CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers

threadblock → arch Relation

File in include/cutlass/gemm/threadblockIncludes file in include/cutlass/arch
default_mma.harch.h
default_mma.hwmma.h
default_mma_core_wmma.hwmma.h
mma_base.hmemory.h