Search for: All records

Power modeling is an essential building block for computer systems in support of energy optimization, energy profiling, and energy-aware application development. We introduce VESTA, a novel approach to modeling the power consumption of applications with one key insight: language runtime events are often correlated with a sustained level of power consumption. When compared with the established approach of power modeling based on hardware performance counters (HPCs), VESTA has the benefit of solely requiring application-scoped information and enabling a higher level of explainability, while achieving comparable or even higher precision. Through experiments performed on 37 real-world applications on the Java Virtual Machine (JVM), we find the power model built by VESTA is capable of predicting energy consumption with a mean absolute percentage error of 1.56%, while the monitoring of language runtime events incurs small performance and energy overhead.

 

The current techniques and tools for collecting, aggregating, and reporting verifiable sustainability data are vulnerable to cyberattacks and misuse, requiring new security and privacy-preserving solutions. This article outlines security challenges and research directions for addressing these requirements. 

Despite several calls from the community for improving the sustainability of computing, sufficient progress is yet to be made on one of the key prerequisites of sustainable computing---the ability to define and measure computing sustainability holistically. This position paper proposes metrics that aim to measure the end-to-end sustainability footprint in data centers. To enable useful sustainable computing efforts, these metrics can track the sustainability footprint at various granularities---from a single request to an entire data center. The proposed metrics can also broadly influence sustainable computing practices by incentivizing end-users and developers to participate in sustainable computing efforts in data centers. 

Data processing systems are a fundamental component of the modern computing stack. These systems are routinely deployed online: they continuously receive the requests of data processing operations, and continuously return the results to end users or client applications. Online data processing systems have unique features beyond conventional data processing, and the optimizations designed for them are complex, especially when data themselves are structured and dynamic. This paper describes DON Calculus, the first rigorous foundation for online data processing. It captures the essential behavior of both the backend data processing engine and the frontend application, with the focus on two design dimensions essential yet unique to online data processing systems: incremental operation processing (IOP) and temporal locality optimization (TLO). A novel design insight is that the operations continuously applied to the data can be defined as an operation stream flowing through the data structure, and this abstraction unifies diverse designs of IOP and TLO in one calculus. DON Calculus is endowed with a mechanized metatheory centering around a key observable equivalence property: despite the significant non-deterministic executions introduced by IOP and TLO, the observable result of DON Calculus data processing is identical to that of conventional data processing without IOP and TLO. Broadly, DON Calculus is a novel instance in the active pursuit of providing rigorous guarantees to the software system stack. The specification and mechanization of DON Calculus provide a sound base for the designers of future data processing systems to build upon, helping them embrace rigorous semantic engineering without the need of developing from scratch.

 

Sustainability is crucial for combating climate change and protecting our planet. While there are various systems that can pose a threat to sustainability, data centers are particularly significant due to their substantial energy consumption and environmental impact. Although data centers are becoming increasingly accountable to be sustainable, the current practice of reporting sustainability data is often mired with simple green-washing. To improve this status quo, users as well as regulators need to verify the data on the sustainability impact reported by data center operators. To do so, data centers must have appropriate infrastructures in place that provide the guarantee that the data on sustainability is collected, stored, aggregated, and converted to metrics in a secure, unforgeable, and privacy-preserving manner. Therefore, this paper first introduces the new security challenges related to such infrastructure, how it affects operators and users, and potential solutions and research directions for addressing the challenges for data centers and other industry segments. 

The security of isolated execution architectures such as Intel SGX has been significantly threatened by the recent emer- gence of side-channel attacks. Cache side-channel attacks allow adversaries to leak secrets stored inside isolated en- claves without having direct access to the enclave memory. In some cases, secrets can be leaked even without having the knowledge of the victim application code or having OS-level privileges. We propose the concept of Composable Cachelets (CC), a new scalable strategy to dynamically partition the last-level cache (LLC) for completely isolating enclaves from other applications and from each other. CC supports enclave isolation in caches with the capability to dynamically readjust the cache capacity as enclaves are created and destroyed. We present a cache-aware and enclave-aware operational seman- tics to help rigorously establish security properties of CC, and we experimentally demonstrate that CC thwarts side-channel attacks on caches with modest performance and complexity impact. 

Visual SLAM systems are concurrent, performance-critical systems that respond to real-time environmental conditions and are frequently deployed on resource-constrained hardware. Previous SLAM frameworks have primarily focused on algorithmic advances and their systems core has largely remained unchanged. In turn, SLAM systems suffer from performance problems that could be alleviated with improved systems design. In this paper, we present a quantitative analysis of the systems challenges to building consistent, accurate, and robust SLAM systems in the face of concurrency, variable environmental conditions, and resource-constrained hardware. We identify three interconnected challenges on systems design --- timeliness, concurrency, and context awareness --- and clarify their effects on performance.