-
Notifications
You must be signed in to change notification settings - Fork 350
Optimization_4x4_8
Jianyu Huang edited this page Aug 11, 2016
·
4 revisions
Copy the contents of file MMult_4x4_7.c
into a file named MMult_4x4_8.c
and change the contents:
Change the first lines in the makefile
to
OLD := MMult_4x4_7
NEW := MMult_4x4_8
make run
octave:3> PlotAll % this will create the plot
This time the performance graph will look something like
We now use registers to store the elements of the current row of B. (Notice that we did not do this for the case where we computed C four elements at a time.) The performance actually drops slightly. But this step enables further optimizations.