MétaCan
Menu
Back to cohort
Record W2513926952

Optimizing the java virtual machine instruction set by despecialization and multicode substitution

2006· article· en· W2513926952 on OpenAlexaff
Ben Stephenson

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicParallel Computing and Optimization Techniques
Canadian institutionsWestern University
Fundersnot available
KeywordsComputer scienceJava annotationJavaJava appletstrictfpJava concurrencyGenerics in JavaProgramming languageJava Modeling LanguageReal time JavaBytecodeOperating system
DOInot available

Abstract

fetched live from OpenAlex

Since its public introduction; Java has grown into one of the most widely used programming languages. Its popularity can be attributed to the wide variety of features that it provides, including platform independence. In order to achieve platform independence, Java applications are represented by a set of binary, platform independent Java class files. Within the class files, the functionality of each Java method is expressed using a sequence of Java bytecodes. This thesis examines the set of Java bytecodes defined by the Java Virtual Machine Specification, and describes two techniques that have been developed for manipulating the set. When the current set of Java bytecodes was analyzed, it was discovered that over one third of the bytecodes were specialized, redundant bytecodes. In many cases, these provided functionality that was easily replicated using one other bytecode. In a small number of other cases, a short sequence of bytecodes was used in order to achieve identical functionality. The Java class files for a set of standard benchmarks were transformed so that uses of specialized bytecodes were removed. Performance testing revealed that this transformation increased average execution Lime by approximately 2.0 percent when 67 specialized bytecodes were replaced with their equivalent general-purpose forms. The impact this transformation had on class file size and the correctness of the class files was also examined. A second transformation, which has come to be known as multicode substitution, was also developed. It employed profiling in order to determine which sequences of bytecodes executed with greatest frequency. A new Java bytecode, known as a multicode, was introduced for each frequently executed bytecode sequence. Performing this transformation reduced the total number of bytecodes executed by the application, improving Java interpreter performance by reducing the number of transfers of control from one bytecode to the next. Furthermore, performing this transformation presented additional optimization opportunities within the implementation of the multicode. Such optimizations could not be exploited previously because of the presence of the intervening transfers of control. When performance testing was conducted using industry standard benchmarks, performing multicode substitution reduced application runtime by as much as 30 percent. Keywords. Java Virtual Machine. Java Bytecode, Instruction Set Design, Optimization, Multicode Substitution, Despecialization

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.806
Threshold uncertainty score0.292

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.011
GPT teacher head0.235
Teacher spread0.224 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2006
Admission routes1
Has abstractyes

Explore more

Same topicParallel Computing and Optimization TechniquesFrench-language works237,207