How do I use multiple inputs in mexcuda?

3 views (last 30 days)
jsbbs hsyhs
jsbbs hsyhs on 23 Apr 2024
Commented: jsbbs hsyhs on 24 Apr 2024
I found a mexGPUExample.cu and compiled it successfully. In this file, there is only one input and one output. But I'd like to verify multiple inputs and single outputs. Changed codes are as below:
/*
* Example of how to use the mxGPUArray API in a MEX file. This example shows
* how to write a MEX function that takes a gpuArray input and returns a
* gpuArray output, e.g. B=mexFunction(A).
*
* Copyright 2012 The MathWorks, Inc.
*/
#include "mex.h"
#include "gpu/mxGPUArray.h"
#include "matrix.h"
/*
* Device code
*/
void __global__ TimesTwo(double const * const A, double const* const C, double * const B, int const N)
{
/* Calculate the global linear index, assuming a 1-d grid. */
int const i = blockDim.x * blockIdx.x + threadIdx.x;
if (i < N) {
B[i] = 2.0 * A[i];
B[i+N] = 2.0 * C[i];
}
}
/*
* Host code
*/
void mexFunction(int nlhs, mxArray *plhs[],
int nrhs, mxArray const *prhs[])
{
/* Declare all variables.*/
mxGPUArray const *A, *C;
mxGPUArray *B;
double const *d_A, *d_C;
double *d_B;
int N;
char const * const errId = "parallel:gpu:mexGPUExample:InvalidInput";
char const * const errMsg = "Invalid input to MEX file.";
/* Choose a reasonably sized number of threads for the block. */
int const threadsPerBlock = 256;
int blocksPerGrid;
/* Initialize the MathWorks GPU API. */
mxInitGPU();
/* Throw an error if the input is not a GPU array. */
if ((nrhs!=1) || !(mxIsGPUArray(prhs[0]))) {
mexErrMsgIdAndTxt(errId, errMsg);
}
A = mxGPUCreateFromMxArray(prhs[0]);
C = mxGPUCreateFromMxArray(prhs[1]);
/*
* Verify that A really is a double array before extracting the pointer.
*/
if (mxGPUGetClassID(A) != mxDOUBLE_CLASS) {
mexErrMsgIdAndTxt(errId, errMsg);
}
/*
* Now that we have verified the data type, extract a pointer to the input
* data on the device.
*/
d_A = (double const *)(mxGPUGetDataReadOnly(A));
d_C = (double const *)(mxGPUGetDataReadOnly(C));
/* Create a GPUArray to hold the result and get its underlying pointer. */
mwSize ndim = 2, dims[2] = {2,4};
B = mxGPUCreateGPUArray(ndim,
dims,
mxGPUGetClassID(A),
mxGPUGetComplexity(A),
MX_GPU_DO_NOT_INITIALIZE);
d_B = (double *)(mxGPUGetData(B));
/*
* Call the kernel using the CUDA runtime API. We are using a 1-d grid here,
* and it would be possible for the number of elements to be too large for
* the grid. For this example we are not guarding against this possibility.
*/
N = (int)(mxGPUGetNumberOfElements(A));
blocksPerGrid = (N + threadsPerBlock - 1) / threadsPerBlock;
TimesTwo<<<blocksPerGrid, threadsPerBlock>>>(d_A, d_C, d_B, N);
/* Wrap the result up as a MATLAB gpuArray for return. */
plhs[0] = mxGPUCreateMxArrayOnGPU(B);
/*
* The mxGPUArray pointers are host-side structures that refer to device
* data. These must be destroyed before leaving the MEX function.
*/
mxGPUDestroyGPUArray(A);
mxGPUDestroyGPUArray(B);
mxGPUDestroyGPUArray(C);
}
There is all changed codes.
And then I'll type in matlab mexcuda xxx.cu, the matlab tell me compiled successfully. Then I provide two matrix and tansfer them to GPU. Finally, the question is typing xxx(data_gpu1,data_gpu2) will report an error: Invalid input to MEX file. I would like to know how to make xxx.cu recognize multiple inputs.

Answers (1)

Joss Knight
Joss Knight on 23 Apr 2024
You have passed in two inputs but you have a check if (nrhs!=1), so you are erroring because you don't have one input. You need to change that bit.

Products


Release

R2021a

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!