Power Modeling and Capping for Heterogeneous ARM/FPGA SoCs

Low-power processors and accelerators that were originally designed for the embedded systems market are emerging as building blocks for servers. Power capping has been actively explored as a technique to reduce the energy footprint of high-performance processors. The opportunities and limitations of power capping on the new low-power processor and accelerator ecosystem are less understood. This paper presents an efficient power capping and management infrastructure for heterogeneous SoCs based on hybrid ARM/FPGA designs. The infrastructure coordinates dynamic voltage and frequency scaling with task allocation on a customised Linux system for the Xilinx Zynq SoC. We present a compiler-assisted power model to guide voltage and frequency scaling, in conjunction with workload allocation between the ARM cores and the FPGA, under given power caps. The model achieves less than 5% estimation bias to mean power consumption. In an FFT case study, the proposed power capping schemes achieve on average 97.5% of the performance of the optimal execution and match the optimal execution in 87.5% of the cases, while always meeting power constraints.

Barrier characteristics of PtSi/p-Si schottky diodes as determined from I-V-T measurements

The current-voltage-temperature characteristics of PtSi/p-Si Schottky barrier diodes were measured in the temperature range 60-115 K. Deviation of the ideality factor from unity below 80 K may be modelled using the so-called T-0 parameter with T-0 = 18 K. It is also shown that the curvature in the Richardson plots may be remedied by using the flatband rather than the zero-bias saturation current density. Physically, the departure from ideality is interpreted in terms of an inhomogeneous Schottky contact. Here we determine a mean barrier height at T = 0 K, phi(b)(-0) = 223 mV, with an (assumed) Gaussian distribution of standard deviation sigma(phi) = 12.5 mV. These data are correlated with the zero-bias barrier height, phi(j)(0) = 192 mV (at T = 90 K), the photoresponse barrier height, phi(ph) = 205 mV, and the flatband barrier height, phi(fb) = 214 mV. Finally, the temperature coefficient of the flatband barrier was found to be -0.121 mV K-1, which is approximately equal to 1/2(dE(g)(i)/dT), thus suggesting that the Fermi level at the interface is pinned to the middle of the band gap.

Electrostatic Solitary Waves in Relativistic Degenerate Electron-Positron-Ion Plasma

The linear and nonlinear properties of ion acoustic excitations propagating in warm dense electron-positron-ion plasma are investigated. Electrons and positrons are assumed relativistic and degenerate, following the Fermi-Dirac statistics, whereas the warm ions are described by a set of classical fluid equations. A linear dispersion relation is derived in the linear approximation. Adopting a reductive perturbation method, the Korteweg-de Vries equation is derived, which admits a localized wave solution in the form of a small-amplitude weakly super-acoustic pulse-shaped soliton. The analysis is extended to account for arbitrary amplitude solitary waves, by deriving a pseudoenergy-balance like equation, involving a Sagdeev-type pseudopotential. It is shown that the two approaches agree exactly in the small-amplitude weakly super-acoustic limit. The range of allowed values of the pulse soliton speed (Mach number), wherein solitary waves may exist, is determined. The effects of the key plasma configuration parameters, namely, the electron relativistic degeneracy parameter, the ion (thermal)-to-the electron (Fermi) temperature ratio, and the positron-to-electron density ratio, on the soliton characteristics and existence domain, are studied in detail. Our results aim at elucidating the characteristics of ion acoustic excitations in relativistic degenerate plasmas, e.g., in dense astrophysical objects, where degenerate electrons and positrons may occur.

Numerical modelling of low temperature laser produced magnesium plasma

The two-dimensional laser-plasma-interaction hydrodynamic code POLLUX has been used to simulate the ablation of a magnesium target by a 30-ns, 248-nm KrF excimer laser at low laser fluences of ≤10 J cm2. This code, originally written for much higher laser intensities, has been recently extended to include a detailed description of the equation of state in order to treat changes of phase within the target material, and also includes a Thomas Fermi description of the electrons. The simulated temporal and spatial evolution of the plasma plume in the early phase of the expansion (≤100 ns) is compared with experimental interferometric measurements of electron density. The expansion dynamics are in good agreement, although the simulated electron number density is about 2.5 times higher than the experimental values.

Nonlinear hydrodynamic Langmuir waves in fully degenerate relativistic plasma

The combined effect of special relativity and electron degeneracy on Langmuir waves is analyzed by utilizing a rigorous fully relativistic hydrodynamic model. Assuming a traveling wave solution form, a set of conservation laws is identified, together with a pseudo-potential function depending on the relativistic parameter p<inf>F</inf>/(m c) (where p<inf>F</inf> is the Fermi momentum, m is the mass of the charge carriers and c the speed of light), as well as on the amplitude of the electrostatic energy perturbation.

King David’s City at Khirbet Qeiyafa: Results of the Second Radiocarbon Dating Project

Fifteen samples of burnt olive pits discovered inside a jar in the destruction layer of the Iron Age city of Khirbet Qeiyafa were analyzed by accelerator mass spectrometry (AMS) radiocarbon dating. Of these, four were halved and sent to two different laboratories to minimize laboratory bias. The dating of these samples is ~1000 BC. Khirbet Qeiyafa is currently the earliest known example of a fortified city in the Kingdom of Judah and contributes direct evidence to the heated debate on the biblical narrative relating to King David. Was he the real historical ruler of an urbanized state-level society in the early 10th century BC or was this level of social development reached only at the end of the 8th century BC? We can conclude that there were indeed fortified centers in the Davidic kingdom from the studies presented. In addition, the dating of Khirbet Qeiyafa has far-reaching implications for the entire Levant. The discovery of Cypriot pottery at the site connects the 14C datings to Cyprus and the renewal of maritime trade between the island and the mainland in the Iron Age. A stone temple model from Khirbet Qeiyafa, decorated with triglyphs and a recessed doorframe, points to an early date for the development of this typical royal architecture of the Iron Age Levant.

Temporal Narrowing of Neutrons Produced by High-Intensity Short-Pulse Lasers

The production of neutron beams having short temporal duration is studied using ultraintense laser pulses. Laser-accelerated protons are spectrally filtered using a laser-triggered microlens to produce a short duration neutron pulse via nuclear reactions induced in a converter material (LiF). This produces a similar to 3 ns duration neutron pulse with 10(4) n/MeV/sr/shot at 0.56 m from the laser-irradiated proton source. The large spatial separation between the neutron production and the proton source allows for shielding from the copious and undesirable radiation resulting from the laser-plasma interaction. This neutron pulse compares favorably to the duration of conventional accelerator sources and should scale up with, present and future, higher energy laser facilities to produce brighter and shorter neutron beams for ultrafast probing of dense materials.

Optimised Multiplication Architectures for Accelerating Fully Homomorphic Encryption

Large integer multiplication is a major performance bottleneck in fully homomorphic encryption (FHE) schemes over the integers. In this paper two optimised multiplier architectures for large integer multiplication are proposed. The first of these is a low-latency hardware architecture of an integer-FFT multiplier. Secondly, the use of low Hamming weight (LHW) parameters is applied to create a novel hardware architecture for large integer multiplication in integer-based FHE schemes. The proposed architectures are implemented, verified and compared on the Xilinx Virtex-7 FPGA platform. Finally, the proposed implementations are employed to evaluate the large multiplication in the encryption step of FHE over the integers. The analysis shows a speed improvement factor of up to 26.2 for the low-latency design compared to the corresponding original integer-based FHE software implementation. When the proposed LHW architecture is combined with the low-latency integer-FFT accelerator to evaluate a single FHE encryption operation, the performance results show that a speed improvement by a factor of approximately 130 is possible.

Streaming Elements for FPGA Signal and Image Processing Accelerators

Field programmable gate array devices boast abundant resources with which custom accelerator components for signal, image and data processing may be realised; however, realising high performance, low cost accelerators currently demands manual register transfer level design. Software-programmable ’soft’ processors have been proposed as a way to reduce this design burden but they are unable to support performance and cost comparable to custom circuits. This paper proposes a new soft processing approach for FPGA which promises to overcome this barrier. A high performance, fine-grained streaming processor, known as a Streaming Accelerator Element, is proposed which realises accelerators as large scale custom multicore networks. By adopting a streaming execution approach with advanced program control and memory addressing capabilities, typical program inefficiencies can be almost completely eliminated to enable performance and cost which are unprecedented amongst software-programmable solutions. When used to realise accelerators for fast fourier transform, motion estimation, matrix multiplication and sobel edge detection it is shown how the proposed architecture enables real-time performance and with performance and cost comparable with hand-crafted custom circuit accelerators and up to two orders of magnitude beyond existing soft processors.

The role of complexity metrics in a multi-institutional dosimetry audit of VMAT

OBJECTIVE: To demonstrate the benefit of complexity metrics such as the modulation complexity score (MCS) and monitor units (MUs) in multi-institutional audits of volumetric-modulated arc therapy (VMAT) delivery.

METHODS: 39 VMAT treatment plans were analysed using MCS and MU. A virtual phantom planning exercise was planned and independently measured using the PTW Octavius(®) phantom and seven29(®) 2D array (PTW-Freiburg GmbH, Freiburg, Germany). MCS and MU were compared with the median gamma index pass rates (2%/2 and 3%/3 mm) and plan quality. The treatment planning systems (TPS) were grouped by VMAT modelling being specifically designed for the linear accelerator manufacturer's own treatment delivery system (Type 1) or independent of vendor for VMAT delivery (Type 2). Differences in plan complexity (MCS and MU) between TPS types were compared.

RESULTS: For Varian(®) linear accelerators (Varian(®) Medical Systems, Inc., Palo Alto, CA), MCS and MU were significantly correlated with gamma pass rates. Type 2 TPS created poorer quality, more complex plans with significantly higher MUs and MCS than Type 1 TPS. Plan quality was significantly correlated with MU for Type 2 plans. A statistically significant correlation was observed between MU and MCS for all plans (R = -0.84, p < 0.01).

CONCLUSION: MU and MCS have a role in assessing plan complexity in audits along with plan quality metrics. Plan complexity metrics give some indication of plan deliverability but should be analysed with plan quality.

ADVANCES IN KNOWLEDGE: Complexity metrics were investigated for a national rotational audit involving 34 institutions and they showed value. The metrics found that more complex plans were created for planning systems which were independent of vendor for VMAT delivery.

A laser driven pulsed X-ray backscatter technique for enhanced penetrative imaging

X-ray backscatter imaging can be used for a wide range of imaging applications, in particular for industrial inspection and portal security. Currently, the application of this imaging technique to the detection of landmines is limited due to the surrounding sand or soil strongly attenuating the 10s to 100s of keV X-rays required for backscatter imaging. Here, we introduce a new approach involving a 140 MeV short-pulse (< 100 fs) electron beam generated by laser wakefield acceleration to probe the sample, which produces Bremsstrahlung X-rays within the sample enabling greater depths to be imaged. A variety of detector and scintillator configurations are examined, with the best time response seen from an absorptive coated BaF₂ scintillator with a bandpass filter to remove the slow scintillation emission components. An X-ray backscatter image of an array of different density and atomic number items is demonstrated. The use of a compact laser wakefield accelerator to generate the electron source, combined with the rapid development of more compact, efficient and higher repetition rate high power laser systems will make this system feasible for applications in the field.

Electron-phonon thermalization in a scalable method for real-time quantum dynamics

We present a quantum simulation method that follows the dynamics of out-of-equilibrium many-body systems of electrons and oscillators in real time. Its cost is linear in the number of oscillators and it can probe time scales from attoseconds to hundreds of picoseconds. Contrary to Ehrenfest dynamics, it can thermalize starting from a variety of initial conditions, including electronic population inversion. While an electronic temperature can be defined in terms of a nonequilibrium entropy, a Fermi-Dirac distribution in general emerges only after thermalization. These results can be used to construct a kinetic model of electron-phonon equilibration based on the explicit quantum dynamics.

Guided post-acceleration of laser-driven ions by a miniature modular structure

All-optical approaches to particle acceleration are currently attracting a significant research effort internationally. Although characterized by exceptional transverse and longitudinal emittance, laser-driven ion beams currently have limitations in terms of peak ion energy, bandwidth of the energy spectrum and beam divergence. Here we introduce the concept of a versatile, miniature linear accelerating module, which, by employing laser-excited electromagnetic pulses directed along a helical path surrounding the laser-accelerated ion beams, addresses these shortcomings simultaneously. In a proof-of-principle experiment on a university-scale system, we demonstrate post-acceleration of laser-driven protons from a flat foil at a rate of 0.5 GeVm^-1, already beyond what can be sustained by conventional accelerator technologies, with dynamic beam collimation and energy selection. These results open up new opportunities for the development of extremely compact and cost-effective ion accelerators for both established and innovative applications.

 Graphitization of Small Carbonate Samples for Paleoceanographic Research at the Godwin Radiocarbon Laboratory, University of Cambridge

A new radiocarbon preparation facility was set up in 2010 at the Godwin Laboratory for Palaeoclimate Research, at the University of Cambridge. Samples are graphitized via hydrogen reduction on an iron powder catalyst before being sent to the Chrono Centre, Belfast, or the Australian National University for accelerator mass spectrometry (AMS) analysis. The experimental setup and procedure have recently been developed to investigate the potential for running small samples of foraminiferal carbonate. By analyzing background values of samples ranging from 0.04 to 0.6 mg C along with similar sized secondary standards, the setup and experimental procedures were optimized for small samples. “Background” modern 14C contamination has been minimized through careful selection of iron powder, and graphitization has been optimized through the use of “small volume” reactors, allowing samples containing as little as 0.08 mg C to be graphitized and accurately dated. Graphitization efficiency/fractionation is found not to be the main limitation on the analysis of samples smaller than 0.07 mg C, which rather depends primarily on AMS ion beam optics, suggesting further improvements in small sample analysis might yet be achieved with our methodology.

The use of Log-file analysis within VMAT audits

OBJECTIVE: This work investigates the delivery accuracy of different Varian linear accelerator models using log-file derived MLC RMS values.

METHODS: Seven centres independently created a plan on the same virtual phantom using their own planning system and the log files were analysed following delivery of the plan in each centre to assess MLC positioning accuracy. A single standard plan was also delivered by seven centres to remove variations in complexity and the log files were analysed for Varian TrueBeams and Clinacs (2300IX or 2100CD models).

RESULTS: Varian TrueBeam accelerators had better MLC positioning accuracy (<1.0mm) than the 2300IX (<2.5mm) following delivery of the plans created by each centre and also the standard plan. In one case log files provided evidence that reduced delivery accuracy was not associated with the linear accelerator model but was due to planning issues.

CONCLUSIONS: Log files are useful in identifying differences between linear accelerator models, and isolate errors during end-to-end testing in VMAT audits. Log file analysis can rapidly eliminate the machine delivery from the process and divert attention with confidence to other aspects. Advances in Knowledge: Log file evaluation was shown to be an effective method to rapidly verify satisfactory treatment delivery when a dosimetric evaluation fails during end-to-end dosimetry audits. MLC RMS values for Varian TrueBeams were shown to be much smaller than Varian Clinacs for VMAT deliveries.