The purpose of this paper is to detail a high-level analytical modelling and optimisation environment for mixed-granularity Field Programmable Gate Arrays (FPGAs). The work carried out for the purposes of this study involves the creation of an analytical framework that can be used to optimise the design of a reconfigurable device for a set of benchmarks. The strengths of this approach are the simultaneous placement, module selection and architecture generation. In this paper, the problem is cast as a formal optimisation, and may be solved using existing optimisation tools. In addition, the approach is adapted into an heuristic for larger benchmark sets. The design space is explored by examining the tradeoffs between area, speed and flexibility, and some comparisons to commercial architectures are drawn.
Abstract-This paper is concerned with the application of formal optimisation methods to the design of mixed-granularity FPGAs. In particular, we investigate the appropriate mix and floorplan of heterogeneous elements: multipliers, RAMs, and LUT-based logic, in order to maximise the performance of a set of DSP benchmark applications, given a fixed silicon budget. A mathematical programming framework is introduced, along with a set of heuristics, capable of providing upper-bounds on the achievable reconfigurable-to-fixed-logic performance ratio. Moreover, we use linear-programming bounding procedures from the operations research community to provide lower-bounds on the same quantity. Our results provide, for the first time, quantifications of the optimal performance/area-enhancing capability of multipliers and RAM blocks within a system context. The approach detailed provides a formal mechanism to explore future technology nodes.
Low-resolution face recognition (LR FR) has become an active research subarea due to its significances for real applications. Conventional low-resolution face recognition approaches meet challenges like noise affection and lack of effective features with LR faces. In this paper, we propose a deep learning method for LR FR. Our convolutional neural network (CNN) model directly learns an end-to-end classification on LR faces. Different from normal CNN for high-resolution (HR) face recognition, ours integrates a lightweight hallucination network mapping LR images into HR ones. Furthermore, we concatenate the hallucination and classification networks so that the training propagation is operated in one model, which largely boosts the performance over basic CNN and separate two-step models. Besides, our model is robust to varying poses and illuminations in the wild, and also portable to embedded system for its memoryand energy-saving features.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.