java is often accused of being too slow for serious programming, especially for scientific problem solving. However, we found that for a large-scale geophysical application, java code compiled with current just-in-tim...
详细信息
java is often accused of being too slow for serious programming, especially for scientific problem solving. However, we found that for a large-scale geophysical application, java code compiled with current just-in-time compilers runs slower than Fortran by a factor of at most 4, on both a shared-memory parallel machine (SGI Origin2000) and a distributed-memory parallel machine (IBM SP/2). The moderate slowdown is easily offset by the following advantages: (a) object-oriented java code is easier to maintain and reuse than Fortran code;(b) java code is fully portable, even among parallel computers with different memory models. Furthermore, better compiler technology Is an the horizon, which will narrow the performance gap even more. (C) 1998 John Whey & Sons, Ltd.
The distinct feature of data acquisition for magnetic resonance imaging (MRI) is that the data are sampled in frequency domain instead of spatial domain. Therefore, the acquired data must be inverse Fourier transforme...
详细信息
The distinct feature of data acquisition for magnetic resonance imaging (MRI) is that the data are sampled in frequency domain instead of spatial domain. Therefore, the acquired data must be inverse Fourier transformed to generate images. To apply fast Fourier transform (FFT), the data are usually acquired on rectilinear grids. However, acquiring data on rectilinear grids is not very efficient in MRI. A spiral trajectory, which starts at the origin of the frequency domain and spins out to higher spatial frequency is more efficient and faster than the conventional method. Since the spiral trajectories do not sample on rectilinear grids, raw data must be re-interpolated onto rectilinear grids prior to inverse FFT. This re-gridding process is done using a reconstruction program. When the platforms to run the program grow, the efforts required to maintain the program become prohibitive. This problem can be solved through the platform-independent java programming language. In this paper, we report on our attempt to implement the spiral MRI reconstruction program in java. We show that the performance is not significantly affected and that it is practical to use a platform-independent reconstruction software. (C) 2002 Elsevier Science Ireland Ltd. All rights reserved.
The Real-Time Specification for java (RTSJ) provides an integrated approach to scheduling periodic real-time threads and monitoring their CPU execution time. It defines a cost enforcement model whereby a periodic real...
详细信息
The Real-Time Specification for java (RTSJ) provides an integrated approach to scheduling periodic real-time threads and monitoring their CPU execution time. It defines a cost enforcement model whereby a periodic real-time thread is suspended when it consumes more CPU time (budget) than it requested in a single release. However, compliant implementations need not support this model, as the underlying operating systems mechanisms are not widely available. Consequently, experience with the model is limited (it is generally not provided in most implementations of the RTSJ). In previous work we showed, using model checking techniques, that the current version of the cost enforcement model can, under certain unlikely scenarios, allow a periodic thread more than its CPU budget in a single period. Such a behaviour can undermine any schedulability analysis that has been undertaken. In this paper, we present a revised formal model, which corrects this anomalous behaviour, and evaluate its properties. We also extend the formal model, so it allows support for real-time threads with sporadic and aperiodic releases, and show how our revised cost enforcement model is valid for all types of threads.
We demonstrate a model, including operational semantics, for the reverse execution of stack-based code. We discuss our modification of the Kaffe implementation of the java Virtual Machine, supporting a debugger capabl...
详细信息
We demonstrate a model, including operational semantics, for the reverse execution of stack-based code. We discuss our modification of the Kaffe implementation of the java Virtual Machine, supporting a debugger capable of running java bytecode backwards. We achieve reverse execution by logging the state lost during each operation or by directly reversing instructions. Our debugger has facilities for stepping, stepping over methods and running to breakpoints, in both directions. Multi-threading is supported. It is also possible to step through the bytecode when the java source code is not available. The debugger has both a command line user interface and a graphical user interface with facilities for editing code and running the java compiler.
Efficient implementation of monitors and exceptions is crucial for the performance of java One implementation of threads showed a factor of 30 difference in runtime on some benchmark programs. This paper describes an ...
详细信息
Efficient implementation of monitors and exceptions is crucial for the performance of java One implementation of threads showed a factor of 30 difference in runtime on some benchmark programs. This paper describes an efficient implementation of monitors for java as used in the CACAO just-in-time compiler. With this implementation the thread overhead is less than 40% for typical application programs and can be completely eliminated for some applications. This paper also gives the implementation details of the new exception handling scheme in CACAO, The new approach reduces the size of the generated native code by a half and allows null pointers to be checked by hardware, By using these techniques, the CACAO system has become the fastest java VM implementation for the Alpha processor. (C) 1998 John Wiley & Sons, Ltd.
Non-interference guarantees the absence of illicit information flow throughout program execution. It can be enforced by appropriate information flow type systems. Much of the previous work on type systems for non-inte...
详细信息
Non-interference guarantees the absence of illicit information flow throughout program execution. It can be enforced by appropriate information flow type systems. Much of the previous work on type systems for non-interference has focused on calculi or high-level programminglanguages, and existing type systems for low-level languages typically omit objects, exceptions and method calls. We define an information flow type system for a sequential JVM-like language that includes all these programming features, and we prove, in the Coq proof assistant, that it guarantees non-interference. An additional benefit of the formalisation is that we have extracted from our proof a certified lightweight bytecode verifier for information flow. Our work provides, to the best of our knowledge, the first sound and certified information flow type system for such an expressive fragment of the JVM.
System development using java and distributed object technology (DOT) is becoming common, and tan become the standard way of doing network computing in the near future. The performance of DOTs is crucial in high-perfo...
详细信息
System development using java and distributed object technology (DOT) is becoming common, and tan become the standard way of doing network computing in the near future. The performance of DOTs is crucial in high-performance network computing systems, In this paper, the performance of popular DOTs for java is evaluated in a common environment employing the fastest available PCs and 100 Mbit/s Ethernet. We evaluate HORB, java RMI, Voyager, two commercial CORBA. IIOP implementations, and Distributed COM, For comparison a java socket version and a C socket version are also evaluated. To represent the characteristics of the DOT, the performance of primitive object operations including remote object creation, remote method call, transferring arrays of objects and transferring large numerical data is measured and evaluated, No DOT won all benchmarks, but BORE showed very good performance for most benchmarks. (C) 1998 John Wiley & Sons, Ltd.
java and distributed object models are important for building modern, scalable and interoperable applications. This paper is focused on the comparison and performance analysis of four important distributed object mode...
详细信息
java and distributed object models are important for building modern, scalable and interoperable applications. This paper is focused on the comparison and performance analysis of four important distributed object models for java: RMI (Remote Method Invocation) and RMI-IIOP (Remote Method Invocation over Internet Inter-ORB Protocol), CORBA and DCOM. The paper presents a detailed performance analysis of the models and an overhead analysis to identify the bottlenecks in the models.
Konrad Zuse's Z3, built in Berlin from 1938 to 1941, was destroyed during World War II. The reconstruction project started in 1994. A functional replica was built and unveiled at a conference commemorating the 60t...
详细信息
Konrad Zuse's Z3, built in Berlin from 1938 to 1941, was destroyed during World War II. The reconstruction project started in 1994. A functional replica was built and unveiled at a conference commemorating the 60th anniversary of the public presentation of the original machine in 2001. The reconstruction project includes several java simulations of components of the whole machine and a 3D functional simulation of the Z3 and its user console.
The paper describes a distributed brute-force attack on RC5 cipher using java applets. It introduces a novel model for long-term parallel computing based on the abstraction of solvers with limited lifetime, The associ...
详细信息
The paper describes a distributed brute-force attack on RC5 cipher using java applets. It introduces a novel model for long-term parallel computing based on the abstraction of solvers with limited lifetime, The associated problems and scheduling policy are discussed. The paper comments on the inherent performance problems of the java Virtual Machine and presents performance measurements of the cipher breaking applet for several computing platforms. (C) 1998 John Whey & Sons, Ltd.
暂无评论