Energy of computing is a serious environmental concern and mitigating it is an important technological challenge. Accurate measurement of energy consumption during an application execution is key to application-level energy minimization techniques. There are three popular approaches to providing it: (a) System-level physical measurements using external power meters; (b) Measurements using on-chip power sensors and (c) Energy predictive models. In this work, we present a comprehensive study comparing the accuracy of state-of-the-art on-chip power sensors and energy predictive models against system-level physical measurements using external power meters, which we consider to be the ground truth. We show that the average error of the dynamic energy profiles obtained using on-chip power sensors can be as high as 73% and the maximum reaches 300% for two scientific applications, matrix-matrix multiplication and 2D fast Fourier transform for a wide range of problem sizes. The applications are executed on three modern Intel multicore CPUs, two Nvidia GPUs and an Intel Xeon Phi accelerator. The average error of the energy predictive models employing performance monitoring counters (PMCs) as predictor variables can be as high as 32% and the maximum reaches 100% for a diverse set of seventeen benchmarks executed on two Intel multicore CPUs (one Haswell and the other Skylake). We also demonstrate that using inaccurate energy measurements provided by on-chip sensors for dynamic energy optimization can result in significant energy losses up to 84%. We show that, owing to the nature of the deviations of the energy measurements provided by on-chip sensors from the ground truth, calibration can not improve the accuracy of the on-chip sensors to an extent that can allow them to be used in optimization of applications for dynamic energy. Finally, we present the lessons learned, our recommendations for the use of on-chip sensors and energy predictive models and future directions.

No abstract

No abstract

PurposeJetting‐based additive manufacturing processes are gaining attention due to their high speed of operation, accuracy and resolution. Support material plays an important role in the additive manufacturing of parts by using processes that utilise jetting (inkjet) technology. This research aims to present novel support material compositions consisting of methylcellulose (MC) and propylene glycol or butylene glycol. These compositions form gels which are easy to remove and provide the advantage of reusability.Design/methodology/approachMC was mixed in propylene glycol or butylene glycol in different concentrations and examined for gel formation on heating and subsequent cooling. The viscosity and surface tension of these compositions were measured at temperatures suitable for jetting. Gel strength was characterised using texture analysis.FindingsThe viscosity and surface tension values at elevated temperatures (i.e. 800°C) show the suitability of these compositions for jetting‐based additive manufacturing processes. Due to their softness, these gels can be removed easily and their low melting points (i.e. near 500°C) allow their reusability as support materials.Practical implicationsThis paper provides a novel approach of using polymer gels as support materials for additive manufacturing processes. These gels are easy to prepare and enhance the sustainability due to their reusability.Originality/valueAlthough, MC in water have shown to form gels and these aqueous gels have been used in many applications such as medicine and food industries, the compositions presented in this paper are unique. Such combinations of MC and non‐aqueous solvents (i.e. propylene glycol and butylene glycol) have not been discussed before and provide an early step towards a new application area (i.e. additive manufacturing) for these gels.

Additive manufacturing has stepped down from the world of Sci-Fi into reality. Since its conception in the 1980s the technology has come a long way. May variants of the technology are now available to the consumer. With the advent of custom built (open source) Fused Deposition Modeling based printing technology Fused Filament Fabrication (FFF), FDM/FFF has become the most used Additive Manufacturing technology. The effects of the different infill patterns of FDM/FFF on the mechanical properties of a specimen made from ABS are studied in this paper. It is shown that due to changes in internal structures, the tensile strength of the specimen changes. The study also investigate the effect of infill pattern on the build time of the specimen. Extensive testing yielded the optimal infill pattern for FDM/FFF. An open source Arduino based RepRap printer was used for the preparation of specimen and showed promising results for rapid prototyping of custom built parts to bear high loads. The study can help with the increase in the use of additive manufacturing for the manufacturing of mechanically functioning parts such as prosthetics