以下内核函数是 cuda 库 (http://gpgpu.org/developer/cudpp) 中的紧凑操作。
我的问题是为什么开发人员重复写作部分 8 次?为什么它可以提高性能?
为什么一个线程处理 8 个元素,为什么不是每个线程处理一个元素?
template <class T, bool isBackward>
__global__ void compactData(T *d_out,
size_t *d_numValidElements,
const unsigned int *d_indices, // Exclusive Sum-Scan Result
const unsigned int *d_isValid,
const T *d_in,
unsigned int numElements)
{
if (threadIdx.x == 0)
{
if (isBackward)
d_numValidElements[0] = d_isValid[0] + d_indices[0];
else
d_numValidElements[0] = d_isValid[numElements-1] + d_indices[numElements-1];
}
// The index of the first element (in a set of eight) that this
// thread is going to set the flag for. We left shift
// blockDim.x by 3 since (multiply by 8) since each block of
// threads processes eight times the number of threads in that
// block
unsigned int iGlobal = blockIdx.x * (blockDim.x << 3) + threadIdx.x;
// Repeat the following 8 (SCAN_ELTS_PER_THREAD) times
// 1. Check if data in input array d_in is null
// 2. If yes do nothing
// 3. If not write data to output data array d_out in
// the position specified by d_isValid
if (iGlobal < numElements && d_isValid[iGlobal] > 0) {
d_out[d_indices[iGlobal]] = d_in[iGlobal];
}
iGlobal += blockDim.x;
if (iGlobal < numElements && d_isValid[iGlobal] > 0) {
d_out[d_indices[iGlobal]] = d_in[iGlobal];
}
iGlobal += blockDim.x;
if (iGlobal < numElements && d_isValid[iGlobal] > 0) {
d_out[d_indices[iGlobal]] = d_in[iGlobal];
}
iGlobal += blockDim.x;
if (iGlobal < numElements && d_isValid[iGlobal] > 0) {
d_out[d_indices[iGlobal]] = d_in[iGlobal];
}
iGlobal += blockDim.x;
if (iGlobal < numElements && d_isValid[iGlobal] > 0) {
d_out[d_indices[iGlobal]] = d_in[iGlobal];
}
iGlobal += blockDim.x;
if (iGlobal < numElements && d_isValid[iGlobal] > 0) {
d_out[d_indices[iGlobal]] = d_in[iGlobal];
}
iGlobal += blockDim.x;
if (iGlobal < numElements && d_isValid[iGlobal] > 0) {
d_out[d_indices[iGlobal]] = d_in[iGlobal];
}
iGlobal += blockDim.x;
if (iGlobal < numElements && d_isValid[iGlobal] > 0) {
d_out[d_indices[iGlobal]] = d_in[iGlobal];
}
}