A leakage-aware L2 cache management technique for producer-consumer sharing in low-power chip multiprocessors

This paper proposes a novel leakage management technique for applications with producer-consumer sharing patterns. Although previous research has proposed leakage management techniques by turning off inactive cache blocks, these techniques can be further improved by exploiting the various run-time characteristics of target applications in CMPs. By exploiting particular access sequences observed in producer-consumer sharing patterns and the spatial locality of shared buffers, our technique enables a more aggressive turn-off of L2 cache blocks of these buffers. Experimental results using a CMP simulator show that our proposed technique reduces the energy consumption of on-chip L2 caches, a shared bus, and off-chip memory by up to 31.3% over the existing cache leakage power management techniques with no significant performance loss.     

Victim retention for reducing cache misses in tiled chip multiprocessors

This paper presents CMP-VR (Chip-Multiprocessor with Victim Retention), an approach to improve cache performance by reducing the number of off-chip memory accesses. The objective of this approach is to retain the chosen victim cache blocks on the chip for the longest possible time. It may be possible that some sets of the CMPs last level cache (LLC) are heavily used, while certain others are not. In CMP-VR, some number of ways from every set are used as reserved storage. It allows a victim block from a heavily used set to be stored into the reserve space of another set. In this way the load of heavily used sets are distributed among the underused sets. This logically increases the associativity of the heavily used sets without increasing the actual associativity and size of the cache. Experimental evaluation using full-system simulation shows that CMP-VR has less off-chip miss-rate as compared to baseline Tiled CMP. Results are presented for different cache sizes and associativity for CMP-VR and baseline configuration. The best improvements obtained are 45.5% and 14% in terms of miss rate and cycles per instruction (CPI) respectively for a 4 MB, 4-way set associative LLC. Reduction in CPI and miss rate together guarantees performance improvement.     

Virtual-Cache: A cache-line borrowing technique for efficient GPU cache architectures

GPUs provide megabytes of registers and shared memories to maintain the contexts for thousands of threads and enable fast data sharing amongst threads of a thread block, respectively. Besides, GPUs employ L1 cache to provide the high bandwidth service for memory requests. However, the average L1 cache capacity per thread is very limited, resulting in cache thrashing which in turn impairs the performance. Meanwhile, many registers and shared memories are unassigned to any warps or thread blocks. Moreover, registers and shared memories that are assigned can be idle when warps or thread blocks are finished. Exploiting the above insights, we propose Virtual-Cache to cost-effectively increase the effective size of L1 cache by utilizing the unassigned and released registers and shared memories as cache-lines in this paper. Specifically, we leverage the unassigned registers and shared memories to serve cache requests directly. Regarding the registers assigned to a warp, they can work as cache-lines after the warp completes the execution and before they are accessed again by a new launched warp. Regarding the shared memories of a thread block, they are enabled to serve cache requests when the thread block is finished till they are referenced by shared memory instructions of the relaunched thread block. The register file, shared memory and L1 cache are physically independent but logically unified as a large virtual cache with redesigned cache-line management. We develop the control and data path for the register file, making the register file accessible for cache requests by borrowing an operand collector to serve the cache requests. We also expand the control and data path for the shared memory to serve the cache requests. Our evaluation results show that Virtual-Cache makes the performance improved by 28% over the previously proposed cache management technique for cache-sensitive applications.     

MUPPET: A programming environment for message-based multiprocessors

MUPPET is a problem-solving environment for scientific computing with message-based multiprocessors. It consists of four part—concurrent languages, programming environments, application environments and man-machine interfaces. The programming paradigm of MUPPET is based on parallel abstract machines and transformations between them. This paradigm allows the development of programs which are portable among multiprocessors with different interconnection topologies.

In this paper we discuss the MUPPET programming paradigm. We give an introduction to the language CONCURRENT MODULA-2 and the graphic specification system GONZO. The graphic specification system tries to introduce graphics as a tool for programming. It is also the basis for programming generation and transformation.     

CoFM:一种加速Middlebox应用的软硬件协同流管理机制

流管理是Middlebox实现有状态报文处理的基础,负责管理端到端通信所建立的连接及其状态。为了满足不同Middlebox对于流管理的多样化需求,流管理功能通常采用软件实现,以保证灵活性,例如Bro、mOS。但是,受限于CPU的处理性能,软件流管理的性能有限。针对现有解决方案无法兼顾性能和灵活性的缺点,提出一种软硬件协同的流管理机制——CoFM,将流管理解耦为应用无关的映射管理(即根据流标识查找连接)和应用相关的连接管理2部分,将映射管理卸载到硬件上实现,在减少软件的访存次数提升性能的同时,保持了软件连接管理的灵活性。此外,CoFM的映射管理还支持新映射的动态插入和超时映射的删除,分别用于减少软硬件交互次数和降低硬件资源开销。最后,使用Verilog语言在FPGA上实现了映射管理功能,并基于CAIDA数据集对其做了相应的性能和资源开销测试。实验结果表明,CoFM的映射管理具有50 Gbps的吞吐率和极低的处理延时(<1μs),且硬件资源开销相对较少,适合用于流管理的加速。     

Synchronization coherence: A transparent hardware mechanism for cache coherence and fine-grained synchronization

The quest to improve performance forces designers to explore finer-grained multiprocessor machines. Ever increasing chip densities based on CMOS improvements fuel research in highly parallel chip multiprocessors with 100s of processing elements. With such increasing levels of parallelism, synchronization is set to become a major performance bottleneck and efficient support for synchronization an important design criterion. Previous research has shown that integrating support for fine-grained synchronization can have significant performance benefits compared to traditional coarse-grained synchronization. Not much progress has been made in supporting fine-grained synchronization transparently to processor nodes: a key reason perhaps why wide adoption has not followed.     

A lightweight mechanism for detection of cache pollution attacks in Named Data Networking

Content-Centric Networking (CCN) is an emerging paradigm being considered as a possible replacement for the current IP-based host-centric Internet infrastructure. In CCN, named content – rather than addressable hosts – becomes a first-class entity. Content is therefore decoupled from its location. This allows, among other things, the implementation of ubiquitous caching.     

An optimization-based adaptive resource management framework for economic Grids: A switching mechanism

The application of Grid computing has been broadening day by day. An increasing number of users has led to the requirement of a job scheduling process, which can benefit them through optimizing their utility functions. On the other hand, resource providers are exploring strategies suitable for economically efficient resource allocation so that they can maximize their profit through satisfying more users. In such a scenario, economic-based resource management strategies (economic models) have been found to be compelling to satisfy both communities. However, existing research has identified that different economic models are suitable for different scenarios in Grid computing. The Grid application and resource models are typically very dynamic, making it challenging for a particular model for delivering stable performance all the time. In this work, our focus is to develop an adaptive resource management architecture capable of dealing with multiple models based on the models’ domains of strengths (DOS). Our preliminary results show promising outcomes if we consider multiple models rather than relying on a single model throughout the life cycle of a Grid.     

A relational framework for join implementation in model management systems

Two important issues in the design of relational model banks are the degree to which they should be aggregated or disaggregated and the methods by which disaggregated model banks might be integrated in response to user queries. Three topics relevant to this issue are addressed in this paper. The first is whether a universal model and its projections may possess the lossy join property. We will show that they do not. The second is the development of a relational algebra for the specification of join implementation in model banks, and the third is the realization of such an algebra in a language similar to Query-by-Example.     

A protocol for machine-readable cache policies in OGC web services: Application to the EuroGeoSource information system

An efficient access to the contents provided through OGC web services, widely used in environmental information systems, is usually achieved by means of caching strategies. Service-owners may be interested in expressing the conditions required to allow for this. If these conditions are expressed in a machine-readable way, automatic harvesters can be programmed to follow them.This paper proposes a protocol to specify and follow cache policies for OGC web services expressed in a machine-readable language. A preliminary implementation of this protocol has been tested in the EuroGeoSource project, where a number of Web Feature Services providing mineral deposits and energy resources are periodically cached to improve the efficiency and availability of several applications. The protocol addresses a nowadays common case, and can possibly be extended to allow for more detailed policies. Further work will help to determine how it could be integrated into a full Digital Rights Management system.     

Spillover Algorithm: A decentralised coordination approach for multi-robot production planning in open shared factories

Open and shared manufacturing factories typically dispose of a limited number of industrial robots and/or other production resources that should be properly allocated to tasks in time for an effective and efficient system performance. In particular, we deal with the dynamic capacitated production planning problem with sequence independent setup costs where quantities of products to manufacture need to be determined at consecutive periods within a given time horizon and products can be anticipated or back-ordered related to the demand period. We consider a decentralised multi-agent variant of this problem in an open factory setting with multiple owners of robots as well as different owners of the items to be produced, both considered self-interested and individually rational. Existing solution approaches to the classic constrained lot-sizing problem are centralised exact methods that require sharing of global knowledge of all the participants’ private and sensitive information and are not applicable in the described multi-agent context. Therefore, we propose a computationally efficient decentralised approach based on the spillover effect that solves this NP-hard problem by distributing decisions in an intrinsically decentralised multi-agent system environment while protecting private and sensitive information. To the best of our knowledge, this is the first decentralised algorithm for the solution of the studied problem in intrinsically decentralised environments where production resources and/or products are owned by multiple stakeholders with possibly conflicting objectives. To show its efficiency, the performance of the Spillover Algorithm is benchmarked against state-of-the-art commercial solver CPLEX 12.8.     

AVHRR-based mapping of fires in Russia: New products for fire management and carbon cycle studies

A new database of fire activity in Russia derived from 1-km resolution remote sensing imagery is presented and discussed. The procedure used to generate this burned-area product is described, including active-fire detection and burn-scar mapping approaches. Fire detection makes use of a probabilistic procedure using image data from the United States National Oceanic and Atmospheric Administration's (NOAA) advanced very high resolution radiometer (AVHRR) system. Using the combination of AVHRR data collected at the Krasnoyarsk, Russia, high-resolution picture transmission (HRPT) receiving station, and data from the NOAA Satellite Active Archive (SAA), fire maps are being created for all of Russia for 1995 to 1997 and all of Eastern Russia (east of the Ural Mountains) for 1995 to 2002. This mapping effort has resulted in the most complete set of historic fire maps available for Russia. An initial validation indicates that the burned-area estimates are conservative because the approaches do not detect smaller fires, and, in many cases, fire areas are slightly underestimated. Analyses using the fire database showed that an average of 7.7×10⁶ ha yr⁻¹ of fire occurred in Eastern Russia between 1996 and 2002 and that fire was widely dispersed in different regions. The satellite-based burned-area estimates area were two to five times greater than those contained in official government burned-area statistics. The data show that there is significant interannual variability in area burned, ranging between a low of 1.5×10⁶ ha in 1997 to a high of 12.1×10⁶ ha in 2002. Seasonal patterns of fire are similar to patterns seen in the North American boreal region, with large-fire seasons experiencing more late-season burning (in August and September) than during low-fire years. There was a distinct zonal distribution of fires in Russia; 65% of the area burned occurred in the taiga zone, which includes southern, middle, and northern taiga subzones, 20% in the steppe and forest steppe zones, 12% in the mixed forest zone, and 3% in the tundra and forest-tundra zones. Lands classified as forest experienced 55% of all burned area, while crops and pastures, swamps and bogs, and grass and shrubs land cover categories experienced 13% to 15% each. Finally, the utility of the products is discussed in the context of fire management and carbon cycling.     

Mixed reality environment for learning sensing technology applications in Construction: A usability study

Mixed reality is gradually becoming ubiquitous and significant in education owning to the inherent benefits of active participation and tacit knowledge development in a safe and engaging environment. However, limited studies have explored design features that facilitate its use as a pedagogical tool in construction education, particularly in equipping students with experiential skills that are otherwise challenging to obtain due to resource constraints and limited access to construction sites. By evaluating eye tracking, usability questions, and think-aloud protocol data and verbal feedback, this study investigated the usability of a mixed reality environment designed for equipping construction engineering students with competencies for deploying sensing technologies on construction projects. Results revealed features such as accuracy of represented construction activities, quality of animations, and easy access to information and resources as important for designing efficient mixed reality learning environments. While the usability data suggested that the user interface was usable, eye tracking provided profundity on encountered difficulties with the user interface. Through concise outline and sequential design of the user interface, this study revealed that knowledge scaffolding can improve task performance in a mixed reality learning environment. This study adds value to existing literature, in particular by providing insights into the affordances of mixed reality environments that address the technological gap between the construction industry and construction engineering education. The mixed reality learning environment contributes to the cognitive apprenticeship theory through the use of game objects to develop procedural knowledge for addressing construction industry challenges with sensing technologies.     

FlexiFrag: A design pattern for flexible file sharing in distributed collaborative applications

The need for flexible file sharing in distributed systems is increasing in applications such as calendar management, collaborative editing of documents, collaborative software developments etc. The file sharing policies required in these applications are often very different from the traditional read/write policies. Hence, a flexible way of specifying and implementing sharing policies on individual files in file systems is required. We propose a distributed object-based system model of constructing file systems. The object-based system model is based on a pattern called FlexiFrag. We show how a distributed object-based system and in particular distributed file system can be constructed using the pattern in a flexible way.     

A new flexible and reliable interval valued fuzzy VIKOR method based on uncertainty risk reduction in decision making process: An application for determining a suitable location for digging some pits for municipal wet waste landfill

Facility location selection problem is one of the challenging and famous kinds of MCDM problems including both quantitative and qualitative criteria. For each Multiple Criteria Decision Making (MCDM) problem, when the ratings of alternatives with respect to the criteria and/or the values of criteria’s weights are presented by Interval Valued Fuzzy Numbers (IVFNs), the conventional fuzzy MCDM methods (Type-1 fuzzy MCDM methods) tend to be less effective. Therefore, the IVF-MCDM (Interval Valued Fuzzy MCDM) methods should be applied for solving such fuzzy MCDM problems. In this paper, we propose an IVF-VIKOR (VlseKriterijumska Optimizacija I Kompromisno Resenje) method based on uncertainty risk reduction in decision making process. By using such method, the reliability of the captured decisions in an IVF decision making problem is significantly increased. The proposed method is applied for solving two numerical examples that the former of which is a real application problem related to selecting a suitable location for digging some pits for municipal wet waste landfill in one of the largest cities in Iran. The second numerical example is presented with an aim of comparing our method with the two other IVF-MCDM methods. As a result, we found out the proposed method is reliable and practical for the facility location selection problems and other MCDM problems. Moreover, the proposed method has a considerable accuracy and is flexible and easy to use.     

Vertical collaboration in the semiconductor industry: A decision framework for supply chain relationships

Vertical collaboration problem focuses on integrating and modeling the decision problems of the suppliers and buyers together with the market intermediary by identifying the inefficiencies in the traditional marketplace and aligning the incentives of members in the e-marketplace. The present work develops and solves real life e-marketplace models for complex buyers–suppliers procurement problems by estimating the order quantities in the collaborated supply chain. The newsvendor framework considers demand to be independent of the selling price as is generally the case in the semiconductor industry supply chain dealing with techno-savvy customers. The vertical collaboration process would be more effective if the length of the planning horizon and order size is considered as a negotiation parameter between the buyer and supplier. It is observed that the supplier’s expected profit function increases with the buyers’ ordering quantity, which is important in characterizing the general structure of the collaboration scheme of the supply chain.     

WRF-LTNGDA: A lightning data assimilation technique implemented in the WRF model for improving precipitation forecasts

This study introduces WRF-LTNGDA, a lightning data assimilation technique implemented in the Weather Research and Forecasting (WRF) model. This technique employs lightning for improving the representation of convection by means of controlling the triggering of the model's convection parameterization scheme. The development and implementation of WRF-LTNGDA was carried out in a framework that could easily allow for its exploitation in real-time forecasting activities. The assimilation algorithm was evaluated over eight precipitation events that took place in Greece in the years 2010–2013. Results clearly show that lightning forcing has a positive impact on model performance. The conducted analysis revealed that the employment of WRF-LTNGDA induces statistically significant improvements in precipitation verification scores, especially for high rainfall accumulations. Separate examination of one of the eight case studies highlighted the overall better agreement between the modelled and observed spatial distribution of precipitation when lightning data assimilation was applied, than in the control simulation.     

Topology management techniques for tolerating node failures in wireless sensor networks: A survey

In wireless sensor networks (WSNs) nodes often operate unattended in a collaborative manner to perform some tasks. In many applications, the network is deployed in harsh environments such as battlefield where the nodes are susceptible to damage. In addition, nodes may fail due to energy depletion and breakdown in the onboard electronics. The failure of nodes may leave some areas uncovered and degrade the fidelity of the collected data. However, the most serious consequence is when the network gets partitioned into disjoint segments. Losing network connectivity has a very negative effect on the applications since it prevents data exchange and hinders coordination among some nodes. Therefore, restoring the overall network connectivity is very crucial. Given the resource-constrained setup, the recovery should impose the least overhead and performance impact. This paper focuses on network topology management techniques for tolerating/handling node failures in WSNs. Two broad categories based on reactive and proactive methods have been identified for classifying the existing techniques. Considering these categories, a thorough analysis and comparison of all the recent works have been provided. Finally, the paper is concluded by outlining open issues that warrant additional research.