fill_stub Class — pytorch Architecture
Architecture documentation for the fill_stub class in FlashAttentionKernel.cpp from the pytorch codebase.
Entity Profile
Source Code
aten/src/ATen/native/cpu/FlashAttentionKernel.cpp lines 172–186
template <typename scalar_t>
inline void fill_stub(scalar_t* data, scalar_t val, int64_t size) {
using Vec = Vectorized<scalar_t>;
Vec data_vec = Vec(val);
int64_t d = 0;
for (; d < size - (size % Vec::size()); d += Vec::size()) {
data_vec.store(data + d);
}
#if !defined(_MSC_VER) && !defined(COMPILING_FOR_MIN_SIZE)
# pragma unroll
#endif
for (; d < size; d++) {
data[d] = val;
}
}
Source
Analyze Your Own Codebase
Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.
Try Supermodel Free