（Cuda）存储器Memory（二）

本文地址:http://blog.csdn.net/mounty_fsc/article/details/51092925

本部分内容为[1]CUDA_C_Programming_Guide中笔记

1 Device Memory

• 这是对后边的shared memory, global memory等的总称
• 可分为linear memory和 CUDA arrays
• CUDA arrays为纹理获取做了优化，见纹理存储器

对于线性存储器，一般用以下函数处理：

函数	描述
cudaMalloc()
cudaMemcpy()
cudaMallocPitch()	2D,返回的pitch需要在访问时使用
cudaMemcpy2D()	2D
cudaMalloc3D()	3D
cudaMemcpy3D()	3D
cudaFree()

cudaMallocPitch例子

// Host code
int width = 64, height = 64;
float* devPtr;
size_t pitch;
cudaMallocPitch(&devPtr, &pitch,
width * sizeof(float), height);
MyKernel<<<100, 512>>>(devPtr, pitch, width, height);

// Device code
__global__ void MyKernel(float* devPtr,
size_t pitch, int width, int height)
{
    for (int r = 0; r < height; ++r) {
        float* row = (float*)((char*)devPtr + r * pitch);
        for (int c = 0; c < width; ++c) {
            float element = row[c];
        }
    }
}

2 shared Memory

2.1 不使用共享内存

1. 对于C中每个元素，使用一个线程去计算。
2. 共访问全局存储器次数：对矩阵A中的每个元素，共B.width次，对矩阵B中的元素，共访问了A.height次

2.2 使用共享内存

1. 本质上还是，使用一个线程去计算C中的一个元素。只是角度不一样了，一个block计算一个Csub，一个block中的线程计算一个Csub中的元素。
2. 策略是，对于同一个block中的线程，只读取一次全局存储器。
3. 共访问全局存储器次数：对矩阵A中的每个元素，共(B.width/block_size)次，对矩阵B中的元素，共访问了(A.height/block_size)次
4. 共享存储器示例代码见最后一部分

3 Page-Locked Host Memory

• 分页锁定主机存储器（也叫pinned），区别为malloc()分配的可分页的主机存储器（可分页为操作系统策略，将导致内存中只保存部分数据）
• 分页锁定主机存储器资源有限，比可分页的要容易分配失败。

• 相关函数：

  函数	说明
  cudaHostAlloc()
  cudaFreeHost()
  cudaHostRegister()	分页锁定一段malloc()分配的内存

• 类别

  中文	英文	说明	符号
  可分享存储器	Portable Memory		cudaHostAllocPortable, cudaHostRegisterPortable
  写结合存储器	Write-Combining Memory
  映射存储器	Mapped Memory

4 Texture Memory

5 Surface Memory

相关代码

1. 共享存储器示例代码：

// Matrices are stored in row-major order:
// M(row, col) = *(M.elements + row * M.stride + col)
typedef struct {
    int width;
    int height;
    int stride; 
    float* elements;
} Matrix;

// Get a matrix element
__device__ float GetElement(const Matrix A, int row, int col)
{
    return A.elements[row * A.stride + col];
}

// Set a matrix element
__device__ void SetElement(Matrix A, int row, int col,
                           float value)
{
    A.elements[row * A.stride + col] = value;
}

// Get the BLOCK_SIZExBLOCK_SIZE sub-matrix Asub of A that is
// located col sub-matrices to the right and row sub-matrices down
// from the upper-left corner of A
 __device__ Matrix GetSubMatrix(Matrix A, int row, int col) 
{
    Matrix Asub;
    Asub.width    = BLOCK_SIZE;
    Asub.height   = BLOCK_SIZE;
    Asub.stride   = A.stride;
    Asub.elements = &A.elements[A.stride * BLOCK_SIZE * row
                                         + BLOCK_SIZE * col];
    return Asub;
}

// Thread block size
#define BLOCK_SIZE 16

// Forward declaration of the matrix multiplication kernel
__global__ void MatMulKernel(const Matrix, const Matrix, Matrix);

// Matrix multiplication - Host code
// Matrix dimensions are assumed to be multiples of BLOCK_SIZE
void MatMul(const Matrix A, const Matrix B, Matrix C)
{
    // Load A and B to device memory
    Matrix d_A;
    d_A.width = d_A.stride = A.width; d_A.height = A.height;
    size_t size = A.width * A.height * sizeof(float);
    cudaMalloc(&d_A.elements, size);
    cudaMemcpy(d_A.elements, A.elements, size,
               cudaMemcpyHostToDevice);
    Matrix d_B;
    d_B.width = d_B.stride = B.width; d_B.height = B.height;
    size = B.width * B.height * sizeof(float);

    cudaMalloc(&d_B.elements, size);
    cudaMemcpy(d_B.elements, B.elements, size,
    cudaMemcpyHostToDevice);

    // Allocate C in device memory
    Matrix d_C;
    d_C.width = d_C.stride = C.width; d_C.height = C.height;
    size = C.width * C.height * sizeof(float);
    cudaMalloc(&d_C.elements, size);

    // Invoke kernel
    dim3 dimBlock(BLOCK_SIZE, BLOCK_SIZE);
    // 这里因为cuda中为列优先，事实上对C作了个转置
    dim3 dimGrid(B.width / dimBlock.x, A.height / dimBlock.y);
    MatMulKernel<<<dimGrid, dimBlock>>>(d_A, d_B, d_C);

    // Read C from device memory
    cudaMemcpy(C.elements, d_C.elements, size,
               cudaMemcpyDeviceToHost);

    // Free device memory
    cudaFree(d_A.elements);
    cudaFree(d_B.elements);
    cudaFree(d_C.elements);
}

// Matrix multiplication kernel called by MatMul()
 __global__ void MatMulKernel(Matrix A, Matrix B, Matrix C)
{
    // Block row and column
    // 可以理解为在物理上是列优先，从逻辑上又转成行优先
    int blockRow = blockIdx.y;
    int blockCol = blockIdx.x;

    // Each thread block computes one sub-matrix Csub of C
    Matrix Csub = GetSubMatrix(C, blockRow, blockCol);

    // Each thread computes one element of Csub
    // by accumulating results into Cvalue
    float Cvalue = 0;

    // Thread row and column within Csub
    int row = threadIdx.y;
    int col = threadIdx.x;

    // Loop over all the sub-matrices of A and B that are
    // required to compute Csub
    // Multiply each pair of sub-matrices together
    // and accumulate the results
    for (int m = 0; m < (A.width / BLOCK_SIZE); ++m) {

        // Get sub-matrix Asub of A
        Matrix Asub = GetSubMatrix(A, blockRow, m);

        // Get sub-matrix Bsub of B
        Matrix Bsub = GetSubMatrix(B, m, blockCol);

        // Shared memory used to store Asub and Bsub respectively
        __shared__ float As[BLOCK_SIZE][BLOCK_SIZE];
        __shared__ float Bs[BLOCK_SIZE][BLOCK_SIZE];

        // Load Asub and Bsub from device memory to shared memory
        // Each thread loads one element of each sub-matrix
        As[row][col] = GetElement(Asub, row, col);
        Bs[row][col] = GetElement(Bsub, row, col);

        // Synchronize to make sure the sub-matrices are loaded
        // before starting the computation
        __syncthreads();

        // Multiply Asub and Bsub together
        for (int e = 0; e < BLOCK_SIZE; ++e)
            Cvalue += As[row][e] * Bs[e][col];

        // Synchronize to make sure that the preceding
        // computation is done before loading two new
        // sub-matrices of A and B in the next iteration
        __syncthreads();
    }

    // Write Csub to device memory
    // Each thread writes one element
    SetElement(Csub, row, col, Cvalue);
}

[1]. CUDA_C_Programming_Guide