gtx 470 showing 112 cores

Accelerated Computing CUDA CUDA Programming and Performance
1

Hi

I just got a GTX 470 for my own development and cuda-3.0 shows 112 cores as following:

[codebox]Device 0: “GeForce GTX 470”

CUDA Driver Version: 3.0

CUDA Runtime Version: 3.0

CUDA Capability Major revision number: 2

CUDA Capability Minor revision number: 0

Total amount of global memory: 1341325312 bytes

Number of multiprocessors: 14

Number of cores: 112

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 block: 1024

Maximum sizes of each dimension of a block: 1024 x 1024 x 64

Maximum sizes of each dimension of a grid: 65535 x 65535 x 1

Maximum memory pitch: 2147483647 bytes

Texture alignment: 512 bytes

Clock rate: 1.22 GHz

Concurrent copy and execution: Yes

Run time limit on kernels: Yes

Integrated: No

Support host page-locked memory mapping:       Yes

Compute mode: Default (multiple host threads can use this device simultaneously)

[/codebox]

I’m not really sure what this means? does it mean only 112 cores is being used? or this hardware is configured to run with 112 cores or I need to install the 3.1 driver?

Thanks

2

deviceQuery assumes 8 cores per MP: an invalid assumption for compute 2.0 devices.

3

deviceQuery assumes 8 cores per MP: an invalid assumption for compute 2.0 devices.

4

Interesting… But wont deviceQuery get the info from “cudaGetDeviceProperties” – which should be returned by the driver, as such… No?

5

Interesting… But wont deviceQuery get the info from “cudaGetDeviceProperties” – which should be returned by the driver, as such… No?

6

The device properties structure only returns the number of multiprocessors, not the number of CUDA cores. You have to check the compute capability value and multiply by 8 or 32 depending on it. The newer version of deviceQuery for CUDA >3.0 does this properly, but the older version does not.

7

The device properties structure only returns the number of multiprocessors, not the number of CUDA cores. You have to check the compute capability value and multiply by 8 or 32 depending on it. The newer version of deviceQuery for CUDA >3.0 does this properly, but the older version does not.

8

installed 3.1 driver and toolkit and sdk, now showing 448 cores.

thanks all.

9

installed 3.1 driver and toolkit and sdk, now showing 448 cores.

thanks all.