We call a garbage collector conservative if it has only partial information about the location of pointers, and is thus forced to treat arbitrary bit patterns as though they might be pointers, in at least some cases. We show that some very inexpensive, but previously unused techniques can have dramatic impact on the effectiveness of conservative garbage collectors in reclaiming memory. Our most significant observation is that static data that appears to point to the heap should not result in misidentified references to the heap. The garbage collector has enough information to allocate around such references. We also observe that programming style has a significant impact on the amount of spuriously retained storage, typically even if the collector is not terribly conservative. Some fairly common C and C programming styles significantly decrease the effectiveness of any garbage collector. These observations suffice to explain some of the different assessments of conservative collection that have appeared in the literature.

Compilers for monomorphic languages, such as C and Pascal, take advantage of types to determine data representations, alignment, calling conventions, and register selection. However, these languages lack important features including polymorphism, abstract datatypes, and garbage collection. In contrast, modern programming languages such as Standard ML (SML), provide all of these features, but existing implementations fail to take full advantage of types. The result is that performance of SML code is quite bad when compared to C. In this thesis, I provide a general framework, called type-directed compilation, that allows compiler writers to take advantage of types at all stages in compilation. In the framework, types are used not only to determine efficient representations and calling conventions, but also to prove the correctness of the compiler. A key property of typedirected compilation is that all but the lowest levels of the compiler use typed intermediate languages. An advantage of this approach is that it provides a means for automatically checking the integrity of the resulting code. An important

Object-oriented programming languages confer many benefits, including abstraction, which lets the programmer hide the details of an object’s implementation from the object’s clients. Unfortunately, crossing abstraction boundaries often incurs a substantial run-time overhead in the form of frequent procedure calls. Thus, pervasive use of abstraction, while desirable from a design standpoint, may be impractical when it leads to inefficient programs. Aggressive compiler optimizations can reduce the overhead of abstraction. However, the long compilation times introduced by optimizing compilers delay the programming environment‘s responses to changes in the program. Furthermore, optimization also conflicts with source-level debugging. Thus, programmers are caught on the horns of two dilemmas: they have to choose between abstraction and efficiency, and between responsive programming environments and efficiency. This dissertation shows how to reconcile these seemingly contradictory goals by performing optimizations lazily. Four new techniques work together to achieve high performance and high responsiveness: • Type feedback achieves high performance by allowing the compiler to inline message sends based on information extracted from the runtime system. On average, programs run 1.5 times faster than the previous SELF system; compared to a commercial Smalltalk implementation, two medium-sized benchmarks run about three times faster. This level of performance is obtained with a compiler that is both simpler and faster than previous SELF compilers. • Adaptive optimization achieves high responsiveness without sacrificing performance by using a fast nonoptimizing compiler to generate initial code while automatically recompiling heavily used parts of the program with an optimizing compiler. On a previous-generation workstation like the SPARCstation-2, fewer than 200 pauses exceeded 200 ms during a 50-minute interaction, and 21 pauses exceeded one second. On a currentgeneration workstation, only 13 pauses exceed 400 ms. • Dynamic deoptimization shields the programmer from the complexity of debugging optimized code by transparently recreating non-optimized code as needed. No matter whether a program is optimized or not, it can always be stopped, inspected, and single-stepped. Compared to previous approaches, deoptimization allows more debugging while placing fewer restrictions on the optimizations that can be performed. • Polymorphic inline caching generates type-case sequences on-the-fly to speed up messages sent from the same call site to several different types of object. More significantly, they collect concrete type information for the optimizing compiler. With better performance yet good interactive behavior, these techniques make exploratory programming possible both for pure object-oriented languages and for application domains requiring higher ultimate performance, reconciling exploratory programming, ubiquitous abstraction, and high performance.

The cost of accessing main memory is increasing. Machine designers have tried to mitigate the consequences of the processor and memory technology trends underlying this increasing gap with a variety of techniques to reduce or tolerate memory latency. These techniques, unfortunately, are only occasionally successful for pointer-manipulating programs. Recent research has demonstrated the value of a complementary approach, in which pointer-based data structures are reorganized to improve cache locality. This paper studies a technique for using a generational garbage collector to reorganize data

Standard ML is a major revision of earlier dialects of the functional language ML. We describe the first compiler written for Standard ML in Standard ML. The compiler incorporates a number of novel features and techniques, and is probably the largest system written to date in Standard ML. Great attention was paid to modularity in the construction of the compiler, leading to a successful large-scale test of the modular capabilities of Standard ML. The front end is useful for purposes other than compilation, and the back end is easily retargetable (we have code generators for the VAX and MC68020). The module facilities of Standard ML were taken into account early in the design of the compiler, and they particularly influenced the environment management component of the front end. For example, the symbol table structure is designed for fast access to opened structures. The front end of the compiler is a single phase that integrates parsing, environment management, and type checking. The m...

Most specifications of garbage collectors concentrate on the low-level algorithmic details of how to find and preserve accessible objects. Often, they focus on bit-level manipulations such as "scanning stack frames," "marking objects," "tagging data," etc. While these details are important in some contexts, they often obscure the more fundamental aspects of memory management: what objects are garbage and why? We develop a series of calculi that are just low-level enough that we can express allocation and garbage collection, yet are sufficiently abstract that we may formally prove the correctness of various memory management strategies. By making the heap of a program syntactically apparent, we can specify memory actions as rewriting rules that allocate values on the heap and automatically dereference pointers to such objects when needed. This formulation permits the specification of garbage collection as a relation that removes portions of the heap without affecting the outcome of the evaluation. Our high-level approach allows us to specify in a compact manner a wide variety of memory management techniques, including standard trace-based garbage collection (i.e., the family of copying and mark/sweep collection algorithms), generational collection, and type-based, tag-free collection. Furthermore, since the definition of garbage is based on the semantics of the underlying language instead of the conservative approximation of inaccessibility, we are able to specify and prove the idea that type inference can be used to collect some objects that are accessible but never used.

Increasingly popular languages such as Java and C # require efficient garbage collection. This paper presents the design, implementation, and evaluation of MMTk, a Memory Management Toolkit for and in Java. MMTk is an efficient, composable, extensible, and portable framework for building garbage collectors. MMTk uses design patterns and compiler cooperation to combine modularity and efficiency. The resulting system is more robust, easier to maintain, and has fewer defects than monolithic collectors. Experimental comparisons with monolithic Java and C implementations reveal MMTk has significant performance advantages as well. Performance critical system software typically uses monolithic C at the expense of flexibility. Our results refute common wisdom that only this approach attains efficiency, and suggest that performance critical software can embrace modular design and high-level languages. 1

Abstract. We present an analysis of the memory usage for six of the Java programs in the SPECjvm98 benchmark suite. Most of the programs are realworld applications with high demands on the memory system. For each program, we measured as much low level data as possible, including age and size distribution, type distribution, and the overhead of object alignment. Among other things, we found that non-pointer data usually represents more than 50 % of the allocated space for instance objects, that Java objects tend to live longer than objects in Smalltalk or ML, and that they are fairly small. 1

this paper, I evaluate the costs of different dynamic storage management algorithms, including domain-specific allocators, widelyused general-purpose allocators, and a publicly available conservative garbage collection algorithm. Surprisingly, I find that programmer enhancements often have little effect on program performance. I also find that the true cost of conservative garbage collection is not the CPU overhead, but the memory system overhead of the algorithm. I conclude that conservative garbage collection is a promising alternative to explicit storage management and that the performance of conservative collection is likely to improve in the future. C programmers should now seriously consider using conservative garbage collection instead of explicitly calling free in programs they write

Program-synchronous exceptions, for example, breakpoints, watchpoints, illegal opcodes, and memory access violations, provide information about exceptional conditions, interrupting the program and vectoring to an operating system handler. Over the last decade, however, programs and run-time systems have increasingly employed these mechanisms as a performance optimization to detect normal and expected conditions. Unfortunately, current architecture and operating system structures are designed for exceptional or erroneous conditions, where performance is of secondary importance, rather than normal conditions. Consequently, this has limited the practicality of such hardware-based detection mechanisms. We propose both hardware and software structures that permit efficient handling of synchronous exceptions by user-level code. We demonstrate a software implementation that reduces exceptiondelivery cost by an order-of-magnitude on current RISC processors, and show the performance benefits o...