DFL: A Data Flow Language

Many novel computer architectures like array and multiprocessors which achieve high performance through the use of concurrency exploit variations of the von Neumann model of computation. The effective utilization of the machines makes special demands on programmers and their programming languages, such as the structuring of data into vectors or the partitioning of programs into concurrent processes. In comparison, the data flow model of computation demands only that the principle of structured programming be followed. A data flow program, often represented as a data flow graph, is a program that expresses a computation by indicating the data dependencies among operators. A data flow computer is a machine designed to take advantage of concurrency in data flow graphs by executing data independent operations in parallel. In this paper, we discuss the design of a high level language (DFL: Data Flow Language) suitable for data flow computers. Some sample procedures in DFL are presented. The implementation aspects have not been discussed in detail since there are no new problems encountered. The language DFL embodies the concepts of functional programming, but in appearance closely resembles Pascal. The language is a better vehicle than the data flow graph for expressing a parallel algorithm. The compiler has been implemented on a DEC 1090 system in Pascal.

Block- and strand-multiplexing for fast computation of a class of transforms

The transforms dealt with in this paper are defined in terms of the transform kernels which are Kroneeker products of the two or more component kernels. The signal flow-graph for the computation of such a transform is obtained with the flow-graphs for the component transforms as building blocks.

Taming Control Divergence in GPUs through Control Flow Linearization

Branch divergence is a very commonly occurring performance problem in GPGPU in which the execution of diverging branches is serialized to execute only one control flow path at a time. Existing hardware mechanism to reconverge threads using a stack causes duplicate execution of code for unstructured control flow graphs. Also the stack mechanism cannot effectively utilize the available parallelism among diverging branches. Further, the amount of nested divergence allowed is also limited by depth of the branch divergence stack. In this paper we propose a simple and elegant transformation to handle all of the above mentioned problems. The transformation converts an unstructured CFG to a structured CFG without duplicating user code. It incurs only a linear increase in the number of basic blocks and also the number of instructions. Our solution linearizes the CFG using a predicate variable. This mechanism reconverges the divergent threads as early as possible. It also reduces the depth of the reconvergence stack. The available parallelism in nested branches can be effectively extracted by scheduling the basic blocks to reduce the effect of stalls due to memory accesses. It can also increase execution efficiency of nested loops with different trip counts for different threads. We implemented the proposed transformation at PTX level using the Ocelot compiler infrastructure. We evaluated the technique using various benchmarks to show that it can be effective in handling the performance problem due to divergence in unstructured CFGs.

Low-power pipelined LMS adaptive filter architectures with minimal adaptation delay

The use of delayed coefficient adaptation in the least mean square (LMS) algorithm has enabled the design of pipelined architectures for real-time transversal adaptive filtering. However, the convergence speed of this delayed LMS (DLMS) algorithm, when compared with that of the standard LMS algorithm, is degraded and worsens with increase in the adaptation delay. Existing pipelined DLMS architectures have large adaptation delay and hence degraded convergence speed. We in this paper, first present a pipelined DLMS architecture with minimal adaptation delay for any given sampling rate. The architecture is synthesized by using a number of function preserving transformations on the signal flow graph representation of the DLMS algorithm. With the use of carry-save arithmetic, the pipelined architecture can support high sampling rates, limited only by the delay of a full adder and a 2-to-1 multiplexer. In the second part of this paper, we extend the synthesis methodology described in the first part, to synthesize pipelined DLMS architectures whose power dissipation meets a specified budget. This low-power architecture exploits the parallelism in the DLMS algorithm to meet the required computational throughput. The architecture exhibits a novel tradeoff between algorithmic performance (convergence speed) and power dissipation. (C) 1999 Elsevier Science B.V. All rights resented.

SARAS: a precision system for measurement of the cosmic radio background and signatures from the epoch of reionization

SARAS is a correlation spectrometer purpose designed for precision measurements of the cosmic radio background and faint features in the sky spectrum at long wavelengths that arise from redshifted 21-cm from gas in the reionization epoch. SARAS operates in the octave band 87.5-175 MHz. We present herein the system design arguing for a complex correlation spectrometer concept. The SARAS design concept provides a differential measurement between the antenna temperature and that of an internal reference termination, with measurements in switched system states allowing for cancellation of additive contaminants from a large part of the signal flow path including the digital spectrometer. A switched noise injection scheme provides absolute spectral calibration. Additionally, we argue for an electrically small frequency-independent antenna over an absorber ground. Various critical design features that aid in avoidance of systematics and in providing calibration products for the parametrization of other unavoidable systematics are described and the rationale discussed. The signal flow and processing is analyzed and the response to noise temperatures of the antenna, reference termination and amplifiers is computed. Multi-path propagation arising from internal reflections are considered in the analysis, which includes a harmonic series of internal reflections. We opine that the SARAS design concept is advantageous for precision measurement of the absolute cosmic radio background spectrum; therefore, the design features and analysis methods presented here are expected to serve as a basis for implementations tailored to measurements of a multiplicity of features in the background sky at long wavelengths, which may arise from events in the dark ages and subsequent reionization era.

Response time measurement in flow induced signal generation on semiconductors

Measurable electrical signal is generated when a gas flows over a variety of solids, including doped semiconductors, even at the modest speed of a few meters per second. The underlying mechanism is an interesting interplay of Bernoulli's principle and the Seebeck effect. The electrical signal depends on the square of Mach number (M) and is proportional to the Seebeck coefficient (S) of the solids. Here we present experimental estimate of the response time of the signal rise and fall process, i.e. how fast the semiconductor materials respond to a steady flow as soon as it is set on or off. A theoretical model is also presented to understand the process and the dependence of the response time on the nature and physical dimensions of the semiconductor material used and they are compared with the experimental observations. (c) 2007 Elsevier B.V. All rights reserved.

Dynamic analysis of small signal voltage instability decoupled from angle instability

This paper presents a methodology for dynamic analysis of short term small signal voltage instability in a multi-machine power system. The formulation of the problem is done by decoupling the angle instability from the voltage instability. The method is based on the incremental reactive current flow network (IRCFN), where the incremental reactive current injection at each bus is related to the incremental voltage magnitude at all the buses. Small signal stability using the eigenvalue analysis is illustrated utilizing a single-machine load bus (SMLB) and three-machine system examples. The role of a static var compensator (SVC) at the load bus is also examined.

Analytical studies of gain optimization in CO2-N2 gasdynamic lasers employing two-dimensional wedge nozzles

An analytical method has been proposed to optimise the small-signaloptical gain of CO2-N2 gasdynamic lasers (gdl) employing two-dimensional (2D) wedge nozzles. Following our earlier work the equations governing the steady, inviscid, quasi-one-dimensional flow in the wedge nozzle of thegdl are reduced to a universal form so that their solutions depend on a single unifying parameter. These equations are solved numerically to obtain similar solutions for the various flow quantities, which variables are subsequently used to optimize the small-signal-gain. The corresponding optimum values like reservoir pressure and temperature and 2D nozzle area ratio also have been predicted and graphed for a wide range of laser gas compositions, with either H2O or He as the catalyst. A large number of graphs are presented which may be used to obtain the optimum values of small signal gain for a wide range of laser compositions without further computations.

An (O)over-tilde(mn) Gomory-Hu Tree Construction Algorithm for Unweighted Graphs

We present a fast algorithm for computing a Gomory-Hu tree or cut tree for an unweighted undirected graph G = (V, E). The expected running time of our algorithm is (O) over tilde (mc) where vertical bar E vertical bar = m and c is the maximum u-v edge connectivity, where u, v is an element of V. When the input graph is also simple (i.e., it has no parallel edges), then the u-v edge connectivity for each pair of vertices u and v is at most n - 1; so the expected run-ning time of our algorithm for simple unweighted graphs is (O) over tilde (mn). All the algorithms currently known for constructing a Gomory-Hu tree [8, 9] use n - 1 minimum s-t cut (i.e., max flow) subroutines. This in conjunction with the current fastest (O) over tilde (n(20/9)) max flow algorithm due to Karger and Levine[11] yields the current best running time of (O) over tilde (n(20/9)n) for Gomory-Hu tree construction on simple unweighted graphs with m edges and n vertices. Thus we present the first (O) over tilde (mn) algorithm for constructing a Gomory-Hu tree for simple unweighted graphs. We do not use a max flow subroutine here; we present an efficient tree packing algorithm for computing Steiner edge connectivity and use this algorithm as our main subroutine. The advantage in using a tree packing algorithm for constructing a Gomory-Hu tree is that the work done in computing a minimum Steiner cut for a Steiner set S subset of V can be reused for computing a minimum Steiner cut for certain Steiner sets S' subset of S.

Flow driven electronic transport in carbon nan otubes

The flow of a liquid on single-walled carbon nanotube bundles induces an electrical signal (voltage/current) in the sample along the direction of the flow. The electrical response is found to be logarithmic in the flow speed over a wide range. The magnitude of the flow induced electrical signal generated depends sensitively on the ionic conductivity and the polar nature of the liquid, and electrical biasing of the nanotubes can control its direction. Our measurements suggest that the dominant mechanism responsible for this highly sub-linear response should involve a direct forcing of the free charge carriers in the nanotubes by the fluctuating Coulombic field of the liquid flowing past it.

Conjugate MHD flow past a flat plate

A boundary layer solution for the conjugate forced convection flow of an electrically conducting fluid over a semi-infinite flat plate in the presence of a transverse magnetic field is presented. The governing nonsimilar partial differential equations are solved numerically using the Keller box method. Values of the temperature profiles of the plate are obtained for various values of the parameters entering the problem and are given in a table and shown on graphs.

An O(mn) Gomory-Hu Tree Construction Algorithm for Unweighted Graphs

We present a fast algorithm for computing a Gomory-Hu tree or cut tree for an unweighted undirected graph G = (V,E). The expected running time of our algorithm is Õ(mc) where |E| = m and c is the maximum u-vedge connectivity, where u,v ∈ V. When the input graph is also simple (i.e., it has no parallel edges), then the u-v edge connectivity for each pair of vertices u and v is at most n-1; so the expected running time of our algorithm for simple unweighted graphs is Õ(mn).All the algorithms currently known for constructing a Gomory-Hu tree [8,9] use n-1 minimum s-t cut (i.e., max flow) subroutines. This in conjunction with the current fastest Õ(n20/9) max flow algorithm due to Karger and Levine [11] yields the current best running time of Õ(n20/9n) for Gomory-Hu tree construction on simpleunweighted graphs with m edges and n vertices. Thus we present the first Õ(mn) algorithm for constructing a Gomory-Hu tree for simple unweighted graphs.We do not use a max flow subroutine here; we present an efficient tree packing algorithm for computing Steiner edge connectivity and use this algorithm as our main subroutine. The advantage in using a tree packing algorithm for constructing a Gomory-Hu tree is that the work done in computing a minimum Steiner cut for a Steiner set S ⊆ V can be reused for computing a minimum Steiner cut for certain Steiner sets S' ⊆ S.

An instantaneous control model for flow control in an ATM network

This paper is concerned with the optimal flow control of an ATM switching element in a broadband-integrated services digital network. We model the switching element as a stochastic fluid flow system with a finite buffer, a constant output rate server, and a Gaussian process to characterize the input, which is a heterogeneous set of traffic sources. The fluid level should be maintained between two levels namely b1 and b2 with b1

Scalable flow-sensitive pointer analysis for fava with strong updates

The ability to perform strong updates is the main contributor to the precision of flow-sensitive pointer analysis algorithms. Traditional flow-sensitive pointer analyses cannot strongly update pointers residing in the heap. This is a severe restriction for Java programs. In this paper, we propose a new flow-sensitive pointer analysis algorithm for Java that can perform strong updates on heap-based pointers effectively. Instead of points-to graphs, we represent our points-to information as maps from access paths to sets of abstract objects. We have implemented our analysis and run it on several large Java benchmarks. The results show considerable improvement in precision over the points-to graph based flow-insensitive and flow-sensitive analyses, with reasonable running time.

Evaluation of polyvinylidene fluoride nasal sensor to assess deviated nasal septum in comparision with peak nasal inspiratory flow measurements

Background: Deviated nasal septum (DNS) is one of the major causes of nasal obstruction. Polyvinylidene fluoride (PVDF) nasal sensor is the new technique developed to assess the nasal obstruction caused by DNS. This study evaluates the PVDF nasal sensor measurements in comparison with PEAK nasal inspiratory flow (PNIF) measurements and visual analog scale (VAS) of nasal obstruction. Methods: Because of piezoelectric property, two PVDF nasal sensors provide output voltage signals corresponding to the right and left nostril when they are subjected to nasal airflow. The peak-to-peak amplitude of the voltage signal corresponding to nasal airflow was analyzed to assess the nasal obstruction. PVDF nasal sensor and PNIF were performed on 30 healthy subjects and 30 DNS patients. Receiver operating characteristic was used to analyze the DNS of these two methods. Results: Measurements of PVDF nasal sensor strongly correlated with findings of PNIF (r = 0.67; p < 0.01) in DNS patients. A significant difference (p < 0.001) was observed between PVDF nasal sensor measurements and PNIF measurements of the DNS and the control group. A cutoff between normal and pathological of 0.51 Vp-p for PVDF nasal sensor and 120 L/min for PNIF was calculated. No significant difference in terms of sensitivity of PVDF nasal sensor and PNIF (89.7% versus 82.6%) and specificity (80.5% versus 78.8%) was calculated. Conclusion: The result shows that PVDF measurements closely agree with PNIF findings. Developed PVDF nasal sensor is an objective method that is simple, inexpensive, fast, and portable for determining DNS in clinical practice.