This paper describes the work carried out to extend the NOEL-V platform to include data-level parallelism (DLP) by implementing an integer subset of the RISC-V Vector Extension. The performance and resource utilization efficiency of the resulting vector processor for different levels of DLP (i.e., number of lanes) have been compared to the baseline scalar processor on a Xilinx Kintex Ultrascale field-programmable gate array, employing typical kernels for compute-intensive applications. The role of the memory subsystem has also been investigated, comparing the results obtained with a low-latency and a high-latency main memory. The results show that the speed-up due to the use of the vector pipeline increases with the number of lanes in the vector processor, achieving up to 23.0× the performance of the scalar processor with only 4.3× the resources of the baseline scalar processor. Using an implementation with 32 lanes increases performance even for problem sizes larger than the number of lanes, achieving up to more than 11.7× the performance of the scalar processor with just 1.9× its resource utilization for 128 × 128 matrix multiplications. This work proves that implementations of the selected subset are easily scalable and fit for small-processor implementations in highly constrained space embedded systems.

@en

RISC-V is an open and modular Instruction Set Architecture(ISA) which is rapidly growing in popularity in terrestrial applications. This paper presents the place in future space embedded systems ESA's roadmap for RISC-V based processors. In order to satisfy different applications with contrasting requirements in satellite data systems, four different types of processors are identified: 1) General-Purpose (GP) processors for payloads 2) main platform On-Board Computers (OBCs) controllers 3) low-area/low-power microcontrollers (uCs), 4) enhanced payload processors with support for Artificial Intelligence (AI). We also describe the state of the art of the RISC-V software ecosystem, including the currently available hardware platforms, with a focus on developments for space applications and what has already been done in the European Space Industry. Finally, planned activities are presented, with a focus on the role of the European ecosystem.@en

The use of deep neural networks (DNNs) in terrestrial applications went from niche to widespread in a few years, thanks to relatively inexpensive hardware for both training and inference, and large datasets available. The applicability of this paradigm to space systems, where both large datasets and inexpensive hardware are not readily available, is more difficult and thus still rare. This paper analyzes the impact of DNNs on the system-level capabilities of space systems in terms of on-board decision making (OBDM) and identifies the specific criticalities of deploying DNNs on satellites. The workload of DNNs for on-board image and telemetry analysis is analyzed, and the results are used to drive the preliminary design of a RISC-V vector processor to be employed as a generic platform to enable energy-efficient OBDM for both payload and platform applications. The design of the memory subsystem is carried out in detail to allow full exploitation of the computational resources in typically resource-constrained space systems.

@en

This paper discusses principles and techniques to evaluate processors for dependable computing in space applications. The focus is on soft errors, which dominate the failure rate of processors in space. Error, failure and propagation models from literature are selected and employed to estimate the failure rate due to soft errors in typical processor designs. A similar approach can be followed for applications with different radiation environments (e.g. automotive, servers, experimental instrumentation exposed to radiation on ground), by adapting the error models. This detailed white-box analysis is possible only for open-source Intellectual Property (IP) cores and in this work it will be applied to several open-source IP cores based on the RISC-V Instruction Set Architecture (ISA). For these case studies, several types of redundancy described in literature for space processors will be evaluated in terms of their cost-effectiveness and expected final in-orbit behavior. This work provides a comprehensive framework to assess efficacy and cost-effectiveness of redundancy, instead of listing and categorizing the techniques described in literature without assessing their relevance to state-of-the-art designs in space applications.

@en

This paper proposes a roadmap to address present and future needs in space systemswithRISC-Vprocessors. RISCVis an open and modular instruction set architecture, which is rapidly growing in popularity in terrestrial applications. To satisfy different applications with contrasting requirements in satellite data systems, four different types of processors are identified: 1) low-area/low-power microcontrollers, 2) on-board computers, 3) general-purpose processors for payloads, and 4) enhanced payload processors for artificial intelligence. Several solutions based onRISCVare proposed for eachof these types of processors and comparedwith proprietary commercial-off-the-shelf andspacegrade solutions. An extensive analysis of the results available fromliterature is conducted to show that RISC-V has the potential to solve such a wide range of needs. This paper will also show the unprecedented number of open-source implementations and models that were developed in a relative short time on a single instruction set architecture. Future space systemscouldbenefit frommanyof those developments, andthisworkidentifies andhighlightswhat is stillmissing to satisfy the specific needs of processors for space, especially in terms of fault tolerance and technology readiness level. @en

This paper analyzes the contribution of caches to failures at processor level due to soft errors. In order to do this, approximated methodologies to estimate the percentage of the total Sensitive Area (SA) of a processor for each unit during early design exploration are proposed. Then, to identify the most vulnerable units, a metric called Relative Soft Error Vulnerability (RSEV) is defined. The analysis shows that caches are the most vulnerable units of state-of-the-art processors and that, even when considering higher-frequency and more complex pipelines representative of next-generation processors for space applications, the final in-orbit failure rate is dominated by failures caused by upsets in cache arrays. Even when protecting memory arrays with information redundancy, the large fraction of upsets occurring in caches is potentially the biggest threat to processor availability and reliability, especially if errors are modelled with invalid assumptions and are not properly handled when detected.

@en

This paper presents preliminary position on the use of the novel, free and open RISC-V Instruction Set Architecture (ISA) for on-board electronics in space. The modular nature of this ISA, the availability of a rich software ecosystem, a rapidly growing community and a pool of open-source IP cores will allow Space Industry to spin-in developments from terrestrial fields (in terms of security, artificial intelligence, support for operating systems, hardware acceleration etc.) while focusing its efforts mainly on aspects related to the specific needs of on-board electronics for space applications (e.g. fault tolerance, observability, error signaling, etc.). This will improve reuse and avoid the necessity of developments from scratch when not strategically needed, eventually increasing productivity and reducing costs. The use of an open, non proprietary ISA will allow ad-hoc design of microarchitecture-level soft error countermeasures that can greatly increase the robustness of Application Specific Standard Products (ASSP) and FPGA implementations.

@en