optimizing system for bukkit

I am looking at taking the openSPARC softcore cpu and adapt it to run bukkit more efficently.

For this to work i need to know what parts of bukkit are hardest the cpu. Based on my experience with a vanilla server im expecting chunk generation to be one of them.

I would also like to know if there is some kind of test kit to measure performance.

Thanks
Glass

Edit: this is the core i was looking at http://en.wikipedia.org/wiki/UltraSPARC_T2