1,720,959 research outputs found
Analyzing and Optimizing Serverless Function Execution
Full text linkServerless computing, implemented as Function-as-a-Service (FaaS), is an emerging and rapidly growing cloud computing model. It attracts users thanks to its simple and flexible programming model, fine-grained billing model, and zero resource-provisioning overhead for the developer. In FaaS, the fundamental unit of computation is a function, defined as a stateless unit of code executed on-demand when triggered by an external event such as an HTTP request. To enable code reuse, FaaS functions are normally small with well-defined purpose and therefore they have a very short execution time, often less than a second. Larger FaaS applications are built by composing multiple individual functions. To communicate, the functions often use high-latency network-backed Remote Procedure Calls (RPC) interfaces. This adds significant overhead to FaaS application execution, especially as the number of functions in an application increases and the communication latencies compound. The short execution time, transient resource allocation, and high communication overhead raise the question of how to build hardware and software platforms for efficiently executing FaaS applications. This thesis addresses this question from two research directions.
The first research direction investigates the hardware perspective of serverless computing. To that end, we first examine the impact of the short execution time of FaaS functions on microarchitectural structures.The driving hypothesis is that, since FaaS functions run for a very short time, they do not give microarchitectural structures enough time to warm up sufficiently to perform optimally. Primarily, our analysis finds that the hypothesis holds only for functions with an extremely short execution time (<1 ms). Our analysis additionally finds that FaaS functions have large instruction working sets. This finding means that FaaS functions are affected by the widely established front-end bottleneck problem. This problem is caused by large instruction working sets overwhelming the capacities of the branch target buffer (BTB) and instruction caches of processors. A long line of research has established that instruction cache prefetching is an effective way to alleviate the frontend bottleneck. Fetch-directed instruction prefetching (FDIP) is a particularly attractive class of such instruction prefetchers. However, for FDIP to be effective it requires a sufficiently large BTB. However, access latency, area, and power constraints preclude simply increasing the size of a conventionally designed BTB.Therefore, to increase BTB storage density, we introduce BTB-X, an optimized BTB organization based on the critical observation that branch target offset lengths are unevenly distributed in server workloads.Therefore, BTB-X offers entries with different storage capacities to accommodate the offset size variance. BTB-X stores 2.24× more branches than a conventional BTB and 1.3× more branches than the state-of-the-art storage-optimized BTB design.
Following the second research direction, we focus on the software aspect of efficiently executing FaaS functions. One of the most significant overheads in FaaS function execution is the excessive latency of the network-backed RPC interfaces often used for inter-function communication. Previous proposals aiming to alleviate this communication latency are unattractive since they sacrifice at least one of the essential properties of FaaS that makes the programming model appealing. To address this, we introduce CoFaaS, a fully automated software-based transformation for FaaS functions that does not sacrifice any of FaaS’ essential properties. We observe that for functions written in different languages to communicate, the RPC interfaces exposed by each function must be well-defined. The critical insight exploited by CoFaaS is that these well-defined interfaces allow us to transform the implementation code of a function freely as long as its external interface is kept unchanged. This allows CoFaaS to retarget the FaaS functions comprising a FaaS application to run on a single WebAssembly runtime. By doing this, CoFaaS alleviates the inter-function communication overhead. CoFaaS reduces the application round-trip time by up to 6× and the inter-function communication and inter-function communication time by up to 100×
SMEIL:A domain-specific language for synchronous message exchange networks
No full textSynchronous Message Exchange (SME) is a CSP-derived model for hardware designs implementing globally synchronous message passing. SME implementations currently exist for several general-purpose languages, some of which, are translatable to VHDL for subsequent implementation on hardware. A common SME language could reduce the duplication and feature disparity present in these independent implementations. This paper introduces a domain-specific language for implementing SME designs. It is usable both as a primary implementation language for SME models and as an intermediate target for general-purpose languages. We describe the language, its implementation and its features. Furthermore, we explain the specific requirements for a language within this domain. Finally, we evaluate the language through a number of simple, but realistic, hardware designs by showing how they may be implemented and tested.</p
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
koamabayili/VECTRON-author-checklist: VECTRON author checklist
No full textWe have done our best to complete the author checklist relating to the use of animals in the hut study. Note that the objective for the hut study was to evaluate the IRS treatment applications for residual efficacy against Anopheles mosquitoes, including the local An. coluzzii mosquito population. Cows were only used to attract mosquitoes into the huts and no tests were carried out directly on the cows. The author checklist is intended for use with studies where experiments are carried out on animals, which is why we have had such difficulty in completing this for the hut study, as many of the questions do not relate to how the cows were used
Author-wise bibliometric analysis based on entropy.
No full textAuthor-wise bibliometric analysis based on entropy.</p
- …
