A Scalable High Throughput Firewall in FPGA

High end network security applications demand high speed operation and large rule set support. Packet classification is the core functionality that demands high throughput in such applications. This paper proposes a packet classification architecture to meet such high throughput. We have implemented a Firewall with this architecture in reconflgurable hardware. We propose an extension to Distributed Crossproducting of Field Labels (DCFL) technique to achieve scalable and high performance architecture. The implemented Firewall takes advantage of inherent structure and redundancy of rule set by using our DCFL Extended (DCFLE) algorithm. The use of DCFLE algorithm results in both speed and area improvement when it is implemented in hardware. Although we restrict ourselves to standard 5-tuple matching, the architecture supports additional fields. High throughput classification invariably uses Ternary Content Addressable Memory (TCAM) for prefix matching, though TCAM fares poorly in terms of area and power efficiency. Use of TCAM for port range matching is expensive, as the range to prefix conversion results in large number of prefixes leading to storage inefficiency. Extended TCAM (ETCAM) is fast and the most storage efficient solution for range matching. We present for the first time a reconfigurable hardware implementation of ETCAM. We have implemented our Firewall as an embedded system on Virtex-II Pro FPGA based platform, running Linux with the packet classification in hardware. The Firewall was tested in real time with 1 Gbps Ethernet link and 128 sample rules. The packet classification hardware uses a quarter of logic resources and slightly over one third of memory resources of XC2VP30 FPGA. It achieves a maximum classification throughput of 50 million packet/s corresponding to 16 Gbps link rate for the worst case packet size. The Firewall rule update involves only memory re-initialization in software without any hardware change.

A Scalable High Throughput Firewall in FPGA

High end network security applications demand high speed operation and large rule set support. Packet classification is the core functionality that demands high throughput in such applications. This paper proposes a packet classification architecture to meet such high throughput. We have Implemented a Firewall with this architecture in reconfigurable hardware. We propose an extension to Distributed Crossproducting of Field Labels (DCFL) technique to achieve scalable and high performance architecture. The implemented Firewall takes advantage of inherent structure and redundancy of rule set by using, our DCFL Extended (DCFLE) algorithm. The use of DCFLE algorithm results In both speed and area Improvement when It is Implemented in hardware. Although we restrict ourselves to standard 5-tuple matching, the architecture supports additional fields.High throughput classification Invariably uses Ternary Content Addressable Memory (TCAM) for prefix matching, though TCAM fares poorly In terms of area and power efficiency. Use of TCAM for port range matching is expensive, as the range to prefix conversion results in large number of prefixes leading to storage inefficiency. Extended TCAM (ETCAM) is fast and the most storage efficient solution for range matching. We present for the first time a reconfigurable hardware Implementation of ETCAM. We have implemented our Firewall as an embedded system on Virtex-II Pro FPGA based platform, running Linux with the packet classification in hardware. The Firewall was tested in real time with 1 Gbps Ethernet link and 128 sample rules. The packet classification hardware uses a quarter of logic resources and slightly over one third of memory resources of XC2VP30 FPGA. It achieves a maximum classification throughput of 50 million packet/s corresponding to 16 Gbps link rate for file worst case packet size. The Firewall rule update Involves only memory re-initialiization in software without any hardware change.

Partial discharges at low pressures in a dielectric interface between uniform field electrodes

Partial discharges in a gaseous interface due to the presence of a dielectric between two uniform field electrodes in air at different pressures from 0.5 to 685 mm Hg have been studied and measurements of inception and extinction voltages, number of pulses and their charge magnitudes at inception are reported. It has been observed that the extinction voltage can be as low as 70% of the inception voltage suggesting that the working voltage in such cases should be about 30% lower than the observed inception voltage. Small magnitude pulses are found to be more in number than large magnitude pulses. The charge is found to be pressure dependent. The results have been explained on the basis of an equivalent circuit consisting of resistance and capacitance in which the discharge gap functions as a switch.

Surface waves in the presence of external high frequency fields

The system equations of a collisionless, unmagnetized plasma, contained in a box where a high frequency (HF) electric field is incident, are solved in the electrostatic approximation. The surface modes of the plasma in the semi-infinite and box geometry are investigated. In thi high frequency limit, the mode frequencies are not significantly changed by the HF field but their group velocities can be quite different. Two long wavelength low frequency modes, which are not excited in the absence of HF field, are found. These modes are true surface modes (decaying on one wavelength from the surface) unlike the only low frequency ion acoustic mode in the zero field case. In the short wavelength limit the low frequency mode occurs at omega i/ square root 2, omega i being the ion plasma frequency, as a result similar to the case of no HF field.

Time dependent rotational flow of a viscous fluid over an infinite porous disk with a magnetic field

Both the semi-similar and self-similar flows due to a viscous fluid rotating with time dependent angular velocity over a porous disk of large radius at rest with or without a magnetic field are investigated. For the self-similar case the resulting equations for the suction and no mass transfer cases are solved numerically by quasilinearization method whereas for the semi-similar case and injection in the self-similar case an implicit finite difference method with Newton's linearization is employed. For rapid deceleration of fluid and for moderate suction in the case of self-similar flow there exists a layer of fluid, close to the disk surface where the sense of rotation is opposite to that of the fluid rotating far away. The velocity profiles in the absence of magnetic field are found to be oscillatory except for suction. For the accelerating freestream, (semi-similar flow) the effect of time is to reduce the amplitude of the oscillations of the velocity components. On the other hand the effect of time for the oscillating case is just the opposite.

Numerical simulation of conductive particle behaviour at the surface of a plate electrode affected by a DC corona field

The electric field in certain electrostatic devices can be modeled by a grounded plate electrode affected by a corona discharge generated by a series of parallel wires connected to a DC high-voltage supply. The system of differential equations that describe the behaviour (i.e., charging and motion) of the conductive particle in such an electric field has been numerically solved, using several simplifying assumptions. Thus, it was possible to investigate the effect of various electrical and mechanical factors on the trajectories of conductive particles. This model has been employed to study the behaviour of coalparticles in fly-ash corona separators.

Phase transition in ammonium aluminium and ammonium chromium alums-A high pressure EPR study

An investigation of the phase transitions at high pressures in the alums mentioned in the title has been carried out using EPR of the Cr3+ ion (at the trivalent metal ion site). It is observed that at ambient as well as at high pressures there is a change of slope in the linear variations of the zero field splitting with temperature and that the low temperature phase is characterised by a large number of lines in the EPR spectra. The transition temperature shows a large positive shift with pressure, for both the alums. All these facts are explained in terms of our model of the origin of the trigonal field at the trivalent metal ion site as well as the details of the motion of NH4+ ion.

Gluon-field contribution in QCD sum rules for the magnetic moments of the nucleons

The Wilson coefficient corresponding to the gluon-field strength GμνGμν is evaluated for the nucleon current correlation function in the presence of a static external electromagnetic field, using a regulator mass Λ to separate the high-momentum part of the Feynman diagrams. The magnetic-moment sum rules are analyzed by two different methods and the sensitivity of the results to variations in Λ are discussed.

Magnetic Field Induced Instabilities In Localized Two-Dimensional Electron Systems

The results of extensive transport studies in localized regime of mesoscopic two-dimensional electron systems (2DES) with varying disorder are presented. A quick overview of previously achieved result is given. The main focus is on the observation of density dependent instabilities manifested by strong resistance oscillations induced by high perpendicular magnetic fields B-perpendicular to. While the amplitude of the oscillations is strongly enhanced with increasing B-perpendicular to, their position in electron density remains unaffected. The temperature dependence of resistivity shows a transition from an activated behaviour at high temperature to a saturated behaviour at low T. In the positions of resistance minima, the T dependence can even become metal-like (d rho/dT > 0). The activation energies obtained from the high T behaviour exhibit a formation of plateaux in connection with the resistance oscillations when analyzed as a function of electron density. We suggest the interplay between a strongly interacting electron phase and the background disorder as a possible explanation for our observation.

Nonlinear transport in semiconducting polymers at high carrier densities

Conducting and semiconducting polymers are important materials in the development of printed, flexible, large-area electronics such as flat-panel displays and photovoltaic cells. There has been rapid progress in developing conjugated polymers with high transport mobility required for high-performance field-effect transistors (FETs), beginning(1) with mobilities around 10(-4) cm(2) V-1 s(-1) to a recent report(2) of 1 cm(2) V-1 s(-1) for poly(2,5-bis(3-tetradecylthiophen-2-yl) thieno[3,2-b] thiophene) (PBTTT). Here, the electrical properties of PBTTT are studied at high charge densities both as the semiconductor layer in FETs and in electrochemically doped films to determine the transport mechanism. We show that data obtained using a wide range of parameters (temperature, gate-induced carrier density, source-drain voltage and doping level) scale onto the universal curve predicted for transport in the Luttinger liquid description of the one-dimensional `metal'.

Sulphate ion dynamics in alpha-alums studied by esr at high pressures

The variation of zero-field splitting and linewidth of Cr3+ ion in KCr and KAI alums with hydrostatic pressure and with temperature is investigated. A model for the apparent phase transition is proposed on the basis of the reorientational motion of the SO2�4 groups.

Surface explosive instability for high frequency waves

High frequency three-wave nonlinear 'explosive' interaction of the surface modes of a semi-infinite beam-plasma system under no external field is investigated. The conditions that favour nonlinear instability, keep the plasma linearly stable. The beam runs parallel to the surface. If at least one of the three wave vectors of the surface modes is parallel to the beam, explosive interaction at the surface takes place after it has happened in the plasma bulk, provided the bulk waves propagate almost perpendicular to the surface and are of short wavelength. On the other hand if the bulk modes have long wavelength and propagate almost parallel to the surface, the surface modes can 'explode' first.

High temperature stability of oxysulfides containing Ce3+ and Y3+ ions

Standard Gibbs energies of formation of oxysulfides of cerium and yttrium from their respective oxedes were determined using solid oxide galvanic cells incorporating calcia-stabilized zirconia as the electrolyte in the temperature range 870–1120 K. The sulfur potential over the electrode containing the oxide and oxysulfide was fixed by a buffer mixture of Ag + Ag2S. A small amount of CaH2 was added to the buffer to generate an equilibrium ratio of H2S and H2 species in a closed system containing the buffer and the electrode. The sulfur potential is transmitted to the electrode via the gas phase. The results can be summarized by the equations 2left angle bracketCeO2right-pointing angle bracket+1/2(S2)→left angle bracketCe2O2Sright-pointing angle bracket+(O2) ΔG°=430600−109·7T(±400)J mol−1 left angle bracketY2O3right-pointing angle bracket+1/2(S2)→left angle bracketY2O2Sright-pointing angle bracket+1/2(O2) ΔG°=114780−1·45T(±200)J mol−1 The values are compared with data reported in the literature. The stability field diagram for the Ce---O---S system has been developed using the results of this study for Ce2O2S and data for other phases from the literature.

Surface waves in the presence of external high frequency fields

The system equations of a collisionless, unmagnetized plasma, contained in a box where a high frequency (h.f.1 electric field is incident, are solved in the electrostatic approximation. The surface modes of the plasma in the semi-infinite and box geometry are investigated. In the high frequency limit, the mode frequencies are not significantly changed by the h.f. field but their group velocities can be quite different. Two long wavelength low frequency modes, which are not excited in the absence of h.f. field, are found. These modes are true surface modes (decaying on one wavelength from the surface) unlike the only low frequency ion acoustic mode in the zero field case. In the short wavelength limit the low frequency mode occurs at &/2, oi being the ion plasma frequency, a result similar to the case of no h.f. field.

Surface instability in a semi-infinite plasma in the presence of high frequency fields

The surface instability of a semi-infinite plasma immersed in a high frequency field is investigated. When the natural Langmuir frequency of the surface is nearly equal to the frequency of the high frequency field, the dispersion relation predicts build-up of oscillations with a growth rate comparable with the real part of the frequency. Threshold values above which the instability is possible are derived.