Application-driven processor design exploration for power-performance trade-off analysis

Acoustic noises in the audible range produced by ceramic capacitors has become an increasingly important concern in consumer electronics. The audible noises deteriorate the consumer experience. In order to locate the ceramic capacitors on a printed circuit board (PCB) that cause acoustic noises, we proposed a three-dimensional (3-D) simulation methodology, which is based on the finite element method. The proposed simulation methodology takes into account the product design, the board design, and the detailed component information. The simulation methodology accurately models the board vibrations, which is considered as the primary and the direct cause of acoustic noises. We conduct sound pressure level and laser Doppler vibrometer measurements to benchmark the accuracy and capability of the proposed simulation methodology. On a testing board, the velocity distributions obtained from the proposed simulation agree very well with the measurement results. Through the proposed simulation methodology, we can characterize the board vibrations and extrapolate design guidelines in order to prevent acoustic noise in the early design stage.

Multi-core processors have become an integral part of mainstream high performance computer systems. In parallel, exponentially increasing power density and packaging costs have necessitated system level thermal management solutions for multi-core systems. Dynamic thermal management (DTM) techniques monitor on-chip temperature continuously and typically employs dynamic voltage and frequency scaling (DVFS) to lower the temperature when it exceeds a pre-defined threshold. State-of-the-art DTM solutions for multi-core systems include distributed DVFS (where each core can scale the voltage/frequency individually) and global DVFS (where all cores scale voltage/frequency simultaneously). Distributed DVFS generally offers higher performance than global DVFS, but it is hard to implement and has major scalability issues.

Electromagnetic analysis (EMA) can be used to compromise secret information by analysing the electric and/or magnetic fields emanating from a device. It follows differential power analysis (DPA) becoming an important side channel cryptanalysis attack on many cryptographic implementations, so that constitutes a real threat to smart card security. A systematic simulation methodology is proposed to identify and assess electromagnetic (EM) leakage characteristics of secure processors at design time. This EM simulation methodology involves current flow simulation, chip layout parasitics extraction, then data processing to simulate direct EM emissions or modulated emissions. Tests implemented on synchronous and asynchronous processors indicates that the synchronous processor has data dependent EM emission, while the asynchronous processor has data dependent timing which is visible in differential EM analysis (DEMA). In particular, DEMA of amplitude demodulated emissions reveals greater leakage compared to DEMA of direct emissions and DPA. The proposed simulation methodology can be easily employed in the framework of an integrated circuit (IC) design flow to perform a systematic EM characteristics analysis.

The Internet of Things (IoT) makes use of ubiquitous internet connectivity to form a network of everyday physical objects for purposes of automation, remote data sensing and centralized management/control. IoT objects need to be embedded with processing capabilities to fulfill these services. The design of processing units for IoT objects is constrained by various stringent requirements, such as performance, power, thermal dissipation etc. In order to meet these diverse requirements, a multitude of processor design parameters need to be tuned accordingly. In this paper, we propose a temporally efficient design space exploration methodology which determines power and performance optimized microarchitecture configurations. We also discuss the possible combinations of these microarchitecture configurations to form an effective two-tiered heterogeneous processor for IoT applications. We evaluate our design space exploration methodology using a cycle-accurate simulator (ESESC) and a standard set of PARSEC and SPLASH2 benchmarks. The results show that our methodology determines microarchitecture configurations which are within 2.23–3.69 percent of the configurations obtained from fully exhaustive exploration while only exploring 3–5 percent of the design space. Our methodology achieves on average 24.16× speedup in design space exploration as compared to fully exhaustive exploration in finding power and performance optimized microarchitecture configurations for processors.

This paper describes several methods for improving the scalability of memory disambiguation hardware for future high ILP processors. As the number of in-flight instructions grows with issue width and pipeline depth, the load/store queues (LSQ) threaten to become a bottleneck in both power and latency. By employing lightweight approximate hashing in hardware with structures called Bloom filters, many improvements to the LSQ are possible. We propose two types of filtering schemes using Bloom filters: search filtering, which uses hashing to reduce both the number of lookups to the LSQ and the number of entries that must be searched, and state filtering, in which the number of entries kept in the LSQs is reduced by coupling address predictors and Bloom filters, permitting smaller queues. We evaluate these techniques for LSQs indexed by both instruction age and the instruction's effective address, and for both centralized and physically partitioned LSQs. We show that search filtering avoids up to 98% of the associative LSQ searches, providing significant power savings and keeping LSQ searches to under one high-frequency clock cycle. We also show that with state filtering, the load queue can be eliminated altogether with only minor reductions n performance for small instruction window machines.

The problem to rectify and optimize distance measures from satellites in GNSS devices has been thoroughly explored in many researches. Instead there is not much information on available procedures to replicate the observed errors. The replication of GNSS errors can, in fact, be useful in many traffic simulation scenarios to test for ITS performances. The purpose of this article is to present cases where such a methodology can be useful and then introduce a methodology for the explicit simulation of errors in GNSS systems. The proposed methodology is based on the experimental analysis of some statistical distributions. Such distributions, arising from multiple observations in the field, are able to reproduce the behavior of the error in time as a function of the factors that influence it. The analyzed data were extracted by the GPS/GLONASS sensors of common smartphones and compared with a high-precision GPS equipment. These data were evaluated in different signal coverage conditions, in an open field where the signal quality is expected to be better, suburban and urban areas, where the signal is expected to be worse. The analysis considers many aspects such as the signal reflection problems and the sudden loss of the signal because of a change of the received satellite constellation. The research was conducted by following various steps: a field survey through smartphones and high-precision instrumentation in different conditions, the creation of reference distributions for each parameter that can have an influence on the error, the analysis of correlation functions between the variables, and a final implementation of the proposed algorithm coupled with microsimulation. The paper intends to shed some light on this problem allowing scientist and developers of new ITS system methodologies to reproduce in a simulated environment not only the movement of single vehicles (as usually carried on with microsimulation) but also the data that could be obtained from on-vechicle GNSS instrumentation. The reproduction of this GNSS tracks can be useful to assess the overall response of some new ITS systems before implementing them in the field. The proposed simulation methodology could become a standard tool to help in making better decisions in ITS implementation and to develop better ITS systems.

This paper presents the concept of an Instruction Path Coprocessor (I-COP), which is a programmable on-chip coprocessor, with its own mini-instruction set, that operates on the core processor's instructions to transform them into an internal format that can be more efficiently executed. It is located off the critical path of the core processor to ensure that it does not negatively impact the core processor's cycle time or pipeline depth. An I-COP is highly versatile and can be used to implement different types of instruction transformations to enhance the IPC of the core processor. We study four potential applications of the I-COP to demonstrate the feasibility of this concept and investigate the design issues of such a coprocessor. A prototype instruction set for the I-COP is presented along with an implementation framework that facilitates achieving high I-COP performance. Initial results indicate that the I-COP is able to efficiently implement the trace cache fill unit as well as the register move, stride data prefetching and linked data structure prefetching trace optimizations.

<div class="htmlview paragraph">JUST YESTERDAY, simulation tackled the issues of digital technology in a new generation of aircraft, but here we face another quantum leap as we look beyond the Boeing 757/767 model airplanes. The engineering simulator has evolved, over a period of 25 years, from a relatively modest beginning, to a sophisticated design tool essential to the development of new airplanes and weapons systems. The decisions involved in the management of simulation facilities has also evolved from choosing a modest “take-what-you-can-get” product line, to picking from warehouses full of “goodies,” all of which have their associated payoffs.</div> <div class="htmlview paragraph">As a background, the authors will attempt to outline from personal experience and long-term history with engineering simulation, the steps that were taken to reach the present level of sophistication in engineering simulators at Boeing. Engineering flight simulators have assumed an increasingly crucial role in the development and testing of new product lines in the aviation industry. Significant flight operational cost savings have resulted from the new generation of digital systems, promoting airline fleet modernization. Both part-task and fully instrumented man-in-the-loop aircraft simulators are being used extensively for the development and integration testing of these new systems. Simulation has proven to be a high payoff tool with increasing recognition from a competitive airline industry. In other words, simulation has “come of age.”</div> <div class="htmlview paragraph">From a present day technology base, we will attempt to look down the tunnel of the future and consider the demands of simulation for 1990 and beyond. An ever-increasing growth in computing requirements arises from the increasing sophistication of new airplane hardware and airborne software, and from a user community which demands ever-increasing fidelity. More models of software need to be incorporated into simulations; more and better data is being made available, all leading to more detailed simulations than ever before. In addition, the user community keeps expanding, which often leads to developing simulations never before attempted. All of this requires management to re-evaluate computing structure, configuration, and implementation into a mini, micro, multi, and/or concurrent processing world.</div> <div class="htmlview paragraph">The arrival of the engineering workstation poses yet another challenge as many of the exclusive functions of the simulation programmer become accessible to the design engineer. This means developing adequate help systems, friendly user interface, and workstation integration into the real-time network. Artificial intelligence technology holds some promise for human interface issues, but systems available today are not sufficient to meet the needs. Last but not least, the demands of the future involve a global re-education of simulation software personnel toward Ada<span class="xref">*</span>, structured methodology, and “embedded” designs. Experience in the most prevalent simulation languages does not easily lend itself to this re-education process.</div> <div class="htmlview paragraph">Engineering flight simulation - it spells out a revolution of change, technology forefronts of the future, and exciting challenges to those involved.</div>

This paper presents a comprehensive stochastic simulation approach combining resistor network embedded metropolis Monte Carlo method and the finite-element method for modeling FinFET oxide degradation. The geometrical impact of the 3-D structure is linked with the stochastic model, and the simulation method can evaluate the degradation behavior of FinFET structures accounting for geometrical variations and multiphysics coupling effects. The leakage current, electric field, current density, and temperature distribution are simulated and show good agreement with electrical stress test data. The simulation results also indicate the need for a bimodal clustering model to best describe FinFET degradation and dielectric breakdown lifetime statistics. The proposed simulation methodology is generic enough to be fine-tuned for reliability modeling of other logic and nonvolatile memory devices in the future.

Impact factor as an indicator of efficiency or sustainability is entirely correlated with the continuous development of the smart city concept technology application. Intelligent transportation systems (ITSs) and particularly autonomous vehicles are expected to play an important role in this challenging environment. Fast and secure connections will be pivotal in order to achieve this new vehicular communications’ application era. The use of millimeter-wave (mmWave) frequency range is the most promising approach to allow these real-time, high-demand applications that require higher bandwidth with the minimum possible latency. However, an in-depth mmWave-channel characterization of the environment is required for a proper mmWave-based solution deployment. In this work, a complete radio wave propagation channel characterization for a mmWave smart parking solution deployment in a complex outdoor environment was assessed at a 28 GHz frequency band. The considered scenario is a parking lot placed in an open free university campus area surrounded by inhomogeneous vegetation. The vehicle and vegetation density within the scenario, in terms of inherent transceivers density and communication impairments, leads to overall system operation challenges, given by multiple communication links operation at line-of-sight (LOS) and non-line-of-sight (NLOS) conditions. By means of an in-house developed 3D ray launching (3D-RL) algorithm, the impact of variable vegetation density is addressed, providing precise modelling estimations of large-scale multipath propagation effects in terms of received power levels and path loss. The obtained results along with the proposed simulation methodology can aid in an adequate characterization of an mmWave communication channel for new vehicular communications networks, applications, and deployments, considering the outdoor conditions as well as the impact of different vegetation densities, for current as well as for future wireless technologies.

Traditionally, distribution uniformity has been obtained by using rain gauges, which makes it a very expensive process. This paper sought to create a simulation strategy using QGIS and EPANET, both free software, that allowed the simulation of the water application results of all the emitters of an irrigation installation. In this way, it was possible to obtain the geospatial representation of the applied water and finally to know the distribution uniformity in the whole installation. The simulation finally fulfilled its objective and was compared with a study of distribution uniformity with rain gauges. The biggest difference between the measured and simulated data was a difference of 5.76% among the sectors. The simulated uniformity was very similar to the measured uniformity, which allowed us to affirm that the proposed simulation methodology was adequate. We believe that the methodology proposed in this article could be very useful in improving the management of sprinkler irrigation systems, particularly those in which distribution uniformity is of special importance. These improvements in management can also result in savings in water and other inputs, which are becoming increasingly important in the current context of climate change and the reduction in the impact of agriculture on the environment. Finally, similar studies could be carried out with the same tools for other pressurized irrigation systems, such as sprinkler irrigation outside greenhouses and drip irrigation.

Tri-axial Seismic Simulation of Solar Inverter – Productivity Improvement

The application of cellular structural materials provide new light-weight capabilities in many engineering fields. But the microstructure significantly influences the strength, the fatigue and fracture behavior as well as the life span of a structure made from cellular materials. The current paper illustrates the general idea how to take into account the cellular microstructure in the stress and strain analysis. The detailed geometry, including all discontinuities in the microstructure is available, for instance from measurements provided by the computed tomography (CT). The proposed simulation methodology is a combination of the finite element method (FEM) and the finite cell method (FCM). The FCM approach is applied in regions where discontinuities occur, avoiding a body-fitted mesh. As basis of the FEM-FCM coupling the commercial FEA package Abaqus is used. The theoretical background and the overall simulation workflow along with specific implementation details are discussed. Finally, academic benchmark problems are used to verify the developed coupling method.

A statistical description of safety aspects of grounding grids based on a new definition for risks of shock for human safety in the transient regime is presented in this paper. The procedure is based on a mathematical approach to evaluate the statistical distribution of lightning current followed by the Monte Carlo simulation of the grounding grid response to the probabilistic distribution of the injected current. The frequency-domain method of moments solution of the governing electric-field integral equation is used to simulate the grounding grid performance. The mapping of frequency-domain data to the corresponding transient data and vice-versa are achieved through appropriate use of the fast Fourier transform (FFT) and inverse FFT techniques, respectively. The proposed simulation methodology is used to obtain the probability by which the safety limits of a given grounding grid are violated. The safety limits are defined by comparing a severity parameter that is calculated by integration of an appropriate function of the current passing through human body over the time span of lighting current. Simulation results demonstrate the compatibility of the low-frequency safety index with that recommended in this paper for transient (high frequency) excitation of a grounding grid.

CHAPTER 5 - Writing Beginning Programs