This shows you the differences between two versions of the page.

Link to this comparison view

seminars:seminar_02_11_14 [2017/09/20 22:02] (current)
Line 1: Line 1:
 +====== The Design of a Database Processing Unit ======
 +==== Martha Kim (Columbia University) ====
 +== Tuesday, Feb. 11th, 4:​00pm-5:​00pm ==
 +== Hamerschlag Hall D-210 ==
 +With the global pool of data growing at 2.5 quintillion bytes per day and
 +90% of it produced in the last two years, there is no doubt the era of big
 +data has arrived. This talk presents a targeted deployment of hardware
 +accelerators to improve the throughput and energy efficiency of large-scale
 +data processing. This talk describes Database Processing Units, or DPUs, a
 +class domain-specific database processors that can efficiently handle
 +database applications,​ and present the instruction set architecture,​
 +microarchitecture,​ and hardware implementation of one DPU, called the Q100.
 +The Q100 has a collection of heterogeneous ASIC tiles that process
 +relational tables and columns quickly and energy-efficiently. ​ The
 +architecture uses coarse grained instructions that manipulate streams of
 +data, thereby maximizing pipeline and data parallelism,​ and minimizing the
 +need to time multiplex the accelerator tiles and spill intermediate results
 +to memory. ​ This talk will outline the motivation, design, evaluation and
 +challenges of such data processing systems.
 +Martha Kim is an Assistant Professor of Computer Science at Columbia
 +University where she leads the ARCADE Lab. Kim's research interests are in
 +computer architecture,​ parallel programming,​ compilers, and low-power
 +computing. Her work has explored low-cost chip manufacturing systems,
 +reconfigurable communication networks, and fine-grained parallel application
 +profiling techniques. Her current research focuses on hardware and software
 +techniques to improve the usability of hardware accelerators as well as
 +data-centric accelerator design. Kim holds a PhD in Computer Science and
 +Engineering from the University of Washington and a bachelors in Computer
 +Science from Harvard University. She is the recipient of the 2013 Rodriguez
 +Family Award in recognition of the research achievements of underrepresented
 +junior faculty and a 2013 NSF CAREER award.