带有OpenACC的GPU上的Gadget3
Gadget3 on GPUs with OpenACC
摘要：
我们目前的GPU移植的所有主要Gadget3模块（重力计算，SPH密度计算，SPH水动力和热传导）使用OpenACC指令的初步结果。在这里，我们为每个MPI秩分配一个GPU，并通过在CPU和GPU上重叠计算来利用主机和加速器的功能：当GPU异步计算MPI秩内粒子之间的交互时，CPU执行树遍历和相邻粒子的MPI通信。我们分析代码的各个部分，以了解我们的加速的起源，我们发现，由于时间步长很少活动粒子，没有达到峰值加速。我们从Magneticum项目运行流体动力学宇宙学模拟，使用$2\cdot10^{7}$粒子，我们发现最终总加速为$\approx 2.$。我们还展示了在EuroHack17事件的背景下运行的初步仅重力OpenACC移植的令人鼓舞的缩放测试结果，其中移植的原型被证明保持恒定的加速到$1024$ GPU。
英文摘要：
We present preliminary results of a GPU porting of all main Gadget3 modules (gravity computation, SPH density computation, SPH hydrodynamic force, and thermal conduction) using OpenACC directives. Here we assign one GPU to each MPI rank and exploit both the host and accellerator capabilities by overlapping computations on the CPUs and GPUs: while GPUs asynchronously compute interactions between particles within their MPI ranks, CPUs perform tree-walks and MPI communications of neighbouring particles. We profile various portions of the code to understand the origin of our speedup, where we find that a peak speedup is not achieved because of time-steps with few active particles. We run a hydrodynamic cosmological simulation from the Magneticum project, with $2\cdot10^{7}$ particles, where we find a final total speedup of $\approx 2.$ We also present the results of an encouraging scaling test of a preliminary gravity-only OpenACC porting, run in the context of the EuroHack17 event, where the prototype of the porting proved to keep a constant speedup up to $1024$ GPUs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
