template <int BLOCK_SIZE> __global__ void
matrixMulCUDA_3(float* C, float* A, float* B, int wA, int wB)
{
// Block index
int bx = blockIdx.x;
int by = blockIdx.y;
// Thread index
int tx = threadIdx.x;
int ty = threadIdx.y;
// Index of the first sub-matrix of A processed by the block
int aBegin = wA * BLOCK_SIZE * by;
// Index of the last sub-matrix of A processed by the block
int aEnd = aBegin + wA - 1;
// Step size used to iterate through the sub-matrices of A
int aStep = BLOCK_SIZE;
// Index of the first sub-matrix of B processed by the block
int bBegin = BLOCK_SIZE * bx;
// Step size used to iterate through the sub-matrices of B
int bStep = BLOCK_SIZE * wB;
// Csub is used to store the element of the block sub-matrix
// that is computed by the thread
float Csub = 0;
// Loop over all the sub-matrices of A and B
// required to compute the block sub-matrix
for (int a = aBegin, b = bBegin;
a <= aEnd;
a += aStep, b += bStep)
{
// Declaration of the shared memory array As used to
// store the sub-matrix of A
__shared__ float As[BLOCK_SIZE][BLOCK_SIZE];
// Declaration of the shared memory array Bs used to
// store the sub-matrix of B
__shared__ float Bs[BLOCK_SIZE][BLOCK_SIZE];
// Load the matrices from device memory
// to shared memory; each thread loads
// one element of each matrix
As[ty][tx] = A[a + wA * ty + tx];
Bs[ty][tx] = B[b + wB * ty + tx];
// Synchronize to make sure the matrices are loaded
__syncthreads();
// Multiply the two matrices together;
// each thread computes one element
// of the block sub-matrix
#pragma unroll
for (int k = 0; k < BLOCK_SIZE; ++k)
{
Csub += As[ty][k] * Bs[k][tx];
}
// 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 the block sub-matrix to device memory;
// each thread writes one element
int c = wB * BLOCK_SIZE * by + BLOCK_SIZE * bx;
C[c + wB * ty + tx] = Csub;
}
Replies to Untitled
Title |
Name |
Language |
UNIX |
When |
Re: Untitled |
Botched Pheasant |
c |
1569350095 |
4 Years ago. |
{"html5":"htmlmixed","css":"css","javascript":"javascript","php":"php","python":"python","ruby":"ruby","lua":"text\/x-lua","bash":"text\/x-sh","go":"go","c":"text\/x-csrc","cpp":"text\/x-c++src","diff":"diff","latex":"stex","sql":"sql","xml":"xml","apl":"apl","asterisk":"asterisk","c_loadrunner":"text\/x-csrc","c_mac":"text\/x-csrc","coffeescript":"text\/x-coffeescript","csharp":"text\/x-csharp","d":"d","ecmascript":"javascript","erlang":"erlang","groovy":"text\/x-groovy","haskell":"text\/x-haskell","haxe":"text\/x-haxe","html4strict":"htmlmixed","java":"text\/x-java","java5":"text\/x-java","jquery":"javascript","mirc":"mirc","mysql":"sql","ocaml":"text\/x-ocaml","pascal":"text\/x-pascal","perl":"perl","perl6":"perl","plsql":"sql","properties":"text\/x-properties","q":"text\/x-q","scala":"scala","scheme":"text\/x-scheme","tcl":"text\/x-tcl","vb":"text\/x-vb","verilog":"text\/x-verilog","yaml":"text\/x-yaml","z80":"text\/x-z80"}