Christophe Poucet

Custom design of multi-level dynamic memory management subsystem for embedded systems

In this paper, we propose a new approach to design convenient dynamic memory management subsystems, profiting from the multiple memory levels. It analyzes the logical phases involved in modem dynamic applications to effectively distribute the dynamically allocated data among the multi-level memory hierarchies present in embedded devices. We assess the effectiveness of the proposed approach for three representative real-life case studies of the new dynamic application domains (i.e., network and 3D rendering applications) ported to embedded systems. The results accomplished with our approach show a very significant reduction in energy consumption (up to 40%) over state-of-the-art solutions for dynamic memory management on embedded systems with typical cache-main memory architectures while respecting the real-time requirements of these applications.

Software metadata: Systematic characterization of the memory behaviour of dynamic applications

Development of new embedded systems requires tuning of the software applications to specific hardware blocks and platforms as well as to the relevant input data instances. The behaviour of these applications heavily relies on the nature of the input data samples, thus making them strongly data-dependent. For this reason, it is necessary to extensively profile them with representative samples of the actual input data. An important aspect of this profiling is done at the dynamic data type level, which actually steers the designers choice of implementation of these data types. The behaviour of the applications is then characterized, through an analysis phase, as a collection of software metadata that can be used to optimize the system as a whole. In this paper we propose to represent the behaviour of data-dependent applications to enable optimizations, rather than to analyze their structure or to define the engineering process behind them. Moreover, we specifically limit ourselves to the scope of applications dominated by dynamically allocated data types running on embedded systems. We characterize the software metadata that these optimizations require, and we present a methodology, as well as appropriate techniques, to obtain this information from the original application. The optimizations performed on a complete case study, utilizing the extracted software metadata, achieve overall improvements of up to 42% in the number of cycles spent accessing memory when compared to code optimized only with the static techniques applied by GNU G++.

Optimization methodology of dynamic data structures based on genetic algorithms for multimedia embedded systems

Modern multimedia application exhibit high resource utilization. In order to efficiently run this kind of applications in embedded systems, the dynamic memory subsystem needs to be optimized. A key role in this optimization is played by the dynamic data structures that reside in every real-life application. This paper presents a novel and automated way to optimize dynamic data structures. The search space is pruned using genetic algorithms that converge to the best multilayered data structure implementation for the targeted applications.

Energy-efficient dynamic memory allocators at the middleware level of embedded systems

The next generation of embedded systems will be dominated by mobile devices, which are able to deliver communications and rich multimedia content anytime, anywhere. The major themes in these ubiquitous computing systems are applications with increased user control and interactivity with the environment. Therefore, the storage of dynamic data increases, thus making the dynamic memory allocation of heap data at run time a very important component with heavy energy consumption. In this paper, we propose a novel script, which heavily customizes the dynamic memory allocator according to the target application domain and the underlying memory hier-archy of the embedded system. The dynamic memory allocator resides in the middleware level or in the Operating System level (whenever it is available). The result of our script and automated tools is the reduction of energy consumption by 72% on average and the reduction of the execution time by 40% on average, which is demonstrated with the use of 1 real life wireless network appli-cation and 1 multimedia application.

Optimization of dynamic data structures in multimedia embedded systems using evolutionary computation

Embedded consumer devices are increasing their capabilities and can now implement new multimedia applications reserved only for powerful desktops a few years ago. These applications share complex and intensive dynamic memory use. Thus, dynamic memory optimizations are a requirement when porting these applications. Within these optimizations, the refinement of the Dynamically (de)allocated Data Type (or DDT) implementations is one of the most important and difficult parts for an efficient mapping onto low-power embedded devices. In this paper, we describe a new automatic optimization approach for the DDTs of object-oriented multimedia applications. It is based on an analytical pre-characterization of the possible elementary DDT blocks, and a multi-objective genetic algorithm to explore the design space and to select the best implementation according to different optimization criteria (i.e., memory accesses, memory footprint and energy consumption). Our results in real-life multimedia applications show that the best implementations of DDTs can be obtained in an automated way in few hours, while typically designers would require days to find a suitable implementation, achieving important savings in exploration time with respect to other state-of-the-art heuristics-based optimization methods for this task.

Template-Based Semi-Automatic Profiling of Multimedia Applications

Modern multimedia applications possess a very dynamic use of the memory hierarchy depending on the actual input, therefore requiring run-time profiling techniques to enable optimizations. Because they can contain hundreds of thousands of lines of complex object-oriented specifications, this constitutes a tedious time-consuming task since the addition of profilecode is usually performed manually. In this paper, we present a high-level library-based approach for profiling both statically and dynamically defined variables using templates in C++. Our results in the visual texture coder of the MPEG4 standard show that using the information it provides, we can easily achieve 70.56% energy savings and 19.22% memory access reduction

Automated Exploration of Pareto-optimal Configurations in Parameterized Dynamic Memory Allocation for Embedded Systems

New applications in embedded systems are becoming increasingly dynamic. In addition to increased dynamism, they have massive data storage needs. Therefore, they rely heavily on dynamic, run-time memory allocation. The design and configuration of a dynamic memory allocation subsystem requires a big design effort, without always achieving the desired results. In this paper, we propose a fully automated exploration of dynamic memory allocation configurations. These configurations are fine tuned to the specific needs of applications with the use of a number of parameters. We assess the effectiveness of the proposed approach in two representative real-life case studies of the multimedia and wireless network domains and show up to 76% decrease in memory accesses and 66% decrease in memory footprint within the Pareto-optimal trade-off space

Dynamic Memory Management Optimization for Multimedia Applications

As already introduced in the first two chapters of this book, due to increasing complexity and drastic rise in memory requirements, new system-level memory management methodologies for multimedia applications need to be developed.

Dynamic Memory Management for Embedded Systems

This book provides a systematic and unified methodology, including basic principles and reusable processes, for dynamic memory management (DMM) in embedded systems. The authors describe in detail how to design and optimize the use of dynamic memory in modern, multimedia and network applications, targeting the latest generation of portable embedded systems, such as smartphones. Coverage includes a variety of design and optimization topics in electronic design automation of DMM, from high-level software optimization to microarchitecture-level hardware support. The authors describe the design of multi-layer dynamic data structures for the final memory hierarchy layers of the target portable embedded systems and how to create a low-fragmentation, cost-efficient, dynamic memory management subsystem out of configurable components for the particular memory allocation and de-allocation patterns for each type of application. The design methodology described in this book is based on propagating constraints among design decisions from multiple abstraction levels (both hardware and software) and customizing DMM according to application-specific data access and storage behaviors.

Systematic intermediate sequence removal for reduced memory accesses

Modern software applications are growing in complexity and demand very intensive use of data. Therefore, a wide variety of data structures are utilized to facilitate the storage and access to these vast amounts of computed information. Additionally, the need for reliable software design and the development of large applications following the object-oriented paradigm increase the amount of dynamic buffers and redundant accesses to the data stored in these buffers. In this paper, we propose a systematic, design optimization methodology to remove these intermediate dynamic buffers, thereby reducing the memory accesses of the targeted applications without altering the input-output behaviour of the algorithms. The reduction is focused on sequences and is especially relevant for embedded systems, which have limited on-chip communication bandwidth and the energy consumption of the memory subsystem is high, due to the energy consumption associated with each memory access. The effectiveness of the proposed methodology is assessed in a 3D reconstruction multimedia application and shows a significant reduction in memory accesses. In addition, the general trends for memory improvement and the scalability of our approach are supported as well by a parameterized benchmark set.