Demonstration of a Hardware Reference - Counting Heap y Technical Report 401 , Revised

A hardware self-managing heap memory (RCM) for languages like LISP, SMALLTALK, and JAVA has been designed, built, tested and benchmarked. On every pointer write from the processor, reference-counting transactions are performed in real time within this memory, and garbage cells are reused without processor cycles. A processor allocates new nodes simply by reading from a distinguished location in its address space. The memory hardware also incorporates support for off-line, multiprocessing, mark-sweep garbage collection. Performance statistics are presented from a partial implementation of SCHEME over five different memory models and two garbage collection strategies, from main memory (no access to RCM) to a fully operational RCM installed on an external bus. The performance of the RCM memory is more than competitive with main memory. CR categories and Subject Descriptors: E.2 [Data Storage Representations]: Linked representations; D.4.2 [Storage Management]: Allocation/Deallocation strategies; B.3.2 [Memory Structures]: Design Styles—primary memory, shared memory; C.1.2 [Processor Architectures]: Multiple Data Stream Architectures (Multiprocessors)—Parallel processors; D.1.1 [Programming Techniques]: Applicative (Functional) Programming Techniques; B.5.1 [Register-transfer-level Implementation]: Design— Memory design. General Term: Performance. Additional