R.A. van Engelen

The gSOAP Toolkit for Web Services and Peer-to-Peer Computing Networks

This paper presents the gSOAP stub and skeleton compiler. The compiler provides a unique SOAP-to-C/C++ language binding for deploying C/C++ applications in SOAP Web Services, clients, and peer-to-peer computing networks. gSOAP enables the integratation of (legacy) C/C++/Fortran codes, embedded systems, and real-time software in Web Services, clients, and peers that share computational resources and information with other SOAP-enabled applications, possibly across different platforms, language environments, and disparate organizations located behind firewalls. Results on interoperability, legacy code integration, scalability, and performance are given.

Toward characterizing the performance of SOAP toolkits

The SOAP protocol underpins Web services as the standard mechanism for exchanging information in a distributed environment. The XML-based protocol offers advantages including extensibility, interoperability, and robustness. The merger of Web services and grid computing promotes SOAP into a standard protocol for the large-scale scientific applications that computational grids promise to support, further elevating the protocols importance and requiring high-performance implementations. Various SOAP implementations differ in their implementation language, invocation model and API, and supported performance optimizations. In this paper we compare and contrast the performance of widely used SOAP toolkits and draw conclusions about their current performance characteristics. We also provide insights into various design features that can lead to optimized SOAP implementations. The SOAP implementations included in our study are gSOAP 2.4, AxisC++ CVS May 28, AxisJava 1.2, .NET 1.1.4322 and XS0AP4/XSUL 1.1.

A Table-Driven Streaming XML Parsing Methodology for High-Performance Web Services

This paper presents a table-driven streaming XML parsing methodology, called TDX. TDX expedites XML parsing by pre-recording the states of an XML parser in tabular form and by utilizing an efficient runtime streaming parsing engine based on a push-down automaton. The parsing tables are automatically produced from the XML schemas of a WSDL service description. Because the schema constraints are pre-encoded in a parsing table, the approach effectively implements a schema-specific XML parsing technique that combines parsing and validation into a single pass. This significantly increases the performance of XML Web services, which results in better response time and may reduce the impact of the flash-crowd effect. To implement TDX, we developed a parser construction toolkit to automatically construct parsers in C code from WSDLs and XML schemas. We applied the toolkit to an example Web services application and measured the raw performance compared to popular high-performance parsers written in C/C++, such as eXpat, gSOAP, and Xerces. The performance results show that TDX can be an order of magnitude faster

Developing Web services for C and C

gSOAP is a platform-independent development environment for deploying efficient SOAP/XML Web services in C and C++.We implemented the traditional remote procedure calling (RPC stub-skeleton design for gSOAP, producing the RPC stub and skeleton routines for Web service applications at compile time. The RPC stub and skeleton routines are precompiled, which speeds encoding and decoding at runtime. The skeleton routines expose a C and C++ application as a Web service on the Internet and are responsible for binding SOAP/XML request and response messages to the application at runtime.

The GSI plug-in for gSOAP: enhanced security, performance, and reliability

In this paper we report on the current status of the GSI plug-in for gSOAP, an open source solution to the problem of securing Web services in grid environments.

An Overview and Evaluation of Web Services Security Performance Optimizations

WS-Security is an essential component of the Web services protocol stack. WS-Security provides end-to-end security properties (integrity, confidentiality, and authentication) through open XML standards. End-to-end message security assures the participation of non-secure transport intermediaries in message exchanges, which is a key advantage for Web-based systems and service-oriented architectures. However, point-to-point message security based on TLS (transport layer security) is known to significantly outperform WS-Security. In this paper we analyze the overhead of the WS-Security protocol processing stages and evaluate existing and new techniques for WS-Security signature performance optimizations to speed up end-to-end message integrity assurance and authentication.

High-Performance XML Parsing and Validation with Permutation Phrase Grammar Parsers

The extensibility, flexibility, expressiveness, and platform-neutrality of XML delivers key advantages for interoperability. The interoperability of XML Web services often comes at the price of reduced efficiency of message composition, transfer, and parsing compared to simple binary protocols. This paper presents a high-performance XML parsing and validation technique that is time and space optimal. A schema-specific parsing method is developed that uses a two-stack push-down automaton (PDA) for single-pass parsing and validation without backtracking. The schema validity constraints are packed in a compact parsing table derived from a permutation phrase grammar. This approach reduces both the space and time requirements of XML parsing and validation. By contrast, other XML schema-specific parsing methods trade efficiency for space (larger code and/or data size) or trade space for efficiency (backtracking). Performance results show that the method is significantly faster than traditional validating and non-validating XML parsers.

An Adaptive XML Parser for Developing High-Performance Web Services

This paper presents an adaptive XML parser that is based on table-driven XML (TDX) parsing technology. This technique can be used for developing extensible high-performance Web services for large complex systems that typically require extensible schemas. The parser integrates scanning, parsing, and validation into a single-pass without backtracking by utilizing compact tabular representations of schemas and a push-down automaton (PDA) at runtime. The tabular forms are constructed from a set of schemas or WSDL descriptions through the use of permutation grammar. The engine is implemented as a PDA-based, table-driven driver, as a result, it is independent of XML schemas. When XML schemas are updated or extended, the tabular forms can be regenerated and populated to the generic engine without requirement of redeployment of the parser. This adaptive approach balances the need for performance against the requirements of reconstruction and redeployment of the Web services. Our experiments show the adaptive parser usually demonstrates performance of 5 times faster than traditional validating parsers and performance drop within 20% of the fastest fully compiled traditional validating parsers.

Array Data Dependence Testing with the Chains of Recurrences Algebra

This paper presents a new approach to dependence testing in the presence of nonlinear and non-closed array index expressions and pointer references. The chains of recurrences formalism and algebra is used to analyze the recurrence relations of induction variables, and for constructing recurrence forms of array index expressions and pointer references. We use these recurrence forms to determine if the array and pointer references are free of dependences in a loop nest. Our recurrence formulation enhances the accuracy of standard dependence algorithms such as the extreme value test and range test. Because the recurrence forms are easily converted to closed forms (when they exist), induction variable substitution and array recovery can be delayed until after the loop is analyzed

An empirical evaluation of chains of recurrences for array dependence testing

Code restructuring compilers rely heavily on program analysis techniques to automatically detect data dependences between program statements. Dependences between statement instances in the iteration space of a loop nest impose ordering constraints that must be preserved in order to produce valid optimized, vectorized, and parallelized loop nests. This paper evaluates a new approach for fast and accurate nonlinear array dependence testing using Chains of Recurrences (CRs). A flow-sensitive loop analysis algorithm is presented for constructing the CR forms of array index expressions. Unlike other approaches, the CR forms are directly integrated into a standard dependence test to solve nonlinear CR-based dependence equations. To study the coverage and performance of the proposed CR-based enhancements of a standard test, we chose the inexact Banerjee test. We implemented a new CR-based Banerjee test in the Polaris compiler and compared the results to the Omega test and Range test on a set of SPEC and LAPACK Benchmark programs. The experimental results suggest that a CR enhancement can dramatically increase the effectiveness of a dependence test without a significant cost increase. More surprisingly, the findings indicate that the enhanced test exceeds the capabilities of the Omega and Range tests for many nonlinear dependence relations detected in the PERFECT Club and LAPACK Benchmark programs.