Re: Brain-scratcher: New example of the delay
- Posted by mattlewis (admin) Jun 15, 2009
- 958 views
CladStone said...
Thanks for reproducing this for me. Yes, a processor caching issue was my first thought when I came across the delay, but now that I've seen that they bind differently, that seems to defy the idea that that's ALL it is.
I suspect it may have to do with where the memory is allocated, and how close to a page boundary it is. The magic values seem to change, but the effect seems consistent, whether translated or bound or interpreted. It really does look like something going on with OS/processor memory management.
Is there some real situation where this issue is causing problems? I don't think there's anything that euphoria can do about this.
Matt