CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers

gemm → reduction Relation

File in include/cutlass/gemmIncludes file in include/cutlass/reduction
device / device/gemm_splitk_parallel.hkernel / reduce_split_k.h
device / device/gemm_splitk_parallel.hthread / reduction_operators.h
thread / gemm/thread/mma_sm60.hthread / reduce.h