System level DSP synthesis using voltage overscaling, unequal error protection & adaptive quality tuning

In this paper, we propose a system level design approach considering voltage over-scaling (VOS) that achieves error resiliency using unequal error protection of different computation elements, while incurring minor quality degradation. Depending on user specifications and severity of process variations/channel noise, the degree of VOS in each block of the system is adaptively tuned to ensure minimum system power while providing "just-the-right" amount of quality and robustness. This is achieved, by taking into consideration system level interactions and ensuring that under any change of operating conditions only the "lesscrucial" computations, that contribute less to block/system output quality, are affected. The design methodology applied to a DCT/IDCT system shows large power benefits (up to 69%) at reasonable image quality while tolerating errors induced by varying operating conditions (VOS, process variations, channel noise). Interestingly, the proposed IDCT scheme conceals channel noise at scaled voltages. ©2009 IEEE.

Logic and Memory Design Based on Unequal Error Protection for Voltage-scalable, Robust and Adaptive DSP Systems

In this paper, we propose a system level design approach considering voltage over-scaling (VOS) that achieves error resiliency using unequal error protection of different computation elements, while incurring minor quality degradation. Depending on user specifications and severity of process variations/channel noise, the degree of VOS in each block of the system is adaptively tuned to ensure minimum system power while providing "just-the-right" amount of quality and robustness. This is achieved, by taking into consideration block level interactions and ensuring that under any change of operating conditions, only the "less-crucial" computations, that contribute less to block/system output quality, are affected. The proposed approach applies unequal error protection to various blocks of a system-logic and memory-and spans multiple layers of design hierarchy-algorithm, architecture and circuit. The design methodology when applied to a multimedia subsystem shows large power benefits ( up to 69% improvement in power consumption) at reasonable image quality while tolerating errors introduced due to VOS, process variations, and channel noise.

Targeting FPGA DSP Slices for a Large Integer Multiplier for Integer Based FHE

Homomorphic encryption offers potential for secure cloud computing. However due to the complexity of homomorphic encryption schemes, performance of implemented schemes to date have been unpractical. This work investigates the use of hardware, specifically Field Programmable Gate Array (FPGA) technology, for implementing the building blocks involved in somewhat and fully homomorphic encryption schemes in order to assess the practicality of such schemes. We concentrate on the selection of a suitable multiplication algorithm and hardware architecture for large integer multiplication, one of the main bottlenecks in many homomorphic encryption schemes. We focus on the encryption step of an integer-based fully homomorphic encryption (FHE) scheme. We target the DSP48E1 slices available on Xilinx Virtex 7 FPGAs to ascertain whether the large integer multiplier within the encryption step of a FHE scheme could fit on a single FPGA device. We find that, for toy size parameters for the FHE encryption step, the large integer multiplier fits comfortably within the DSP48E1 slices, greatly improving the practicality of the encryption step compared to a software implementation. As multiplication is an important operation in other FHE schemes, a hardware implementation using this multiplier could also be used to improve performance of these schemes.

Novel Application of Genetic Sequencing algorithms to optimisation of hardware resource sharing for DSP

Field programmable gate array (FPGA) technology is a powerful platform for implementing computationally complex, digital signal processing (DSP) systems. Applications that are multi-modal, however, are designed for worse case conditions. In this paper, genetic sequencing techniques are applied to give a more sophisticated decomposition of the algorithmic variations, thus allowing an unified hardware architecture which gives a 10-25% area saving and 15% power saving for a digital radar receiver.

Adaptive generalized predictive control algorithm implemented over a DSP network

In this paper a parallel implementation of an Adaprtive Generalized Predictive Control (AGPC) algorithm is presented. Since the AGPC algorithm needs to be fed with knowledge of the plant transfer function, the parallelization of a standard Recursive Least Squares (RLS) estimator and a GPC predictor is discussed here.

Results of a DSP based adaptive cancellation filter system for the chirp, pulsar and localiser sirens

Sirens’ used by police, fire and paramedic vehicles generate noise that propagates inside the vehicle cab that subsequently corrupts intelligibility of voice communications from the emergency vehicle to the control room. It is even common for the siren to be turned off to enable the control room to hear what is being said. Both fixed filter and adaptive filter systems have previously been developed to help cancel the transmission of the siren noise over the radio. Previous cancellation systems have only concentrated on the traditional 2-tone, wail and yelp sirens. This paper discusses an improvement to a previous adaptive filter system and presents the cancellation results to three new types of sirens; being chirp pulsar and localiser. A siren noise filter system has the capability to improve the response time for an emergency vehicle and thus help save lives. To date, this system has been tested using live recordings taken from a nonemergency situation with good results.

Performance Improvement of Tomographic Image Reconstruction Based on DSP Processors

This paper presents the use of a multiprocessor architecture for the performance improvement of tomographic image reconstruction. Image reconstruction in computed tomography (CT) is an intensive task for single-processor systems. We investigate the filtered image reconstruction suitability based on DSPs organized for parallel processing and its comparison with the Message Passing Interface (MPI) library. The experimental results show that the speedups observed for both platforms were increased in the same direction of the image resolution. In addition, the execution time to communication time ratios (Rt/Rc) as a function of the sample size have shown a narrow variation for the DSP platform in comparison with the MPI platform, which indicates its better performance for parallel image reconstruction.

DSP-based sliding-mode control for electromagnetic-levitation precise position system

This paper investigates the robust tracking control problem for a bipolar electromagnetic-levitation precise-position system. The dynamic model of the precise-position device is derived by conducting a thorough analysis on the nonlinear electromagnetic forces. Conventional sliding-mode control and terminal sliding-mode control strategies are developed to guarantee asymptotic and finite-time tracking capabilities of the closed-loop system. A lumped uncertainty estimator is proposed to estimate the system uncertainties. The estimated information is then used to construct a smooth uniformly ultimately bounded sliding-mode control. An exact estimator is also proposed to exactly estimate the unknown uncertainties in finite time. The output of the exact estimator is used to design a continuous chattering free terminal sliding-mode control. The time taken for the closed-loop system to reach zero tracking error is proven to be finite. Experiment results are presented, using a real time digital-signal-processor (DSP) based electromagnetic-levitation system to validate the analysis.

Operadores aritméticos de baixo consumo para arquiteturas de circuitos DSP

Este trabalho tem como foco a aplicação de técnicas de otimização de potência no alto nível de abstração para circuitos CMOS, e em particular no nível arquitetural e de transferência de registrados (Register Transfer Leve - RTL). Diferentes arquiteturas para projetos especificos de algorítmos de filtros FIR e transformada rápida de Fourier (FFT) são implementadas e comparadas. O objetivo é estabelecer uma metodologia de projeto para baixa potência neste nível de abstração. As técnicas de redução de potência abordadas tem por obetivo a redução da atividade de chaveamento através das técnicas de exploração arquitetural e codificação de dados. Um dos métodos de baixa potência que tem sido largamente utilizado é a codificação de dados para a redução da atividade de chaveamento em barramentos. Em nosso trabalho, é investigado o processo de codificação dos sinais para a obtenção de módulos aritméticos eficientes em termos de potência que operam diretamente com esses códigos. O objetivo não consiste somente na redução da atividade de chavemanto nos barramentos de dados mas também a minimização da complexidade da lógica combinacional dos módulos. Nos algorítmos de filtros FIR e FFT, a representação dos números em complemento de 2 é a forma mais utilizada para codificação de operandos com sinal. Neste trabalho, apresenta-se uma nova arquitetura para operações com sinal que mantém a mesma regularidade um multiplicador array convencional. Essa arquitetura pode operar com números na base 2m, o que permite a redução do número de linhas de produtos parciais, tendo-se desta forma, ganhos significativos em desempenho e redução de potência. A estratégia proposta apresenta resultados significativamente melhores em relação ao estado da arte. A flexibilidade da arquitetura proposta permite a construção de multiplicadores com diferentes valores de m. Dada a natureza dos algoritmos de filtro FIR e FFT, que envolvem o produto de dados por apropriados coeficientes, procura-se explorar o ordenamento ótimo destes coeficientes nos sentido de minimizar o consumo de potência das arquiteturas implementadas.

The selective neurotoxin DSP-4 impairs the noradrenergic projections from the locus coeruleus to the inferior colliculus in rats

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)