Adapting application execution in CMPs using helper threads

In parallel to the changes in both the architecture domain–the move toward chip multiprocessors (CMPs)–and the application domain–the move toward increasingly data-intensive workloads–issues such as performance, energy efficiency and CPU availability are becoming increasingly critical. The CPU availability can change dynamically due to several reasons such as thermal overload, increase in transient errors, or operating system scheduling. An important question in this context is how to adapt, in a CMP, the execution of a given application to CPU availability change at runtime. Our paper studies this problem, targeting the energy-delay product (EDP) as the main metric to optimize. We first discuss that, in adapting the application execution to the varying CPU availability, one needs to consider the number of CPUs to use, the number of application threads to accommodate and the voltage/frequency levels to employ (if the CMP has this capability). We then propose to use helper threads to adapt the application execution to CPU availability change in general with the goal of minimizing the EDP. The helper thread runs parallel to the application execution threads and tries to determine the ideal number of CPUs, threads and voltage/frequency levels to employ at any given point in execution. We illustrate this idea using four applications (Fast Fourier Transform, MultiGrid, LU decomposition and Conjugate Gradient) under different execution scenarios. The results collected through our experiments are very promising and indicate that significant EDP reductions are possible using helper threads. For example, we achieved up to 66.3%, 83.3%, 91.2%, and 94.2% savings in EDP when adjusting all the parameters properly in applications FFT, MG, LU, and CG, respectively. We also discuss how our approach can be extended to address multi-programmed workloads.     

Influence of compiler optimizations on system power

Optimizing for energy constraints is of critical importance due to the proliferation of battery-operated embedded devices. Thus, it is important to explore both hardware and software solutions for optimizing energy. The focus of high-level compiler optimizations has traditionally been on improving performance. In this paper, we present an experimental evaluation of several state-of-the-art high-level compiler optimizations on energy consumption, considering both the processor core (datapath) and memory system. This is in contrast to many of the previous works that have considered them in isolation     

Foliar epidermal anatomical characteristics of taxa of Iris subg. Scorpiris Spach (Iridaceae) from Turkey

Iris L. is one of the important genus of family Iridaceae, consist of 56 taxa naturally occurred in Turkey. The similarities and variations in the subgenus overlapping the taxonomic positions of the species in the subgenera and needs anatomical assessment especially by microscopic techniques. In this study, the taxonomic significance of leaf anatomical characters of 10 Iris subgenus Scorpiris taxa were studied in detail and the relationship among these taxa were evaluated using microscopy techniques. Fresh leaf samples of species were fixed in 70% alcohol solution for anatomical observation under microscope. Eleven different micromorphological features were statistically analyzed to delimit the species in subgenus. Based on morphological and anatomical similarities, we studied relationships among; (1) ssp. turcica, ssp. caucasica, I. nezahatiae and I. pseudocaucasica; (2) correlation between ssp. turcica and ssp. caucasica; (3) association of I. galatica, I. persica, ssp. margaretiae and ssp. stenophylla with each other; (4) relationship between ssp. stenophylla and ssp. margaretiae; and (5) relevance between I. aucheri and I. peshmeniana. Moreover, the taxonomy of subgenus Scorpiris has been discussed in detail with novel and diagnostic features based on micromorphological physiognomies. We found that four species in this study are endemic to Turkey, while seven are critically endangered geophytes in the country. The leaf anatomical characteristics of 10 taxa were divided into three groups. Main aim of this research was to study the taxonomy of the complex subgenus Scorpiris through microscopic techniques.     

Assessment of coal deposit using multivariate statistical analysis techniques

Energy is one of the indispensable factors regarding the economic development of Turkey. Examination of calorific values in coal deposits has importance in the production of energy, and thus planning of the coal deposit. In this article, multivariate statistical analysis techniques, including cluster analysis and discriminant analysis, were applied to calorific values obtained from boreholes. Cluster analysis grouped borehole locations into two clusters based on the similarity of calorific values. Afterwards, discriminant functions were supported to cluster analysis and developed a linear discriminant function. Based on the locations of the boreholes, it was concluded that calorific values are a highly central part of the coal deposit. Thus, this article shows the usefulness of multivariate statistical analysis techniques for understanding spatial variation of coal deposits and effective deposit management.     

Memory Partitioning in the Limit

International Journal of Parallel Programming - The key difficulties in designing memory hierarchies for future computing systems with extreme scale parallelism include (1) overcoming the design...     

Optimum insulation thickness of the piping system with combined economic and environmental method

In the present study, an alternative method combining economic and environmental costs is suggested for the pipe insulation. This method is called as combined economic and environment method (CEEM). Bilecik, which is located in the Marmara region, Turkey, is chosen. Rockwool and glass wool are chosen as insulation materials. The optimum insulation thicknesses of three different methods including CEEM, economic, and environmental approaches are calculated and compared. Optimum points are 0.46 m (CEEM), 0.39 m (economic approach), and 0.54 m (environmental approach) for rockwool; and 0.46 m (CEEM), 0.40 m (economic approach), and 0.59 m (environmental approach) for glass wool. In addition, annual cost savings and energy savings are determined.     

Microstructural and Defect Analysis of Metal Nanoparticles in Functional Catalysts by Diffraction and Electron Microscopy: The Cu/ZnO Catalyst for Methanol Synthesis

The application of different methods for a microstructural analysis of functional catalysts is reported for the example of different Cu/ZnO-based methanol synthesis catalysts. Transmission electron microscopy and diffraction were used as complementary techniques to extract information on the size and the defect concentration of the Cu nano-crystallites. The results, strengths and limitations of the two techniques and of different evaluation methods for line profile analysis of diffraction data including Rietveld-refinement, Scherrer- and (modified) Williamson–Hall-analyses, single peak deconvolution and whole powder pattern modeling are compared and critically discussed. It was found that in comparison with a macrocrystalline pure Cu sample, the catalysts were not only characterized by a smaller crystallite size, but also by a high concentration of lattice defects, in particular stacking faults. Neutron diffraction was introduced as a valuable tool for such analysis, because of the larger number of higher-order diffraction peaks that can be detected with this method. An attempt is reported to quantify the different types of defects for a selected catalyst.