Geometric and dimensional variations in objects are caused by inevitable uncertainties in manufacturing processes and often lead to product quality challenges. Failing to model the effect of object shape errors, i.e., geometric and dimensional errors of parts, early during the design phase inhibits the ability to predict such quality challenges. This consequently leads to expensive design changes after freezing of design. State-of-art methodologies for modelling and simulating object shape error have limited defect fidelity, data versatility, and designer centricity that prevent their effective application during the early design phase. To overcome these limitations, this paper presents a novel Morphing Gaussian Random Field (MGRF) methodology for object shape error modelling and simulation. The MGRF methodology models the spatial correlation in the deviations of the part from its nominal design using Gaussian Random Fields and then, utilises the modelled spatial correlations to generate non-ideal parts by conditional simulations. The MGRF methodology has (i) high defect fidelity enabling it to simulate various part defects including local and global deformations, and technological patterns; (ii) high data versatility allowing it to simulate non-ideal parts under the constraint of limited data availability and to utilise historical non-ideal part data of similar parts; (iii) designer centric capabilities such as performing ‘what if?’ analysis of defects of practical importance; and; (iv) the ability to generate non-ideal parts conforming to statistical form tolerance specification without additional modelling effort. The aforementioned characteristics enable the MGRF methodology to accurately model and simulate the effect of object shape variations on product quality during the early design phase. Practical applications of the developed MGRF methodology and its advantages are demonstrated using sport-utility-vehicle door parts and compared against state-of-art methodologies.

Dynamic resource management techniques rely on power consumption and performance models to optimize the operating frequency and utilization of processing elements, such as CPU and GPU. Despite the importance of these decisions, many existing approaches rely on fixed power and performance models that are learned offline. However, offline models cannot guarantee accuracy when workloads differ significantly from the training available at design time. This paper presents an online learning framework (STAFF) that constructs adaptive run-time models for stationary and non-stationary workloads. STAFF is the first framework that (1) guarantees stability while quickly adapting to workload changes, (2) performs online feature selection with linear complexity, and (3) adapts to new model coefficients by employing adaptively varying forgetting factor, all at the same time. Experiments on an Intel® Coreh™ i5 6th generation platform demonstrate up to 6× improvement in the performance prediction accuracy compared to existing techniques.

Approximately 18 percent of the 3.2 million smartphone applications rely on integrated graphics processing units (GPUs) to achieve competitive performance. Graphics performance, typically measured in frames per second, is a strong function of the GPU frequency, which in turn has a significant impact on mobile processor power consumption. Consequently, dynamic power management algorithms have to assess the performance sensitivity to the frequency accurately to choose the operating frequency of the GPU effectively. Since the impact of GPU frequency on performance varies rapidly over time, there is a need for online performance models that can adapt to varying workloads. This paper presents a light-weight adaptive runtime performance model that predicts the frame processing time of graphics workloads at runtime without apriori characterization. We employ this model to estimate the frame time sensitivity to the GPU frequency, i.e., the partial derivative of the frame time with respect to the GPU frequency. The proposed model does not rely on any parameter learned offline. Our experiments on commercial platforms with common GPU benchmarks show that the mean absolute percentage error in frame time and frame time sensitivity prediction are 4.2 and 6.7 percent, respectively.