CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers

gemm → thread Relation

File in include/cutlass/gemmIncludes file in include/cutlass/epilogue/thread
kernel / default_gemm.hlinear_combination.h
device / default_gemm_configuration.hlinear_combination.h
device / default_gemm_configuration.hlinear_combination_clamp.h
device / device/gemm_splitk_parallel.hconversion_op.h