[java-dev] Re: Performance differences between Windows & Mac OS Jit/Java
Joshua Kit Clayton
jkc at musork.com
Wed Jan 23 09:22:17 MST 2008
- Previous message: [java-dev] Re: Performance differences between Windows & Mac OS Jit/Java
- Next message: [java-dev] multicast receive byte limit?
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
On Jan 23, 2008, at 3:06 AM, Peter Castine wrote: > > Some examination last night turned up another bottleneck... I was > using the very convenient JitterMatrix.getcell2dInt(), but the > copyMatrixToArray() methods appear to be a lot more efficient. > After thinking about it a bit I'm feeling a little stoopid for > having chosen the cell-by-cell approach at all, but just based on > the docs it's not immediately obvious that the one approach would > be more efficient than the other. Cell process and vec process examples are pretty clear. Yes. Never do cell by cell access if it can be avoided. This results in a boundary crossing (Java->C) for each cell, rather than once per row, or per matrix. Sounds like context switches are much slower on OS X than Windows, though on any platform, they are relatively expensive operations. -Joshua
- Previous message: [java-dev] Re: Performance differences between Windows & Mac OS Jit/Java
- Next message: [java-dev] multicast receive byte limit?
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
