Virtual Machines (VMs) with Just-In-Time (JIT) compilers are traditionally thought to execute programs in two phases: the initial warmup phase determines which parts of a program would most benefit from dynamic compilation, before JIT compiling those parts into machine code; subsequently the program is said to be at a steady state of peak performance. Measurement methodologies almost always discard data collected during the warmup phase such that reported measurements focus entirely on peak performance. We introduce a fully automated statistical approach, based on changepoint analysis, which allows us to determine if a program has reached a steady state and, if so, whether that represents peak performance or not. Using this, we show that even when run in the most controlled of circumstances, small, deterministic, widely studied microbenchmarks often fail to reach a steady state of peak performance on a variety of common VMs. Repeating our experiment on 3 different machines, we found that at most 43.5% of ⟨VM, benchmark⟩ pairs consistently reach a steady state of peak performance.
In this paper, we compose six different Python and Prolog VMs into 4 pairwise compositions: one using C interpreters; one running on the JVM; one using meta-tracing interpreters; and one using a C interpreter and a meta-tracing interpreter. We show that programs that cross the language barrier frequently execute faster in a meta-tracing composition, and that meta-tracing imposes a significantly lower overhead on composed programs relative to mono-language programs.
Language composition approaches have traditionally suffered from poor performance. In this paper we hypothesise that meta-tracing provides a means to compose independent language interpreters while retaining the performance levels of each. To study this approach, we compose Python and Prolog interpreters to form Unipycation. We present a case study of its use and a suite of micro-benchmarks which give us some understanding of its cross-language performance.
COTS components are ubiquitous in military, industrial and governmental systems. However, the benefits of reduced development and maintainance costs are compromised by security concerns. Since source code is unavailable, security audits necessarily occur at the binary level. Push-button formal method techniques, such as model checking and abstract interpretation, can support this process by, among other things, inferring ranges of values for registers. Ranges aid the security engineer in checking for vulnerabilities that relate, for example, to integer wrapping, uninitialised variables and buffer overflows. Yet the lack of structure in binaries limits the effectiveness of classical range analyses based on widening. This paper thus contributes a simple but novel range analysis, formulated in terms of linear programming, which calculates ranges without manual intervention.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.