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.

Multi-dimensional SLA-Based Resource Allocation for Multi-tier Cloud Computing Systems

Abstract: With increasing demand for computing and memory, distributed computing systems have attracted a lot of attention. Resource allocation is one of the most important challenges in the distributed systems specially when the clients have Service Level Agreements (SLAs) and the total profit in the system depends on how the system can meet these SLAs. In this paper, an SLA-based resource allocation problem for multi-tier applications in the cloud computing is considered. An upper bound on the total profit is provided and an algorithm based on force-directed search is proposed to solve the problem. The processing, memory requirement, and communication resources are considered as three dimensions in which optimization is performed. Simulation results demonstrate the effectiveness of the proposed heuristic algorithm.

Minimizing data center cooling and server power costs

Abstract: This paper focuses on power minimization in a data center accounting for both the information technology equipment and the air conditioning power usage. In particular we address the server consolidation (on/off state assignment) concurrently with the task assignment. We formulate the resulting optimization problem as an Integer Linear Programming problem and present a heuristic algorithm that solves it in polynomial time. Experimental results show an average of 13% power saving for different data center utilization rates compared to a baseline task assignment technique, which does not perform server consolidation.

High-level power modeling, estimation, and optimization

Abstract: Silicon area, performance, and testability have been, so far, the major design constraints to be met during the development of digital very-large-scale-integration (VLSI) systems. In recent years, however, things have changed; increasingly, power has been given weight comparable to the other design parameters. This is primarily due to the remarkable success of personal computing devices and wireless communication systems, which demand high-speed computations with low power consumption. In addition, there exists a strong pressure for manufacturers of high-end products to keep power under control, due to the increased costs of packaging and cooling this type of device. Last, the need of ensuring high circuit reliability has turned out to be more stringent. The availability of tools for the automatic design of low-power VLSI systems has thus become necessary. More specifically, following a natural trend, the interests of the researchers have lately shifted to the investigation of power modeling, estimation, synthesis, and optimization techniques that account for power dissipation during the early stages of the design flow. This paper surveys representative contributions to this area that have appeared in the recent literature.

Fine-grained dynamic voltage and frequency scaling for precise energy and performance tradeoff based on the ratio of off-chip access to on-chip computation times

Abstract: This work presents an intraprocess dynamic voltage and frequency scaling (DVFS) technique targeted toward nonreal-time applications running on an embedded system platform. The key idea is to make use of runtime information about the external memory access statistics in order to perform CPU voltage and frequency scaling with the goal of minimizing the energy consumption while translucently controlling the performance penalty. The proposed DVFS technique relies on dynamically constructed regression models that allow the CPU to calculate the expected workload and slack time for the next time slot and, thus, adjust its voltage and frequency in order to save energy, while meeting soft timing constraints. This is, in turn, achieved by estimating and exploiting the ratio of the total off-chip access time to the total on-chip computation time. The proposed technique has been implemented on an XScale-based embedded system platform and actual energy savings have been calculated by current measurements in hardware. For memory-bound programs, a CPU energy saving of more than 70% with a performance degradation of 12% was achieved. For CPU-bound programs, 15% /spl sim/ 60% CPU energy saving was achieved at the cost of 5%-20% performance penalty.

Modeling and analysis of nonuniform substrate temperature effects on global ULSI interconnects

Abstract: Nonuniform thermal profiles on the substrate in high-performance ICs can significantly impact the performance of global on-chip interconnects. This paper presents a detailed modeling and analysis of the interconnect performance degradation due to the nonuniform temperature profiles that are encountered along long metal interconnects as a result of existing thermal gradients in the underlying Silicon substrate. A nonuniform temperature-dependent distributed RC interconnect delay model is proposed. The model is applied to a wide variety of interconnect layouts and substrate temperature distributions to quantify the impact of such thermal nonuniformities on signal integrity issues including speed degradation in global interconnect lines and skew fluctuations in clock signal distribution networks. Subsequently, a new thermally dependent zero-skew clock-routing methodology is presented. This study suggests that thermally aware analysis should become an integrated part of the various optimization steps in physical-synthesis flow to improve the performance and integrity of signals in global ultra large scale integration interconnects.

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.