Computer Systems Research
See program guidelines for contact information.
The Computer Systems Research (CSR) program supports transformative scientific and engineering research on computer systems. Much of the current research in computer systems is being driven by the demands and impacts of warehouse-scale computing, but computers are now everywhere. There is a broad set of applications driving systems research including, but not limited to, wearable computing, "smart dust," the Internet of Things, and cyber-physical systems; these applications create their own systems' challenges. In addition, novel technologies and significant improvement to existing technologies provide opportunities for the creation of novel applications and require us to reconsider the fundamental design assumptions underlying existing systems. Examples of potential novelty include, but are not limited to, nonvolatile universal memory; low-power, scalable, many-core architectures; silicon photonics; and natural user interfaces. There are also challenges that cut across many computer systems that continue to demand attention, including making reliable systems from unreliable components, enabling systems to adapt to changing environments and to grow without practical limit, and addressing the economical, environmental and social aspects of the sustainability of computer systems. Note: The technologies and applications specified above are merely intended as examples and not meant to be exhaustive.
CSR proposals should address problems that are appropriate to the CSR Core Area or to one of the current highlighted areas. Note that proposals that address problems in the CSR highlighted areas are not targeted for special handling or funding -- they simply represent emerging areas or areas of current national interest.
CSR proposals are strongly encouraged to include validation plans that describe mechanisms to assess success of the proposed research efforts.
CSR Core Area
The CSR program supports transformative research, whether foundational or in computing systems, ranging from multi-core architectures and operating systems to mobile and sensor systems. Research in computer systems is typically complicated by two factors. First, modern systems are increasingly large, complex, and heterogeneous. Second, they are usually required to provide, during their executions, high degrees of availability, responsiveness, fault-tolerance, and security. Indeed, some systems are safety-critical. Other system properties of interest include speed, storage requirements, energy consumption, and real-time constraints.
Research in the CSR Core Area involves developing methodologies, techniques, heuristics, and tools for the analysis, design, construction, optimization, and certification of computing systems to meet specified goals, as well as hardware and software execution platforms and environments.
The CSR core supports and sustains progress in the contributing disciplinary areas that underlie computing systems including: distributed systems; high performance computing; operating systems and middleware; design and programming models; and real-time, embedded, and hybrid systems.
CSR Highlighted Areas
For this solicitation, there are four CSR highlighted areas: Cloud Computing (CC), Embedded and Hybrid Systems (EHS), Extensible Distributed Systems (EDS), and Sustainable Computing (SC). These four areas are described below.
- Cloud Computing (CC)
Cloud computing is a computing paradigm of on-demand access (as a service) to computing, data, and software utilities. It is based on an abstraction of unlimited availability of virtual resources, and a model of usage-based billing where users essentially "rent" virtual resources and pay only for the virtual resources that they rent.
The main focus of the CC highlight area is to stimulate and promote basic, applied, and experimental research in several directions, in the area of cloud computing, that includes (but is not limited to): cloud architectures and systems; network support for cloud computing; real-time clouds and QoS; data virtualization, replication, consistency, availability, and management; programming models for the cloud; cloud self-monitoring, prediction, and autonomic control; fault-masking and reliability; cloud security, privacy, authorization, and auditing; debugging, certification, diagnosis, and update in the cloud; data portability, interoperability, and standardization; green or energy-efficient clouds; and cloud test-beds.
- Embedded and Hybrid Systems (EHS)
Embedded and hybrid systems control devices and physical or engineered systems that range from hearing aids and pacemakers to automobiles, aircraft, chemical processing plants, electrical power grids, and global aviation infrastructure. The EHS highlight area supports research and education in scientific foundations and technology that will revolutionize the design and development of such systems.
The goal is to supply technologies for designing and building increasingly capable and certifiably dependable embedded and control systems, with real-time, interoperability, survivability, reliability, and security guarantees. A central challenge is to create unified foundations for interacting physical and computational systems.
Specific topics of interest include: embedded systems software and programming methods; real-time services and platforms; foundations and technology for hybrid (discrete and continuous) control; innovative embedded hardware technology; scalable support for embedded sensing; architecture and design principles for complex embedded systems; and resource management and optimization.
- Extensible Distributed Systems (EDS)
Smart phones, tablets, and other types of edge devices have attained increasing prominence in our everyday lives over the last decade. Users expect these systems to be robust, reliable, safe, secure, and efficient. At the same time, new applications leveraging these platforms require a rich environment that enables sensing and computing, along with communication among the devices and between the devices and warehouse-scale facilities via the cloud. This coupling underpins many ‘smart’ technologies and infrastructures of the future, such as smart buildings and informatics infrastructures, intelligent transportation systems, and smart energy distribution and consumption systems, as well as how humans interact with such technologies and infrastructures.
The EDS highlight area supports research into the science and design of extensible distributed systems, advancing software and hardware architectures to enable us to move from small-scale to planetary-scale systems. Research challenges may include (but are not limited to): balancing constraints such as low energy use, tight form factors, and tight time constraints with adequate computational capacity; consistency, reliability, and fault models for EDS; system assumptions for dependability and performance; scaling-out and elasticity with large numbers of nodes; fully decentralized versus central control architectures; robust and efficient protocols for unstructured overlay networks; and data storage and recovery for EDS.
- Sustainable Computing (SC)
The SC highlight area addresses fundamental advances in methods and models to address power, thermal and sustainability issues in the design and operation of computing devices at all scales (from PDAs to large servers and storage boxes) and at all levels (from chips to entire data centers) that are essential to reduce the carbon footprint of fast expanding computing technologies and to deliver the performance that customers and applications demand. As energy generation becomes more distributed and relies on renewable sources, integration of energy generation and consumption by IT becomes an important aspect to consider. With energy consumption of IT systems becoming a major issue, tradeoffs between energy efficiency, performance, and other factors such as reliability or space become essential.
Both the CSR Core and the CSR highlighted areas seek proposals focused on advances in system computing and systems programming that are particular to an application domain or a specific hardware platform as well as generic across domains and platforms. Investigators interested in the CSR program may also wish to consider the Software and Hardware Foundations (SHF) program, which supports research on the design, verification, operation, utilization, and evaluation of computer hardware and software through novel approaches, robust theories, high leverage tools, and lasting principles.
Computer Systems Research (CSR) Staff
Funding Opportunities for the Computer Systems Research (CSR) Program:
Computer and Network Systems (CNS): Core Programs. NSF 14-597
THIS PROGRAM IS PART OF
Computer and Network Systems (CNS): Core Programs