Profiling Tools for FPGA-Based Embedded Systems: Survey and Quantitative Comparison

Abstract

<p class="MsoNormal" style="text-align: left; margin: 0cm 0cm 0pt; layout-grid-mode: char;" align="left"><span class="text"><span style="font-family: ";Arial";,";sans-serif";; font-size: 9pt;">Profiling tools are computer-aided design (CAD) tools that help in determining the computationally intensive portions in software. Embedded systems consist of hardware and software components that execute concurrently and efficiently to execute a specific task or application. Profiling tools are used by embedded system designers to choose computationally intensive functions for hardware implementation and acceleration. In this paper we review and compare various existing profiling tools for FPGA-based embedded systems. We then describe Airwolf, an FPGAbased profiling tool. We present a quantitative comparison of Airwolf and a well known software-based profiling tool, GNU gprof. Four software benchmarks were used to obtain profiling results using Airwolf and gprof. We show that Airwolf provides up to 66.2% improvement in accuracy of profiled results and reduces the run time performance overhead, caused by software-based profiling tools, by up to 41.3%. The results show that Airwolf provides accurate profiling results with minimal overhead and it can help the designers of FPGA-based embedded systems in identifying the computationally intensive portions of software code for hardware implementation and acceleration.</span></span><span style="font-family: ";Arial";,";sans-serif";; font-size: 9pt;"></span></p&gt

Energy profiling of FPGA designs

“…In [1], a detailed survey of a tool which perform power evaluation for design which use processing systems (usually based on soft-processors) is presented. Such tools include: SnoopP, Frequent Loop Analysis Tool (FLAT), WOoDSTOCK (Watches Over Data STreaming On Computing element linKs) or Airwolf.…”

“…Most FPGA profiling tools, such as the ones described in [1] [2][3] [4][5] [6], mainly use code instrumentation and code analysis for soft-core based systems implemented on FPGAs. This type of approach has the following drawbacks:…”

A design methodology for soft-core platforms on FPGA with SMP Linux, OpenMP support, and distributed hardware profiling system

“…Various examples of hardware-based profiling approaches have been presented in literature. For example, SnoopP [18] and Airwolf [19] are two function-level profilers for software applications running on soft-core processors. In a multicore scenario, Shannon et al [20] adapted the ABACUS profiling system to work on heterogeneous platforms composed of multiple cores and accelerators, while Nam Ho et al [21] proposed an infrastructure for performance monitoring of LEON3 in multicore configuration.…”

Low-cost hardware profiling of run-time and energy in FPGA embedded processors

“…Other recent work includes Airwolf [26], which is a software FPGA-based profiler for the Altera Nios II soft processor [7] that inserts software drivers into each software function call/return to enable/disable individual counters. Comet [12] is another software FPGA-based profiler for the Altera Nios [5] soft processor that requires the user to modify the application to be profiled with pragma-like labels to specify the starts and ends of regions of interest.…”