 32
Maximum number of threads per block: 512
Maximum sizes of each dimension of a block: 512 x 512 x 64
Maximum sizes of each dimension of a grid: 65535 x 65535 x 1
Maximum memory pitch: 262144 bytes
Texture alignment: 256 bytes
Clock rate: 1.30 GHz
Concurrent copy and execution: Yes
Run time limit on kernels: No
Integrated: No
Support host page-locked memory mapping: Yes
Compute mode: Default (multiple host threads can use this device simultaneously)

Device 1: “GeForce 9500 GT”
CUDA Driver Version: 2.20
CUDA Capability Major revision number: 1
CUDA Capability Minor revision number: 3
Total amount of global memory: 536150016 bytes
Number of multiprocessors: 4
Number of cores: 32
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 16384 bytes
Total number of registers available per block: 8192
Warp size: 32
Maximum number of threads per block: 512
Maximum sizes of each dimension of a block: 512 x 512 x 64
Maximum sizes of each dimension of a grid: 65535 x 65535 x 1
Maximum memory pitch: 262144 bytes
Texture alignment: 256 bytes
Clock rate: 1.40 GHz
Concurrent copy and execution: Yes
Run time limit on kernels: Yes
Integrated: No
Support host page-locked memory mapping: No
Compute mode: Default (multiple host threads can use this device simultaneously)

Test PASSED

Press ENTER to exit…

Any help is much appreciated.

R

2

R,

My environment is similar to yours and bandwidth test also crashed. Friday I installed 64-bit Fedora 10 on a machine with a GTX 275 and the AMD 8200 mGPU. Today (from home) I installed Cuda 2.2. After building the SDK applications, the first one I ran was bandwidthTest - and it locked up the machine. I can ping it but I can’t ssh in to see what happened.

Edit: Installed Cuda 2.2.1 on another machine with the same hardware and OS (part of a new GPU cluster), ran simpleMultiGPU and locked up this machine harder than the first one. It doesn’t even respond to ping.

3

Hi,
I am facing similar issues on an ASUS machine which runs ubuntu 9.04 with 2 GPU cards:

  1. GTX 280
  2. Quadro 5800

I am using CUDA 2.3
Were you able to troubleshoot it?

kpg

4

Hi,

I eventually figured out the issue to be with the CUDA api version. The device query should work cleanly and should print out the device features correctly. I got stuff working with cuda 2.3. I am using a tesla and GEForce 9500 GT card. It seems to work fine and am able to program it as well.

regards,

Ramesh

5

I also found out that it did not work with the version of fedora I had and had to down grade to a lower version.