Parallel Processing of Large-Scale XML-Based Application Documents on Multi-core Architectures with PiXiMaL

Abstract

Very large scientific datasets are becoming increasingly available in XML formats. Our earlier benchmarking results show that parsing XML is a time consuming process when compared with binary formats optimized for large scale documents. This performance bottleneck will get exacerbated as size of XML data increases in e-science applications. Our focus in this paper is on addressing this performance bottleneck. In recent times, the microprocessor industry has made rapid strides towards Chip Multi Processors (CMPs). The widely available XML parsers have been unable to take advantage of the opportunities presented by CMPs, instead, passing the task of parallelization to the application programmer. The paradigms used thusfar to process large size XML documents on uni-processors are not applicable for CMPs. We present the design, implementation, and performance analysis of PiXiMaL, a parallel processing library for large-scale XML-data files. In particular, we discuss an effective scheme to parallelize the tokenization process to achieve an overall performance increase when parsing large-scale XML documents that are increasingly in use today. Our approach is to build a DFAbased parser that recognizes a useful subset of the XML specification and converts the DFA into an NFA which can be applied on any subset of the input.

SOAP Processing Performance and Enhancement

“…Recent benchmarking works in [32,33] demonstrate that most existing implementations of WS do not scale well when the size of the SOAP/XML document being processed is increased. The authors in [32,33]argue that most existing software toolkitsare typically designed to process small-sized XML datasets, and thus are not suited for large-scale comptuging applications, e.g., [25,62].Hence, recent studies have attempted to alleviate the limitations of XML software performance bottlenecks by applying nontraditional parallel processor architectures, e.g., [8,23,30,36,55,78]. On one hand, general-purpose (scalar) processorsare characterized by the sequential nature of instruction execution, where instructions are selected based on their sequential memory addresses, conditions being evaluated one at a time.…”

“…Handling XMLstreams entirely in software (for instance, by mapping processing pipeline stages to software threads) prevents the execution speed to be improved beyond a best processing rate of tens of clock cycles per character, and that best case performance can result in rates on the order of hundreds of clock cycles per character for many practical XML applications [78]. As a result, recent studies have addressed these performance bottlenecks by investigating non-traditional processors, namely parallel processing architectures and ‚XML ma-chines‛, e.g., [8,23,30].…”

Parallel and distributed approach for processing large-scale XML datasets

“…In our previous work in this area, we focused on statescalability for the parser and the memory requirements for arrays of primitives when multiple threads operate concurrently to read large input files [18]. One related project by Pan et.…”

Performance enhancement with speculative execution based parallelism for processing large-scale xml-based application data

“…A thorough description and analysis of the effective memory bandwidth of the PIXIMAL approach is presented in another venue [9]. In this section, we present a summary of research findings on these two topics.…”

“…While this technique works well for serial processing, it is not tailored for processing on multi-core nodes, especially for very large document sizes. In our previous work in this area, we focused just on the memory bandwidth in multi-core architectures when multiple threads operate concurrently to read large input files [9].…”