Compiler-Directed Frequency and Voltage Scaling for a Multiple Clock Domain

Multiple Clock Domain processors provide an attractive solution to the increasingly challenging problems of clock distribution and power dissipation. They allow their chips to be partitioned into different clock domains, and each domain’s frequency (voltage) to be independently configured. This flexibility adds new dimensions to the Dynamic Voltage and Frequency Scaling problem, while providing better scope for saving energy and meeting performance demands. In this paper, we propose a compiler directed approach for MCD-DVFS. We build a formal petri net based program performance model, parameterized by settings of microarchitectural components and resource configurations, and integrate it with our compiler passes for frequency selection.Our model estimates the performance impact of a frequency setting, unlike the existing best techniques which rely on weaker indicators of domain performance such as queue occupancies(used by online methods) and slack manifestation for a particular frequency setting (software based methods).We evaluate our method with subsets of SPECFP2000,Mediabench and Mibench benchmarks. Our mean energy savings is 60.39% (versus 33.91% of the best software technique)in a memory constrained system for cache miss dominated benchmarks, and we meet the performance demands.Our ED2 improves by 22.11% (versus 18.34%) for other benchmarks. For a CPU with restricted frequency settings, our energy consumption is within 4.69% of the optimal.

A Real-time clustering system for spatio-temporal signals from network of neurons

Over past few years, the studies of cultured neuronal networks have opened up avenues for understanding the ion channels, receptor molecules, and synaptic plasticity that may form the basis of learning and memory. The hippocampal neurons from rats are dissociated and cultured on a surface containing a grid of 64 electrodes. The signals from these 64 electrodes are acquired using a fast data acquisition system MED64 (Alpha MED Sciences, Japan) at a sampling rate of 20 K samples with a precision of 16-bits per sample. A few minutes of acquired data runs in to a few hundreds of Mega Bytes. The data processing for the neural analysis is highly compute-intensive because the volume of data is huge. The major processing requirements are noise removal, pattern recovery, pattern matching, clustering and so on. In order to interface a neuronal colony to a physical world, these computations need to be performed in real-time. A single processor such as a desk top computer may not be adequate to meet this computational requirements. Parallel computing is a method used to satisfy the real-time computational requirements of a neuronal system that interacts with an external world while increasing the flexibility and scalability of the application. In this work, we developed a parallel neuronal system using a multi-node Digital Signal processing system. With 8 processors, the system is able to compute and map incoming signals segmented over a period of 200 ms in to an action in a trained cluster system in real time.

Streaming FFT on REDEFINE-v2: An Application-Architecture Design Space Exploration

In this paper we explore an implementation of a high-throughput, streaming application on REDEFINE-v2, which is an enhancement of REDEFINE. REDEFINE is a polymorphic ASIC combining the flexibility of a programmable solution with the execution speed of an ASIC. In REDEFINE Compute Elements are arranged in an 8x8 grid connected via a Network on Chip (NoC) called RECONNECT, to realize the various macrofunctional blocks of an equivalent ASIC. For a 1024-FFT we carry out an application-architecture design space exploration by examining the various characterizations of Compute Elements in terms of the size of the instruction store. We further study the impact by using application specific, vectorized FUs. By setting up different partitions of the FFT algorithm for persistent execution on REDEFINE-v2, we derive the benefits of setting up pipelined execution for higher performance. The impact of the REDEFINE-v2 micro-architecture for any arbitrary N-point FFT (N > 4096) FFT is also analyzed. We report the various algorithm-architecture tradeoffs in terms of area and execution speed with that of an ASIC implementation. In addition we compare the performance gain with respect to a GPP.

A Combinatorial Family of Near Regular LDPC Codes

An elementary combinatorial Tanner graph construction for a family of near-regular low density parity check (LDPC) codes achieving high girth is presented. These codes are near regular in the sense that the degree of a left/right vertex is allowed to differ by at most one from the average. The construction yields in quadratic time complexity an asymptotic code family with provable lower bounds on the rate and the girth for a given choice of block length and average degree. The construction gives flexibility in the choice of design parameters of the code like rate, girth and average degree. Performance simulations of iterative decoding algorithm for the AWGN channel on codes designed using the method demonstrate that these codes perform better than regular PEG codes and MacKay codes of similar length for all values of Signal to noise ratio.

Two-level Mapping Based Cache Index Selection for Packet Forwarding Engines

Packet forwarding is a memory-intensive application requiring multiple accesses through a trie structure. The efficiency of a cache for this application critically depends on the placement function to reduce conflict misses. Traditional placement functions use a one-level mapping that naively partitions trie-nodes into cache sets. However, as a significant percentage of trie nodes are not useful, these schemes suffer from a non-uniform distribution of useful nodes to sets. This in turn results in increased conflict misses. Newer organizations such as variable associativity caches achieve flexibility in placement at the expense of increased hit-latency. This makes them unsuitable for L1 caches.We propose a novel two-level mapping framework that retains the hit-latency of one-level mapping yet incurs fewer conflict misses. This is achieved by introducing a secondlevel mapping which reorganizes the nodes in the naive initial partitions into refined partitions with near-uniform distribution of nodes. Further as this remapping is accomplished by simply adapting the index bits to a given routing table the hit-latency is not affected. We propose three new schemes which result in up to 16% reduction in the number of misses and 13% speedup in memory access time. In comparison, an XOR-based placement scheme known to perform extremely well for general purpose architectures, can obtain up to 2% speedup in memory access time.

Optimal Parameterized Policies for Resource Allocation in Communication Networks

The problem of finding optimal parameterized feedback policies for dynamic bandwidth allocation in communication networks is studied. We consider a queueing model with two queues to which traffic from different competing flows arrive. The queue length at the buffers is observed every T instants of time, on the basis of which a decision on the amount of bandwidth to be allocated to each buffer for the next T instants is made. We consider two different classes of multilevel closed-loop feedback policies for the system and use a two-timescale simultaneous perturbation stochastic approximation (SPSA) algorithm to find optimal policies within each prescribed class. We study the performance of the proposed algorithm on a numerical setting and show performance comparisons of the two optimal multilevel closedloop policies with optimal open loop policies. We observe that closed loop policies of Class B that tune parameters for both the queues and do not have the constraint that the entire bandwidth be used at each instant exhibit the best results overall as they offer greater flexibility in parameter tuning. Index Terms — Resource allocation, dynamic bandwidth allocation in communication networks, two-timescale SPSA algorithm, optimal parameterized policies. I.

Quaternary association in beta-prism I fold plant lectins: Insights from X-ray crystallography, modelling and molecular dynamics

Dimeric banana lectin and calsepa, tetrameric artocarpin and octameric heltuba are mannose-specific beta-prism I fold lectins of nearly the same tertiary structure. MD simulations on individual subunits and the oligomers provide insights into the changes in the structure brought about in the protomers on oligomerization, including swapping of the N-terminal stretch in one instance. The regions that undergo changes also tend to exhibit dynamic flexibility during MD simulations. The internal symmetries of individual oligomers are substantially retained during the calculations. Energy minimization and simulations were also carried out on models using all possible oligomers by employing the four different protomers. The unique dimerization pattern observed in calsepa could be traced to unique substitutions in a peptide stretch involved in dimerization. The impossibility of a specific mode of oligomerization involving a particular protomer is often expressed in terms of unacceptable steric contacts or dissociation of the oligomer during simulations. The calculations also led to a rationale for the observation of a heltuba tetramer in solution although the lectin exists as an octamer in the crystal, in addition to providing insights into relations among evolution, oligomerization and ligand binding.

Insights into the Substrate Specificity of a Thioesterase Rv0098 of Mycobacterium Tuberculosis through X-ray Crystallographic and Molecular Dynamics Studies

The crystal structure of Rv0098, a long-chain fatty acyl-CoA thioesterase from Mycobacterium tuberculosis with bound dodecanoic acid at the active site provided insights into the mode of substrate binding but did not reveal the structural basis of substrate specificities of varying chain length. Molecular dynamics studies demonstrated that certain residues of the substrate binding tunnel are flexible and thus modulate the length of the tunnel. The flexibility of the loop at the base of the tunnel was also found to be important for determining the length of the tunnel for accommodating appropriate substrates. A combination of crystallographic and molecular dynamics studies thus explained the structural basis of accommodating long chain substrates by Rv0098 of M. tuberculosis.

A neural network based automatic generation control design through reinforcement learning

This paper presents the design and implementation of a learning controller for the Automatic Generation Control (AGC) in power systems based on a reinforcement learning (RL) framework. In contrast to the recent RL scheme for AGC proposed by us, the present method permits handling of power system variables such as Area Control Error (ACE) and deviations from scheduled frequency and tie-line flows as continuous variables. (In the earlier scheme, these variables have to be quantized into finitely many levels). The optimal control law is arrived at in the RL framework by making use of Q-learning strategy. Since the state variables are continuous, we propose the use of Radial Basis Function (RBF) neural networks to compute the Q-values for a given input state. Since, in this application we cannot provide training data appropriate for the standard supervised learning framework, a reinforcement learning algorithm is employed to train the RBF network. We also employ a novel exploration strategy, based on a Learning Automata algorithm,for generating training samples during Q-learning. The proposed scheme, in addition to being simple to implement, inherits all the attractive features of an RL scheme such as model independent design, flexibility in control objective specification, robustness etc. Two implementations of the proposed approach are presented. Through simulation studies the attractiveness of this approach is demonstrated.

Dimethyl sulfoxide induced structural transformations and non-monotonic concentration dependence of conformational fluctuation around active site of lysozyme

Experimental studies have observed significant changes in both structure and function of lysozyme (and other proteins) on addition of a small amount of dimethyl sulfoxide (DMSO) in aqueous solution. Our atomistic molecular dynamic simulations of lysozyme in water-DMSO reveal the following sequence of changes on increasing DMSO concentration. (i) At the initial stage (around 5% DMSO concentration) protein's conformational flexibility gets markedly suppressed. From study of radial distribution functions, we attribute this to the preferential solvation of exposed protein hydrophobic residues by the methyl groups of DMSO. (ii) In the next stage (10-15% DMSO concentration range), lysozome partially unfolds accompanied by an increase both in fluctuation and in exposed protein surface area. (iii) Between 15-20% concentration ranges, both conformational fluctuation and solvent accessible protein surface area suddenly decrease again indicating the formation of an intermediate collapse state. These results are in good agreement with near-UV circular dichroism (CD) and fluorescence studies. We explain this apparently surprising behavior in terms of a structural transformation which involves clustering among the methyl groups of DMSO. (iv) Beyond 20% concentration of DMSO, the protein starts its final sojourn towards the unfolding state with further increase in conformational fluctuation and loss in native contacts. Most importantly, analysis of contact map and fluctuation near the active site reveal that both partial unfolding and conformational fluctuations are centered mostly on the hydrophobic core of active site of lysozyme. Our results could offer a general explanation and universal picture of the anomalous behavior of protein structure-function observed in the presence of cosolvents (DMSO, ethanol, tertiary butyl alcohol, dioxane) at their low concentrations. (C) 2012 American Institute of Physics. [http://dx.doi.org/10.1063/1.3694268]

Structure and Mechanistic Insights into Novel Iron-mediated Moonlighting Functions of Human J-protein Cochaperone, Dph4

J-proteins are obligate cochaperones of Hsp70s and stimulate their ATPase activity via the J-domain. Although the functions of J-proteins have been well understood in the context of Hsp70s, their additional co-evolved ``physiological functions'' are still elusive. We report here the solution structure and mechanism of novel iron-mediated functional roles of human Dph4, a type III J-protein playing a vital role in diphthamide biosynthesis and normal development. The NMR structure of Dph4 reveals two domains: a conserved J-domain and a CSL-domain connected via a flexible linker-helix. The linker-helix modulates the conformational flexibility between the two domains, regulating thereby the protein function. Dph4 exhibits a unique ability to bind iron in tetrahedral coordination geometry through cysteines of its CSL-domain. The oxidized Fe-Dph4 shows characteristic UV-visible and electron paramagnetic resonance spectral properties similar to rubredoxins. Iron-bound Dph4 (Fe-Dph4) also undergoes oligomerization, thus potentially functioning as a transient ``iron storage protein,'' thereby regulating the intracellular iron homeostasis. Remarkably, Fe-Dph4 exhibits vital redox and electron carrier activity, which is critical for important metabolic reactions, including diphthamide biosynthesis. Further, we observed that Fe-Dph4 is conformationally better poised to perform Hsp70-dependent functions, thus underlining the significance of iron binding in Dph4. Yeast Jjj3, a functional ortholog of human Dph4 also shows a similar iron-binding property, indicating the conserved nature of iron sequestration across species. Taken together, our findings provide invaluable evidence in favor of additional co-evolved specialized functions of J-proteins, previously not well appreciated.

Changing resonator geometry to boost sound power decouples size and song frequency in a small insect

Despite their small size, some insects, such as crickets, can produce high amplitude mating songs by rubbing their wings together. By exploiting structural resonance for sound radiation, crickets broadcast species-specific songs at a sharply tuned frequency. Such songs enhance the range of signal transmission, contain information about the signaler's quality, and allow mate choice. The production of pure tones requires elaborate structural mechanisms that control and sustain resonance at the species-specific frequency. Tree crickets differ sharply from this scheme. Although they use a resonant system to produce sound, tree crickets can produce high amplitude songs at different frequencies, varying by as much as an octave. Based on an investigation of the driving mechanism and the resonant system, using laser Doppler vibrometry and finite element modeling, we show that it is the distinctive geometry of the crickets' forewings (the resonant system) that is responsible for their capacity to vary frequency. The long, enlarged wings enable the production of high amplitude songs; however, as a mechanical consequence of the high aspect ratio, the resonant structures have multiple resonant modes that are similar in frequency. The drive produced by the singing apparatus cannot, therefore, be locked to a single frequency, and different resonant modes can easily be engaged, allowing individual males to vary the carrier frequency of their songs. Such flexibility in sound production, decoupling body size and song frequency, has important implications for conventional views of mate choice, and offers inspiration for the design of miniature, multifrequency, resonant acoustic radiators.

Analysis of Parameter Values in the van der Waals and Platteeuw Theory for Methane Hydrates Using Monte Carlo Molecular Simulations

The van der Waals and Platteuw (vdVVP) theory has been successfully used to model the thermodynamics of gas hydrates. However, earlier studies have shown that this could be due to the presence of a large number of adjustable parameters whose values are obtained through regression with experimental data. To test this assertion, we carry out a systematic and rigorous study of the performance of various models of vdWP theory that have been proposed over the years. The hydrate phase equilibrium data used for this study is obtained from Monte Carlo molecular simulations of methane hydrates. The parameters of the vdWP theory are regressed from this equilibrium data and compared with their true values obtained directly from simulations. This comparison reveals that (i) methane-water interactions beyond the first cage and methane-methane interactions make a significant contribution to the partition function and thus cannot be neglected, (ii) the rigorous Monte Carlo integration should be used to evaluate the Langmuir constant instead of the spherical smoothed cell approximation, (iii) the parameter values describing the methane-water interactions cannot be correctly regressed from the equilibrium data using the vdVVP theory in its present form, (iv) the regressed empty hydrate property values closely match their true values irrespective of the level of rigor in the theory, and (v) the flexibility of the water lattice forming the hydrate phase needs to be incorporated in the vdWP theory. Since methane is among the simplest of hydrate forming molecules, the conclusions from this study should also hold true for more complicated hydrate guest molecules.

Mesh Simplification Based on Edge Collapsing Could Improve Computational Efficiency in Near Infrared Optical Tomographic Imaging

The diffusion equation-based modeling of near infrared light propagation in tissue is achieved by using finite-element mesh for imaging real-tissue types, such as breast and brain. The finite-element mesh size (number of nodes) dictates the parameter space in the optical tomographic imaging. Most commonly used finite-element meshing algorithms do not provide the flexibility of distinct nodal spacing in different regions of imaging domain to take the sensitivity of the problem into consideration. This study aims to present a computationally efficient mesh simplification method that can be used as a preprocessing step to iterative image reconstruction, where the finite-element mesh is simplified by using an edge collapsing algorithm to reduce the parameter space at regions where the sensitivity of the problem is relatively low. It is shown, using simulations and experimental phantom data for simple meshes/domains, that a significant reduction in parameter space could be achieved without compromising on the reconstructed image quality. The maximum errors observed by using the simplified meshes were less than 0.27% in the forward problem and 5% for inverse problem.

Probabilistic Shared Cache Management (PriSM)

Effective sharing of the last level cache has a significant influence on the overall performance of a multicore system. We observe that existing solutions control cache occupancy at a coarser granularity, do not scale well to large core counts and in some cases lack the flexibility to support a variety of performance goals. In this paper, we propose Probabilistic Shared Cache Management (PriSM), a framework to manage the cache occupancy of different cores at cache block granularity by controlling their eviction probabilities. The proposed framework requires only simple hardware changes to implement, can scale to larger core count and is flexible enough to support a variety of performance goals. We demonstrate the flexibility of PriSM, by computing the eviction probabilities needed to achieve goals like hit-maximization, fairness and QOS. PriSM-HitMax improves performance by 18.7% over LRU and 11.8% over previously proposed schemes in a sixteen core machine. PriSM-Fairness improves fairness over existing solutions by 23.3% along with a performance improvement of 19.0%. PriSM-QOS successfully achieves the desired QOS targets.