Energy-performance tradeoffs in software transactional memory

Transactional memory (TM) is a new synchronization mechanism devised to simplify parallel programming, thereby helping programmers to unleash the power of current multicore processors. Although software implementations of TM (STM) have been extensively analyzed in terms of runtime performance, little attention has been paid to an equally important constraint faced by nearly all computer systems: energy consumption. In this work we conduct a comprehensive study of energy and runtime tradeoff sin software transactional memory systems. We characterize the behavior of three state-of-the-art lock-based STM algorithms, along with three different conflict resolution schemes. As a result of this characterization, we propose a DVFS-based technique that can be integrated into the resolution policies so as to improve the energy-delay product (EDP). Experimental results show that our DVFS-enhanced policies are indeed beneficial for applications with high contention levels. Improvements of up to 59% in EDP can be observed in this scenario, with an average EDP reduction of 16% across the STAMP workloads. © 2012 IEEE.

Paralelização da ferramenta de alinhamento de sequências MUSCLE para um ambiente distribuído

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

Traduzir na contemporaneidade: efeitos da adoção de sistemas de memórias sobre a concepção ética da prática tradutória

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

A prática contemporânea de tradução com auxílio de sistemas de memórias e os limites da responsabilidade do tradutor

This paper analyzes the growing adoption of translation tools by the contemporary translator working for markets such as the localization industry. The fast turnaround pace of translation of electronic texts ends up conditioning the employment of translators to their ability to use the resources provided by tools such as translation memories systems efficiently. These systems, as envisioned in their early conception, would allow users to increase productivity and, simultaneously, standardize their terminological production. Seeking to go beyond the predominantly descriptive approaches of these tools, some theoretical assumptions upholding the use of translation memories are examined. From this perspective, the translator’s involvement with the work in progress is analyzed, mainly when this professional is part of a larger process of production and distribution of information by electronic means and for diverse audiences. Ultimately, the consequences of the employment of these tools are taken into consideration, such as those between translator/translation and translator/client, as well as the extension of the responsibility of the translator dedicated to developing partially automated translations.

Tecnologias de tradução: implicações éticas para a prática tradutória

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

A concepção de ferramentas de tradução como dinamizadoras da produção tradutória e seus reflexos para a prática

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

Using Threads to Overcome Synchronization Delays in Parallel Multiple Progressive Alignment Algorithms

Sao Paulo State Research Foundation-FAPESP

Consumo de energia em escalonadores de transações em sistemas de memória transacional em software

Pós-graduação em Ciência da Computação - IBILCE

Effect of the Oxygen on the Mechanical Properties of Ti-Mo Systems Alloys

Titanium alloys normally contain oxygen, nitrogen, or carbon as impurities, and although this concentration is low, these impurities cause changes in the mechanical properties of Ti alloys. Oxygen is a strong alpha-phase stabilizer and its addition causes solid-solution strengthening, shape memory effect, and superelasticity. The most promising alloys are those with Nb, Zr, Ta, and Mo as alloying elements. In this paper, the preparation, processing, and characterization of Ti-Mo alloys (5 and 10 wt%) used as biomaterials are presented, along with the influence of oxygen on their mechanical properties. The addition of oxygen causes an increase in the elasticity modulus of the Ti-5Mo alloy due to an increase in the alpha' phase volume fraction, which possesses a higher modulus than the alpha '' phase. Ti-10Mo possesses a mixture between alpha '' and beta phases, oxygen enters these two structures and causes a dominating effect.

Modeling and Experimental Aspects of Self-healing Bolted Joint through Shape Memory Alloy Actuators

Bolted joints are a form of mechanical coupling largely used in machinery due to their reliability and low cost. Failure of bolted joints can lead to catastrophic events, such as leaking, train derailments, aircraft crashes, etc. Most of these failures occur due to the reduction of the pre-load, induced by mechanical vibration or human errors in the assembly or maintenance process. This article investigates the application of shape memory alloy (SMA) washers as an actuator to increase the pre-load on loosened bolted joints. The application of SMA washer follows a structural health monitoring procedure to identify a damage (reduction in pre-load) occurrence. In this article, a thermo-mechanical model is presented to predict the final pre-load achieved using this kind of actuator, based on the heat input and SMA washer dimension. This model extends and improves on the previous model of Ghorashi and Inman [2004, "Shape Memory Alloy in Tension and Compression and its Application as Clamping Force Actuator in a Bolted Joint: Part 2 - Modeling," J. Intell. Mater. Syst. Struct., 15:589-600], by eliminating the pre-load term related to nut turning making the system more practical. This complete model is a powerful but complex tool to be used by designers. A novel modeling approach for self-healing bolted joints based on curve fitting of experimental data is presented. The article concludes with an experimental application that leads to a change in joint assembly to increase the system reliability, by removing the ceramic washer component. Further research topics are also suggested.

Incorporating memory effects in phase separation processes

We consider the modification of the Cahn-Hilliard equation when a time delay process through a memory function is taken into account. We then study the process of spinodal decomposition in fast phase transitions associated with a conserved order parameter. Finite-time memory effects are seen to affect the dynamics of phase transition at short times and have the effect of delaying, in a significant way, the process of rapid growth of the order parameter that follows a quench into the spinodal region. These effects are important in several systems characterized by fast processes, like non-equilibrium dynamics in the early universe and in relativistic heavy-ion collisions. (C) 2006 Elsevier B.V. All rights reserved.

Crossover between the extended and localized regimes in stochastic partially self-avoiding walks in one-dimensional disordered systems

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

A low-voltage low-power analog memory cell with built-in 4-quadrant multiplication

An accurate switched-current (SI) memory cell and suitable for low-voltage low-power (LVLP) applications is proposed. Information is memorized as the gate-voltage of the input transistor, in a tunable gain-boosting triode-transconductor. Additionally, four-quadrant multiplication between the input voltage to the transconductor regulation-amplifier (X-operand) and the stored voltage (Y-operand) is provided. A simplified 2 x 2-memory array was prototyped according to a standard 0.8 mum n-well CMOS process and 1.8-V supply. Measured current-reproduction error is less than 0.26% for 0.25 muA less than or equal to I-SAMPLE less than or equal to 0.75 muA. Standby consumption is 6.75 muW per cell @I-SAMPLE = 0.75 muA. At room temperature, leakage-rate is 1.56 nA/ms. Four-quadrant multiplier (4QM) full-scale operands are 2x(max) = 320 mV(pp) and 2y(max). = 448 mV(pp), yielding a maximum output swing of 0.9 muA(pp). 4QM worst-case nonlinearity is 7.9%.

An accurate low-voltage analog memory-cell with built-in multiplication

A CMOS memory-cell for dynamic storage of analog data and suitable for LVLP applications is proposed. Information is memorized as the gate-voltage of input-transistor of a gain-boosting triode-transconductor. The enhanced output-resistance improves accuracy on reading out the sampled currents. Additionally, a four-quadrant multiplication between the input to regulation-amplifier of the transconductor and the stored voltage is provided. Designing complies with a low-voltage 1.2μm N-well CMOS fabrication process. For a 1.3V-supply, CCELL=3.6pF and sampling interval is 0.25μA≤ ISAMPLE ≤ 0.75μA. The specified retention time is 1.28ms and corresponds to a charge-variation of 1% due to junction leakage @75°C. A range of MR simulations confirm circuit performance. Absolute read-out error is below O.40% while the four-quadrant multiplier nonlinearity, at full-scale is 8.2%. Maximum stand-by consumption is 3.6μW/cell.