Hardware-in-the-loop Simulation for CPU/GPU Heterogeneous Platforms

Abstract

Multi-core CPU/GPU heterogeneous platforms became popular in embedded systems. A full system simulator is typically used to observe the internal system behavior by running complete software stacks without modification on simulation models of CPUs and other devices in the system. However, there are few known full system simulators for CPU/GPU heterogeneous platforms and existent GPU simulators are prohibitively slow for running application software. In this paper, we propose a hardware-in-the-loop simulation technique that integrates GPU hardware into a full system simulator. A novel interfacing mechanism between CPU simulator and the development board, where GPU hardware is integrated, is devised. In the experiments, we took Exynos 4412 as a case study, where gem5 simulator is used to simulate mainly a quad-core ARM CPU in the platform and an Exynos development board is used to run the Mali GPU hardware. We could successfully run Android apps on the proposed hardware-in-the-loop simulation framework with up to 1.5 M cycles per second performance.

Low cost DSP‐based educational embedded platform for real‐time simulation and fast implementation of complex systems in Simulink

“…Right now, there is a wide variety of real-time emulators, most of them are commercialize by important companies such as National Instruments, dSPACE, OPAL-RT, RTDS, as well as noncommercial options developed by different universities [1,19]. Different embedded technologies are used taking advantage of their architecture settings to maximize the design such as DSPs [20,24,[29][30][31], graphics processing unit [7,14,[16][17][18]25], FPGAs [2,5,6,15,23,27], and genericuse processors. The opportunities to apply these realtime simulators in engineering are wide and vary due to the several advantages [11] that bring such as cost, prototypes speed, fidelity, and results consistency.…”