Implementation of Art1 and Art2 Artificial Neural Networks on Ring and Mesh Architectures

The Artificial Neural Networks (ANNs) are being used to solve a variety of problems in pattern recognition, robotic control, VLSI CAD and other areas. In most of these applications, a speedy response from the ANNs is imperative. However, ANNs comprise a large number of artificial neurons, and a massive interconnection network among them. Hence, implementation of these ANNs involves execution of computer-intensive operations. The usage of multiprocessor systems therefore becomes necessary. In this article, we have presented the implementation of ART1 and ART2 ANNs on ring and mesh architectures. The overall system design and implementation aspects are presented. The performance of the algorithm on ring, 2-dimensional mesh and n-dimensional mesh topologies is presented. The parallel algorithm presented for implementation of ART1 is not specific to any particular architecture. The parallel algorithm for ARTE is more suitable for a ring architecture.

Compiling Techniques for Coarse Grained Runtime Reconfigurable Architectures

In this paper we develop compilation techniques for the realization of applications described in a High Level Language (HLL) onto a Runtime Reconfigurable Architecture. The compiler determines Hyper Operations (HyperOps) that are subgraphs of a data flow graph (of an application) and comprise elementary operations that have strong producer-consumer relationship. These HyperOps are hosted on computation structures that are provisioned on demand at runtime. We also report compiler optimizations that collectively reduce the overheads of data-driven computations in runtime reconfigurable architectures. On an average, HyperOps offer a 44% reduction in total execution time and a 18% reduction in management overheads as compared to using basic blocks as coarse grained operations. We show that HyperOps formed using our compiler are suitable to support data flow software pipelining.

Compiler-assisted instruction decoder energy optimization for clustered VLIW architectures

Traditionally, an instruction decoder is designed as a monolithic structure that inhibit the leakage energy optimization. In this paper, we consider a split instruction decoder that enable the leakage energy optimization. We also propose a compiler scheduling algorithm that exploits instruction slack to increase the simultaneous active and idle duration in instruction decoder. The proposed compiler-assisted scheme obtains a further 14.5% reduction of energy consumption of instruction decoder over a hardware-only scheme for a VLIW architecture. The benefits are 17.3% and 18.7% in the context of a 2-clustered and a 4-clustered VLIW architecture respectively.

High-Throughput Flexible Constraint Length Viterbi Decoders on De Bruijn, Shuffle-Exchange and Butterfly Connected Architectures

Flexible constraint length channel decoders are required for software defined radios. This paper presents a novel scalable scheme for realizing flexible constraint length Viterbi decoders on a de Bruijn interconnection network. Architectures for flexible decoders using the flattened butterfly and shuffle-exchange networks are also described. It is shown that these networks provide favourable substrates for realizing flexible convolutional decoders. Synthesis results for the three networks are provided and a comparison is performed. An architecture based on a 2D-mesh, which is a topology having a nominally lesser silicon area requirement, is also considered as a fourth point for comparison. It is found that of all the networks considered, the de Bruijn network offers the best tradeoff in terms of area versus throughput.

Analysis of network architectures for zigbee sensor clusters

We provide a comparative performance analysis of network architectures for beacon enabled Zigbee sensor clusters using the CSMA/CA MAC defined in the IEEE 802.15.4 standard, and organised as (i) a star topology, and (ii) a two-hop topology. We provide analytical models for obtaining performance measures such as mean network delay, and mean node lifetime. We find that the star topology is substantially superior both in delay performance and lifetime performance than the two-hop topology.

Compiler-assisted power optimization for clustered VLIW architectures

Clustered VLIW architectures solve the scalability problem associated with flat VLIW architectures by partitioning the register file and connecting only a subset of the functional units to a register file. However, inter-cluster communication in clustered architectures leads to increased leakage in functional components and a high number of register accesses. In this paper, we propose compiler scheduling algorithms targeting two previously ignored power-hungry components in clustered VLIW architectures, viz., instruction decoder and register file. We consider a split decoder design and propose a new energy-aware instruction scheduling algorithm that provides 14.5% and 17.3% benefit in the decoder power consumption on an average over a purely hardware based scheme in the context of 2-clustered and 4-clustered VLIW machines. In the case of register files, we propose two new scheduling algorithms that exploit limited register snooping capability to reduce extra register file accesses. The proposed algorithms reduce register file power consumption on an average by 6.85% and 11.90% (10.39% and 17.78%), respectively, along with performance improvement of 4.81% and 5.34% (9.39% and 11.16%) over a traditional greedy algorithm for 2-clustered (4-clustered) VLIW machine. (C) 2010 Elsevier B.V. All rights reserved.

Comparative-Study of Photonic Switching architectures

The basic photonic switching elements of practical importance are outlined. A detailed comparative study of photonic switching architectures is presented both for guided wave fabrics and free-space fabrics. The required equations for comparative study are obtained, after considering the parameters like bend losses, effects of waveguide crossings, etc. The potential areas of application of photonic switching are pointed out.

Scheduling expression trees with reusable registers on delayed-load architectures

In this paper, we look at the problem of scheduling expression trees with reusable registers on delayed load architectures. Reusable registers come into the picture when the compiler has a data-flow analyzer which is able to estimate the extent of use of the registers. Earlier work considered the same problem without allowing for register variables. Subsequently, Venugopal considered non-reusable registers in the tree. We further extend these efforts to consider a much more general form of the tree. We describe an approximate algorithm for the problem. We formally prove that the code schedule produced by this algorithm will, in the worst case, generate one interlock and use just one more register than that used by the optimal schedule. Spilling is minimized. The approximate algorithm is simple and has linear complexity.

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.

Mapping adaptive resonance theory onto ring and mesh architectures

In recent years, parallel computers have been attracting attention for simulating artificial neural networks (ANN). This is due to the inherent parallelism in ANN. This work is aimed at studying ways of parallelizing adaptive resonance theory (ART), a popular neural network algorithm. The core computations of ART are separated and different strategies of parallelizing ART are discussed. We present mapping strategies for ART 2-A neural network onto ring and mesh architectures. The required parallel architecture is simulated using a parallel architectural simulator, PROTEUS and parallel programs are written using a superset of C for the algorithms presented. A simulation-based scalability study of the algorithm-architecture match is carried out. The various overheads are identified in order to suggest ways of improving the performance. Our main objective is to find out the performance of the ART2-A network on different parallel architectures. (C) 1999 Elsevier Science B.V. All rights reserved.

Scheduling expression trees for delayed-load architectures

In this paper we consider the problem of scheduling expression trees on delayed-load architectures. The problem tackled here takes root from the one considered in [Proceedings of the ACM SIGPLAN '91 Conf. on Programming Language Design and Implementation, 1991. p. 256] in which the leaves of the expression trees all refer to memory locations. A generalization of this involves the situation in which the trees may contain register variables, with the registers being used only at the leaves. Solutions to this generalization are given in [ACM Trans. Prog. Lang. Syst. 17 (1995) 740, Microproc. Microprog. 40 (1994) 577]. This paper considers the most general case in which the registers are reusable. This problem is tackled in [Comput. Lang, 21 (1995) 49] which gives an approximate solution to the problem under certain assumptions about the contiguity of the evaluation order: Here we propose an optimal solution (which may involve even a non-contiguous evaluation of the tree). The schedule generated by the algorithm given in this paper is optimal in the sense that it is an interlock-free schedule which uses the minimum number of registers required. An extension to the algorithm incorporates spilling. The problem as stated in this paper is an instruction scheduling problem. However, the problem could also be rephrased as an operations research problem with a difference in terminology. (C) 2002 Elsevier Science B.V. All rights reserved.

Simultaneous MultiStreaming for complexity-effective VLIW architectures

Very Long Instruction Word (VLIW) architectures exploit instruction level parallelism (ILP) with the help of the compiler to achieve higher instruction throughput with minimal hardware. However, control and data dependencies between operations limit the available ILP, which not only hinders the scalability of VLIW architectures, but also result in code size expansion. Although speculation and predicated execution mitigate ILP limitations due to control dependencies to a certain extent, they increase hardware cost and exacerbate code size expansion. Simultaneous multistreaming (SMS) can significantly improve operation throughput by allowing interleaved execution of operations from multiple instruction streams. In this paper we study SMS for VLIW architectures and quantify the benefits associated with it using a case study of the MPEG-2 video decoder. We also propose the notion of virtual resources for VLIW architectures, which decouple architectural resources (resources exposed to the compiler) from the microarchitectural resources, to limit code size expansion. Our results for a VLIW architecture demonstrate that: (1) SMS delivers much higher throughput than that achieved by speculation and predicated execution, (2) the increase in performance due to the addition of speculation and predicated execution support over SMS averages around 12%. The minor increase in performance might not warrant the additional hardware complexity involved, and (3) the notion of virtual resources is very effective in reducing no-operations (NOPs) and consequently reduce code size with little or no impact on performance.

Middleware for Long-running Applications on Batch Grids. Student Research Symposium poster

Computational grids with multiple batch systems (batch grids) can be powerful infrastructures for executing long-running multicomponent parallel applications. In this paper, we have constructed a middleware framework for executing such long-running applications spanning multiple submissions to the queues on multiple batch systems. We have used our framework for execution of a foremost long-running multi-component application for climate modeling, the Community Climate System Model (CCSM). Our framework coordinates the distribution, execution, migration and restart of the components of CCSM on the multiple queues where the component jobs of the different queues can have different queue waiting and startup times.

Register File Energy Optimization for Snooping Based Clustered VLIW Architectures

Frequent accesses to the register file make it one of the major sources of energy consumption in ILP architectures. The large number of functional units connected to a large unified register file in VLIW architectures make power dissipation in the register file even worse because of the need for a large number of ports. High power dissipation in a relatively smaller area occupied by a register file leads to a high power density in the register file and makes it one of the prime hot-spots. This makes it highly susceptible to the possibility of a catastrophic heatstroke. This in turn impacts the performance and cost because of the need for periodic cool down and sophisticated packaging and cooling techniques respectively. Clustered VLIW architectures partition the register file among clusters of functional units and reduce the number of ports required thereby reducing the power dissipation. However, we observe that the aggregate accesses to register files in clustered VLIW architectures (and associated energy consumption) become very high compared to the centralized VLIW architectures and this can be attributed to a large number of explicit inter-cluster communications. Snooping based clustered VLIW architectures provide very limited but very fast way of inter-cluster communication by allowing some of the functional units to directly read some of the operands from the register file of some of the other clusters. In this paper, we propose instruction scheduling algorithms that exploit the limited snooping capability to reduce the register file energy consumption on an average by 12% and 18% and improve the overall performance by 5% and 11% for a 2-clustered and a 4-clustered machine respectively, over an earlier state-of-the-art clustered scheduling algorithm when evaluated in the context of snooping based clustered VLIW architectures.