Tesla C870 spec Cards identified as being cuda1.0

Hi,

We have some Tesla C870 cards within our department that I would like to use for applications involving streaming. However, when I query them I get the output attached below. This appears to show that these cards are only able to use Cuda 1.0, and so cannot take advantage of streams. Is this correct? For the record, we are using on of the 1u units, attached to an HP server running Red Hat enterprise 5.2.

Any thoughts/clarification would be appreciated.

Daniel

./deviceQuery 

There are 2 devices supporting CUDA

Device 0: "Tesla C870"

  Major revision number:						 1

  Minor revision number:						 0

  Total amount of global memory:				 1610350592 bytes

  Number of multiprocessors:					 16

  Number of cores:							   128

  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:									1.35 GHz

  Concurrent copy and execution:				 Yes

Device 1: "Tesla C870"

  Major revision number:						 1

  Minor revision number:						 0

  Total amount of global memory:				 1610350592 bytes

  Number of multiprocessors:					 16

  Number of cores:							   128

  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:									1.35 GHz

  Concurrent copy and execution:				 Yes

Test PASSED

Press ENTER to exit...

I’m pretty sure that refers to the compute capability of the device. I believe the Tesla C870 is built on the G80 core, so that would make sense. The compute capability is different than the version of CUDA you are running. The C870 will work with CUDA 2.0.

This refers to the Compute Capability your device supports, not the CUDA version. Your Card should be able to use Streams if you use CUDA 2.0

As has already been mentioned twice, streams will work on the C870. I will add, however, that kernels will not execute overlaping with asynchronous memory copies on G80. The “concurrent copy and execution: yes” in your output above is coming from a CUDA bug.