I want to convert my large array-multiply logic into a faster called library, need some advice on the C code.

[mk@opc]

For measuring the timing I just had a simple flat sequence structure with 4 parts.

1) initialization stuff

2) high resolution timer

3) the code

4) 2nd high resolution timer

and I just run the code in continous mode and show the output of the subtraction of the two timers

[nathand]

One more small note, although it won't affect performance - when you wire an autoindexed array to a for loop, there's no need to also wire a value to the N terminal. The loop will iterate once per array element (if there are multiple arrays, or if N is wired, it uses the smallest number).