Modern embedded systems integrate more and more complex functionalities. At the same time, the semiconductor technology advances enable to increase the amount of hardware resources on a chip for the execution. Massively parallel embedded systems specifically deal with the optimized usage of such hardware resources to efficiently execute their functionalities. The design of these systems mainly relies on the following challenging issues: first, how to deal with the parallelism in order to increase the performance; second, how to abstract their implementation details in order to manage their complexity; third, how to refine these abstract representations in order to produce efficient implementations. This article presents the Gaspard design framework for massively parallel embedded systems as a solution to the preceding issues. Gaspard uses the repetitive Model of Computation (MoC), which offers a powerful expression of the regular parallelism available in both system functionality and architecture. Embedded systems are designed at a high abstraction level with the MARTE (Modeling and Analysis of Real-time and Embedded systems) standard profile, in which our repetitive MoC is described by the so-called Repetitive Structure Modeling (RSM) package. Based on the Model-Driven Engineering (MDE) paradigm, MARTE models are refined towards lower abstraction levels, which make possible the design space exploration. By combining all these capabilities, Gaspard allows the designers to automatically generate code for formal verification, simulation and hardware synthesis from high-level specifications of high-performance embedded systems. Its effectiveness is demonstrated with the design of an embedded system for a multimedia application.

As technology scales for increased circuit density and performance, the management of power consumption in system-on-chip (SoC) is becoming critical. Today, having the appropriate electronic system level (ESL) tools for power estimation in the design flow is mandatory. The main challenge for the design of such dedicated tools is to achieve a better tradeoff between accuracy and speed. This paper presents a consumption estimation approach allowing taking the consumption criterion into account early in the design flow during the system cosimulation. The originality of this approach is that it allows the power estimation for both white-box intellectual properties (IPs) using annotated power models and black-box IPs using standalone power estimators. In order to obtain accurate power estimates, our simulations were performed at the cycle-accurate bit-accurate (CABA) level, using SystemC. To make our approach fast and not tedious for users, the simulated architectures, including standalone power estimators, were generated automatically using a model driven engineering (MDE) approach. Both annotated power models and standalone power estimators can be used together to estimate the consumption of the same architecture, which makes them complementary. The simulation results showed that the power estimates given by both estimation techniques for a hardware component are very close, with a difference that does not exceed 0.3%. This proves that, even when the IP code is not accessible or not modifiable, our approach allows obtaining quite accurate power estimates that early in the design flow thanks to the automation offered by the MDE approach.

No abstract

No abstract

No abstract

No abstract

The relationship between CPU and hardware accelerator is critical especially in some systems that require intensive tasks and large amount of data to deal with such as video coding systems. This cooperation provides significant improvements in run-time speed and power consumption. As software (SW) and hardware (HW) solutions provide better flexibility and performance, HW/SW implementation has emerged as a more efficient and desirable methodology for real-time implementation. In order to evaluate different implementation methods (SW) and (HW/SW) in terms of power consumption, run-time and area cost, we choose the Xilinx Zynq-based FPGA as a target to perform some hardware acceleration tasks. In this case, we choose to accelerate the intra prediction block because it is one of the most complex modules defined in the high efficiency video coding decoder chain. Experimental results show that HW/SW accelerations are more than 50% improved in term of run-time speed relative to SW modules. Moreover, the power consumption of HW/SW designs is saved by nearly 80% compared with SW cases.

SummaryTwo main design methods are currently widely adopted in dealing with complex signal processing algorithms. The first method is based on low‐level synthesis (LLS), which consists in writing the hardware description languages (HDL) code manually. However, the second method, called high‐level synthesis (HLS), generates the register transfer level (RTL) description automatically starting from a high‐level description language. The challenge in this paper was to study the impact of both design methods on such a complex application as the High Efficiency Video Coding (HEVC) decoder. With this end in view, we analyzed the complexity of the HEVC decoder in a software environment using version 10 of the HEVC test model (HM) reference software to determine which portions tended to get optimized. The combined architecture for the intra prediction (IP) and the inverse quantization and transform (IQ/IT) was then implemented in hardware using HLS and LLS. The findings obtained under the Xilinx Zynq 7045‐based field‐programmable gate array (FPGA) proved that the HLS implementation enabled a gain of about 80% in Look Up Table (LUTs) with an increase of 93% in DSP blocks compared with LLS implementation. Yet only the LLS solution could achieve the real‐time decoding of 4K@26fps instead of the 1080p@24fps by the HLS design.