Scope

The ACM/SPEC International Conference on Performance Engineering (ICPE) is the leading international forum for presenting and discussing novel ideas, innovations, trends, and experiences in the field of performance engineering.

Today’s systems are complex, rely increasingly on dynamic distributed architectures, and raise continuously important challenges related to end-to-end performance management. This applies equally to emerging domains, such as systems of systems, interconnected and embedded systems, distributed data and intelligence, machine learning environments, human-centered computing, non-von Neumann architectures, cloud/edge/fog infrastructures, data streaming, and social networks, and also to traditional domains, such as web-based, data centers, mobile and wireless systems, and real-time systems. As a result, our systems become more complex and, therefore, more difficult to engineer and understand. We need to manage this complexity so that our systems remain reliable, trustworthy, and performant.

ICPE brings together researchers and practitioners to report state-of-the-art and in-progress research on performance engineering of software, networks, and systems, including but not limited to performance modeling, analysis, measurement, benchmark design, and run-time performance management. The focus is both on classical metrics such as response time, throughput, resource utilization, and (energy) efficiency and on the relationship of such metrics to other system properties, including but not limited to scalability, elasticity, availability, reliability, cost, sustainability, security, and privacy.

Topics of interest

Topics of interest include, but are not limited to:

Performance Measurement and Empirical Evaluation

    Data collection techniques, simulation, measurement, instrumentation, profiling
    Controlled experiment design, data-driven experiments, diagnostics
    Data management and interchange, tool interoperability
    Statistical analysis, exploration, visualization, visual data mining

Performance Benchmarking

    Design and standardization process
    Benchmark suites, investigative benchmarks
    Benchmark synthesis, benchmark workload generation
    Benchmarking energy efficiency, resilience, stability, security, and related quality metrics

Performance Modeling of Software and Systems

    Approaches and metrics for describing performance and related quality attributes
    Modeling languages and formalisms, modeling methods and tools
    Explanatory and predictive models, online models
    Model learning and extraction techniques
    Model validation and calibration
    Workload characterization

Design and Development Processes

    Requirements engineering, agile and experiment-driven techniques, devops
    Performance-oriented design, software architectures, performance patterns
    Performance testing
    Model-driven engineering
    Humans in the loop, ethical concerns

Run-time Performance Management and Adaptation

    Adaptive systems, monitoring, autotuning, elasticity and autoscaling, power management
    Virtualization and consolidation, resource scheduling, capacity management
    Anomaly detection, service level (definition and monitoring)

Platform-Related Optimizations

    Parallel programming, multi-core and many-core systems
    Compiler optimizations, managed languages, and runtime optimization
    Performance and efficiency of hardware accelerators and novel memory systems

Systems of Interest

Systems of interest include, but are not limited to:

    Cyber-physical domain, iot, industrial internet
    Networked and embedded systems
    Advanced computer architectures, including non-von Neumann
    Communication networks, wireless and mobile
    Peer-to-peer environments, ad-hoc networks
    Machine learning and AI-based systems
    SOA, microservices, web-based environments
    Big data systems, stream, and graph processing
    HPC systems, cloud, edge, grid, and fog
    Social networks, multimedia systems, and applications