CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers

Files  
file  conversion_op.h [code] 
Functor performing conversion operations used by epilogues.  
file  linear_combination.h [code] 
Functor performing linear combination operations used by epilogues.  
file  linear_combination_clamp.h [code] 
Functor performing linear scaling operations used by epilogues. Values are clamped before converting to the output element type.  
file  linear_combination_relu.h [code] 
Functor performing linear combination operations used by epilogues. Values are clamped before converting to the output element type.  
file  reduction_op.h [code] 
Functor performing reduction operations used by epilogues.  