A framework for memory contention analysis in multi-core platforms

The last decade has witnessed a major shift towards the deployment of embedded applications on multi-core platforms. However, real-time applications have not been able to fully benefit from this transition, as the computational gains offered by multi-cores are often offset by performance degradation due to shared resources, such as main memory. To efficiently use multi-core platforms for real-time systems, it is hence essential to tightly bound the interference when accessing shared resources. Although there has been much recent work in this area, a remaining key problem is to address the diversity of memory arbiters in the analysis to make it applicable to a wide range of systems. This work handles diverse arbiters by proposing a general framework to compute the maximum interference caused by the shared memory bus and its impact on the execution time of the tasks running on the cores, considering different bus arbiters. Our novel approach clearly demarcates the arbiter-dependent and independent stages in the analysis of these upper bounds. The arbiter-dependent phase takes the arbiter and the task memory-traffic pattern as inputs and produces a model of the availability of the bus to a given task. Then, based on the availability of the bus, the arbiter-independent phase determines the worst-case request-release scenario that maximizes the interference experienced by the tasks due to the contention for the bus. We show that the framework addresses the diversity problem by applying it to a memory bus shared by a fixed-priority arbiter, a time-division multiplexing (TDM) arbiter, and an unspecified work-conserving arbiter using applications from the MediaBench test suite. We also experimentally evaluate the quality of the analysis by comparison with a state-of-the-art TDM analysis approach and consistently showing a considerable reduction in maximum interference.

WCET analysis considering contention on memory bus in COTS-based multicores

The usage of COTS-based multicores is becoming widespread in the field of embedded systems. Providing realtime guarantees at design-time is a pre-requisite to deploy real-time systems on these multicores. This necessitates the consideration of the impact of the contention due to shared low-level hardware resources on the Worst-Case Execution Time (WCET) of the tasks. As a step towards this aim, this paper first identifies the different factors that make the WCET analysis a challenging problem in a typical COTS-based multicore system. Then, we propose and prove, a mathematically correct method to determine tight upper bounds on the WCET of the tasks, when they are co-scheduled on different cores.

Response time analysis of COTS-Based multicores considering the contention on the shared memory bus

The current industry trend is towards using Commercially available Off-The-Shelf (COTS) based multicores for developing real time embedded systems, as opposed to the usage of custom-made hardware. In typical implementation of such COTS-based multicores, multiple cores access the main memory via a shared bus. This often leads to contention on this shared channel, which results in an increase of the response time of the tasks. Analyzing this increased response time, considering the contention on the shared bus, is challenging on COTS-based systems mainly because bus arbitration protocols are often undocumented and the exact instants at which the shared bus is accessed by tasks are not explicitly controlled by the operating system scheduler; they are instead a result of cache misses. This paper makes three contributions towards analyzing tasks scheduled on COTS-based multicores. Firstly, we describe a method to model the memory access patterns of a task. Secondly, we apply this model to analyze the worst case response time for a set of tasks. Although the required parameters to obtain the request profile can be obtained by static analysis, we provide an alternative method to experimentally obtain them by using performance monitoring counters (PMCs). We also compare our work against an existing approach and show that our approach outperforms it by providing tighter upper-bound on the number of bus requests generated by a task.

Finding an upper bound on the increase in execution time due to contention on the memory bus in COTS-based multicore systems

Contention on the memory bus in COTS based multicore systems is becoming a major determining factor of the execution time of a task. Analyzing this extra execution time is non-trivial because (i) bus arbitration protocols in such systems are often undocumented and (ii) the times when the memory bus is requested to be used are not explicitly controlled by the operating system scheduler; they are instead a result of cache misses. We present a method for finding an upper bound on the extra execution time of a task due to contention on the memory bus in COTS based multicore systems. This method makes no assumptions on the bus arbitration protocol (other than assuming that it is work-conserving).

Managing contention of software transactional memory in real-time systems

The foreseen evolution of chip architectures to higher number of, heterogeneous, cores, with non-uniform memory and non-coherent caches, brings renewed attention to the use of Software Transactional Memory (STM) as an alternative to lock-based synchronisation. However, STM relies on the possibility of aborting conflicting transactions to maintain data consistency, which impacts on the responsiveness and timing guarantees required by real-time systems. In these systems, contention delays must be (efficiently) limited so that the response times of tasks executing transactions are upperbounded and task sets can be feasibly scheduled. In this paper we defend the role of the transaction contention manager to reduce the number of transaction retries and to help the real-time scheduler assuring schedulability. For such purpose, the contention management policy should be aware of on-line scheduling information.

An analysis of the impact of bus contention on the WCET in multicores

The use of multicores is becoming widespread inthe field of embedded systems, many of which have real-time requirements. Hence, ensuring that real-time applications meet their timing constraints is a pre-requisite before deploying them on these systems. This necessitates the consideration of the impact of the contention due to shared lowlevel hardware resources like the front-side bus (FSB) on the Worst-CaseExecution Time (WCET) of the tasks. Towards this aim, this paper proposes a method to determine an upper bound on the number of bus requests that tasks executing on a core can generate in a given time interval. We show that our method yields tighter upper bounds in comparison with the state of-the-art. We then apply our method to compute the extra contention delay incurred by tasks, when they are co-scheduled on different cores and access the shared main memory, using a shared bus, access to which is granted using a round-robin arbitration (RR) protocol.

Software transactional memory as a building block for parallel embedded realtime systems

The recent trends of chip architectures with higher number of heterogeneous cores, and non-uniform memory/non-coherent caches, brings renewed attention to the use of Software Transactional Memory (STM) as a fundamental building block for developing parallel applications. Nevertheless, although STM promises to ease concurrent and parallel software development, it relies on the possibility of aborting conflicting transactions to maintain data consistency, which impacts on the responsiveness and timing guarantees required by embedded real-time systems. In these systems, contention delays must be (efficiently) limited so that the response times of tasks executing transactions are upper-bounded and task sets can be feasibly scheduled. In this paper we assess the use of STM in the development of embedded real-time software, defending that the amount of contention can be reduced if read-only transactions access recent consistent data snapshots, progressing in a wait-free manner. We show how the required number of versions of a shared object can be calculated for a set of tasks. We also outline an algorithm to manage conflicts between update transactions that prevents starvation.

Optimizing memory transactions for large-scale programs

Even though Software Transactional Memory (STM) is one of the most promising approaches to simplify concurrent programming, current STM implementations incur significant overheads that render them impractical for many real-sized programs. The key insight of this work is that we do not need to use the same costly barriers for all the memory managed by a real-sized application, if only a small fraction of the memory is under contention lightweight barriers may be used in this case. In this work, we propose a new solution based on an approach of adaptive object metadata (AOM) to promote the use of a fast path to access objects that are not under contention. We show that this approach is able to make the performance of an STM competitive with the best fine-grained lock-based approaches in some of the more challenging benchmarks. (C) 2015 Elsevier Inc. All rights reserved.

Non-preemptive and SRP-based fullypreemptive scheduling of real-time Software Transactional Memory

Recent embedded processor architectures containing multiple heterogeneous cores and non-coherent caches renewed attention to the use of Software Transactional Memory (STM) as a building block for developing parallel applications. STM promises to ease concurrent and parallel software development, but relies on the possibility of abort conflicting transactions to maintain data consistency, which in turns affects the execution time of tasks carrying transactions. Because of this fact the timing behaviour of the task set may not be predictable, thus it is crucial to limit the execution time overheads resulting from aborts. In this paper we formalise a FIFO-based algorithm to order the sequence of commits of concurrent transactions. Then, we propose and evaluate two non-preemptive and one SRP-based fully-preemptive scheduling strategies, in order to avoid transaction starvation.

Scaling In-Memory databases on multicores

Current computer systems have evolved from featuring only a single processing unit and limited RAM, in the order of kilobytes or few megabytes, to include several multicore processors, o↵ering in the order of several tens of concurrent execution contexts, and have main memory in the order of several tens to hundreds of gigabytes. This allows to keep all data of many applications in the main memory, leading to the development of inmemory databases. Compared to disk-backed databases, in-memory databases (IMDBs) are expected to provide better performance by incurring in less I/O overhead. In this dissertation, we present a scalability study of two general purpose IMDBs on multicore systems. The results show that current general purpose IMDBs do not scale on multicores, due to contention among threads running concurrent transactions. In this work, we explore di↵erent direction to overcome the scalability issues of IMDBs in multicores, while enforcing strong isolation semantics. First, we present a solution that requires no modification to either database systems or to the applications, called MacroDB. MacroDB replicates the database among several engines, using a master-slave replication scheme, where update transactions execute on the master, while read-only transactions execute on slaves. This reduces contention, allowing MacroDB to o↵er scalable performance under read-only workloads, while updateintensive workloads su↵er from performance loss, when compared to the standalone engine. Second, we delve into the database engine and identify the concurrency control mechanism used by the storage sub-component as a scalability bottleneck. We then propose a new locking scheme that allows the removal of such mechanisms from the storage sub-component. This modification o↵ers performance improvement under all workloads, when compared to the standalone engine, while scalability is limited to read-only workloads. Next we addressed the scalability limitations for update-intensive workloads, and propose the reduction of locking granularity from the table level to the attribute level. This further improved performance for intensive and moderate update workloads, at a slight cost for read-only workloads. Scalability is limited to intensive-read and read-only workloads. Finally, we investigate the impact applications have on the performance of database systems, by studying how operation order inside transactions influences the database performance. We then propose a Read before Write (RbW) interaction pattern, under which transaction perform all read operations before executing write operations. The RbW pattern allowed TPC-C to achieve scalable performance on our modified engine for all workloads. Additionally, the RbW pattern allowed our modified engine to achieve scalable performance on multicores, almost up to the total number of cores, while enforcing strong isolation.

The collective memory and challenges of feminism

Includes bibliography

Energy-performance tradeoffs in software transactional memory

Transactional memory (TM) is a new synchronization mechanism devised to simplify parallel programming, thereby helping programmers to unleash the power of current multicore processors. Although software implementations of TM (STM) have been extensively analyzed in terms of runtime performance, little attention has been paid to an equally important constraint faced by nearly all computer systems: energy consumption. In this work we conduct a comprehensive study of energy and runtime tradeoff sin software transactional memory systems. We characterize the behavior of three state-of-the-art lock-based STM algorithms, along with three different conflict resolution schemes. As a result of this characterization, we propose a DVFS-based technique that can be integrated into the resolution policies so as to improve the energy-delay product (EDP). Experimental results show that our DVFS-enhanced policies are indeed beneficial for applications with high contention levels. Improvements of up to 59% in EDP can be observed in this scenario, with an average EDP reduction of 16% across the STAMP workloads. © 2012 IEEE.

The Failure of Silence and the Manipulation of Memory: How Spain's pact of oblivion has failed to rid the country of its troubled past

This thesis is an analysis of Spain’s development from dictatorship to democracy in light of the trauma that it endured during the Spanish Civil War of 1936 – 1939 and the dictatorship of Francisco Franco, which lasted until 1975. Drawing from the work of Maurice Halbwachs and Pierre Nora, this thesis seeks to use the concepts of collective memory and lieux de mémoire to analyze what role memory has played in Spanish society from 1939 to the present day. Theanalysis begins with an overview of the Spanish Civil War and Franco’s ensuing dictatorship in order to establish an understanding of the trauma endured by Spain and its people. Of importance will be the manner in which the presentation of history became manipulated anddistorted under Franco as the dictator sought to control the country’s collective memory. With this background in mind, the thesis then turns to analyze how the memory of Spain’s past has affected the country’s development in two eras: during its transition to democracy in the 1970s and in the present day. Of central importance is the pact of silence that was established during the transition to democracy, which was a tacit agreement among the Spanish people to notdiscuss the past. This pact of silence still clouds Spain’s memory today and affects modern discourse concerning the past. Yet it is clear that Spain has not been reconciled to its past, as the provocation of history inevitably results in tension and controversy. The central contention of this thesis is that the pact of silence that surrounds Spain’s past has not eliminated the trauma of the Civil War and dictatorship, as demonstrated by the controversy stirred up by people, groups and places in the present day. This contention has repercussions for the study of history as a whole, as it indicates that the past cannot be muted in order to achievereconciliation; rather, it suggests that we must engage the past in order to be reconciled to it.

Memory resource balancing for virtualized computing

Virtualization has become a common abstraction layer in modern data centers. By multiplexing hardware resources into multiple virtual machines (VMs) and thus enabling several operating systems to run on the same physical platform simultaneously, it can effectively reduce power consumption and building size or improve security by isolating VMs. In a virtualized system, memory resource management plays a critical role in achieving high resource utilization and performance. Insufficient memory allocation to a VM will degrade its performance dramatically. On the contrary, over-allocation causes waste of memory resources. Meanwhile, a VM’s memory demand may vary significantly. As a result, effective memory resource management calls for a dynamic memory balancer, which, ideally, can adjust memory allocation in a timely manner for each VM based on their current memory demand and thus achieve the best memory utilization and the optimal overall performance. In order to estimate the memory demand of each VM and to arbitrate possible memory resource contention, a widely proposed approach is to construct an LRU-based miss ratio curve (MRC), which provides not only the current working set size (WSS) but also the correlation between performance and the target memory allocation size. Unfortunately, the cost of constructing an MRC is nontrivial. In this dissertation, we first present a low overhead LRU-based memory demand tracking scheme, which includes three orthogonal optimizations: AVL-based LRU organization, dynamic hot set sizing and intermittent memory tracking. Our evaluation results show that, for the whole SPEC CPU 2006 benchmark suite, after applying the three optimizing techniques, the mean overhead of MRC construction is lowered from 173% to only 2%. Based on current WSS, we then predict its trend in the near future and take different strategies for different prediction results. When there is a sufficient amount of physical memory on the host, it locally balances its memory resource for the VMs. Once the local memory resource is insufficient and the memory pressure is predicted to sustain for a sufficiently long time, a relatively expensive solution, VM live migration, is used to move one or more VMs from the hot host to other host(s). Finally, for transient memory pressure, a remote cache is used to alleviate the temporary performance penalty. Our experimental results show that this design achieves 49% center-wide speedup.

All-optical regenerative memory using a single device

In recent years the optical domain has been traditionally reserved for node-to-node transmission with the processing and switching achieved entirely in the electrical domain. However, with the constantly increasing demand for bandwidth and the resultant increase in transmission speeds, there is a very real fear that current electronic technology as used for processing will not be able to cope with future demands. Fuelled by this requirement for faster processing speeds, considerable research is currently being carried out into the potential of All-optical processing. One of the fundamental obstacles in realising All-optical processing is the requirement for All-optical buffering. Without all-optical buffers it is extremely difficult to resolve situations such as contention and congestion. Many devices have been proposed to solve this problem however none of them provide the perfect solution. The subject of this research is to experimentally demonstrate a novel all-optical memory device. Unlike many previously demonstrated optical storage devices the device under consideration utilises only a single loop mirror and a single SOA as its switch, whilst providing full regenerative capabilities required for long-term storage. I will explain some of the principles and characteristics of the device, which will then be experimentally demonstrated. The device configuration will then be studied and investigated as to its suitability for Hybrid Integrated Technology.