• KIPS Transactions on Computer and Communication Systems
• /
• v.2 no.6
• /
• pp.231-236
• /
• 2013

Recently, to improve the user response times of Android applications, several studies have been proposed to combine the idea of Ahead-of-Time compilation into Dalvik virtual machine, which uses Just-in-Time compilation. The studies, however, require modifications of the Dalvik executables of target applications, thus are difficult to be adopted for legacy applications already deployed. This paper proposes a JITwP(JIT with Precompile) technique that precompiles hot traces at application launch time with no modification of the Dalvik executable. It improves the user response times of target applications by providing precompile hints prepared offline. Our experimental results demonstrate a 4% improvement in terms of execution time for the Web browser application.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.560-565
• /
• 2010

가상 머신은 중간코드로 컴파일 되어 한 프로그램을 여러 플랫폼에서 수행 가능하게 한다. 이러한 가상 머신에는 이미 널리 알려진 썬 마이크로시스템즈의 자바 가상 머신과 구글의 안드로이드 플랫폼의 달빅 가상 머신 그리고 애플이 지원하는 LLVM 등이 있으며, 파이어폭스의 TraceMonkey, 구글 크롬의 v8, 사파리의 SquirrelFish Extreme 같은 자바스크립트 엔진도 일종의 가상 머신으로 볼 수 있다. 가상 머신은 필연적으로 성능 저하를 동반하게 되는데, 이는 가상 머신의 주요 이슈 중 하나이다. 본 논문에서는 간단한 벤치마크를 통해서 이들 가상 머신간의 성능을 비교하고, 각 가상 머신의 특징을 알아본다. LLVM은 여러 단계에 걸친 컴파일 전략으로 JIT 컴파일을 사용하였을 때 높은 성능을 보이나 JIT 컴파일을 사용하지 않았을 경우는 매우 낮은 성능을 보인다. 달빅 가상 머신은 인터프리터 모드에서 자바 가상 머신 보다 조금 나았으나, 아직 개발된 지 얼마 되지 않아 JIT 컴파일러가 없다는 것이 약점이다. 자바스크립트 엔진들은 동적 언어인 자바스크립트를 지원하는 특성상 최적화를 적용하지 못해 비교적 낮은 성능을 보였다.

• Communications of the Korean Institute of Information Scientists and Engineers
• /
• v.16 no.4
• /
• pp.5-8
• /
• 1998

• Journal of KIISE:Software and Applications
• /
• v.32 no.12
• /
• pp.1283-1291
• /
• 2005

One of the problems in boosting Java performance using a Just-in-Time (JIT) compiler is removing redundant array bound checks. In conventional static compilers, many powerful algorithms have been developed, yet they are not directly applicable to JIT compilation where the compilation time is part of the whole running time. In the current JIT compilers, we tan use either a naive algorithm that is not powerful enough or an aggressive algorithm which requires the transformation into a static single assignment (SSA) form of programs (and back to the original form after optimization), thus causing too much overhead not appropriate for JIT compilation This paper proposes a new algorithm based on an inequality graph which can eliminate array bounds check codes aggressively without resorting to the SSA form. When we actually perform this type of optimization, there are many constraints in code motion caused by the precise exception rule in Java specification, which would cause the algorithm to miss many opportunities for eliminating away bound checks. We also propose a new method to overcome these constraints.

• Journal of Software Engineering Society
• /
• v.28 no.1
• /
• pp.1-6
• /
• 2019

Google released an initial version of Android that runs Dex(Dalvik Executable) through the Dalvik Runtime. Since Dalvik Runtime is based on interpreter, JIT(Just-in-time) compilation has been applied to improve performance. After Lollipop(Android 5.0) Dalvik Runtime has replaced with ART Runtime which support AOT (Ahead-of-time) compilation of Dex into Native Code. The late st Android has a problem that the application execution speed is slow until the AOT compilation is completed according to the actual usage record after the installation of the app. To improve the problem we have investigate the characteristics of profile that can improve the execution speed of the application and generate the profile automatically. Finally we propose a method that can optimize the application at install time. With the proposed method we can optimize selectively at install time and can help improving the execution speed of the app from the initial execution.

• The Korean Journal of Applied Statistics
• /
• v.33 no.6
• /
• pp.665-682
• /
• 2020

This paper introduces numba library in Python, which improves computational efficiency of the provided implemented code written by naive Python language by applying just-in-time (JIT) compilation. To apply just-in-time compilation, the numba only needs to use a decorator on a target Python function. We provide implementation examples with numba for the permutation test and the parameter estimation for Gaussian mixture distribution. We also numerically show the efficiency of numba by comparing the total computation times of the implementation using naive python and the implementation using numba for each application.

• The KIPS Transactions:PartA
• /
• v.12A no.1 s.91
• /
• pp.59-64
• /
• 2005

In this paper, we propose a method of generating a JIT compiler using JBURG. JBURG is a tool of generating the code generator using bottom-up tree pattern matching for Java. Our method can be derived from some relations over tree patterns. The proposed scheme is more efficient than JBURG because we can avoid unfruitful tests with the smaller site of the scheme. Furthermore, the relevant analyses needed for this proposal are largely achieved at non- compile time, which secures actual efficiency at compilation time.

• Journal of KIISE:Software and Applications
• /
• v.32 no.3
• /
• pp.215-226
• /
• 2005

Loop invariant code motion (LICM) optimization includes relatively heavy code analyses, thus being not readily applicable to Java Just-In-Time (JIT) compilation where the JIT compilation time is part of the whole running time. 'Classical' LICM optimization first analyzes the code and constructs both the def-use chains and the use-def chains. which are then used for performing code motions. This paper proposes a light-weight LICM algorithm, which requires only the def-use chains of loop invariant code (without use-def chains) by exploiting the fact that the Java virtual machine is based on a stack machine, hence generating code with simpler patterns. We also propose two techniques that allow more code motions than classical LICM techniques. First, unlike previous JIT techniques that uses LICM only in single-path loops for simplicity, we apply LICM to multi-path loops (natural loops) safely for partially redundant code. Secondly, we move loop-invariant, partially-redundant null pointer check code via predication support in Itanium. The proposed techniques were implemented in a JIT compiler for Itanium processor on ORP (Open Runtime Platform) Java virtual machine of Intel. On SPECjvrn98 benchmarks, the proposed technique increases the JIT compilation overhead by the geometric mean of 1.3％, yet it improves the total running time by the geometric mean of 2.2％.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10a
• /
• pp.766-768
• /
• 2004

자바는 객체 지향 언어이고, 분산 환경을 지원하고, 플랫폼에 독립적인 장정을 갖지만 다른 C나 C++같은 컴파일언어에 비해서는 실행속도가 느리다는 단점을 가진다. 이러한 단점을 극복하기 위한 방법으로 네이티브 코드로의 변환, 코드 최적화, JIT 컴파일 방법 등을 이용한다. 그러나 이전 방법들은 다음과 같은 한계점을 가진다. 클래스 파일을 네이티브 코드로의 변환은 플랫폼의 종속되고, 코드 최적화 방법은 고유의 최적화 방법만을 적용할 수 있었고, JIT컴파일 방법은 한 번의 실행 후 다음 실행해야 속도향상을 꾀할 수 있었다. 본 논문은 바이트 코드를 최적화하기 위한 자바최적화 프레임워크를 설명하고 자바최적화 프레임워크의 구성을 하는 부분 중 3주소형식의 중간코드를 스택기반 코드로 변환하는 부분을 설계하고. 3주소 코드로 변환한 중간 코드를 스택 기반 코드로 변환하면서 생기는 과다한 load/store의 문제점을 지적하고 그것을 해결할 수 있는 변환기를 제안한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.11B
• /
• pp.1323-1328
• /
• 2011

In this paper, we have shown Dalvik virtual machine implementation to reduce the profiling overhead from the trace of the JIT compiler for the specific method. By running the same Java method on the original Dalvik VM and the modified Dalvik VM, we have achieved around 30% performance improvement with this algorithm. In this paper, to increase the reader's understanding of Android Dalvik virtual machine, we will explain the architecture of Dalvik JIT compiler and we will provide the detailed explanation with source codes for modified parts of Dalvik virtual machine. From the industry perspective, we can expect competitive benefits over the competitors with performance improvement in Android core.