MATLAB: CUDA toolkit version | using constant memory

cudaParallel Computing Toolbox

I've installed CUDA toolkit 4.1 instead of 4.0. And now matlab reports some errors depending on kernel that Im trying to create:

Error using handleKernelArgs (line 48)
The first input to parallel.gpu.CUDAKernel must be a file that contains PTX code or a string that is PTX code.
Error using handleKernelArgs (line 61)
No entries were found in the PTX file

NVIDIA is using new compiler in 4.1, and it seems to me that pct does not support it. Am I right? It is unclear for user which version of toolkit should he use. Maybe I missed something, but I could not find toolkit version requirements.

The second question is about using constant memory. Help says that user should define constant variables in CU file

__constant__ int N;
__constant__ double CONST_DATA[256];

Placing such definition in kernel does not work:

error: a "__constant__" variable declaration is not allowed inside a function body

Best Answer

Hi, I will tackle the second question first as I am pretty certain of the problem. _constants_ must be defined at the global scope, i.e. not inside functions, classes etc. So, for example,

__constant__ double CONST_DATA[256];
__global__ void myKernel(double * out, double * in) {
   // Some code
}

is fine, whilst

__global__ void myKernel(double * out, double * in) {
   __constant__ double CONST_DATA[256];
   // Some code
}

is not. If you already have your constants at global scope then there must be something else amiss. In that case, perhaps you could post some short CU code that shows the problem?

Regarding your first question, I'm afraid I don't have a definite answer. I've just tried compiling a simple kernel to PTX using NVCC from CUDA 4.1 with MATLAB R2012a and it worked fine. However this may depend on the compile options specified. Perhaps you could provide some details about which MATLAB release you are using, what compile command you used, and maybe even a short snippet of code that will help me to understand the problem?

Thanks.

Ben

Related Solutions

MATLAB: GPU CUDA kernel malloc error

You can get that error message if you have a mismatch between the CUDA runtime in use by Parallel Computing Toolbox and the version of nvcc that you're using. If you're using R2010b, you need to use CUDA-3.1; for R2011a, you can use CUDA-3.2. I was able to compile and use the following trivial kernel:

    // simple.cu
    __global__ void fcn( double * out ) {
        int * x = (int *) malloc( 1024 );
        out[0] = x[0];
        free( x );
    }

By compiling like so:

$ /usr/local/cuda32/cuda/bin/nvcc -arch compute_20 -ptx simple.cu

and then using within MATLAB R2011a like so:

>> k = parallel.gpu.CUDAKernel( 'simple.ptx' );
>> gather(k.feval(0))
ans =
       1.768515945000000e+09

MATLAB: How to fix error : unrecognized token in Cuda code with nvcc compiler

There are two problems with what you have attempted, one just a typo and the solution to the other will depend on what you are trying to do. First the typo: you are missing an underscore from each side of the global decorator - they should be double underscores:

__global__ void add1(double * pi, double c) 
{ 
  *pi += c; 
}

Now the more important question: what are you trying to achieve? If you are trying to create a PTX file for use with parallel.gpu.CUDAKernel then you need to compile to PTX:

$ nvcc -ptx -arch=sm_20 <filename>.cu

which will procude <filename>.ptx. If you are trying to make a standalone executable then you need to also define a main function as you would for any C++ program.

Best Answer

Related Solutions

MATLAB: GPU CUDA kernel malloc error

MATLAB: How to fix error : unrecognized token in Cuda code with nvcc compiler

Related Question