Benchmarks set standards for innovation in computer architecture research and industry product development. Consequently, it is of paramount importance that the benchmarks used in computer architecture research and development are representative of real-world applications. However, composing such representative workloads poses practical challenges to application analysis teams and benchmark developers - (1) Benchmarks that are standardized are open-source whereas applications of interest are typically proprietary, (2) Benchmarks are rigid, measure single-point performance, and only represent a sample of the application behavior space (3) Benchmark suites take several years to develop, but applications evolve at a faster rate, and (4) Benchmarks geared towards temperature and power characterization are difficult to develop and standardize. The objective of this dissertation is to develop an adaptive benchmark generation strategy to construct synthetic benchmarks to address these benchmarking challenges. We propose an approach for automatically distilling key hardware-independent performance attributes of a proprietary workload and capture them into a miniature synthetic benchmark clone. The advantage of the benchmark clone is that it hides the functional meaning of the code, but exhibits similar performance and power characteristics as the target application across a wide range of microarchitecture configurations. Moreover, the dynamic instruction count of the synthetic benchmark clone is substantially shorter than the proprietary application, greatly reducing overall simulation time -- for the SPEC CPU 2000 suite, the simulation time reduction is over five orders of magnitude compared to the entire benchmark execution. We develop an adaptive benchmark generation strategy that trades off accuracy to provide the flexibility to easily alter program characteristics. The parameterization of workload metrics makes it possible to succinctly describe an application's behavior using a limited number of fundamental program characteristics. This provides the ability to alter workload characteristics and construct scalable benchmarks that allows researchers to explore a wider range of the application behavior space, conduct program behavior studies, and model emerging workloads. The parameterized workload model is the foundation for automatically constructing power and temperature oriented synthetic workloads. We show that machine learning algorithms can be effectively used to search the application behavior space to automatically construct benchmarks for evaluating the power and temperature characteristics of a computer architecture design. The need for a scientific approach to construct synthetic benchmarks, to complement application benchmarks, has long been recognized by the computer architecture research community, and this dissertation work is a significant step towards achieving that goal.

published_or_final_version / abstract / toc / Computer Science and Information Systems / Master / Master of Philosophy

No description available.

L'objectiu d'aquesta tesis es crear o adaptar models de programació per a fer els processadors multi-core accessibles per a la majoria de programadors. Aquest objectiu inclou la possibilitat de reusar els algoritmes existents, la capacitat de depuració, I la capacitat d'introduir els canvis de forma incremental. Contrastem les solucions proposades en diversos tipus de multi-core, incloent sistemes homogenis i heterogenis, i sistemes de memòria compartida i memòria distribuïda. A més a més contribuïm exposant algorismes i programes reals i ensenyant com aquests es poden ser usat per aplicacions en temps quasi real. / The aim of this thesis is to create or adapt a programming model in order to make multi-core processors accessible by almost every programmer. This objective includes existing codes and algorithms reuse, debuggability, and the capacity to introduce changes incrementally. We face multi-cores with many architectures including homogeneity versus heterogeneity and shared-memory versus distributed-memory. We also contribute by exposing real algorithms and programs and showing how some of them can be used for quasi realtime applications.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.