Pipeline (software)

About: Pipeline (software) is a research topic. Over the lifetime, 14727 publications have been published within this topic receiving 113485 citations. The topic is also known as: pipes and filters design pattern.

BERT Rediscovers the Classical NLP Pipeline

Abstract: Pre-trained text encoders have rapidly advanced the state of the art on many NLP tasks. We focus on one such model, BERT, and aim to quantify where linguistic information is captured within the network. We find that the model represents the steps of the traditional NLP pipeline in an interpretable and localizable way, and that the regions responsible for each step appear in the expected sequence: POS tagging, parsing, NER, semantic roles, then coreference. Qualitative analysis reveals that the model can and often does adjust this pipeline dynamically, revising lower-level decisions on the basis of disambiguating information from higher-level representations.

Halide: a language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines

Abstract: Image processing pipelines combine the challenges of stencil computations and stream programs. They are composed of large graphs of different stencil stages, as well as complex reductions, and stages with global or data-dependent access patterns. Because of their complex structure, the performance difference between a naive implementation of a pipeline and an optimized one is often an order of magnitude. Efficient implementations require optimization of both parallelism and locality, but due to the nature of stencils, there is a fundamental tension between parallelism, locality, and introducing redundant recomputation of shared values.We present a systematic model of the tradeoff space fundamental to stencil pipelines, a schedule representation which describes concrete points in this space for each stage in an image processing pipeline, and an optimizing compiler for the Halide image processing language that synthesizes high performance implementations from a Halide algorithm and a schedule. Combining this compiler with stochastic search over the space of schedules enables terse, composable programs to achieve state-of-the-art performance on a wide range of real image processing pipelines, and across different hardware architectures, including multicores with SIMD, and heterogeneous CPU+GPU execution. From simple Halide programs written in a few hours, we demonstrate performance up to 5x faster than hand-tuned C, intrinsics, and CUDA implementations optimized by experts over weeks or months, for image processing applications beyond the reach of past automatic compilers.

Automated Structure Solution With autoSHARP

Abstract: We present here the automated structure solution pipeline "autoSHARP." It is built around the heavy-atom refinement and phasing program SHARP, the density modification program SOLOMON, and the ARP/wARP package for automated model building and refinement (using REFMAC). It allows fully automated structure solution, from merged reflection data to an initial model, without any user intervention. We describe and discuss the preparation of the user input, the data flow through the pipeline, and the various results obtained throughout the procedure.

High-performance complex event processing over streams

Abstract: In this paper, we present the design, implementation, and evaluation of a system that executes complex event queries over real-time streams of RFID readings encoded as events. These complex event queries filter and correlate events to match specific patterns, and transform the relevant events into new composite events for the use of external monitoring applications. Stream-based execution of these queries enables time-critical actions to be taken in environments such as supply chain management, surveillance and facility management, healthcare, etc. We first propose a complex event language that significantly extends existing event languages to meet the needs of a range of RFID-enabled monitoring applications. We then describe a query plan-based approach to efficiently implementing this language. Our approach uses native operators to efficiently handle query-defined sequences, which are a key component of complex event processing, and pipeline such sequences to subsequent operators that are built by leveraging relational techniques. We also develop a large suite of optimization techniques to address challenges such as large sliding windows and intermediate result sizes. We demonstrate the effectiveness of our approach through a detailed performance analysis of our prototype implementation under a range of data and query workloads as well as through a comparison to a state-of-the-art stream processor.