刘超俊-cuda编程.pptx

CUDA编程介绍;GPU和CPU的比较 Cuda编程模型 核函数的定义以及调用 线程结构 线程通信（共享内存）及同步 --向量点积运算的实例;GPU与CPU的比较;为什么使用GPU;GPU编程模型;核函数的定义及调用;线程结构;线程结构;// Kernel definition global void MatAdd(float A[N][N], float B[N][N],float C[N][N]) { int i = threadIdx.x; int j = threadIdx.y; C[i ][ j ] = A[i][ j ] + B[i ][ j ]; } int main() { ... // Kernel invocation with one block of N * N * 1 threads int numBlocks = 1; dim3 threadsPerBlock(N, N); MatAddnumBlocks, threadsPerBlock(A, B, C); ... };线程结构;线程结构;// Kernel definition _global_ void MatAdd(float A[N][N], float B[N][N],float C[N][N]) { int i = blockIdx.x * blockDim.x + threadIdx.x; int j = blockIdx.y *blockDim.y + threadIdx.y; while(iNjN) { C[i ][ j ] = A[i][ j ] + B[i ][ j ]; i+=blockDim.x*gridDim.x; j+=blockDim.y*gridDim.y; } } int main() { ... // Kernel invocation dim3 threadsPerBlock(32, 32); //32*32=1024 dim3 numBlocks(256, 256); //256*256=65536 MatAddnumBlocks, threadsPerBlock(A, B, C); ... } ;共享内存及同步;点积运算程序 ;完成块内线程同步之后，需要对cache内的全部元素进行求和，此处采用归约运算。;;;;;;