Zachary R. Anderson

Dependent types for low-level programming

In this paper, we describe the key principles of a dependent type system for low-level imperative languages. The major contributions of this work are (1) a sound type system that combines dependent types and mutation for variables and for heap-allocated structures in a more flexible way than before and (2) a technique for automatically inferring dependent types for local variables. We have applied these general principles to design Deputy, a dependent type system for C that allows the user to describe bounded pointers and tagged unions. Deputy has been used to annotate and check a number of real-world C programs.

Synopsis diffusion for robust aggregation in sensor networks

Previous approaches for computing duplicate-sensitive aggregates in wireless sensor networks have used a tree topology, in order to conserve energy and to avoid double-counting sensor readings. However, a tree topology is not robust against node and communication failures, which are common in sensor networks. In this article, we present synopsis diffusion, a general framework for achieving significantly more accurate and reliable answers by combining energy-efficient multipath routing schemes with techniques that avoid double-counting. Synopsis diffusion avoids double-counting through the use of order- and duplicate-insensitive (ODI) synopses that compactly summarize intermediate results during in-network aggregation. We provide a surprisingly simple test that makes it easy to check the correctness of an ODI synopsis. We show that the properties of ODI synopses and synopsis diffusion create implicit acknowledgments of packet delivery. Such acknowledgments enable energy-efficient adaptation of message routes to dynamic message loss conditions, even in the presence of asymmetric links. Finally, we illustrate using extensive simulations the significant robustness, accuracy, and energy-efficiency improvements of synopsis diffusion over previous approaches.

Lightweight annotations for controlling sharing in concurrent data structures

SharC is a recently developed system for checking data-sharing in multithreaded programs. Programmers specify sharing rules (read-only, protected by a lock, etc.) for individual objects, and the SharC compiler enforces these rules using static and dynamic checks. Violations of these rules indicate unintended data sharing, which is the underlying cause of harmful data-races. Additionally, SharC allows programmers to change the sharing rules for a specific object using a sharing cast, to capture the fact that sharing rules for an object often change during the objects lifetime. SharC was successfully applied to a number of multi-threaded C programs. However, many programs are not readily checkable using SharC because their sharing rules, and changes to sharing rules, effectively apply to whole data structures rather than to individual objects. We have developed a system called Shoal to address this shortcoming. In addition to the sharing rules and sharing cast of SharC, our system includes a new concept that we call groups. A group is a collection of objects all having the same sharing mode. Each group has a distinguished member called the group leader. When the sharing mode of the group leader changes by way of a sharing cast, the sharing mode of all members of the group also changes. This operation is made sound by maintaining the invariant that at the point of a sharing cast, the only external pointer into the group is the pointer to the group leader. The addition of groups allows checking safe concurrency at the level of data structures rather than at the level of individual objects. We demonstrate the necessity and practicality of groups by applying Shoal to a wide range of concurrent C programs (the largest approaching a million lines of code). In all benchmarks groups entail low annotation burden and no significant additional performance overhead.

Choosing beacon periods to improve response times for wireless HTTP clients

The IEEE 802.11 wireless LAN standard power-saving mode (PSM) allows the network interface card (NIC) to periodically sleep between receiving data. In this paper, we show that 802.11 PSM performs poorly due to the fact that an access point is unable to adapt to the requirements of each client. Therefore, we propose a novel power saving algorithm, named Dynamic Beacon Period, where the access point uses different beacon periods for different clients. During HTTP downloads, each client carefully chooses a good beacon period for itself, based on the RTT of its current connections, and informs the access point of this beacon period. This technique enables download times for Web pages that are comparable to those without any power-saving and provides energy savings comparable to the standard 802.11 PSM. We show, using real-world measurements and emulation-based experiments, that it is feasible for both clients and access points to efficiently support such per-client beacon periods, instead of having a common, static beacon for all clients. The solution is simple enough that it can be implemented with just small enhancements to the existing 802.11 specification.

Automatic Alignment of X-Ray Beams

Protein crystals and other biological samples diffract weakly in X-rays. It is therefore important that the X-ray beam be very stable. Cubic smoothing splines were fit to ion chamber counts versus the vertical position of the sample. The extrema, inflection points about the maximum, and other information about the spline were calculated to determine whether the data corresponded to a beam profile. The algorithm developed here correctly identified the absence of a beam profile in all data gathered over the course of a year from four beam lines at the Stanford Synchrotron Radiation Laboratory. This algorithm is effective and can be adapted to other beam lines.