共享内存：
如变量存储空间说明符中详细描述的，共享内存是使用__shared__内存空间说明符分配的。
共享内存预计比全局内存快得多，如线程层次结构中所提及，并在共享内存中详述。 因此，任何通过共享内存访问来取代全局内存访问的机会应该被利用，如下面的矩阵乘法例子所示。
下面的代码示例是没有利用共享内存的矩阵乘法的直接实现。 每个线程读取A的一行和B的一列，并计算C的相应元素。
// Matrices are stored in row-major order:
// M(row, col) = *(M.elements + row * M.width + col)
typedef struct {
int width;
int height;
float* elements;
} Matrix;
// 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 = 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 = 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 = 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);
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, Cd.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)
{
// Each thread computes one element of C
// by accumulating results into Cvalue
float Cvalue = 0;
int row = blockIdx.y * blockDim.y + threadIdx.y;
int col = blockIdx.x * blockDim.x + threadIdx.x;
for (int e = 0; e < A.width; ++e)
Cvalue += A.elements[row * A.width + e]
* B.elements[e * B.width + col];
C.elements[row * C.width + col] = Cvalue;
}
有点像caffe的卷积
下面的代码示例是利用共享内存的矩阵乘法的实现。在这个实现中，每个线程块负责计算C的一个方形子矩阵Csub，并且该块内的每个线程负责计算Csub的一个元素。如图10所示，Csub等于两个矩形矩阵的乘积：具有与Csub相同行索引的维度（A.width，block_size）的A的子矩阵和维度B的子矩阵（block_size，A.width）与Csub具有相同的列索引。为了适应设备的资源，这两个矩形矩阵根据需要被划分为尺寸为block_size的许多平方矩阵，并且Csub被计算为这些平方矩阵的乘积之和。这些产品中的每一个都是通过首先将两个对应的方形矩阵从全局存储器加载到共享存储器来执行的，其中一个线程加载每个矩阵的一个元素，然后通过使每个线程计算产品的一个元素。每个线程将每个这些产品的结果累加到一个寄存器中，并且一旦完成就将结果写入全局内存。通过这种方式阻塞计算，我们利用快速共享内存，节省了很多全局内存带宽，因为A只读（B.width / block_size）时间，B被读取（A.height / block_size）次
// 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);
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
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);
}
