Massoud Pedram

Bio: Massoud Pedram is an academic researcher from University of Southern California. The author has contributed to research in topics: Energy consumption & CMOS. The author has an hindex of 77, co-authored 780 publications receiving 23047 citations. Previous affiliations of Massoud Pedram include University of California, Berkeley & Syracuse University.

Chromatic Encoding: A Low Power Encoding Technique for Digital Visual Interface

Abstract: This paper presents a low-power encoding technique, called chromatic encoding, for the Digital Visual Interface standard (DVI), a digital serial video interface. Chromatic encoding reduces power consumption by minimizing the transition counts on the DVI. This technique relies on the notion of tonal locality, i.e., the observation that the signal differences between adjacent pixels in images follow a Gaussian distribution. Based on this observation, an optimal code assignment is performed to minimize the transition counts. Furthermore, the three color channels of the DVI may be reciprocally encoded to achieve even more power saving. The idea is that given the signal values from the three color channels, one or two of these channels are encoded by reciprocal differences with a number of redundant bits used to indicate the selection. The proposed technique requires only three redundant bits for each 24-bit pixel. Experimental results show up to a 75% transition reduction.

Improving the efficiency of Monte Carlo power estimation [VLSI]

Abstract: In this paper, we propose two efficient statistical sampling techniques for estimating the total power consumption of large hierarchical circuits. We first show that, due to the characteristic of the sampling efficiency in Monte Carlo simulation, granularity of samples is an important issue in achieving high overall efficiency. The proposed techniques perform sampling both temporally (across different clock cycles) and spatially (across different modules) so that a smaller sample granularity can be achieved while maintaining the normality of samples. The first proposed technique, which is referred to as the module-based approach, samples each module independently when forming a power sample. The second technique, which is referred to as the cluster-based approach, lumps the modules of a hierarchical circuit into a number of clusters on which sampling is then performed. Both techniques adapt stratification to further improve the efficiency. Experimental results show that these techniques provide a reduction of 23/spl times/ in simulation run time compared to existing Monte-Carlo simulation techniques.

TEI-ULP: Exploiting Body Biasing to Improve the TEI-Aware Ultralow Power Methods

Abstract: Temperature effect inversion (TEI) phenomenon in ultralow power (ULP) very large scale integration circuits has been identified as an important effect by both academia and industry. Although a number of ULP methods that attempt to exploit the TEI phenomenon have been proposed, the small size of the design exploration space when applying these methods to ULP circuits hinders them from achieving their full potential. This is mainly due to the limited granularity of the supply voltage level control. Starting with an intuition that the body biasing (BB) technique is a key to overcome this limitation, this paper exploits the BB technique along with the TEI-aware voltage scaling (TEI-VS) method and TEI-aware frequency scaling (TEI-FS) method, so as to substantially increase the design spaces of these methods. Techniques for optimally combining the BB technique with TEI-VS and TEI-FS are introduced. Simulation results with the latest commercial CMOS process technologies for ULP designs demonstrate the effectiveness of the proposed methodology.

A class of irredundant encoding techniques for reducing bus power

Abstract: This paper proposes a number of encoding techniques for decreasing power dissipation on global buses. The best target for these techniques is a wide and highly capacitive memory bus. Switching activity of the bus is reduced by means of encoding the values that are conveyed over them. More precisely, three irredundant bus-encoding techniques are presented in this paper. These techniques decrease the bus activity by as much as 86% for instruction addresses without the need to add redundant bus lines. Having no redundancy means that exercising these techniques on any existing system does not require redesign and remanufacturing of the printed circuit board of the system. The power dissipation of the encoder and decoder blocks is insignificant in comparison with the power saved on the memory address bus. This makes these techniques capable of reducing the total power consumption.

I and i

Abstract: There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality. Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

Machine learning

Abstract: Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.