Abstract:In this paper, we describe an approach that we explored for low-power synthesis and optimization of digital signal, image, and video processing (DSP) applications. In particular, we consider the systematic exploitation of data parallelism across the operations of an application dataflow graph when synthesizing a dedicated hardware implementation. Data parallelism occurs commonly in DSP applications, and provides flexible opportunities to increase throughput or lower power consumption. Exploiting this paralleli… Show more
“…This restriction allows for strong compile time predictability properties. SDF is a relatively mature form of dataflow and SDF-based hardware synthesis has been explored in [9] [13]. These restrictions imposed by SDF, however, are too stringent for some applications, especially applications with dynamic production and consumption rates.…”
This paper develops techniques for mapping rigid image registration applications onto configurable hardware. Image registration is a computationally intensive domain that places stringent requirements on performance and memory management efficiency. Building on the framework of homogeneous parameterized dataflow, which provides an effective formal model for design and analysis of hardware and software for signal processing applications, we develop novel methods for representing and exploring the hardware design space when mapping image registration algorithms into configurable hardware. Our techniques result in an efficient framework for trading off performance and configurable hardware resource usage based on the constraints of a given registration application.
“…This restriction allows for strong compile time predictability properties. SDF is a relatively mature form of dataflow and SDF-based hardware synthesis has been explored in [9] [13]. These restrictions imposed by SDF, however, are too stringent for some applications, especially applications with dynamic production and consumption rates.…”
This paper develops techniques for mapping rigid image registration applications onto configurable hardware. Image registration is a computationally intensive domain that places stringent requirements on performance and memory management efficiency. Building on the framework of homogeneous parameterized dataflow, which provides an effective formal model for design and analysis of hardware and software for signal processing applications, we develop novel methods for representing and exploring the hardware design space when mapping image registration algorithms into configurable hardware. Our techniques result in an efficient framework for trading off performance and configurable hardware resource usage based on the constraints of a given registration application.
“…The DAG shows all the individual units of computation and the flow of data between them, and the hardware structure can be generated. Sen and Bhattacharyya extend this technique providing an algorithm and framework to find the optimal application of data-parallel hardware implementations from SDF graphs [26].…”
Section: Temporal Models For Hardware Designmentioning
Functional languages as input specifications for HLS-tools allow to specify data dependencies but do not contain a notion of time nor execution order. In this paper, we propose a method to add this notion to the functional description using the dataflow model SDF-AP. SDF-AP consists of patterns that express consumption and production that we can use to enforce resource usage. We created an HLS-tool that can synthesize parallel hardware, both data and control path, based on the repetition, expressed in Higher-Order Functions, combined with specified SDF-AP patterns.Our HLS-tool, based on Template Haskell, generates an Abstract Syntax Tree based on the given patterns and the functional description uses the Clash-compiler to generate VHDL/Verilog.Case studies show consistent resource consumption and temporal behavior for our HLS-tool. A comparison with a commercially available HLS-tool shows that our tool outperforms in terms of latency and sometimes in resource consumption.The method and tool presented in this paper offer more transparency to the developer and allow to specify more accurately the synthesized hardware compared to what is possible with pragmas of the Vitis HLStool.
“…The synchronous dataflow (SDF) model [8] has strong compile time predictability properties, and is the most mature form of dataflow for signal processing system design. SDF-based hardware synthesis has been explored in [13] [16]. However, the SDF model is highly restrictive for many computer vision applications because the model cannot handle data-dependent rates of data transfer between actors [11].…”
Section: Forms Of Dataflow For Signal Processingmentioning
Image registration is computationally intensive, and hence difficult to implement in real-time. In recent efforts, image registration algorithms have been implemented in field-programmable gate array (FPGA) technology to improve performance, while providing programmability and dynamic reconfigurability. In this paper, we present a novel architecture for dynamically-reconfigurable image registration, along with details on the methodology used to derive the architecture. Unlike previous FPGA implementations for image registration, the architecture developed in this paper tunes its parallel processing structure adaptively based on relevant characteristics of the input images.
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.