LIME: a future-proof programming model for multi-cores

نویسندگان

  • Pjotr Kourzanov
  • Orlando Moreira
  • Henk Sips
چکیده

The Less Is More (LIME) programming model addresses known programmability, compositionality, predictability, and scalability problems related to parallel programming in embedded systems of new as well as legacy code in streaming applications. With LIME, the high-level functional aspects of algorithm design and implementation are decoupled from the low-level platform-specific mechanisms pertaining to communication and synchronization. The integration of both in the end-product is assisted by a tool-chain that has complete access to the computations and has compile-time knowledge of hardware-dependent performance aspects. Rather than proposing intrusive modifications of a sequential language, LIME postulates rules and restrictions on how to express algorithms using standard C and (de)compose them using a simple XML schema for connecting components in a graph. In the paper, we describe the design rationales behind LIME and discuss its features in detail. We outline the LIME tool-chain, show how it interacts with analysis tools, and describe how multi-core back-ends are constructed. We illustrate this by showing a LIME implementation on a real-life parallel embedded platform for Software-Defined Radio (SDR) and an implementation on a commodity GPU platform.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Disciplined Multi-core Programming in C

The problem of programmability on modern heterogeneous multi-core and future many-core embedded platforms is still not solved satisfactorily: although many existing but incompatible approaches do provide new languages, language extensions and library interfaces that all focus on specific solutions, and powerful analytical models do exist, no single integrated programming model has been proposed...

متن کامل

A Novel Method for Selecting the Supplier Based on Association Rule Mining

One of important problems in supply chains management is supplier selection. In a company, there are massive data from various departments so that extracting knowledge from the company’s data is too complicated. Many researchers have solved this problem by some methods like fuzzy set theory, goal programming, multi objective programming, the liner programming, mixed integer programming, analyti...

متن کامل

Designing a new multi-objective fuzzy stochastic DEA model in a dynamic ‎environment to estimate efficiency of decision making units (Case Study: An Iranian Petroleum Company)

This ‎paper presents a new multi-objective fuzzy stochastic data envelopment analysis model          (MOFS-DEA) under mean chance constraints and common weights to estimate the efficiency of decision making units for future financial periods of them. In the initial MOFS-DEA ‏model, the outputs and inputs are ‎characterized by random triangular fuzzy variables with normal distribution, in which ...

متن کامل

An Optimization Model for Multi-objective Closed-loop Supply Chain Network under uncertainty: A Hybrid Fuzzy-stochastic Programming Method

In this research, we address the application of uncertaintyprogramming to design a multi-site, multi-product, multi-period,closed-loop supply chain (CLSC) network. In order to make theresults of this article more realistic, a CLSC for a case study inthe iron and steel industry has been explored. The presentedsupply chain covers three objective functions: maximization ofprofit, minimization of n...

متن کامل

Accelerator Exoskeleton

To maximize performance and power efficiency, future multi-core architectures may be heterogeneous, incorporating some accelerator cores alongside the IA cores. Accelerator Exoskeletons provide a shared virtual memory heterogeneous multi-threaded programming paradigm for these accelerators using novel CPU instruction set extensions and software tool chains with an Intel Architecture (IA) look-n...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2008