HI, I'm reading that paper and seeing few design pattens.
I agree with you that we should measure about the number of iterations. And, as you said, there is still I/O overhead involved in reading and writing materialized data every time, even if avoiding the situation shuffle and sort of reduce phase. IMO, BSP will communication only some vertices which can't be solved locally, and I'm sure that the number of iterations will be less or equal to (M/R based) Schimmy approach. More I hope we can compare them using Hama BSP soon. On Fri, Jul 2, 2010 at 11:12 AM, Felix Halim <[email protected]> wrote: > I have. See my comment in this blog: > > http://blog.udanax.org/2010/06/summary-of-google-pregel.html > > Felix Halim > > > On Tue, Jun 8, 2010 at 4:00 AM, Mark Kerzner <[email protected]> wrote: >> Hi, >> >> anybody has read it? >> >> Thank you, >> Mark >> > -- Best Regards, Edward J. Yoon [email protected] http://blog.udanax.org
