The Hoard Memory Allocator Copyright (C) 1998-2012 by Emery Berger <http://www.hoard.org> <http://www.cs.umass.edu/~emery> <mailto:emery@cs.umass.edu> The Hoard memory allocator is a fast, scalable, and memory-efficient memory allocator for Linux, Solaris, Mac OS X, and Windows. Hoard is a drop-in replacement for malloc that can dramatically improve application performance, especially for multithreaded programs running on multiprocessors and multicore CPUs. No source code changes necessary: just link it in or set one environment variable (see below). Press ----- "If you'll be running on multiprocessor machines, ... use Emery Berger's excellent Hoard multiprocessor memory management code. It's a drop-in replacement for the C and C++ memory routines and is very fast on multiprocessor machines." -- Debugging Applications for Microsoft .NET and Microsoft Windows, Microsoft Press "(To improve scalability), consider an open source alternative such as the Hoard Memory Manager..." -- Windows System Programming, Addison-Wesley "Hoard dramatically improves program performance through its more efficient use of memory. Moreover, Hoard has provably bounded memory blowup and low synchronization costs." -- Principles of Parallel Programming, Addison-Wesley Users ----- Companies using Hoard in their products and servers include AOL, British Telecom, Blue Vector, Business Objects (formerly Crystal Decisions), Cisco, Credit Suisse, Entrust, InfoVista, Kamakura, Novell, Oktal SE, OpenText, OpenWave Systems (for their Typhoon and Twister servers), Pervasive Software, Plath GmbH, Quest Software, Reuters, Royal Bank of Canada, SAP, Sonus Networks, Tata Communications, and Verite Group. Open source projects using Hoard include the Asterisk Open Source Telephony Project, Bayonne GNU telephony server, the Cilk parallel programming language, the GNU Common C++ system, the OpenFOAM computational fluid dynamics toolkit, and the SafeSquid web proxy. Hoard is now a standard compiler option for the Standard Performance Evaluation Corporation's CPU2006 benchmark suite for the Intel and Open64 compilers. Hoard is also included with some Linux distributions, including Mandriva and Debian. Licensing --------- Hoard is distributed under the GPL (v2.0), and can also be licensed for commercial use. Because of the restrictions imposed by the GPL license (you must make your code open-source), commercial users of Hoard can purchase non-GPL licenses through the University of Texas at Austin. Please consult this current Hoard pricing information (updated 2/5/2009), which lists a number of options for purchasing licenses, as well as Software license terms and conditions, and the software license agreement: note that the main UT-Austin licensing page always contains the most up-to-date documents. To obtain a license, please contact Jitendra Jain or myself, Emery Berger (emery@cs.umass.edu). Jitendra Jain's full contact information follows: Jitendra Jain The University of Texas at Austin Office of Technology Commercialization MCC Building, Suite 1.9A 3925 West Braker Lane Austin, Texas 78759 (512) 471-9055 (512) 475-6894 (FAX) Why Hoard? ---------- There are a number of problems with existing memory allocators that make Hoard a better choice. -- Contention -- Multithreaded programs often do not scale because the heap is a bottleneck. When multiple threads simultaneously allocate or deallocate memory from the allocator, the allocator will serialize them. Programs making intensive use of the allocator actually slow down as the number of processors increases. Your program may be allocation-intensive without you realizing it, for instance, if your program makes many calls to the C++ Standard Template Library (STL). -- False Sharing -- The allocator can cause other problems for multithreaded code. It can lead to false sharing in your application: threads on different CPUs can end up with memory in the same cache line, or chunk of memory. Accessing these falsely-shared cache lines is hundreds of times slower than accessing unshared cache lines. -- Blowup -- Multithreaded programs can also lead the allocator to blowup memory consumption. This effect can multiply the amount of memory needed to run your application by the number of CPUs on your machine: four CPUs could mean that you need four times as much memory. Hoard is a fast allocator that solves all of these problems. Technical Information --------------------- For technical details of a previous version of Hoard, read "Hoard: A Scalable Memory Allocator for Multithreaded Applications", by Emery D. Berger, Kathryn S. McKinley, Robert D. Blumofe, and Paul R. Wilson. The Ninth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS-IX). Cambridge, MA, November 2000. Building Hoard (Unix/Mac) ------------------------- To build Hoard on non-Windows platforms, change into the src/ directory and run "make" followed by the appropriate target. If you type "make", it will present a list of available targets. These include linux-gcc-x86, solaris-sunw-sparc, etc. You can then use Hoard by linking it with your executable, or by setting the LD_PRELOAD environment variable, as in % export LD_PRELOAD=/path/to/libhoard.so in Solaris: % export LD_PRELOAD="/path/to/libhoard_32.so:/usr/lib/libCrun.so.1" (32-bit version) % export LD_PRELOAD="/path/to/libhoard_64.so:/usr/lib/64/libCrun.so.1" (64-bit version) or, in Mac OS X: % export DYLD_INSERT_LIBRARIES=/path/to/libhoard.dylib Building Hoard (Windows) ------------------------ Change into the src directory and type "nmake windows", as in: C:\hoard\src> nmake windows To use Hoard, link your executable with 'source\uselibhoard.cpp' and 'winhoard.lib'. You *must* use the /MD flag. Example: C:\hoard\src> cl /Ox /MD yourapp.cpp source\uselibhoard.cpp libhoard.lib To run yourapp.exe, you will need to have libhoard.dll in your path. Benchmarks ---------- The directory benchmarks/ contains a number of benchmarks used to evaluate and tune Hoard.
