mirror of https://github.com/boostorg/fiber.git synced 2026-02-20 02:32:19 +00:00

Go to file

xaqq e9092f5d0d Fix allocator-aware fiber::async() overload allocator forwarding.

The fiber::async() overload which is aware of allocator doesn't use the
allocator to contruct its internal fiber object.

Signed-off-by: Oliver Kowalke <oliver.kowalke@gmx.de>

2016-11-16 08:47:50 +01:00

build

use SPMC (chase-lev algoritm) for ready-queue (work stealing)

2016-11-03 11:05:51 +01:00

doc

documentation: perforamnce numbers of threads

2016-11-14 08:02:09 +01:00

examples

use SPMC (chase-lev algoritm) for ready-queue (work stealing)

2016-11-03 11:05:51 +01:00

include/boost/fiber

Fix allocator-aware fiber::async() overload allocator forwarding.

2016-11-16 08:47:50 +01:00

README.md

boost.fiber

boost.fiber provides a framework for micro-/userland-threads (fibers) scheduled cooperativly. 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 its yields to allow another fiber to run (context switching).

A context switch between threads costs usally thousends 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!