100
edits
Changes
→Assignment 3
*24 x 24: 84% thread occupancy
*32 x 32: 100% thread occupancy
Running the tests with the various block sizes revealed that the optimal block size is 16 x 16, timings below. The timing for the kernel has gone down from 179 ms to 106 ms.
[[File:DPS915 Team7 Block size 16 x 16.PNG]]