GPU demo +makefile

makefile

INCLUDE=-I/usr/local/cuda-9.2/include
LIB= -lcudadevrt  # -lcudart -lcublas
CUDA_FLAG=-rdc=true  -gencode=arch=compute_35,code=\"sm_35,compute_35\"

#all:TestGpu
NPV.a:link.o cashflow_3.o qss_date4c_cu.o
    ar crv $@ $^
oTestGpu:TestGPU.cu
    nvcc -o $@ $(INCLUDE) $^
cashflow_3:qss_date4c_cu.o cashflow_3.o
    nvcc -o $@ $(INCLUDE) $(CUDA_FLAG) $(LIB) $^
Testcashflow_3:qss_date4c_cu.o cashflow_3.o Testcase_CashFlow_cuda.o excel.o
    nvcc -o $@ $(INCLUDE) $(CUDA_FLAG) $(LIB) $^
link.o:cashflow_3.o qss_date4c_cu.o
    nvcc $(INCLUDE) $(CUDA_FLAG) $(LIB)  -dlink $^ -o $@
Testcase_CashFlow_cuda.o:Testcase_CashFlow_cuda.cu
    nvcc -c $@ $(INCLUDE) $(CUDA_FLAG) $(LIB) $^
excel.o:excel.cc
    g++ -c -std=c++11  $^
cashflow_3.o:cashflow_3.cu
    nvcc -c $@ $(INCLUDE) $(CUDA_FLAG) $(LIB) $^
qss_date4c_cu.o:qss_date4c_cu.cu
    nvcc -c $@ $(INCLUDE) $(CUDA_FLAG) $(LIB) $^


clean:
    rm *.o

#lspci | grep -i nvidia
#lspci -v -s 09:00.0
#nvidia-smi
#

GPUDEMO

// Helper function for using CUDA to add vectors in parallel.
cudaError_t addWithCuda(int *c, const int *a, const int *b, unsigned int size)
{
    int *dev_a = 0;
    int *dev_b = 0;
    int *dev_c = 0;
    cudaError_t cudaStatus;

    // Choose which GPU to run on, change this on a multi-GPU system.
    cudaStatus = cudaSetDevice(0);
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaSetDevice failed!  Do you have a CUDA-capable GPU installed?");
        goto Error;
    }

    // Allocate GPU buffers for three vectors (two input, one output)    .
    cudaStatus = cudaMalloc((void**)&dev_c, size * sizeof(int));
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaMalloc failed!");
        goto Error;
    }

    cudaStatus = cudaMalloc((void**)&dev_a, size * sizeof(int));
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaMalloc failed!");
        goto Error;
    }

    cudaStatus = cudaMalloc((void**)&dev_b, size * sizeof(int));
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaMalloc failed!");
        goto Error;
    }

    // Copy input vectors from host memory to GPU buffers.
    cudaStatus = cudaMemcpy(dev_a, a, size * sizeof(int), cudaMemcpyHostToDevice);
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaMemcpy failed!");
        goto Error;
    }

    cudaStatus = cudaMemcpy(dev_b, b, size * sizeof(int), cudaMemcpyHostToDevice);
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaMemcpy failed!");
        goto Error;
    }

    // Launch a kernel on the GPU with one thread for each element.
    addKernel <<<1, size >>> (dev_c, dev_a, dev_b);

    // Check for any errors launching the kernel
    cudaStatus = cudaGetLastError();
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "addKernel launch failed: %s\n", cudaGetErrorString(cudaStatus));
        goto Error;
    }

    // cudaDeviceSynchronize waits for the kernel to finish, and returns
    // any errors encountered during the launch.
    cudaStatus = cudaDeviceSynchronize();
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaDeviceSynchronize returned error code %d after launching addKernel!\n", cudaStatus);
        goto Error;
    }

    // Copy output vector from GPU buffer to host memory.
    cudaStatus = cudaMemcpy(c, dev_c, size * sizeof(int), cudaMemcpyDeviceToHost);
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaMemcpy failed!");
        goto Error;
    }

Error:
    cudaFree(dev_c);
    cudaFree(dev_a);
    cudaFree(dev_b);

    return cudaStatus;
}