Luciano Ost

HERMES: an infrastructure for low area overhead packet-switching networks on chip

The increasing complexity of integrated circuits drives the research of new on-chip interconnection architectures. A network on chip draws on concepts inherited from distributed systems and computer networks subject areas to interconnect IP cores in a structured and scalable way. The main goal pursued is to achieve superior bandwidth when compared to conventional on-chip bus architectures. This paper reviews the state of the art in networks on chip. Then, it describes an infrastructure called Hermes, targeted to implement packet-switching mesh and related interconnection architectures and topologies. The basic element of Hermes is a switch with five bi-directional ports, connecting to four other switches and to a local IP core. The switch employs an XY routing algorithm, and uses input queuing. The main design objective was to develop a small size switch, enabling its immediate practical use. The paper also presents the design validation of the Hermes switch and of a network on chip based on it. A Hermes NoC case study has been successfully prototyped in hardware as described in the paper, demonstrating the functionality of the approach. Quantitative data for the Hermes infrastructure is advanced.

Accuracy evaluation of GEM5 simulator system

Design space exploration (DSE) of complex embedded systems that combine a number of CPUs, dedicated hardware and software is a tedious task for which a broad range of approaches exists, from the use of high-level models to hardware prototyping. Each of these entails different simulation speed/accuracy tradeoffs, and thereby enables exploring a certain subset of the design space in a given time. Some simulation frameworks devoted to CPU-centric systems have been developed over the past decade, that either feature near real-time simulation speed or moderate to high speed with quasi-cycle level accuracy, often by means of instruction-set simulators or binary translation techniques. This paper presents an evaluation in term of accuracy in modeling real systems using the GEM5 simulator that belong to the first class. Performance figures of a wide range of benchmarks (e.g. in domains such as scientific computing and media applications) are captured and compared to results obtained on real hardware.

MAIA: a framework for networks on chip generation and verification

The increasing complexity of SoCs makes networks on chip (NoC) a promising substitute for busses and dedicated wires interconnection schemes. However, new tools need to be developed to integrate NoC interconnection architectures and IP cores into SoCs. Such tools have to fulfill three main requirements: (i) automated NoC generation; (ii) automated production of NoC-IP core interfaces; and (iii) seamless analysis of NoC traffic parameters. The objective of this paper is to present the MAIA framework, which includes functions to address all these requirements. NoCs generated by the MAIA framework have been used to successfully prototype SoCs in FPGAs.

Multi-task dynamic mapping onto NoC-based MPSoCs

Task mapping defines the best placement of a given task in the MPSoC, according to some criteria, as energy or Manhattan distance minimization. The ITRS roadmap forecast in a near future MPSoCs with hundreds of processing elements (PEs). Therefore, dynamic mapping heuristics are required. An important gap is observed in the mapping literature: the lack of proposals targeting multi-task dynamic mapping. In this context, the present work proposes an energy-aware dynamic task mapping heuristic, allowing multiple tasks allocation per PE. Experimental results are executed in an actual MPSoC running distributed applications. Comparing a single-task to the multi-task mapping, the energy spent in the NoC is reduced in average by 51% (best case: 72%), with an average execution time overhead of 18%. Besides the communication energy reduction, the multi-task mapping enables a greater number of applications executing simultaneously, or smaller MPSoCs, which reduces the system cost.

Energy-aware dynamic task mapping for NoC-based MPSoCs

To cope with the dynamic workload of actual NoC-based MPSoCs, dynamic mechanisms are required to guarantee the application requirements. Application mapping may drastically influence the system performance and the energy consumption, which can be crucial to the success (or failure) of a product, even more for battery-powered embedded systems. In this context, the current work presents an energy-aware dynamic task mapping heuristic, which was evaluated in a real NoC-based MPSoC platform. Results show that the proposed heuristic may reduces up to 22.8% of the communication energy consumption compared to other dynamic mapping heuristics.

RTOS Scheduler Implementation in Hardware and Software for Real Time Applications

In order to enhance performance and improve predictability of the real time systems, implementing some critical operating system functionalities, like time management and task scheduling, in software and others in hardware is an interesting approach. Scheduling decision for real-time embedded software applications is an important problem in real-time operating system (RTOS) and has a great impact on system performance. In this paper, we evaluate the pros and cons of migrating RTOS scheduler implementation from software to hardware. We investigate three different RTOS scheduler implementation approaches: (i) implemented in software running in the same processor of the application tasks, (ii) implemented in software running in a co-processor, and (iii) implemented in hardware, while application tasks are running on a processor. We demonstrate the effectiveness of each approach by simulating and analyzing a set of benchmarks representing different embedded application classes

Power-aware dynamic mapping heuristics for NoC-based MPSoCs using a unified model-based approach

The mapping of tasks to processing elements of an MPSoC has critical impact on system performance and energy consumption. To cope with complex dynamic behavior of applications, it is common to perform task mapping during runtime so that the utilization of processors and interconnect can be taken into account when deciding the allocation of each task. This paper has two major contributions, one of them targeting the general problem of evaluating dynamic mapping heuristics in NoC-based MPSoCs, and another focusing on the specific problem of finding a task mapping that optimizes energy consumption in those architectures.

Exploring NoC-Based MPSoC Design Space with Power Estimation Models

This model-based methodology and supporting toolset lets designers estimate application-specific network-on-chip (NoC) power dissipation at early stages of the design flow. An actor-oriented simulation framework captures the NoCs dynamic behavior and feeds its parameters to a rate-based power estimation model. Integrating this model into the proposed design flow enables the analysis of different design parameters and the identification of the most power-efficient application platform mappings.

A simplified executable model to evaluate latency and throughput of networks-on-chip

This paper proposes a technique that mixes simulation and an analytical method to evaluate the characteristics of Networks-on-Chips (NoCs). The advantage of this technique is to reduce the simulation time by reducing the complexity of the NoC model while still obtaining accurate results for latency and throughput. The basis of this technique is: (i) to send the whole payload data at once in the packet header; (ii) to reduce the NoC simulation complexity by omitting the flit by flit payload forwarding; (iii) to use an algorithm for controlling the release of the packet trailer in order to close the connection at the right time. For the evaluation of this technique, an actor-oriented model of a NoC, JOSELITO, was created. Simulation results show that JOSELITO is in average 2.3 times faster in 88% of the executed case studies than the implementation without using the proposed technique. The worst case simulation results for latency and throughput have, respectively, 5.26% and 0.1% error compared to the corresponding Register Transfer Level (RTL) model.

Open-Scale: A Scalable, Open-Source NOC-based MPSoC for Design Space Exploration

As complexity of embedded system increases, configurable hardware is becoming more attractive because it provides a fast and efficient basis for design development. As a consequence, one of the most promising embedded architecture consists in the replication of Processing Elements (PEs) connected through a Network-on-Chip (NoC). Such architectures provide computation parallelism, scalability, and reduced design time thanks to reusability. This paper describes the development of a scalable, distributed memory, open source NoC-based platform called Open-Scale and its implementation into FPGA devices. The main objective of this platform is to provide a complete framework for research development on NoC-based distributed memory MPSoCs.