CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers
Functions
cutlass::debug Namespace Reference

Functions

template<typename Fragment >
CUTLASS_DEVICE void dump_fragment (Fragment const &frag, int N=0, int M=0, int S=1)
 
template<typename Element >
CUTLASS_DEVICE void dump_shmem (Element const *ptr, size_t size, int S=1)
 

Function Documentation

template<typename Fragment >
CUTLASS_DEVICE void cutlass::debug::dump_fragment ( Fragment const &  frag,
int  N = 0,
int  M = 0,
int  S = 1 
)

The first N threads dump the first M elements from their fragments with a stride of S elements. If N is not specified, dump the data of all the threads. If M is not specified, dump all the elements of the fragment.

template<typename Element >
CUTLASS_DEVICE void cutlass::debug::dump_shmem ( Element const *  ptr,
size_t  size,
int  S = 1 
)

Dump the shared memory contents. ptr is the begin address, size specifies the number of elements that need to be dumped, and S specifies the stride.