|  | CUTLASS
    CUDA Templates for Linear Algebra Subroutines and Solvers | 
| Functions | |
| template<typename WarpShape > | |
| constexpr int | simt_get_warp_threads_m () | 
| constexpr int | simt_transpose_padding (int threads, int crosswise, int size_in_bits) | 
| Computes padding in shared memory to perform efficient transpose without bank conflicts.  More... | |
| constexpr int cutlass::gemm::threadblock::detail::simt_get_warp_threads_m | ( | ) | 
| constexpr int cutlass::gemm::threadblock::detail::simt_transpose_padding | ( | int | threads, | 
| int | crosswise, | ||
| int | size_in_bits | ||
| ) | 
 1.8.11
 1.8.11