Is anybody using CUDA on laptops with fermi GPUs with Optimus Technology?

Accelerated Computing CUDA CUDA Programming and Performance
1

Hi there,

I want to buy a laptop for coding and debugging CUDA software to be launched on a desktop with GT470.

I have seen many posts on this forums saying that there are no drivers for FERMI mobile GPUs with Optimus technology under LINUX. Is that true?
If so, what about Windows 7 using Visual Studio 2010?

Is anybody actually using FERMI enabled laptops for CUDA computing?

Thx!
den3b

2

Hi there,

I want to buy a laptop for coding and debugging CUDA software to be launched on a desktop with GT470.

I have seen many posts on this forums saying that there are no drivers for FERMI mobile GPUs with Optimus technology under LINUX. Is that true?
If so, what about Windows 7 using Visual Studio 2010?

Is anybody actually using FERMI enabled laptops for CUDA computing?

Thx!
den3b

3

Hi,

Using Fermi based laptops shouldn’t be a problem on windows 7 and Visual studio. I read people had some issues with VS2010 but later hade them resolved.

Not to hijack your thread but if can add a question to yours, is it possible to do nexus debugging on a laptop with both integrated graphics and a discrete GF1xx/GT200 GPU ? Debug the discrete NV GPU while the IGP handles the screen output. Does this in any way depend on optimus?

Thanks,

Jimmy

4

Hi,

Using Fermi based laptops shouldn’t be a problem on windows 7 and Visual studio. I read people had some issues with VS2010 but later hade them resolved.

Not to hijack your thread but if can add a question to yours, is it possible to do nexus debugging on a laptop with both integrated graphics and a discrete GF1xx/GT200 GPU ? Debug the discrete NV GPU while the IGP handles the screen output. Does this in any way depend on optimus?

Thanks,

Jimmy

5

I got NSight to work just fine on an ASUS 1215N (Ion 2). Some pointers are available in this thread The Official NVIDIA Forums | NVIDIA

6

I got NSight to work just fine on an ASUS 1215N (Ion 2). Some pointers are available in this thread The Official NVIDIA Forums | NVIDIA

7

Thanks rjl that’s really good to know. I haven’t attempted this on my laptop yet but now I will give it a try :)

One thing that didn’t become clarified was wheter or not optimus is a requirement for this to work?

8

Thanks rjl that’s really good to know. I haven’t attempted this on my laptop yet but now I will give it a try :)

One thing that didn’t become clarified was wheter or not optimus is a requirement for this to work?

9

I am not smart enough to answer whether or not Optimus is required. I can only tell you that when I look at my 1215N, there are three stickers. Intel Atom. Nvidia Ion. Nvidia Optimus. So this combination works. (Note that it is equal to a GT218, which is compute capability 1.2). It definitely has limited capability (deviceQuery output below) but it is easy to work on code snippets or learning new functionality.

devicequery Starting…

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

There is 1 device supporting CUDA

Device 0: “ION”

CUDA Driver Version: 3.20

CUDA Runtime Version: 3.20

CUDA Capability Major/Minor version number: 1.2

Total amount of global memory: 431620096 bytes

Multiprocessors x Cores/MP = Cores: 2 (MP) x 8 (Cores/MP) = 16 (Cores)

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: 2147483647 bytes

Texture alignment: 256 bytes

Clock rate: 1.09 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)

Concurrent kernel execution: No

Device has ECC support enabled: No

Device is using TCC driver mode: No

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 3.20, CUDA Runtime Version = 3.20, NumDevs = 1, Device = ION

PASSED

Press to Quit…

10

I am not smart enough to answer whether or not Optimus is required. I can only tell you that when I look at my 1215N, there are three stickers. Intel Atom. Nvidia Ion. Nvidia Optimus. So this combination works. (Note that it is equal to a GT218, which is compute capability 1.2). It definitely has limited capability (deviceQuery output below) but it is easy to work on code snippets or learning new functionality.

devicequery Starting…

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

There is 1 device supporting CUDA

Device 0: “ION”

CUDA Driver Version: 3.20

CUDA Runtime Version: 3.20

CUDA Capability Major/Minor version number: 1.2

Total amount of global memory: 431620096 bytes

Multiprocessors x Cores/MP = Cores: 2 (MP) x 8 (Cores/MP) = 16 (Cores)

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: 2147483647 bytes

Texture alignment: 256 bytes

Clock rate: 1.09 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)

Concurrent kernel execution: No

Device has ECC support enabled: No

Device is using TCC driver mode: No

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 3.20, CUDA Runtime Version = 3.20, NumDevs = 1, Device = ION

PASSED

Press to Quit…

11

someone have succeed to run Cuda on asus 1215N under linux?
I don’t find any driver where the ION2 card work (for cuda)… External Image

12

someone have succeed to run Cuda on asus 1215N under linux?
I don’t find any driver where the ION2 card work (for cuda)… External Image

13

No. I was responding to the Windows 7 / VS2010 portion of the question. Sorry for the confusion.

14

No. I was responding to the Windows 7 / VS2010 portion of the question. Sorry for the confusion.

15

Here is a comment made by someone from Nvidia:

http://www.nvnews.net/vbulletin/showthread.php?p=2183477#post2183477

As far as I know, nothing has changed in that respect.

16

Here is a comment made by someone from Nvidia:

http://www.nvnews.net/vbulletin/showthread.php?p=2183477#post2183477

As far as I know, nothing has changed in that respect.