Hi, You should definitely consider using the MMU also - using separate > processes allows you to use (usually) faster global variables without > having to use pointer indirection (and/or slow tls variables) for every > access, and the MMU in your cpu will do the job at no extra cost: the MMU > overhead is there in any case, but for multi-core systems, you can take > advantage of having more registers available, which is very important on > x86, but also on less register-starved machines such as amd64.
Yes, I understand, but this particular platform (Android) doesn't give me control over that; I have to work within the process created for me. The architecture relies on every process being forked from a specific process at a specific point. I agree about avoiding tls (although an mmu ought be be able to optimise that as well, but it seems to be done much less effectively than global variables on many platforms). Thanks - Paddy
_______________________________________________ libev mailing list libev@lists.schmorp.de http://lists.schmorp.de/cgi-bin/mailman/listinfo/libev
