Error while compiling jCUDA sample from SDK in eclipse 'Input file not found: JCudaVectorAddKernel.cu'

Question

I am new to jCUDA and java as well. I am trying to compile a vector addition program from NVIDIA samples using eclipse on Redhat Linux.

Steps I followed: 1. Enter: nvcc -ptx JCudaVectorAddKernel.cu -> It generates JCudaVectorAddKernel.ptx file 2. Execute following program: JCudaVectorAdd.java:

package JCudaVectorAdd;

import static jcuda.driver.JCudaDriver.*;

import java.io.*;

import jcuda.*;
import jcuda.driver.*;


public class JCudaVectorAdd 
{

    public static void main(String[] args) throws IOException
    {
        // Enable exceptions and omit all subsequent error checks
        JCudaDriver.setExceptionsEnabled(true);

        // Create the PTX file by calling the NVCC
        String ptxFileName = preparePtxFile("JCudaVectorAddKernel.cu");

        // Initialize the driver and create a context for the first device.
        cuInit(0);
        CUdevice device = new CUdevice();
        cuDeviceGet(device, 0);
        CUcontext context = new CUcontext();
        cuCtxCreate(context, 0, device);


     // Load the ptx file.
        CUmodule module = new CUmodule();
        cuModuleLoad(module, ptxFileName);

        // Obtain a function pointer to the "add" function.
        CUfunction function = new CUfunction();
        cuModuleGetFunction(function, module, "add");

        int numElements = 100000;

        // Allocate and fill the host input data
        float hostInputA[] = new float[numElements];
        float hostInputB[] = new float[numElements];
        for(int i = 0; i < numElements; i++)
        {
            hostInputA[i] = (float)i;
            hostInputB[i] = (float)i;
        }

        // Allocate the device input data, and copy the
        // host input data to the device
        CUdeviceptr deviceInputA = new CUdeviceptr();
        cuMemAlloc(deviceInputA, numElements * Sizeof.FLOAT);
        cuMemcpyHtoD(deviceInputA, Pointer.to(hostInputA),
            numElements * Sizeof.FLOAT);
        CUdeviceptr deviceInputB = new CUdeviceptr();
        cuMemAlloc(deviceInputB, numElements * Sizeof.FLOAT);
        cuMemcpyHtoD(deviceInputB, Pointer.to(hostInputB),
            numElements * Sizeof.FLOAT);

        // Allocate device output memory
        CUdeviceptr deviceOutput = new CUdeviceptr();
        cuMemAlloc(deviceOutput, numElements * Sizeof.FLOAT);

        // Set up the kernel parameters: A pointer to an array
        // of pointers which point to the actual values.
        Pointer kernelParameters = Pointer.to(
            Pointer.to(new int[]{numElements}),
            Pointer.to(deviceInputA),
            Pointer.to(deviceInputB),
            Pointer.to(deviceOutput)
        );

        // Call the kernel function.
        int blockSizeX = 256;
        int gridSizeX = (int)Math.ceil((double)numElements / blockSizeX);
        cuLaunchKernel(function,
            gridSizeX,  1, 1,      // Grid dimension
            blockSizeX, 1, 1,      // Block dimension
            0, null,               // Shared memory size and stream
            kernelParameters, null // Kernel- and extra parameters
        );
        cuCtxSynchronize();

        // Allocate host output memory and copy the device output
        // to the host.
        float hostOutput[] = new float[numElements];
        cuMemcpyDtoH(Pointer.to(hostOutput), deviceOutput,
            numElements * Sizeof.FLOAT);

        // Verify the result
        boolean passed = true;
        for(int i = 0; i < numElements; i++)
        {
            float expected = i+i;
            if (Math.abs(hostOutput[i] - expected) > 1e-5)
            {
                System.out.println(
                    "At index "+i+ " found "+hostOutput[i]+
                    " but expected "+expected);
                passed = false;
                break;
            }
        }
        System.out.println("Test "+(passed?"PASSED":"FAILED"));

        // Clean up.
        cuMemFree(deviceInputA);
        cuMemFree(deviceInputB);
        cuMemFree(deviceOutput);
    }

    private static String preparePtxFile(String cuFileName) throws IOException
    {
        int endIndex = cuFileName.lastIndexOf('.');
        if (endIndex == -1)
        {
            endIndex = cuFileName.length()-1;
        }
        String ptxFileName = cuFileName.substring(0, endIndex+1)+"ptx";
        File ptxFile = new File(ptxFileName);
        if (ptxFile.exists())
        {
            return ptxFileName;
        }

        File cuFile = new File(cuFileName);
        if (!cuFile.exists())
        {
            throw new IOException("Input file not found: "+cuFileName);
        }
        String modelString = "-m"+System.getProperty("sun.arch.data.model");
        String command =
            "nvcc " + modelString + " -ptx "+
            cuFile.getPath()+" -o "+ptxFileName;

        System.out.println("Executing\n"+command);
        Process process = Runtime.getRuntime().exec(command);

        String errorMessage = new String(toByteArray(process.getErrorStream()));
        String outputMessage= new String(toByteArray(process.getInputStream()));
        int exitValue = 0;
        try
        {
            exitValue = process.waitFor();
        }
        catch (InterruptedException e)
        {
            Thread.currentThread().interrupt();
            throw new IOException(
                "Interrupted while waiting for nvcc output", e);
        }

        if (exitValue != 0)
        {
            System.out.println("nvcc process exitValue "+exitValue);
            System.out.println("errorMessage:\n"+errorMessage);
            System.out.println("outputMessage:\n"+outputMessage);
            throw new IOException(
                "Could not create .ptx file: "+errorMessage);
        }

        System.out.println("Finished creating PTX file");
        return ptxFileName;
    }

    private static byte[] toByteArray(InputStream inputStream) throws IOException
    {
        ByteArrayOutputStream baos = new ByteArrayOutputStream();
        byte buffer[] = new byte[8192];
        while (true)
        {
            int read = inputStream.read(buffer);
            if (read == -1)
            {
                break;
            }
            baos.write(buffer, 0, read);
        }
        return baos.toByteArray();
    }

}

JCudaVectorAddKernel.cu:

extern "C"
__global__ void add(int n, float *a, float *b, float *sum)
{
    int i = blockIdx.x * blockDim.x + threadIdx.x;
    if (i<n)
    {
        sum[i] = a[i] + b[i];
    }

}

Both 'JCudaVectorAddKernel.cu' and 'JCudaVectorAddKernel.java' are in on the same path: /home/sandeep/workspace1/jCuda/jCudaVectorAdd/src/jCudaVectorAdd

When I execute the program in eclipse it gives me following error:

Exception in thread "main" java.io.IOException: Input file not found: JCudaVectorAddKernel.cu
at JCudaVectorAdd.JCudaVectorAdd.preparePtxFile(JCudaVectorAdd.java:128)
    at JCudaVectorAdd.JCudaVectorAdd.main(JCudaVectorAdd.java:20)

Is there anything to do related to the compile command? or ptx/.cu file path? Please guide me if I am going in the wrong direction.

Answer 1

The sample is trying to compile the PTX file at runtime, and it prints the command that it is trying to execute. When you are compiling the PTX file manually, this may actually not be necessary, and you can change

String ptxFileName = preparePtxFile("JCudaVectorAddKernel.cu");

to

String ptxFileName = "JCudaVectorAddKernel.ptx";

In any case, you may print the file names

File ptxFile = new File(ptxFileName);
System.out.println(ptxFile.getCanonicalPath());

and

File cuFile = new File(cuFileName);
System.out.println(cuFile.getCanonicalPath());

to see whether they match the expected directories. But the PTX file (and the CU file) should probably be located in

/home/sandeep/workspace1/jCuda/jCudaVectorAdd/

(that is, in the "root" directory of your project)