|
|
| Line 36: |
Line 36: |
| === Coding example === | | === Coding example === |
| The following is a CUDA programming example using UM [https://devblogs.nvidia.com/unified-memory-cuda-beginners/] | | The following is a CUDA programming example using UM [https://devblogs.nvidia.com/unified-memory-cuda-beginners/] |
| <syntaxhighlight lang="python">
| | {{NVIDIA CUDA Memory Management-Template2}} |
| #include <iostream>
| |
| #include <math.h>
| |
|
| |
| // CUDA kernel to add elements of two arrays
| |
| __global__
| |
| void add(int n, float *x, float *y)
| |
| { | |
| int index = blockIdx.x * blockDim.x + threadIdx.x;
| |
| int stride = blockDim.x * gridDim.x;
| |
| for (int i = index; i < n; i += stride)
| |
| y[i] = x[i] + y[i];
| |
| }
| |
|
| |
| int main(void)
| |
| { | |
| int N = 1<<20;
| |
| float *x, *y;
| |
|
| |
| // Allocate Unified Memory -- pointers accessible from CPU or GPU
| |
| cudaMallocManaged(&x, N*sizeof(float));
| |
| cudaMallocManaged(&y, N*sizeof(float));
| |
|
| |
| // initialize x and y arrays on the host (CPU)
| |
| for (int i = 0; i < N; i++) {
| |
| x[i] = 1.0f;
| |
| y[i] = 2.0f;
| |
| }
| |
|
| |
| // Launch kernel on 1M elements on the GPU
| |
| int blockSize = 256;
| |
| int numBlocks = (N + blockSize - 1) / blockSize;
| |
| add<<<numBlocks, blockSize>>>(N, x, y);
| |
|
| |
| // Wait for GPU to finish before accessing on host**
| |
| cudaDeviceSynchronize();
| |
|
| |
| // Check for errors (all values should be 3.0f)
| |
| float maxError = 0.0f;
| |
| for (int i = 0; i < N; i++)
| |
| maxError = fmax(maxError, fabs(y[i]-3.0f));
| |
| std::cout << "Max error: " << maxError << std::endl;
| |
|
| |
| // Free memory
| |
| cudaFree(x);
| |
| cudaFree(y);
| |
|
| |
| return 0;
| |
| } | |
| </syntaxhighlight>
| |
|
| |
|
| ==NVIDIA Jetson TX2== | | ==NVIDIA Jetson TX2== |
