Lecture Series Archive

Abstract – High Performance Computing and Data Centers are driving the demand for high bandwidth interconnects. According to Cisco, cloud data center traffic is projected to grow to 8.6 Zettabytes per year, with 73% of that traffic within the data center. Future exascale supercomputers capable of more than a quintillion operations per second will demand higher performance networks characterized by lower power consumption, lower cost, and higher bit rate. VCSEL-based multimode optical links are one key solution to enable this growth. In this talk, I will present three projects to address the demands of future optical links. In the first part, I will describe a 30Gb/s 90nm CMOS-driven multimode optical link that uses equalization to achieve higher data rates and lower power consumption. In the second part, I will describe a 4-channel wavelength division multiplexing solution for uncooled lasers using injection-molded optics to reduce system costs. In the third part, I will describe a system to characterize VCSELs using hyperspectral imaging, and I will show how this system can be used to improve multimode fiber bandwidth from 6.3GHz to 17.5GHz over 300m.

Dr. Brendan Hamel-Bissell is an Assistant Professor at the Department of Engineering, SSU. He grew up in Underhill, Vermont, where he spent most of his time in the mountains skiing, including 6 years on the US National Ski Patrol. He did his undergrad at McGill University in Montréal, Canada, and became interested in the applications of optics, especially optical communications. He completed his PhD in electrical engineering at Stanford University in 2016, with a focus of optical communications in data centers. While at Stanford, he worked with industry researchers as a Senior Scientist at Finisar Corporation and taught electrical engineering at De Anza College. Brendan is passionate about supporting the LGBTQ community; he has served on the Board of Directors of Stanford Pride, Stanford's LGBT alumni association since 2012 and as the Director of Admissions for the Out for Undergrad Engineering Conference since 2014.

Abstract – Stored data needs to be protected against device failures, irrecoverable read errors, and other risks that become increasingly challenging at scale. At the same time, it is essential to manage underlying storage efficiently, and to do so in the face of incremental and dramatic changes to the underlying storage technologies. In this talk, we will discuss the building of large-scale reliable storage systems, and the problems encountered when employing new storage technologies. In particular we will discuss the problems posed by the recent shift in magnetic disk-based data storage to what is termed shingled magnetic recording (SMR). This shift is an important step in continuing the increase in data storage densities, but it also makes updates to existing data potentially destructive and requires software-based approaches to mitigate this behavior. We will go on to discuss the ways in which future storage systems software can address these challenges efficiently.

Dr. Ahmed Amer is an associate professor of Computer Engineering at Santa Clara University. His research areas are systems, particularly storage systems, operating systems, and distributed systems. His work has included the predictive management of data and storage, with recent work involving data grouping and the management of shingled magnetic recording technologies, the design of highly reliable systems at scale, and energy management. He is especially interested in alternative and upcoming storage technologies, and their most practical and effective application.