clGetPlatformIDs() with NV driver 196.21

Accelerated Computing CUDA CUDA Programming and Performance
1

Hello,

I have installed the 196.21 drier and the GPU computing SDK 2.3. I am trying the following but getting “Run-Time Check Failure #0 - The value of ESP was not properly saved across a function call. This is usually a result of calling a function declared with one calling convention with a function pointer declared with a different calling convention.”

Any solution ? workaround ?

cl_platform_id pPlatforms[10] = {0};
cl_uint uiPlatformsCount = 0;
cl_int err = clGetPlatformIDs(10, pPlatforms, &uiPlatformsCount);
…

–Yariv

2

SDK 2.3 is not compatible with drivers newer than 195, get SDK 3.0

3

I installed the CUDA SDK 3.0 beta toolkit but did not find any OpenCL code in its folders… are you saying that cuda sdk 3.0 installs a new lib which binds correctly to the OpenCL dlls in 196.21 ?

or I am totaly confused and you are talking about GPU Computing sdk 3.0 which I am not aware of ?

Thanks for the continuous support. --Yariv

4

Yes you have to install the GPU Computing SDK 3.0 to get the opencl code.