Porting and Optimization of LIBXC on the Domestic Heterogeneous Platform

doi:10.11871/jfdc.issn.2096-742X.2025.05.005

Abstract

Abstract:

[Objective] LLIBXC is a widely used exchange-correlation functional library in quantum chemistry software and has been integrated into mainstream quantum chemistry program packages. Porting and optimizing LIBXC on a homegrown acceleration platform is of great significance for enhancing the computational capabilities of quantum chemistry software and advancing related research. [Methods] Based on the HIP architecture, this study automated the source code translation of LIBXC and reconfigured the building system using the cross-platform tool CMake. Manual optimizations and code modifications were performed to address unsupported platform-specific features, successfully enabling LIBXC’s porting to the domestic heterogeneous platform. Additionally, optimizations such as pinned memory and stream technology were introduced to further improve the performance. [Results] The ported and optimized LIBXC library passes regression testing, achieving full compliance with accuracy requirements. Performance evaluations demonstrate that the speedup of LDA functionals can exceed 1,000 times, and GGA functionals for energy calculations can reach up to 1,699 times speedup compared to the single-threaded CPU version. Under the same testing conditions, the performance of a single acceleration card is comparable to that of the NVIDIA Tesla V100. [Conclusions] This work provides a foundational technical support for the localization of quantum chemistry software, facilitating the porting and optimization of such software on domestic platforms. It contributes to the ongoing development of the software ecosystem for China’s homegrown supercomputing platforms.

Key words: exchange-correlation functional, heterogeneous computing, unified virtual memory, stream, Heterogeneous-compute Interface for Portability

SHEN Ao,YAN Yuqi,BIE Lihua. Porting and Optimization of LIBXC on the Domestic Heterogeneous Platform[J]. Frontiers of Data and Computing, 2025, 7(5): 54-64, https://cstr.cn/32002.14.jfdc.CN10-1649/TP.2025.05.005.

Figures/Tables 15

Table 1

Fig.1

Fig.2

Fig.3

Table 2

Fig.4

Fig.5

Table 3

Table 4

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

Fig.11

References 18

[1]	MARQUES M A L, OLIVEIRA M J T, BURNUS T. Libxc: A Library of Exchange and Correlation Functionals for Density Functional Theory[J]. Computer Physics Communications, 2012, 183(10): 2272-2281.
[2]	KOHN W, SHAM L J. Self-Consistent Equations Including Exchange and Correlation Effects[J]. Physical Review, 1965, 140(4A): 1133-1138.
[3]	MARDIROSSIAN N, HEAD-GORDON M. Thirty Years of Density Functional Theory in Computational Chemistry an Overview and Extensive Assessment of 200 Density Functionals[J]. Molecular Physics, 2017, 115(19): 2315-2372.
[4]	WILLIAMS-YOUNG D B, De JONG W A, VAN DAM H J J, et al. On the Efficient Evaluation of the Exchange Correlation Potential on Graphics Processing Unit Clusters[J]. Frontiers in Chemistry, 2020, 8(1): 581058.
[5]	HAOYU S, YU Y Z, ROBERTO PEVERATI, et al. TRUHLAR Minnesota Functional Module 6.0 (Mfm 6.0)[DB/OL]. https://comp.chem.umn.edu/mfm/.
[6]	EKSTRÖM U. Xcfun: A Library of Exchange-Correlation Functionals with Arbitrary-Order Derivati-ves[DB/OL]. (2020-11) [2025-2-10]. https://doi.org/10.5281/zenodo.3796573.
[7]	LEHTOLA S, STEIGEMANN C, OLIVEIRA M J T, et al. Recent Developments in Libxc- a Comprehensive Library of Functionals for Density Functional Theory[J]. SoftwareX, 2018, 7(2018): 1-5.
[8]	LEHTOLA S, STEIGEMANN C, OLIVEIRA M J T, et al. MARQUES. Library[DB/OL]. (2017-6-7)[2025-2-10]. https://gitlab.com/libxc/libxc.
[9]	LEHTOLA S, STEIGEMANN C, OLIVEIRA M J T, et al. Libxc: A Library of Exchange and Correlation Functionals for Density Functional Theory[DB/OL]. (2010-07-09)[2025-2-10]. https://libxc.gitlab.io/.
[10]	ZHANG Y, SUO B, WANG Z, et al. Bdf: A Relativistic Electronic Structure Program Package[J]. The Jou-rnal of Chemical Physics, 2020, 152(064113): 1-11.
[11]	MARQUES M A L, CASTRO A, BERTSCH G F, et al. Octopus: A First-Principles Tool for Excited Electron-Ion Dynamics[J]. Computer Physics Communications, 2003, 151(1): 60-78.
[12]	CASTRO A, APPEL H, OLIVEIRA M, et al. Octopus: A Tool for the Application of Time-Dependent Density Functional Theory[J]. basic solid state physics, 2006, 243(11): 2465-2488.
[13]	GONZE X, AMADON B, ANGLADE P M, et al. Abinit: First-Principles Approach to Material and Nanosystem Properties[J]. Computer Physics Communications, 2009, 180(2009): 2582-2615.
[14]	HUTTER J, IANNUZZI M, SCHIFFMANN F, et al. Cp2k: Atomistic Simulations of Condensed Matter Systems[J]. Wiley Interdisciplinary Reviews. Computational Molecular Science, 2014, 4(1): 15-25.
[15]	MOHR S, RATCLIFF L E, GENOVESE L, et al. Accurate and Efficient Linear Scaling Dft Calculations with Universal Applicability[J]. Physical Chemistry Chemical Physics, 2015, 17(47): 31360-31370. doi: 10.1039/c5cp00437c pmid: 25958954
[16]	BAHN S R, JACOBSEN K W. An Object-Oriented Scripting Interface to a Legacy Electronic Structure Code[J]. Computing in Science & Engineering, 2002, 4(3): 56-66.
[17]	先进计算(天津)信息技术有限公司. 超算互联网[DB/OL]. (2024-8)[2025-2-10]. https://www.scnet.cn/ui/mall.
[18]	MANATHUNGA M, MIAO Y, MU D, et al. Parallel Implementation of Density Functional Theory Methods in the Quantum Interaction Computational Kernel Program[J]. Journal of Chemical Theory and Computation, 2020, 16(7): 4315-4526. doi: 10.1021/acs.jctc.0c00290 pmid: 32511916

泛函库	源码	接口	泛函数量	最近更新	GPU支持
LIBXC	C	C、Fortran、Python	680	2024.10	有
MFM	Fortran77	Fortran	25	2022.02	无
XCFun	C++	C、Fortran	41	2020.11	无
ExchCXX	C++	C++	50+	2023.10	有

CUDA版源码	策略
统一内存管理	手工管理
自动深拷贝	手工深拷贝
不规范的预处理及宏定义	代码修改
设备端动态内存分配	静态数组

软硬件	版本及型号
ToolKit	DTK 22.04.1
C编译器	gcc 7.3.1
HIP编译器	hipcc 4.3
CMake	cmake-3.22.0-rc1
CPU	Hygon C86 7185 32核
内存	8×16GB DDR4

	lda_xc_teter93	gga_x_b88	gga_c_pbe
CPU	-624.9572773	-595.1637854	-49.19756366
移植版	-624.9572773	-595.1637854	-49.19756366
Error	0.00E+00	0.00E+00	0.00E+00