Puneet Gupta

Bio: Puneet Gupta is an academic researcher from University of California, Los Angeles. The author has contributed to research in topics: Medicine & Multiple patterning. The author has an hindex of 37, co-authored 288 publications receiving 6517 citations. Previous affiliations of Puneet Gupta include University of California, San Diego & University of California, Berkeley.

Trading Accuracy for Power with an Underdesigned Multiplier Architecture

Abstract: We propose a novel multiplier architecture with tunable error characteristics, that leverages a modified inaccurate 2x2 building block. Our inaccurate multipliers achieve an average power saving of 31.78% ? 45.4% over corresponding accurate multiplier designs, for an average error of 1.39%?3.32%. Using image filtering and JPEG compression as sample applications we show that our architecture can achieve 2X - 8X better Signal-Noise-Ratio (SNR) for the same power savings when compared to recent voltage over-scaling based power-error tradeoff methods. We project the multiplier power savings to bigger designs highlighting the fact that the benefits are strongly design dependent. We compare this circuit-centric approach to power quality tradeoffs with a pure software adaptation approach for a JPEG example. We also enhance the design to allow for correct operation of the multiplier using a residual adder, for non error resilient applications.

Manufacturing-Aware Physical Design

Abstract: Ultra-deep submicron manufacturability impacts physical design (PD) through complex layout rules and large guard-bands for process variability; this creates new requirements for new manufacturing-aware PD technologies. The first part of this tutorial reviews PD complications and methodology changes notably in the detailed routing arena - that arise from subwavelength lithography and deep-submicron manufacturing (antennas, metal planarization and mask-wafer mismatch). Process variations and their sources are taxonomized for modeling and simulation. A framework of design for cost and value is described. The second part covers yield-constrained optimizations in PD, especially "beyond corners" approaches that escape today's pessimistic or even incorrect corner-based approaches. Statistical timing and noise analyses enable optimization of parametric yield and reliability. Yield-aware cell libraries and "analog" design rules (as opposed to "digital", 0/1 rules) can help designers explore yield-cost tradeoffs, especially for low-volume parts. We then examine performance impact-limited fill insertion which goes beyond mere capacitance rules. Modeling, objectives, and filling strategies are discussed. Finally, we discuss current and near-term prospects for the overall design-to-manufacturing PD methodology. Key aspects include better integrations with analysis and manufacturing interfaces, as well as cost-benefit tradeoffs for "regular" layout structures that are likely beyond 90 nm, cost optimizations for low-volume production, and the role of robust and/or stochastic optimization in PD.

Selective gate-length biasing for cost-effective runtime leakage control

Abstract: With process scaling, leakage power reduction has become one of the most important design concerns. Multi-threshold techniques have been used to reduce runtime leakage power without sacrificing performance. In this paper, we propose small biases of transistor gate-length to further minimize power in a manufacturable manner. Unlike multi-V th techniques, gate-length biasing requires no additional masks and may be performed at any stage in the design process.Our results show that gate-length biasing effectively reduces leakage power by up to 25% with less than 4% delay penalty. We show the feasibility of the technique in terms of manufacturability and pin-compatibility for post-layout power optimization. We also show up to 54% reduction in leakage uncertainty due to inter-die process variation in circuits when biased gate-lengths, versus only unbiased one, are used. Circuits selectively biased show much less sensitivity to both intra and inter die variations.

Gate-length biasing for digital circuit optimization

Abstract: Methods and apparatus for a gate-length biasing methodology for optimizing integrated digital circuits are described. The gate-length biasing methodology replaces a nominal gate-length of a transistor with a biased gate-length, where the biased gate-length includes a bias length that is small compared to the nominal gate-length. In an exemplary embodiment, the bias length is less than 10% of the nominal gate-length.

Reliable on-chip systems in the nano-era: lessons learnt and future trends

Abstract: Reliability concerns due to technology scaling have been a major focus of researchers and designers for several technology nodes. Therefore, many new techniques for enhancing and optimizing reliability have emerged particularly within the last five to ten years. This perspective paper introduces the most prominent reliability concerns from today's points of view and roughly recapitulates the progress in the community so far. The focus of this paper is on perspective trends from the industrial as well as academic points of view that suggest a way for coping with reliability challenges in upcoming technology nodes.

Approximate computing: An emerging paradigm for energy-efficient design

Abstract: Approximate computing has recently emerged as a promising approach to energy-efficient design of digital systems. Approximate computing relies on the ability of many systems and applications to tolerate some loss of quality or optimality in the computed result. By relaxing the need for fully precise or completely deterministic operations, approximate computing techniques allow substantially improved energy efficiency. This paper reviews recent progress in the area, including design of approximate arithmetic blocks, pertinent error and quality measures, and algorithm-level techniques for approximate computing.

A Survey of Techniques for Approximate Computing

Abstract: Approximate computing trades off computation quality with effort expended, and as rising performance demands confront plateauing resource budgets, approximate computing has become not merely attractive, but even imperative. In this article, we present a survey of techniques for approximate computing (AC). We discuss strategies for finding approximable program portions and monitoring output quality, techniques for using AC in different processing units (e.g., CPU, GPU, and FPGA), processor components, memory technologies, and so forth, as well as programming frameworks for AC. We classify these techniques based on several key characteristics to emphasize their similarities and differences. The aim of this article is to provide insights to researchers into working of AC techniques and inspire more efforts in this area to make AC the mainstream computing approach in future systems.

[서평]「Computer Organization and Design, The Hardware/Software Interface」

Abstract: Recognizing the mannerism ways to get this books computer organization and design the hardware software interface 4th fourth edition by patterson hennessy is additionally useful. You have remained in right site to begin getting this info. acquire the computer organization and design the hardware software interface 4th fourth edition by patterson hennessy join that we manage to pay for here and check out the link.