Vashishta Priya, Kalia Rajiv K, Nakano Aiichiro
Collaboratory for Advanced Computing & Simulations, Department of Chemical Engineering & Materials Science, University of Southern California, 3651 Watt Way, Los Angeles, California 90089-0242, USA.
J Phys Chem B. 2006 Mar 2;110(8):3727-33. doi: 10.1021/jp0556153.
We have developed a first-principles-based hierarchical simulation framework, which seamlessly integrates (1) a quantum mechanical description based on the density functional theory (DFT), (2) multilevel molecular dynamics (MD) simulations based on a reactive force field (ReaxFF) that describes chemical reactions and polarization, a nonreactive force field that employs dynamic atomic charges, and an effective force field (EFF), and (3) an atomistically informed continuum model to reach macroscopic length scales. For scalable hierarchical simulations, we have developed parallel linear-scaling algorithms for (1) DFT calculation based on a divide-and-conquer algorithm on adaptive multigrids, (2) chemically reactive MD based on a fast ReaxFF (F-ReaxFF) algorithm, and (3) EFF-MD based on a space-time multiresolution MD (MRMD) algorithm. On 1920 Intel Itanium2 processors, we have demonstrated 1.4 million atom (0.12 trillion grid points) DFT, 0.56 billion atom F-ReaxFF, and 18.9 billion atom MRMD calculations, with parallel efficiency as high as 0.953. Through the use of these algorithms, multimillion atom MD simulations have been performed to study the oxidation of an aluminum nanoparticle. Structural and dynamic correlations in the oxide region are calculated as well as the evolution of charges, surface oxide thickness, diffusivities of atoms, and local stresses. In the microcanonical ensemble, the oxidizing reaction becomes explosive in both molecular and atomic oxygen environments, due to the enormous energy release associated with Al-O bonding. In the canonical ensemble, an amorphous oxide layer of a thickness of approximately 40 angstroms is formed after 466 ps, in good agreement with experiments. Simulations have been performed to study nanoindentation on crystalline, amorphous, and nanocrystalline silicon nitride and silicon carbide. Simulation on nanocrystalline silicon carbide reveals unusual deformation mechanisms in brittle nanophase materials, due to coexistence of brittle grains and soft amorphous-like grain boundary phases. Simulations predict a crossover from intergranular continuous deformation to intragrain discrete deformation at a critical indentation depth.
我们开发了一种基于第一性原理的分层模拟框架,该框架无缝集成了:(1) 基于密度泛函理论 (DFT) 的量子力学描述;(2) 基于反应力场 (ReaxFF) 的多级分子动力学 (MD) 模拟,该反应力场描述化学反应和极化、采用动态原子电荷的非反应力场以及有效力场 (EFF);(3) 一个基于原子信息的连续介质模型,以达到宏观长度尺度。对于可扩展的分层模拟,我们针对以下方面开发了并行线性缩放算法:(1) 基于自适应多重网格上的分治算法的 DFT 计算;(2) 基于快速 ReaxFF (F-ReaxFF) 算法的化学反应性 MD;(3) 基于时空多分辨率 MD (MRMD) 算法的 EFF-MD。在 1920 个英特尔安腾 2 处理器上,我们展示了 140 万个原子(12 万亿个网格点)的 DFT 计算、5.6 亿个原子的 F-ReaxFF 计算以及 189 亿个原子的 MRMD 计算,并行效率高达 0.953。通过使用这些算法,已经进行了数百万原子的 MD 模拟来研究铝纳米颗粒的氧化。计算了氧化物区域的结构和动态相关性以及电荷的演变、表面氧化物厚度、原子扩散率和局部应力。在微正则系综中,由于与 Al-O 键合相关的巨大能量释放,氧化反应在分子氧和原子氧环境中都会变得爆炸式进行。在正则系综中,在 466 皮秒后形成了厚度约为 40 埃的非晶氧化物层,与实验结果吻合良好。已经进行了模拟以研究对晶体、非晶和纳米晶硅氮化物及碳化硅的纳米压痕。对纳米晶碳化硅的模拟揭示了脆性纳米相材料中不寻常的变形机制,这是由于脆性晶粒和类似软非晶的晶界相共存所致。模拟预测在临界压痕深度处会从晶间连续变形转变为晶内离散变形。