Miguel Peón-Quirós

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++.

Enabling run-time memory data transfer optimizations at the system level with automated extraction of embedded software metadata information

The information about the run-time behavior of software applications is crucial for enabling system level optimizations for embedded systems. This embedded Software Metadata information is especially important today, because several complex multi-threaded applications are mapped on the memory of a single embedded system. Each thread is triggered at run-time by different input events that can not be predicted at design-time. New methods and tools are needed to automatically profile and analyze the dynamic data access behavior of simultaneously executing threads in order to enable memory data transfer optimizations. In this paper, we propose such a method and tool which extract the necessary Software Metadata information to enable these data transfer optimizations at the system level. We assess the effectiveness of our approach with the results for five real-life software applications using seven real-life run-time input traces.

The nearest replica can be farther than you think

Modern distributed systems are geo-distributed for reasons of increased performance, reliability, and survivability. At the heart of many such systems, e.g., the widely used Cassandra and MongoDB data stores, is an algorithm for choosing a closest set of replicas to service a client request. Suboptimal replica choices due to dynamically changing network conditions result in reduced performance as a result of increased response latency. We present GeoPerf, a tool that tries to automate the process of systematically testing the performance of replica selection algorithms for geo-distributed storage systems. Our key idea is to combine symbolic execution and lightweight modeling to generate a set of inputs that can expose weaknesses in replica selection. As part of our evaluation, we analyzed network round trip times between geographically distributed Amazon EC2 regions, and showed a significant number of daily changes in nearest-K replica orders. We tested Cassandra and MongoDB using our tool, and found bugs in each of these systems. Finally, we use our collected Amazon EC2 latency traces to quantify the time lost due to these bugs. For example due to the bug in Cassandra, the median wasted time for 10% of all requests is above 50 ms.

Direct memory access optimization in wireless terminals for reduced memory latency and energy consumption

Today, wireless networks are becoming increasingly ubiquitous. Usually several complex multi-threaded applications are mapped on a single embedded system and all of them are triggered by a single wireless stream (which corresponds to the dynamic run-time behavior of the user). It is almost impossible to analyze these systems fully at design-time. Therefore, run-time information has also to be used in order to produce an efficient design. This introduces new challenges, especially for embedded system designers using a Direct Memory Access (DMA) module, who have to know in advance the memory transfer behavior of the whole system, in order to design and program their DMA efficiently. In this paper, we propose a mixed Hardware/Software optimization at system level. More specifically, we propose to adapt DMA usage parameters automatically at run-time based on online information. With our proposed optimization approach we manage to reduce the mean latency of the memory transfers while optimizing energy consumption and system responsiveness. We evaluate our approach using a set of real-life applications and real wireless dynamic streams.

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.

Toward Automated Testing of Geo-Distributed Replica Selection Algorithms

Many geo-distributed systems rely on a replica selection algorithms to communicate with the closest set of replicas. Unfortunately, the bursty nature of the Internet traffic and ever changing network conditions present a problem in identifying the best choices of replicas. Suboptimal replica choices result in increased response latency and reduced system performance. In this work we present GeoPerf, a tool that tries to automate testing of geo-distributed replica selection algorithms. We used GeoPerf to test Cassandra and MongoDB, two popular data stores, and found bugs in each of these systems.

Intermediate Variable Removal from Dynamic Applications

Modern software applications for embedded systems have massive data storage and transfer needs. This is particularly true for applications that need to deliver a rich multimedia experience to the final user.

Systematic Placement of Dynamic Objects Across Heterogeneous Memory Hierarchies

In the previous chapters we have explained how to improve different aspects of the memory subsystem when dynamic memory is used in an embedded system. In particular, we explained how to design efficient custom dynamic memory managers to serve the dynamic memory requests of the applications.

Dynamic Data Types Optimization in Multimedia and Communication Applications

In future technologies of nomadic embedded systems an increasing amount of applications (e.g., 3D games, video-players) coming from the general-purpose domain need to be mapped onto an extremely compact device. Furthermore, the general trend of ubiquitous mobile access pushes developers to provide cross-platform applications with the same characteristics across a set of devices and desktop systems. Smartphones, tablets, in-car entertainment and navigation systems offer access to the same applications that traditionally run on PCs and servers. However, these new embedded systems, struggle to execute these complex applications because they come from desktop systems, holding very different restrictions regarding memory use features, and more concretely not concerned with an efficient use of the dynamic memory.

Profiling and Analysis of Dynamic Applications

As explained in Chap. 2, the problem of optimizing the design of dynamic embedded systems lays on exploiting as much as possible static (design-time) knowledge on the applications, but still leaving space for run-time considerations that allow tackling dynamic variations without resorting to worst case solutions. This requires extensive information about the static and dynamic characteristics of the applications. However, there is not a standard definition or representation of software metadata to typify the characteristics of the dynamic data access behavior of applications because of varying inputs.