The advent of multicore processors has renewed interest in the idea of incorporating transactions into the programming model used to write parallel programs. This approach, known as transactional memory, offers an alternative, and hopefully better, way to coordinate concurrent threads. The ACI (atomicity, consistency, isolation) properties of transactions provide a foundation to ensure that concurrent reads and writes of shared data do not produce inconsistent or incorrect results. At a higher level, a computation wrapped in a transaction executes atomically - either it completes successfully and commits its result in its entirety or it aborts. In addition, isolation ensures the transaction produces the same result as if no other transactions were executing concurrently. Although transactions are not a parallel programming panacea, they shift much of the burden of synchronizing and coordinating parallel computations from a programmer to a compiler, to a language runtime system, or to hardware. The challenge for the system implementers is to build an efficient transactional memory infrastructure. This book presents an overview of the state of the art in the design and implementation of transactional memory systems, as of early spring 2010. Table of Contents: Introduction / Basic Transactions / Building on Basic Transactions / Software Transactional Memory / Hardware-Supported Transactional Memory / Conclusions

Transactional Memory, 2nd Edition

The study of what can be computed by a team of autonomous mobile robots, originally started in robotics and AI, has become increasingly popular in theoretical computer science (especially in distributed computing), where it is now an integral part of the investigations on computability by mobile entities. The robots are identical computational entities located and able to move in a spatial universe; they operate without explicit communication and are usually unable to remember the past; they are extremely simple, with limited resources, and individually quite weak. However, collectively the robots are capable of performing complex tasks, and form a system with desirable fault-tolerant and self-stabilizing properties. The research has been concerned with the computational aspects of such systems. In particular, the focus has been on the minimal capabilities that the robots should have in order to solve a problem. This book focuses on the recent algorithmic results in the field of distributed computing by oblivious mobile robots (unable to remember the past). After introducing the computational model with its nuances, we focus on basic coordination problems: pattern formation, gathering, scattering, leader election, as well as on dynamic tasks such as flocking. For each of these problems, we provide a snapshot of the state of the art, reviewing the existing algorithmic results. In doing so, we outline solution techniques, and we analyze the impact of the different assumptions on the robots' computability power. Table of Contents: Introduction / Computational Models / Gathering and Convergence / Pattern Formation / Scatterings and Coverings / Flocking / Other Directions

Distributed Computing by Oblivious Mobile Robots

Most high-performance software transactional memories (STM) use optimistic invisible reads. Consequently, a transaction might have an inconsistent view of the objects it accesses unless the consistency of the view is validated whenever the view changes. Although all STMs usually detect inconsistencies at commit time, a transaction might never reach this point because an inconsistent view can provoke arbitrary behavior in the application (e.g., enter an infinite loop). In this paper, we formally introduce a lazy snapshot algorithm that verifies at each object access that the view observed by a transaction is consistent. Validating previously accessed objects is not necessary for that, however, it can be used on-demand to prolong the view's validity. We demonstrate both formally and by measurements that the performance of our approach is quite competitive by comparing other STMs with an STM that uses our algorithm.

https://doc.rero.ch/record/18139/files/Riegel_Torvald_-_A_Lazy_Snapshot_Algorithm_with_Eager_Validation_20100430.pdf

A Lazy Snapshot Algorithm with Eager Validation

What fundamental opportunities for scalability are latent in interfaces, such as system call APIs? Can scalability opportunities be identified even before any implementation exists, simply by considering interface specifications? To answer these questions this paper introduces the following rule: Whenever interface operations commute, they can be implemented in a way that scales. This rule aids developers in building more scalable software starting from interface design and carrying on through implementation, testing, and evaluation.To help developers apply the rule, a new tool named Commuter accepts high-level interface models and generates tests of operations that commute and hence could scale. Using these tests, Commuter can evaluate the scalability of an implementation. We apply Commuter to 18 POSIX calls and use the results to guide the implementation of a new research operating system kernel called sv6. Linux scales for 68% of the 13,664 tests generated by Commuter for these calls, and Commuter finds many problems that have been observed to limit application scalability. sv6 scales for 99% of the tests.

/pdf/the-scalable-commutativity-rule-designing-scalable-software-4ilrf4n7cl.pdf

The scalable commutativity rule: designing scalable software for multicore processors

We study several variants of coordinated consensus in dynamic networks We assume a synchronous model, where the communication graph for each round is chosen by a worst-case adversary The network topology is always connected, but can change completely from one round to the next The model captures mobile and wireless networks, where communication can be unpredictableIn this setting we study the fundamental problems of eventual, simultaneous, and Δ-coordinated consensus, as well as their relationship to other distributed problems, such as determining the size of the network We show that in the absence of a good initial upper bound on the size of the network, eventual consensus is as hard as computing deterministic functions of the input, eg, the minimum or maximum of inputs to the nodes We also give an algorithm for computing such functions that is optimal in every execution Next, we show that simultaneous consensus can never be achieved in less than n - 1 rounds in any execution, where n is the size of the network; consequently, simultaneous consensus is as hard as computing an upper bound on the number of nodes in the networkFor Δ-coordinated consensus, we show that if the ratio between nodes with input 0 and input 1 is bounded away from 1, it is possible to decide in time n-Θ(√ nΔ), where Δ bounds the time from the first decision until all nodes decide If the dynamic graph has diameter D, the time to decide is min{O(nD/Δ),n-Ω(nΔ/D)}, even if D is not known in advance Finally, we show that (a) there is a dynamic graph such that for every input, no node can decide before time n-O(Δ028n072); and (b) for any diameter D = O(Δ), there is an execution with diameter D where no node can decide before time Ω(nD / Δ) To our knowledge, our work constitutes the first study of Δ-coordinated consensus in general graphs

/pdf/coordinated-consensus-in-dynamic-networks-1bpia7otfj.pdf

Coordinated consensus in dynamic networks

Transactional memory (TM) is a popular approach for alleviating the difficulty of programming concurrent applications; TM guarantees that a transaction, consisting of a sequence of operations, appear to be executed atomically. Two fundamental properties of TM implementations are disjoint-access parallelism and the invisibility of read operations. Disjoint access parallelism ensures that operations on disconnected data do not interfere, and thus it is critical for TM scalability. The invisibility of read operations means that their implementation does not write to the memory, thereby reducing memory contention.

This paper proves an inherent tradeoff for implementations of transactional memories: they cannot be both disjoint-access parallel and have read-only transactions that are invisible and always terminate successfully. In fact, a lower bound of Ω(t) is proved on the number of writes needed in order to implement a read-only transaction of t items, which successfully terminates in a disjoint-access parallel TM implementation. The results assume strict serializability and thus hold under the assumption of opacity. It is shown how to extend the results to hold also for weaker consistency conditions, snapshot isolation and serializability.

/pdf/inherent-limitations-on-disjoint-access-parallel-28c1ldd6n4.pdf

Inherent Limitations on Disjoint-Access Parallel Implementations of Transactional Memory

In this paper, we study the exclusive perpetual exploration problem with mobile anonymous and oblivious robots in a discrete space. Our results hold for the most generic settings: robots are asynchronous and are not given any sense of direction, so the left and right sense (i.e. chirality) is decided by the adversary that schedules robots for execution, and may change between invocations of a particular robots (as robots are oblivious). We investigate both the minimal and the maximal number of robots that are necessary and sufficient to solve the exclusive perpetual exploration problem. On the minimal side, we prove that three deterministic robots are necessary and sufficient, provided that the size n of the ring is at least 10, and show that no protocol with three robots can exclusively perpetually explore a ring of size less than 10. On the maximal side, we prove that k = n - 5 robots are necessary and sufficient to exclusively perpetually explore a ring of size n when n is coprime with k.

/pdf/exclusive-perpetual-ring-exploration-without-chirality-38pagh2gth.pdf

Exclusive perpetual ring exploration without chirality

Transactional memory (TM) is a promising approach for designing concurrent data structures, and it is essential to develop better understanding of the formal properties that can be achieved by TM implementations. Two fundamental properties of TM implementations are disjoint-access parallelism, which is critical for their scalability, and the invisibility of read operations, which reduces memory contention.This paper proves an inherent tradeoff for implementations of transactional memories: they cannot be both disjoint-access parallel and have read-only transactions that are invisible and always terminate successfully. In fact, a lower bound of Ω(t) is proved on the number of writes needed in order to implement a read-only transaction of t items, which successfully terminates in a disjoint-access parallel TM implementation. The results assume strict serializability and thus hold under the assumption of opacity. It is shown how to extend the results to hold also for weaker consistency conditions, serializability and snapshot isolation.

/pdf/inherent-limitations-on-disjoint-access-parallel-55726gl8u1.pdf

Inherent limitations on disjoint-access parallel implementations of transactional memory

In this paper, we investigate the exclusive perpetual exploration of grid shaped networks using anonymous, oblivious and fully asynchronous robots. Our results hold for robots without sense of direction (i.e. they do not agree on a common North, nor do they agree on a common left and right ; furthermore, the "North" and "left" of each robot is decided by an adversary that schedules robots for execution, and may change between invocations of particular robots). We focus on the minimal number of robots that are necessary and sufficient to solve the problem in general grids.

In more details, we prove that three deterministic robots are necessary and sufficient, provided that the size of the grid is n ×m with 3≤n≤m or n=2 and m≥4. Perhaps surprisingly, and unlike results for the exploration with stop problem (where grids are "easier" to explore and stop than rings with respect to the number of robots), exclusive perpetual exploration requires as many robots in the ring as in the grid.

Furthermore, we propose a classification of configurations such that the space of configurations to be checked is drastically reduced. This pre-processing lays the bases for the automated verification of our algorithm for general grids as it permits to avoid combinatorial explosion.

/pdf/asynchronous-exclusive-perpetual-grid-exploration-without-2sf1ajnk7e.pdf

Alessia Milani

Papers

Inherent Limitations on Disjoint-Access Parallel Implementations of Transactional Memory

Exclusive perpetual ring exploration without chirality

Inherent limitations on disjoint-access parallel implementations of transactional memory

Asynchronous exclusive perpetual grid exploration without sense of direction

Transactional scheduling for read-dominated workloads