![]() |
COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. | ![]() |
University of Cambridge > Talks.cam > Computer Laboratory Computer Architecture Group Meeting > Combining Scratch-Pad Placement with Loop Parallelisation for FPGAs
![]() Combining Scratch-Pad Placement with Loop Parallelisation for FPGAsAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Prof Simon Moore. I will discuss some joint work with my PhD student, Qiang Liu, on how to combine loop parallelisation with custom memory subsystem design, targeting FPGA -based computation. We will show that the dependence between the two problems can be exposed and optimized over using a form of constrained optimization called “Geometric Programming”. I will try to find time to begin the talk with an overview of convex optimization techniques in general, and geometric programming in particular, in the hope that some of you may find an application for similar techniques in your own work. This talk is part of the Computer Laboratory Computer Architecture Group Meeting series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsPhotonics Summer Seminars 2017 Economics talks John Ray SocietyOther talksProduction Processes Group Seminar - "Evanescent Field Optical Tweezing for Synchrotron X-Ray Crystallography" How to make good scientific figures Zoo and Wildlife Work Finding the past: Medieval Coin Finds at the Fitzwilliam Museum Strong Bonds, Affective Labour: Sexually Transmitted Infections and the Work of History Characterizing Immunogenetic Mechanisms through HIV Disease Analysis |