From: Convolution of large 3D images on GPU and its decomposition
Method
Number of operations
Number of memory transactions
DIF
c(M f + M g ) log(M f + M g ) + (M f + M g )
3(M f + M g )
DIT
c(M f + M g ) log(M f + M g ) + 2(M f + M g )
( 2 + P ) ( M f + M g )
Tilling
c ( M f + P M g ) log ( M f P + M g ) + ( M f + 2 P M g )
2 M f + P + Â 1 M g