Adaptive simulation with Virtual Prototypes in an open-source RISC-V evaluation platform

Recently, Virtual Prototypes (VPs) were introduced for the emerging RISC-V Instruction Set Architecture (ISA) and become an important part of the growing RISC-V ecosystem. A central component of the VP is the Instruction Set Simulator (ISS). VPs should provide a high simulation performance and at the same time yield accurate results, which are two conflicting requirements. To tackle this problem, we present an efficient VP-based adaptive simulation that is tailored for the RISC-V ISA and allows to seamlessly switch the accuracy setting in the ISS at runtime. This enables to selectively simulate the application as fast as possible and as accurate as necessary. In this paper we focus on the performance impact of different accuracy settings and leave the evaluation of accuracy results for future work. Our RISC-V experiments, using bare-metal and operating system based benchmarks, demonstrate that up-to 543x speed-up is possible with a JIT-based setting in the ISS.