A. Adl-Tabatabai, M. Cierniak, G. Lueh, V. Parikh, and J. Stichnoth. Fast,Effective Code Generation in a Just-In-Time Java Compiler. In Proceedings of the ACM SIGPLAN '98 Conference on Programming Language Design and Implementation, October 2000.  Home/Search   Document Not in Database   Summary   Related Articles   Check

.... compilers (one simple and very fast and the other optimizing) For this research, we use an open source, dual compiler system called the Open Runtime Platform (ORP) which was recently released by the Intel Corporation [18] The first compiler (O1) provides very fast translation of Java programs [1] and incorporates a few very basic bytecode optimizations that improve execution performance. The second (O3) compiler performs a small number of commonly used optimizations on bytecode and an intermediate form to produce improved code quality and execution time. O3 optimization algorithms were ....

A. Adl-Tabatabai, M. Cierniak, G. Lueh, V. Parikh, and J. Stichnoth. Fast,Effective Code Generation in a Just-In-Time Java Compiler. In Proceedings of the ACM SIGPLAN '98 Conference on Programming Language Design and Implementation, October 2000.

....by the platform independentstack machine model targeted byJava compilers. On the target machine, this intermediate code representation is either interpreted [13] or compiled into native code using traditional ahead of time [11] or just in time This work supported in part by CAPES. 1 compilers [16,1,3,10,14,26,27]. The safety features of the language are based on the security violation checks performed at load and run time [17] Suchchecks include enforcement of method and variable access modifiers, strict type checking and arrayboundschecking. Manyofthesechecks are implicit in the bytecodes, forcing the ....

.... When compilation time is not a constraint, the most common approach is to translate Javabytecode into some higher level program representation [5,11,21] and then finally to native code (perhaps using an existing compiler, as in [21] When speed of compilation is an issue, optimizing JIT compilers [16,1,3,10,14, 26, 27] try to improve the quality of the native code generated on the fly by adapting traditional optimization techniques to run time code generation. Optimizations can also be applied during load time, i.e. after bytecode generation yet before run time translation to native code# [6, 23] are examples ....

[Article contains additional citation context not shown here]

A. Adl-Tabatabai, M. Cierniak, G. Lueh, V. M. Parikh, and J. M. Stichnoth. Fast, Effective Code Generation in a Just-In-Time Java Compiler. Proceedings of ACM Programming Languages Design and Implementation, pages 280--290, 1998.

....parallel programming. HPJava is somewhat similar to HPF and is designed for SPMD programming. Several projects are developing optimizers for Java. Moreira et al. 26] are developing a static compiler that optimizes array bounds checks and null pointer checks within loops. Adl Tabatabai et al. [1] have developed a JIT compiler that performs a set of optimizations, including subexpression elimination, register 16 allocation, and the elimination of array bounds checking. Such optimizations may allow us to bridge the performance gap between our version with bounds checking and our version ....

A.-R. Adl-Tabatabai, M. Cierniak, G.-Y. Lueh, V. M. Parikh, and J. M. Stichnoth. Fast, effective code generation in a just-in-time Java compiler. In Proceedings of PLDI'98, pages 280--290, Montreal, Canada, June 1998.

....various performance characteristics (invocation count, execution duration, loop count, etc. When measured values reach a given threshold the method (or method piece) is optimized using an optimizing compiler. Compilers in the system are invoked for initial method invocation (demarcated with [1] in the figure) by the on line measurement system (profiler) or by the class loader (demarcated with [2] in the figure) The class loader can load classes from the local disk or across a network. In the following sections, we first describe Self, an adaptive compilation system for programs ....

....replaced with optimized versions. Open Runtime Platform (ORP) A dual compiler, adaptive compilation system for Java, called the Open Runtime Platform (ORP) was recently released as open source by the Intel Corporation [65] The first compiler (O1) provides very fast translation of Java programs [1] and incorporates a few very basic bytecode optimizations that improve execution performance. The second (O3) compiler performs a small number of commonly used optimizations on bytecode and an intermediate form to produce improved code quality and execution time. O3 optimization algorithms were ....

[Article contains additional citation context not shown here]

A. Adl-Tabatabai, M. Cierniak, G. Lueh, V. Parikh, and J. Stichnoth. Fast,Effective Code Generation in a Just-In-Time Java Compiler. In Proceedings of the ACM SIGPLAN '98 Conference on Programming Language Design and Implementation, October 2000.

....October 15 19, 2000. choose compilation targets, typically compiling each method with a fixed set of optimizations the first time it was invoked. These virtual machines include early work such as the Smalltalk 80 [24] and Self 91 [16] systems, as well as a number of more recent Java systems [1, 36, 14, 47]. A second wave of more sophisticated virtual machines moved beyond this simple strategy by dynamically selecting a subset of all executed methods for optimization, attempting to focus optimization effort on program hot spots. Systems in this category include Self 93 [32] the HotSpot JVM [34] ....

....data from previous executions of an application. There are also nonadaptive systems that perform compilation optimization at runtime to avoid the cost of interpretation. This includes early work such as the Smalltalk 80 [24] and Self 91 [16] systems, as well many of today s JIT Java compilers [1, 36, 47]. Previous studies have evaluated the viability of selective optimization. Arnold et al. 6] used the Jalape no JVM to quantify the performance potential of selective optimization. Their results confirmed that selective optimization has the potential to significantly outperform a fixed JIT ....

A.-R. Adl-Tabatabai, M. Cierniak, C.-Y. Lueh, V. M. Parikh, and J. M. Stichnoth. Fast, effective code generation in a Just-in-Time Java compiler. In Proceedings of the ACM SIGPLAN'98 Conference on Programming Language Design and Implementation (PLDI), pages 280--290, Montreal, Canada, 17--19 June 1998. SIGPLAN Notices 33(5), May 1998.

....property of the language is ensured by the platform independent stack machine model targeted by Java compilers. On the target machine, this intermediate code representation is either interpreted [17] or compiled into native code using traditional ahead of time [14] or just in time compilers [1, 2, 16, 18, 24]. The safety features of the language are based on the security violation checks performed at load and run time [11] Such checks include enforcement of methods and variables access modifiers, strict typechecking and array bounds checking. Many of these checks are implicit in the bytecodes, ....

.... time is not a constraint, the most common approach is to translate the bytecodes into some higher level intermediate form [7, 14] or language [21] and then back to native code (perhaps using an existing compiler, as in [21] When speed of compilation is an issue, optimizing JIT compilers [1, 2, 16, 18, 24] try to improve the quality of the native code generated on the fly by adapting traditional optimization techniques to run time code generation. Optimizations can also be applied during load time, i.e. after bytecode generation yet before run time translation to native code; 8] is an example of ....

[Article contains additional citation context not shown here]

A. Adl-Tabatabai, M. Cierniak, G. Lueh, V. M. Parikh, and J. M. Stichnoth. Fast, Effective Code Generation in a Just-In-Time Java Compiler. Proceedings of ACM Programming Languages Design and Implementation, pages 280--290, 1998.

....parallel programming. HPJava is somewhat similar to HPF and is designed for SPMD programming. Several projects are developing optimizers for Java. Moreira et al. 21] are developing a static compiler that optimizes array bounds checks and null pointer checks within loops. Adl Tabatabai et al. [1] have developed a JIT compiler that performs a set of optimizations, including subexpression elimination, register allocation, and the elimination of array bounds checking. Such optimizations may allow us to bridge the performance gap between our version with bounds checking and our version ....

A.-R. Adl-Tabatabai et al. Fast, effective code generation in a just-in-time Java compiler. In Proc. PLDI'98, pages 280--290, Montreal, Canada, June 1998.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC