The author examines the classical notion of persona (the role adopted by the writer) as a term useful in analyzing technical documents. It isolates rhetorical strategies that are components of the user-friendly person...
详细信息
The author examines the classical notion of persona (the role adopted by the writer) as a term useful in analyzing technical documents. It isolates rhetorical strategies that are components of the user-friendly persona and briefly speculates on the usefulness of those strategies given the interactive relationship between the writer and the audience.
Cache miss stalls hurt performance because of the large gap between memory and processor speeds - for example, the popular server benchmark SPEC JBB2000 spends 45% of its cycles stalled waiting for memory requests on ...
详细信息
Cache miss stalls hurt performance because of the large gap between memory and processor speeds - for example, the popular server benchmark SPEC JBB2000 spends 45% of its cycles stalled waiting for memory requests on the Itanium® 2 processor. Traversing linked data structures causes a large portion of these stalls. Prefetching for linked data structures remains a major challenge because serial data dependencies between elements in a linked data structure preclude the timely materialization of prefetch addresses. This paper presents Mississippi Delta (MS Delta), a novel technique for prefetching linked data structures that closely integrates the hardware performance monitor (HPM), the garbage collector's global view of heap and object layout, the type-level metadata inherent in type-safe programs, and JIT compiler analysis. The garbage collector uses the HPM's data cache miss information to identify cache miss intensive traversal paths through linked data structures, and then discovers regular distances (deltas) between these linked objects. JIT compiler analysis injects prefetch instructions using deltas to materialize prefetch addresses. We have implemented MS Delta in a fully dynamic profile-guided optimization system: the StarJIT dynamic compiler and the ORP Java virtual machine, We demonstrate a 28-29% reduction in stall cycles attributable to the high-latency cache misses targeted by MS Delta and a speedup of 11-14% on the cache miss intensive SPEC JBB2000 benchmark.
Constraint-based variability modeling is a flexible, declarative approach to managing solution-space variability. Product variants are defined in a top-down manner by successively restricting the admissible combinatio...
详细信息
Syntactic parsing requires a fine balance between expressivity and complexity, so that naturally occurring structures can be accurately parsed without compromising efficiency. In dependency-based parsing, several cons...
详细信息
We introduce the concept of Grid Speedup as a scalability metric for parallel applications on the grid and analyze it theoretically. It is shown that classes of applications exist for which good grid speedups can be e...
详细信息
We present a case study that illustrates the power of active learning for enabling the automated quality assurance of complex and distributed evolving systems. We illustrate how the development of the OCS, Springer Ve...
详细信息
Today's service mashup technologies usually focus on assisting programmers to provide more powerful and valuable integrated applications to the users. A significant set of scripting languages, graphical tools and ...
详细信息
Today's service mashup technologies usually focus on assisting programmers to provide more powerful and valuable integrated applications to the users. A significant set of scripting languages, graphical tools and web services are used for this purpose, all addressing users with significant IT background. This paper aims at extending the power of mashup development to end users and application experts by automatically taking care of the tedious technical details like interface speci fications, types, and syntactic constraints. In detail we support simple and intuitive mashup specifications which are automatically completed to runnable mashups by means of service discovery-like methods and planning. We illustrate our approach by means of a concrete case study executed within our jABC/jETI development and (remote) execution framework.
The complexity of embedded systems and their safety requirements have risen significantly in recent years. Models and the model based development approach help to keep overview and control of the development. Neverthe...
详细信息
Testing Software Product Lines is a very challenging task and approaches like combinatorial testing and model-based testing are frequently used to reduce the effort of testing Software Product Lines and to reuse test ...
详细信息
ISBN:
(纸本)9781450305709
Testing Software Product Lines is a very challenging task and approaches like combinatorial testing and model-based testing are frequently used to reduce the effort of testing Software Product Lines and to reuse test artifacts. In this contribution we present a tool chain realizing our MoSo-PoLiTe concept combining combinatorial and model-based testing. Our tool chain contains a pairwise configuration selection component on the basis of a feature model. This component implements an heuristic finding a minimal subset of configurations covering 100% pairwise interaction. Additionally, our tool chain allows the model-based test case generation for each configuration within this generated subset. This tool chain is based on commercial tools since it was developed within industrial cooperations. A non-commercial implementation of pairwise configuration selection is available and an integration with an Open Source model-based testing tool is under development. Copyright 2011 ACM.
The paper presents the Electronic Tool Integration platform (ETI), a community platform designed for project-oriented, domainspecific, public or private interactive experimentation with heterogeneous tools. ETI manage...
详细信息
暂无评论