In SX Microcontrollers, SX/B Compiler and SX-Key Tool, mgreen wrote:

Yes, in fact ImageCraft was looking into an automatic overlay scheme where the compiler would identify loops that could fit into a 64 or 128 instruction overlay area in the cog and generate code for the loop to execute there.  A single LMM instruction would load a small block of code following the instruction and execute it.  I don't know whether they actually implemented it.  One problem is that it really has to be used only for small loops that are executed several times to make up for the overhead in copying the code into the cog ... not a big deal for a good optimizer.

Several suggested LMM interpreters that have been posted have included provisions for this sort of overlay mechanism.  Look at some of the threads on the LMM idea from Bill Henning and others.

---------- End of Message ----------


You can view the post on-line at:
http://forums.parallax.com/forums/default.aspx?f=7&p=2&m=373927#m387781

Need assistance? Send an email to the Forum Administrator at forumadmin@parallax.com

The Parallax Forums are powered by dotNetBB Forums, copyright 2002-2009 (http://www.dotNetBB.com)