deviceQuery returns wrong information

Accelerated Computing CUDA CUDA Programming and Performance
1

Hi,

I just started learning about CUDA programming. I bought a “GeForce GT 730 2G 64bit” for testing my codes.

The specification says that this GPU should have 384 cuda cores, but deviceQuery just report 48 number of cudaCores!

Is there something I’m missing?

Here is the output of deviceQuery:

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

Detected 1 CUDA Capable device(s)

Device 0: “GeForce GT 730”
CUDA Driver Version / Runtime Version 8.0 / 8.0
CUDA Capability Major/Minor version number: 2.1
Total amount of global memory: 2048 MBytes (2147483648 bytes)
( 1) Multiprocessors, ( 48) CUDA Cores/MP: 48 CUDA Cores
GPU Max Clock rate: 1620 MHz (1.62 GHz)
Memory Clock rate: 500 Mhz
Memory Bus Width: 64-bit
L2 Cache Size: 65536 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
CUDA Device Driver Mode (TCC or WDDM): WDDM (Windows Display Driver Model)
Device supports Unified Addressing (UVA): Yes
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 = 8.0, CUDA Runtime Version = 8.0, NumDevs = 1, Device0 = GeForce GT 730
Result = PASS

2

What specification did you consult? According to NVIDIA’s spec sheet, there are (at minimum) three different versions of the GT 730, however from a cursory comparison, none of these seems to match exactly the parameters in the DeviceQuery report shown above:

[url]http://www.geforce.com/hardware/desktop-gpus/geforce-gt-730/specifications[/url]

However, the technical specifications returned by DeviceQuery do seem to more closely match with the published specifications of the GT 705 OEM card (except for the name, and the amount of memory):

[url]http://www.geforce.com/hardware/desktop-gpus/geforce-gt-705-oem/specifications[/url]

No idea what’s going on here. Is this a new (not 2nd-hand) GPU acquired from a reputable source?

3

Thanks for your response.

It is new but the source is not reputable. The brand is named “Esonic” which is not mentioned in nvidia’s AIB list:

[url]http://www.nvidia.com/object/pf_boardpartners.html[/url]

Thank you for mentioning GT 705 OEM. I checked it and found that I also can’t allocate more than 1GB memory. The driver crashes in doing so (in contrast to allocating more than 2GB which just throws an exception).

It seems that they used a GT 705 OEM and shamelessly tampered the config to match the things mentioned on the box (i.e. the model and the amount of memory).