Automatic Compilation of MATLAB Programs for Synergistic Execution on Heterogeneous Processors

MATLAB is an array language, initially popular for rapid prototyping, but is now being increasingly used to develop production code for numerical and scientific applications. Typical MATLAB programs have abundant data parallelism. These programs also have control flow dominated scalar regions that have an impact on the program's execution time. Today's computer systems have tremendous computing power in the form of traditional CPU cores and throughput oriented accelerators such as graphics processing units(GPUs). Thus, an approach that maps the control flow dominated regions to the CPU and the data parallel regions to the GPU can significantly improve program performance. In this paper, we present the design and implementation of MEGHA, a compiler that automatically compiles MATLAB programs to enable synergistic execution on heterogeneous processors. Our solution is fully automated and does not require programmer input for identifying data parallel regions. We propose a set of compiler optimizations tailored for MATLAB. Our compiler identifies data parallel regions of the program and composes them into kernels. The problem of combining statements into kernels is formulated as a constrained graph clustering problem. Heuristics are presented to map identified kernels to either the CPU or GPU so that kernel execution on the CPU and the GPU happens synergistically and the amount of data transfer needed is minimized. In order to ensure required data movement for dependencies across basic blocks, we propose a data flow analysis and edge splitting strategy. Thus our compiler automatically handles composition of kernels, mapping of kernels to CPU and GPU, scheduling and insertion of required data transfer. The proposed compiler was implemented and experimental evaluation using a set of MATLAB benchmarks shows that our approach achieves a geometric mean speedup of 19.8X for data parallel benchmarks over native execution of MATLAB.

Scalable Context-Sensitive Points-To Analysis Using Multi-Dimensional Bloom Filters

Context-sensitive points-to analysis is critical for several program optimizations. However, as the number of contexts grows exponentially, storage requirements for the analysis increase tremendously for large programs, making the analysis non-scalable. We propose a scalable flow-insensitive context-sensitive inclusion-based points-to analysis that uses a specially designed multi-dimensional bloom filter to store the points-to information. Two key observations motivate our proposal: (i) points-to information (between pointer-object and between pointer-pointer) is sparse, and (ii) moving from an exact to an approximate representation of points-to information only leads to reduced precision without affecting correctness of the (may-points-to) analysis. By using an approximate representation a multi-dimensional bloom filter can significantly reduce the memory requirements with a probabilistic bound on loss in precision. Experimental evaluation on SPEC 2000 benchmarks and two large open source programs reveals that with an average storage requirement of 4MB, our approach achieves almost the same precision (98.6%) as the exact implementation. By increasing the average memory to 27MB, it achieves precision upto 99.7% for these benchmarks. Using Mod/Ref analysis as the client, we find that the client analysis is not affected that often even when there is some loss of precision in the points-to representation. We find that the NoModRef percentage is within 2% of the exact analysis while requiring 4MB (maximum 15MB) memory and less than 4 minutes on average for the points-to analysis. Another major advantage of our technique is that it allows to trade off precision for memory usage of the analysis.

On the fundamentally asynchronous nature of interference in cooperative base station systems

Cooperative transmission by base stations can significantly improve the spectral efficiency of multiuser, multi-cell multiple input multiple output systems. We show that in such systems the multiuser interference is asynchronous by nature, even when perfect timing-advance mechanisms ensure that the desired signal components arrive synchronously. We establish an accurate mathematical model for the asynchronism, and use it to show that the asynchronism leads to a significant performance degradation of existing linear preceding designs that assumed synchronous interference. We consider three different previously proposed precoding designs, and show how to modify them to effectively mitigate asynchronous interference.

Optimality of orthogonal sequences with multi-dimensional signaling

The sum capacity on a symbol-synchronous CDMA system having processing gain N and supporting K power constrained users is achieved by employing any set of N orthogonal sequences if a few users are allowed to signal along multiple dimensions. Analogously, the minimum received power (energy-per-chip) on the symbolsynchronous CDMA system supporting K users that demand specified data rates is attained by employing any set of N orthogonal sequences. At most (N - 1) users need to be split and if there are no oversized users, these split users need to signal only in two dimensions each. These results show that sum capacity or minimum sum power can be achieved with minimal downlink signaling.

Digital Deadbeat Control Tuning for dc-dc Converters Using Error Correlation

This letter proposes a simple tuning algorithm for digital deadbeat control based on error correlation. By injecting a square-wave reference input and calculating the correlation of the control error, a gain correction for deadbeat control is obtained. The proposed solution is simple, it requires a short tuning time, and it is suitable for different DC-DC converter topologies. Simulation and experimental results on synchronous buck converters confirm the properties of the proposed tuning algorithm.

Base excision and nucleotide excision repair pathways in mycobacteria

About a third of the human population is estimated to be infected with Mycobacterium tuberculosis. The bacterium displays an excellent adaptability to survive within the host macrophages. As the reactive environment of macrophages is capable of inducing DNA damage, the ability of the pathogen to safeguard its DNA against the damage is of paramount significance for its survival within the host. Analysis of the genome sequence has provided important insights into the DNA repair machinery of the pathogen, and the studies on DNA repair in mycobacteria have gained momentum in the past few years. The studies have revealed considerable differences in the mycobacterial DNA repair machinery when compared with those of the other bacteria. This review article focuses especially on the aspects of base excision, and nucleotide excision repair pathways in mycobacteria. (C) 2011 Elsevier Ltd. All rights reserved.

A Novel VSI- and CSI-Fed Active-Reactive Induction Motor Drive with Sinusoidal Voltages and Currents

Till date load-commutated inverter (LCI)-fed synchronous motor drive configuration is popular in high power applications (>10 MW). The leading power factor operation of synchronous motor by excitation control offers this simple and rugged drive structure. On the contrary, LCI-fed induction motor drive is absent as it always draws lagging power factor current. Therefore, complicated commutation circuit is required to switch off thyristors for a current source inverter (CSI)-driven induction motor. It poses the major hindrance to scale up the power rating of CSI-fed induction motor drive. Anew power topology for LCI-fed induction motor drive for medium-voltage drive application is proposed. A new induction machine (active-reactive induction machine) with two sets of three-phase winding is introduced as a drive motor. The proposed power configuration ensures sinusoidal voltage and current at the motor terminals. The total drive power is shared among a thyristor-based LCI, an insulated gate bipolar transistor (IGBT)-based two-level voltage source inverter (VSI), and a three-level VSI. The benefits of SCRs and IGBTs are explored in the proposed drive. Experimental results from a prototype drive verify the basic concepts of the drive.

Switching Transients in Single-Phase Induction Motors

The subject of transients in polyphase induction motors and synchronous machines has been studied in very great detail by several investigators, but no published literature exists dealing exclusively with the analysis of the problem of transients in single-phase induction motors. This particular problem has been studied in this paper by applying the Laplace transform. The results of actual computation of the currents and developed electrical torque are compared with the data obtained by setting up the integro-differential equations of the machine on an electronic differential analyzer. It is shown that if the motor is switched on to the supply when the potential passes through its zero value, there is a pulsating fundamental frequency torque superimposed on the average steady-state unidirectional torque. If, on the other hand, the switch is closed when the applied potential passes through its maximum value, the developed electrical torque settles down to its final steady-state value during the first cycle of the supply voltage.

Improvement of power-system transient stability by phase-shift insertion

Computational studies of the transient stability of a synchronous machine connected to an infinite busbar by a double-circuit transmission line are used to illustrate the effect of relative phase-shift insertion between the machine and its associated power system. This method of obtaining a change in the effective rotor-excitation angle, and thereby the power transfer, is described, together with an outline of possible methods of implementation by a phase-shifting transformer in a power system.

Fast Direct Torque Control of an Open-End Induction Motor Drive Using 12-Sided Polygonal Voltage Space Vectors

A torque control scheme, based on a direct torque control (DTC) algorithm using a 12-sided polygonal voltage space vector, is proposed for a variable speed control of an open-end induction motor drive. The conventional DTC scheme uses a stator flux vector for the sector identification and then the switching vector to control stator flux and torque. However, the proposed DTC scheme selects switching vectors based on the sector information of the estimated fundamental stator voltage vector and its relative position with respect to the stator flux vector. The fundamental stator voltage estimation is based on the steady-state model of IM and the synchronous frequency of operation is derived from the computed stator flux using a low-pass filter technique. The proposed DTC scheme utilizes the exact positions of the fundamental stator voltage vector and stator flux vector to select the optimal switching vector for fast control of torque with small variation of stator flux within the hysteresis band. The present DTC scheme allows full load torque control with fast transient response to very low speeds of operation, with reduced switching frequency variation. Extensive experimental results are presented to show the fast torque control for speed of operation from zero to rated.

Null Dereference Verification via Over-approximated Weakest Pre-conditions Analysis

Null dereferences are a bane of programming in languages such as Java. In this paper we propose a sound, demand-driven, inter-procedurally context-sensitive dataflow analysis technique to verify a given dereference as safe or potentially unsafe. Our analysis uses an abstract lattice of formulas to find a pre-condition at the entry of the program such that a null-dereference can occur only if the initial state of the program satisfies this pre-condition. We use a simplified domain of formulas, abstracting out integer arithmetic, as well as unbounded access paths due to recursive data structures. For the sake of precision we model aliasing relationships explicitly in our abstract lattice, enable strong updates, and use a limited notion of path sensitivity. For the sake of scalability we prune formulas continually as they get propagated, reducing to true conjuncts that are less likely to be useful in validating or invalidating the formula. We have implemented our approach, and present an evaluation of it on a set of ten real Java programs. Our results show that the set of design features we have incorporated enable the analysis to (a) explore long, inter-procedural paths to verify each dereference, with (b) reasonable accuracy, and (c) very quick response time per dereference, making it suitable for use in desktop development environments.

Chemistry and biology of DNA-binding small molecules

Regulation of the transcription machinery is one of the many ways to achieve control of gene expression. This has been done either at the transcription initiation stage or at the elongation stage. Different methodologies are known to inhibit transcription initiation via targeting of double-stranded (ds) DNA by: (i) synthetic oligonucleotides, (ii) ds-DNA-specific, sequenceselective minor-groove binders (distamycin A), intercalators (daunomycin) combilexins and (iii) small molecule (peptide or intercalator)-oligonucleotide conjugates. In some cases, instead of ds-DNA, higher order G-quadruplex structures are formed at the start site of transcription. In this regard G-quadruplex DNA-specific small molecules play a significant role towards inhibition of the transcription machinery. Different types of designer DNA-binding agents act as powerful sequence-specific gene modulators, by exerting their effect from transcription regulation to gene modification. But most of these chemotherapeutic agents have serious side effects. Accordingly, there is always a challenge to design such DNA-binding molecules that should not only achieve maximum specific DNA-binding affinity, and cellular and nuclear transport activity, but also would not interfere with the functions of normal cells.

Network Reconstruction from dynamic data

Over the past decade, many powerful data mining techniques have been developed to analyze temporal and sequential data. The time is now fertile for addressing problems of larger scope under the purview of temporal data mining. The fourth SIGKDD workshop on temporal data mining focused on the question: What can we infer about the structure of a complex dynamical system from observed temporal data? The goals of the workshop were to critically evaluate the need in this area by bringing together leading researchers from industry and academia, and to identify promising technologies and methodologies for doing the same. We provide a brief summary of the workshop proceedings and ideas arising out of the discussions.

Microprocessor-based algorithm for symmetrical-components calculation

This letter presents a microprocessor-based algorithm for calculating symmetrical components from the distorted transient voltage and current signals in a power system. The fundamental frequency components of the 3-phase signals are first extracted using an algorithm based on Haar functions and then "symmetrical-component transformation is applied to obtain the sequence components. The algorithm presented is computationally efficient and fast. This algorithm is better suited for application in microprocessor-based protection schemes of synchronous and induction machines.

Delay Optimal Event Detection on Ad Hoc Wireless Sensor Networks

We consider a small extent sensor network for event detection, in which nodes periodically take samples and then contend over a random access network to transmit their measurement packets to the fusion center. We consider two procedures at the fusion center for processing the measurements. The Bayesian setting, is assumed, that is, the fusion center has a prior distribution on the change time. In the first procedure, the decision algorithm at the fusion center is network-oblivious and makes a decision only when a complete vector of measurements taken at a sampling instant is available. In the second procedure, the decision algorithm at the fusion center is network-aware and processes measurements as they arrive, but in a time-causal order. In this case, the decision statistic depends on the network delays, whereas in the network-oblivious case, the decision statistic does not. This yields a Bayesian change-detection problem with a trade-off between the random network delay and the decision delay that is, a higher sampling rate reduces the decision delay but increases the random access delay. Under periodic sampling, in the network-oblivious case, the structure of the optimal stopping rule is the same as that without the network, and the optimal change detection delay decouples into the network delay and the optimal decision delay without the network. In the network-aware case, the optimal stopping problem is analyzed as a partially observable Markov decision process, in which the states of the queues and delays in the network need to be maintained. A sufficient decision statistic is the network state and the posterior probability of change having occurred, given the measurements received and the state of the network. The optimal regimes are studied using simulation.