Parallel, multithreaded C and C++ programs such as web servers, database managers, news servers, and scientific applications are becoming increasingly prevalent. For these applications, the memory allocator is often a bottleneck that severely limits program performance and scalability on multiprocessor systems. Previous allocators suffer from problems that include poor performance and scalability, and heap organizations that introduce false sharing. Worse, many allocators exhibit a dramatic increase in memory consumption when confronted with a producer-consumer pattern of object allocation and freeing. This increase in memory consumption can range from a factor of P (the number of processors) to unbounded memory consumption.

Dynamic storage allocation has a significant impact on computer performance. A dynamic storage allocator manages space for objects whose lifetimes are not known by the system at the time of their creation. A good dynamic storage allocator should utilize storage efficiently and satisfy requests in as few instructions as possible. A dynamic storage allocator on a multiprocessor should have the ability to satisfy multiple requests concurrently. This paper examines parallel dynamic storage allocation algorithms and how performancescales with increasing numbers of processors. The highest throughputs and lowest instruction counts are achieved with multiple free list fit I. The best memory utilization is achieved using a best fit system.

To my wife and family.

Shared memory multiprocessor systems need efficient dynamic storage allocators, both for system purposes and to support parallel programs. Most memory manager algorithms are based either on a free list, which provides efficient memory use, or on a buddy system, which provides fast allocation and release. In this paper, we present two versions of a memory manager based on the fast fits algorithm, which keeps free memory blocks in a Cartesian tree. A fast fits memory manager provides both efficient memory usage, and fast allocate and release operations. The concurrent implementations of the fast fits algorithm range from a simple moderate concurrency solution to a more complex but high concurrency solution. 1 Introduction A memory manager accepts two kinds of operations: requests to allocate and requests to release blocks of memory, which may be of an arbitrary size. For example, the UNIX system calls malloc() and free() are requests to a memory manager. A concurrent memory manager han...

Shared memory multiprocessor systems need efficient dynamic storage allocators, both for system purposes and to support parallel programs. Memory managers are often based on the buddy system, which provides fast allocation and release. Previous parallel buddy memory managers made no attempt to coordinate the allocation, splitting and release of blocks, and as a result needlessly fragment memory. We a present fast, and simple parallel buddy memory manager that is also as space efficient as a serial buddy memory manager. We test our algorithms using memory allocation/deallocation traces collected from a parallel sparse matrix algorithm. Keywords: Memory management, Concurrent data structure, Buddy system, Parallel algorithm. 1 Introduction A memory manager accepts two kinds of operations: requests to allocate and requests to release blocks of memory, which may be of an arbitrary size. For example, the UNIX system calls malloc() and free() are requests to a memory manager. A concurrent ...