Go to file
2017-06-11 14:11:18 +02:00
build NUMA support 2017-05-06 22:19:57 +02:00
doc correct CPU model used for perforance tests in documentation 2017-06-08 23:22:08 +02:00
examples Revert "no data transferred via continuation::resume()" 2017-06-10 16:33:01 +02:00
include/boost/fiber Revert "no data transferred via continuation::resume()" 2017-06-10 16:33:01 +02:00
meta fix meta infos 2016-11-22 19:59:10 +01:00
performance reset stack-size to 4kB/8kB for skynet-tests 2017-06-10 16:33:01 +02:00
src NUMA topology on Linux: fix if numa-node is not in /sys/devices 2017-06-11 14:11:18 +02:00
test fix compiler warnings in unit-tests 2017-06-10 15:01:23 +02:00
.gitignore ignore cscope files 2013-01-01 15:29:11 +01:00
index.html add index.htm 2016-06-07 08:14:02 +02:00
README.md Fix typos in README.md 2016-11-17 14:41:31 +01:00

boost.fiber

boost.fiber provides a framework for micro-/userland-threads (fibers) scheduled cooperatively. The API contains classes and functions to manage and synchronize fibers similiar to boost.thread.

A fiber is able to store the current execution state, including all registers and CPU flags, the instruction pointer, and the stack pointer and later restore this state. The idea is to have multiple execution paths running on a single thread using a sort of cooperative scheduling (threads are preemptively scheduled) - the running fiber decides explicitly when it yields to allow another fiber to run (context switching).

A context switch between threads costs usally thousands of CPU cycles on x86 compared to a fiber switch with less than 100 cycles. A fiber can only run on a single thread at any point in time.

boost.fiber requires C++11!