Fast functional simulation with a dynamic language

Abstract

Simulation of large computational systems-on-a-chip (SoCs) is increasing challenging as the number and complexity of components is scaled up. With the ubiquity of programmable components in computational SoCs, fast functional instruction-set simulation (ISS) is increasingly important. Much ISS has been done with straightforward functional models of a non-pipelined fetch-decode-execute iteration written in a low-to-mid-level C-family static language, delivering mid-level efficiency. Some ISS programs, such as QEMU, perform dynamic binary translation to allow software emulation to reach more usable speeds. This relatively complex methodology has not been widely adopted for system modeling. We demonstrate a fresh approach to ISS that achieves performance comparable to a fast dynamic binary translator by exploiting recent advances in just-in-time (JIT) compilers for dynamic languages, such as JavaScript and Lua, together with a specific programming idiom inspired by pipelined processor design. We believe that this approach is relatively accessible to system designers familiar with C-family functional simulator coding styles, and may be generally useful for fast modeling of complex SoC components.