| Original author(s) | Emery Berger |
|---|---|
| Developer(s) | Emery Berger |
| Initial release | September 29, 1999 |
| Stable release | 3.8 / November 9, 2009 |
| Development status | Active |
| Operating system | Unix-like, Microsoft Windows and others |
| Platform | Cross-platform |
| Available in | C++ |
| Type | Memory allocation |
| License | GPL v2 and another one for proprietary software |
| Website | http://www.hoard.org/ |
The Hoard memory allocator, or Hoard, is a memory allocator for Linux, Solaris, Microsoft Windows and other operating systems. Hoard is designed to be efficient when used by multithreaded applications on multiprocessor computers. Hoard is distributed under the GPL, but can be purchased for proprietary software.
In 2000, its author Emery Berger benchmarked some famous memory allocators and stated Hoard improves the performance of multithreaded applications by providing fast, scalable memory management functions (malloc and free). In particular, it reduces contention for the heap (the central data structure used in dynamic memory allocation) caused when multiple threads allocate or free memory, and avoids the false sharing that can be introduced by memory allocators. At the same time, Hoard has strict bounds on fragmentation.[1][2]
In 2004, Maged Michael implemented a new memory allocator and benchmarked it with Hoard and some other famous memory allocators. He stated its new memory allocator is more efficient than Hoard.[3][4] Then Maged Michael contributed to improve Hoard's quality.[5]
Nowadays, Hoard is still maintained and improved and software relies on it.[6][7]