Horus: A Modular GPU Emulator Framework

摘要

Graphics Processing Units (GPUs) are widely used to run general-purpose computing workloads. Three approaches currently exist to observe the dynamic behaviour of these workloads: real hardware, architectural simulators, and functional simulators (or emulators). However, the rapid evolution of GPU hardware and software stacks means that, in reality, using hardware is the only option to study current GPU workloads. Unfortunately, GPU toolchain support for advanced characterization capabilities is still far behind CPU toolchains like Pin. In this paper, we present an early glimpse of Horus, an emulator for NVIDIA GPUs. Although it is not the first such emulator, Horus is being engineered using a novel methodology to keep pace with the rapid changes in GPU hardware. Horus is highly modular, and is the first to utilize a specially designed DSL for specifying formal semantics for GPU instruction sets (NVIDIA PTX). A semantics compiler uses these semantics to generate the emulator. Horus also features a well-defined interface by which utility functions – instrumentation, new instruction support, analysis tools – can be coupled with the main emulator to increase reuse while studying the dynamic behaviour of GPU kernels. Horus is now mature enough to run all the Polybench and Rodinia benchmarks correctly.