Behavior-Based branch prediction by dynamically clustering branch instructions

Conditional branches frequently exhibit similar behavior (bias, time-varying behavior,...), a property that can be used to improve branch prediction accuracy. Branch clustering constructs groups or clusters of branches with similar behavior and applies different branch prediction techniques to each branch cluster. We revisit the topic of branch clustering with the aim of generalizing branch clustering. We investigate several methods to measure cluster information, with the most effective the storage of information in the branch target buffer. Also, we investigate alternative methods of using the branch cluster identification in the branch predictor. By these improvements we arrive at a branch clustering technique that obtains higher accuracy than previous approaches presented in the literature for the gshare predictor. Furthermore, we evaluate our branch clustering technique in a wide range of predictors to show the general applicability of the method. Branch clustering improves the accuracy of the local history (PAg) predictor, the path-based perceptron and the PPM-like predictor, one of the 2004 CBP finalists.

Power combining techniques into unbalanced loads for Class-E and inverse Class-E amplifiers

A power combining strategy for Class-E and inverse Class-E amplifiers operating at high frequencies such that they can operate into unbalanced loads is proposed. This power combining method is particularly important for the inverse Class-E amplifier configuration whose single-stage topology is naturally limited for small-to-medium power applications. Design examples for the power combining synthesis of classical Class-E and then inverse Class-E amplifiers with specification 3 V-1.5 W-2.5 GHz are given. For this specification, it is shown that a three-branch combiner has a natural 50 V output impedance. The resulting circuits are simulated within Agilent Advanced Design Systems environment with good agreement to theoretical prediction. Further the performance of the proposed circuits when operated in a Linear amplification using Nonlinear Components transmitter configuration whereby two-branch amplifiers are driven with constant amplitude conjugate input phase signals is investigated.

Ligand and structure-based methodologies for the prediction of the activity of G protein-coupled receptor ligands

Accurate in silico models for the quantitative prediction of the activity of G protein-coupled receptor (GPCR) ligands would greatly facilitate the process of drug discovery and development. Several methodologies have been developed based on the properties of the ligands, the direct study of the receptor-ligand interactions, or a combination of both approaches. Ligand-based three-dimensional quantitative structure-activity relationships (3D-QSAR) techniques, not requiring knowledge of the receptor structure, have been historically the first to be applied to the prediction of the activity of GPCR ligands. They are generally endowed with robustness and good ranking ability; however they are highly dependent on training sets. Structure-based techniques generally do not provide the level of accuracy necessary to yield meaningful rankings when applied to GPCR homology models. However, they are essentially independent from training sets and have a sufficient level of accuracy to allow an effective discrimination between binders and nonbinders, thus qualifying as viable lead discovery tools. The combination of ligand and structure-based methodologies in the form of receptor-based 3D-QSAR and ligand and structure-based consensus models results in robust and accurate quantitative predictions. The contribution of the structure-based component to these combined approaches is expected to become more substantial and effective in the future, as more sophisticated scoring functions are developed and more detailed structural information on GPCRs is gathered.

Prediction-Based Power-Performance Adaptation of Multithreaded Scientific Codes

Computing has recently reached an inflection point with the introduction of multicore processors. On-chip thread-level parallelism is doubling approximately every other year. Concurrency lends itself naturally to allowing a program to trade performance for power savings by regulating the number of active cores; however, in several domains, users are unwilling to sacrifice performance to save power. We present a prediction model for identifying energy-efficient operating points of concurrency in well-tuned multithreaded scientific applications and a runtime system that uses live program analysis to optimize applications dynamically. We describe a dynamic phase-aware performance prediction model that combines multivariate regression techniques with runtime analysis of data collected from hardware event counters to locate optimal operating points of concurrency. Using our model, we develop a prediction-driven phase-aware runtime optimization scheme that throttles concurrency so that power consumption can be reduced and performance can be set at the knee of the scalability curve of each program phase. The use of prediction reduces the overhead of searching the optimization space while achieving near-optimal performance and power savings. A thorough evaluation of our approach shows a reduction in power consumption of 10.8 percent, simultaneous with an improvement in performance of 17.9 percent, resulting in energy savings of 26.7 percent.

Predicting organic acid concentration from UV/vis spectrometry measurements - A comparison of machine learning techniques

The concentration of organic acids in anaerobic digesters is one of the most critical parameters for monitoring and advanced control of anaerobic digestion processes. Thus, a reliable online-measurement system is absolutely necessary. A novel approach to obtaining these measurements indirectly and online using UV/vis spectroscopic probes, in conjunction with powerful pattern recognition methods, is presented in this paper. An UV/vis spectroscopic probe from S::CAN is used in combination with a custom-built dilution system to monitor the absorption of fully fermented sludge at a spectrum from 200 to 750 nm. Advanced pattern recognition methods are then used to map the non-linear relationship between measured absorption spectra to laboratory measurements of organic acid concentrations. Linear discriminant analysis, generalized discriminant analysis (GerDA), support vector machines (SVM), relevance vector machines, random forest and neural networks are investigated for this purpose and their performance compared. To validate the approach, online measurements have been taken at a full-scale 1.3-MW industrial biogas plant. Results show that whereas some of the methods considered do not yield satisfactory results, accurate prediction of organic acid concentration ranges can be obtained with both GerDA and SVM-based classifiers, with classification rates in excess of 87% achieved on test data.

The prediction of intake potential and organic matter digestibility of grass silages by near infrared spectroscopy analysis of undried samples

A study was undertaken to examine a range of sample preparation and near infrared reflectance spectroscopy (NIPS) methodologies, using undried samples, for predicting organic matter digestibility (OMD g kg(-1)) and ad libitum intake (g kg(-1) W-0.75) of grass silages. A total of eight sample preparation/NIRS scanning methods were examined involving three extents of silage comminution, two liquid extracts and scanning via either external probe (1100-2200 nm) or internal cell (1100-2500 nm). The spectral data (log 1/R) for each of the eight methods were examined by three regression techniques each with a range of data transformations. The 136 silages used in the study were obtained from farms across Northern Ireland, over a two year period, and had in vivo OMD (sheep) and ad libitum intake (cattle) determined under uniform conditions. In the comparisons of the eight sample preparation/scanning methods, and the differing mathematical treatments of the spectral data, the sample population was divided into calibration (n = 91) and validation (n = 45) sets. The standard error of performance (SEP) on the validation set was used in comparisons of prediction accuracy. Across all 8 sample preparation/scanning methods, the modified partial least squares (MPLS) technique, generally minimized SEP's for both OMD and intake. The accuracy of prediction also increased with degree of comminution of the forage and with scanning by internal cell rather than external probe. The system providing the lowest SEP used the MPLS regression technique on spectra from the finely milled material scanned through the internal cell. This resulted in SEP and R-2 (variance accounted for in validation set) values of 24 (g/kg OM) and 0.88 (OMD) and 5.37 (g/kg W-0.75) and 0.77 (intake) respectively. These data indicate that with appropriate techniques NIRS scanning of undried samples of grass silage can produce predictions of intake and digestibility with accuracies similar to those achieved previously using NIRS with dried samples. (C) 1998 Elsevier Science B.V.

In silico prediction of the effects of mutations in the human UDP-galactose 4'-epimerase gene:Towards a predictive framework for type III galactosemia

The enzyme UDP-galactose 4'-epimerase (GALE) catalyses the reversible epimerisation of both UDP-galactose and UDP-N-acetyl-galactosamine. Deficiency of the human enzyme (hGALE) is associated with type III galactosemia. The majority of known mutations in hGALE are missense and private thus making clinical guidance difficult. In this study a bioinformatics approach was employed to analyse the structural effects due to each mutation using both the UDP-glucose and UDP-N-acetylglucosamine bound structures of the wild-type protein. Changes to the enzyme's overall stability, substrate/cofactor binding and propensity to aggregate were also predicted. These predictions were found to be in good agreement with previous in vitro and in vivo studies when data was available and allowed for the differentiation of those mutants that severely impair the enzyme's activity against UDP-galactose. Next this combination of techniques were applied to another twenty-six reported variants from the NCBI dbSNP database that have yet to be studied to predict their effects. This identified p.I14T, p.R184H and p.G302R as likely severely impairing mutations. Although severely impaired mutants were predicted to decrease the protein's stability, overall predicted stability changes only weakly correlated with residual activity against UDP-galactose. This suggests other protein functions such as changes in cofactor and substrate binding may also contribute to the mechanism of impairment. Finally this investigation shows that this combination of different in silico approaches is useful in predicting the effects of mutations and that it could be the basis of an initial prediction of likely clinical severity when new hGALE mutants are discovered.

The prediction of process-induced deformation in a thermoplastic composite in support of manufacturing simulation

Digital manufacturing techniques can simulate complex assembly sequences using computer-aided design-based, as-designed' part forms, and their utility has been proven across several manufacturing sectors including the ship building, automotive and aerospace industries. However, the reality of working with actual parts and composite components, in particular, is that geometric variability arising from part forming or processing conditions can cause problems during assembly as the as-manufactured' form differs from the geometry used for any simulated build validation. In this work, a simulation strategy is presented for the study of the process-induced deformation behaviour of a 90 degrees, V-shaped angle. Test samples were thermoformed using pre-consolidated carbon fibre-reinforced polyphenylene sulphide, and the processing conditions were re-created in a virtual environment using the finite element method to determine finished component angles. A procedure was then developed for transferring predicted part forms from the finite element outputs to a digital manufacturing platform for the purpose of virtual assembly validation using more realistic part geometry. Ultimately, the outcomes from this work can be used to inform process condition choices, material configuration and tool design, so that the dimensional gap between as-designed' and as-manufactured' part forms can be reduced in the virtual environment.

The feasibility of using near infrared and Raman spectroscopic techniques to detect fraudulent adulteration of chili powders with Sudan dye

Chili powder is a globally traded commodity which has been found to be adulterated with Sudan dyes from 2003 onwards. In this study, chili powders were adulterated with varying quantities of Sudan I dye (0.1-5%) and spectra were generated using near infrared reflectance spectroscopy (NIRS) and Raman
spectroscopy (on a spectrometer with a sample compartment modified as part of the study). Chemometrics were applied to the spectral data to produce quantitative and qualitative calibration models and prediction statistics. For the quantitative models coefficients of determination (R2) were found to be
0.891-0.994 depending on which spectral data (NIRS/Raman) was processed, the mathematical algorithm used and the data pre-processing applied. The corresponding values for the root mean square error of calibration (RMSEC) and root mean square error of prediction (RMSEP) were found to be 0.208-0.851%
and 0.141-0.831% respectively, once again depending on the spectral data and the chemometric treatment applied to the data. Indications are that the NIR spectroscopy based models are superior to the models produced from Raman spectral data based on a comparison of the values of the chemometric
parameters. The limit of detection (LOD) based on analysis of 20 blank chili powders against each calibration model gave 0.25% and 0.88% for the NIR and Raman data, respectively. In addition, adopting a qualitative approach with the spectral data and applying PCA or PLS-DA, it was possible to discriminate
between adulterated chili powders from non-adulterated chili powders.

Prediction of integral type failures in semiconductor manufacturing through classification methods

Smart management of maintenances has become fundamental in manufacturing environments in order to decrease downtime and costs associated with failures. Predictive Maintenance (PdM) systems based on Machine Learning (ML) techniques have the possibility with low added costs of drastically decrease failures-related expenses; given the increase of availability of data and capabilities of ML tools, PdM systems are becoming really popular, especially in semiconductor manufacturing. A PdM module based on Classification methods is presented here for the prediction of integral type faults that are related to machine usage and stress of equipment parts. The module has been applied to an important class of semiconductor processes, ion-implantation, for the prediction of ion-source tungsten filament breaks. The PdM has been tested on a real production dataset. © 2013 IEEE.

Prediction of surface roughness during hard turning of AISI 4340 steel (69 HRC)

In this study, 39 sets of hard turning (HT) experimental trials were performed on a Mori-Seiki SL-25Y (4-axis) computer numerical controlled (CNC) lathe to study the effect of cutting parameters in influencing the machined surface roughness. In all the trials, AISI 4340 steel workpiece (hardened up to 69 HRC) was machined with a commercially available CBN insert (Warren Tooling Limited, UK) under dry conditions. The surface topography of the machined samples was examined by using a white light interferometer and a reconfirmation of measurement was done using a Form Talysurf. The machining outcome was used as an input to develop various regression models to predict the average machined surface roughness on this material. Three regression models - Multiple regression, Random Forest, and Quantile regression were applied to the experimental outcomes. To the best of the authors’ knowledge, this paper is the first to apply Random Forest or Quantile regression techniques to the machining domain. The performance of these models was compared to each other to ascertain how feed, depth of cut, and spindle speed affect surface roughness and finally to obtain a mathematical equation correlating these variables. It was concluded that the random forest regression model is a superior choice over multiple regression models for prediction of surface roughness during machining of AISI 4340 steel (69 HRC).