An efficient and portable SIMD algorithm for charge/current deposition in Particle-In-Cell codes
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Author(s): Vincenti, H; Lobet, M; Lehe, R; Sasanka, R; Vay, JL | Abstract: © 2016 In current computer architectures, data movement (from die to network) is by far the most energy consuming part of an algorithm (≈20pJ/word on-die to ≈10,000 pJ/word on the network). To increase memory locality at the hardware level and reduce energy consumption related to data movement, future exascale computers tend to use many-core processors on each compute nodes that will have a reduced clock speed to allow for efficient cooling. To compensate for frequency decrease, machine vendors are making use of long SIMD instruction registers that are able to process multiple data with one arithmetic operator in one clock cycle. SIMD register length is expected to double every four years. As a consequence, Particle-In-Cell (PIC) codes will have to achieve good vectorization to fully take advantage of these upcoming architectures. In this paper, we present a new algorithm that allows for efficient and portable SIMD vectorization of current/charge deposition routines that are, along with the field gathering routines, among the most time consuming parts of the PIC algorithm. Our new algorithm uses a particular data structure that takes into account memory alignment constraints and avoids gather/scatter instructions that can significantly affect vectorization performances on current CPUs. The new algorithm was successfully implemented in the 3D skeleton PIC code PICSAR and tested on Haswell Xeon processors (AVX2-256 bits wide data registers). Results show a factor of ×2 to ×2.5 speed-up in double precision for particle shape factor of orders 1–3. The new algorithm can be applied as is on future KNL (Knights Landing) architectures that will include AVX-512 instruction sets with 512 bits register lengths (8 doubles/16 singles). Program summary Program Title: vec_deposition Program Files doi:http://dx.doi.org/10.17632/nh77fv9k8c.1 Licensing provisions: BSD 3-Clause Programming language: Fortran 90 External routines/libraries: OpenMPg4.0 Nature of problem: Exascale architectures will have many-core processors per node with long vector data registers capable of performing one single instruction on multiple data during one clock cycle. Data register lengths are expected to double every four years and this pushes for new portable solutions for efficiently vectorizing Particle-In-Cell codes on these future many-core architectures. One of the main hotspot routines of the PIC algorithm is the current/charge deposition for which there is no efficient and portable vector algorithm. Solution method: Here we provide an efficient and portable vector algorithm of current/charge deposition routines that uses a new data structure, which significantly reduces gather/scatter operations. Vectorization is controlled using OpenMP 4.0 compiler directives for vectorization which ensures portability across different architectures. Restrictions: Here we do not provide the full PIC algorithm with an executable but only vector routines for current/charge deposition. These scalar/vector routines can be used as library routines in your 3D Particle-In-Cell code. However, to get the best performances out of vector routines you have to satisfy the two following requirements: (1) Your code should implement particle tiling (as explained in the manuscript) to allow for maximized cache reuse and reduce memory accesses that can hinder vector performances. The routines can be used directly on each particle tile. (2) You should compile your code with a Fortran 90 compiler (e.g Intel, gnu or cray) and provide proper alignment flags and compiler alignment directives (more details in README file).
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“The ECCOPICcode employed in Refs. 119, 142, 143, and 331 was verified in an international HT-related benchmark involving several codes 84 and validated with experimental data 119,331 , demonstrating the method's functionality.”
From Plasma propulsion modeling with particle-based algorithms (2023) · cites this paper as [331]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Plasma Physics via Computer Simulation
Birdsall, C. K., & Langdon, A. B. (2018) · CRC Press eBooks · doi:10.1201/9781315275048 · Cited by 3,745
Exact charge conservation scheme for particle-in-cell simulation with an arbitrary form-factor
Esirkepov, T. Z. (2001) · Computer Physics Communications · doi:10.1016/s0010-4655(00)00228-9 · Cited by 513
Fonseca, R. A., Vieira, J., Fiuza, F., Davidson, A., Tsung, F. S., Mori, W. B., & Silva, L. O. (2013) · Plasma Physics and Controlled Fusion · doi:10.1088/0741-3335/55/12/124011 · Cited by 124
Particle-in-Cell algorithms for emerging computer architectures
Decyk, V. K., & Singh, T. V. (2014) · Computer Physics Communications · doi:10.1016/j.cpc.2013.10.013 · Cited by 75
Vector calculation of particle code
Nishiguchi, A., Orii, S., & Yabe, T. (1985) · Journal of Computational Physics · doi:10.1016/0021-9991(85)90078-6 · Cited by 27
Vectorizing the interpolation routines of particle-in-cell codes
Horowitz, E. J. (1987) · Journal of Computational Physics · doi:10.1016/0021-9991(87)90044-1 · Cited by 25
Particle code optimization on vector computers
Héron, A., & Adam, J. C. (1989) · Journal of Computational Physics · doi:10.1016/0021-9991(89)90152-6 · Cited by 17
Anderson, D. V., & Shumaker, D. E. (1995) · Computer Physics Communications · doi:10.1016/0010-4655(94)00175-2 · Cited by 12
A vector-efficient and memory-saving interpolation algorithm for PIC codes on a cray X-MP
Paruolo, G. (1990) · Journal of Computational Physics · doi:10.1016/0021-9991(90)90153-r · Cited by 9
Research works printed but not linked: 2
- [11] J. L. Schwarzmeier, T. G. Hewitt, Proceedings, 12th conf. on numerical simulation of plasmas , 1987, San Francisco. -
- [2] R.A. Fonseca, J.Vieira, F. Fiuza, A. Davidson, F. S. Tsung, W. B. Mori and L. O. Siva ArXiv , http://arxiv.org/pdf/1310.0930v1.pdf (2013) - · arXiv
Cited by
Achieving Extreme Light Intensities using Optically Curved Relativistic Plasma Mirrors
Vincenti, H. (2019) · Physical Review Letters · doi:10.1103/physrevlett.123.105001 · Cited by 103
Self-citationIdentification of Coupling Mechanisms between Ultraintense Laser Light and Dense Plasmas
Chopineau, L., Leblanc, A., Blaclard, G., Denoeud, A., Thévenet, M., Vay, J.-L., Bonnaud, G., Martin, P., Vincenti, H., & Quéré, F. (2019) · Physical Review X · doi:10.1103/physrevx.9.011050 · Cited by 96
Self-citationIdentification of coupling mechanisms between ultraintense laser light and dense plasmas
Chopineau, L., Leblanc, A., Blaclard, G., Denoeud, A., Thévenet, M., Vay, J.-L., Bonnaud, G., Martin, P., Vincenti, H., & Quéré, F. (2019) · HAL · Cited by 78
Self-citationPorting WarpX to GPU-accelerated platforms
Myers, A. T., Almgren, A., Amorim, L. D., Bell, J. B., Fedeli, L., Ge, L., Gott, K., Grote, D. P., Hogan, M., Huebl, A., et al. (2021) · Parallel Computing · doi:10.1016/j.parco.2021.102833 · Cited by 77
“Zoni) ticle pushers and field solvers, were handled by the PICSAR library of Fortran kernels [22].”
MethodSelf-citationApplying the Roofline Performance Model to the Intel Xeon Phi Knights Landing Processor
Doerfler, D. W., Deslippe, J. R., Williams, S., Oliker, L., Cook, B., Kurth, T., Lobet, M., Malas, T. B., Vay, J.-L., & Vincenti, H. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46079-6_24 · Cited by 75
Self-citationVincenti, H., & Vay, J.-L. (2018) · Computer Physics Communications · doi:10.1016/j.cpc.2018.03.018 · Cited by 53
Self-citationSpatial Properties of High-Order Harmonic Beams from Plasma Mirrors: A Ptychographic Study
Leblanc, A., Monchocé, S., Vincenti, H., Kahaly, S., Vay, J.-L., & Quéré, F. (2017) · Physical Review Letters · doi:10.1103/physrevlett.119.155001 · Cited by 39
Self-citationInteraction of Ultraintense Radially-Polarized Laser Pulses with Plasma Mirrors
Zaïm, N., Guénot, D., Chopineau, L., Denoeud, A., Lundh, O., Vincenti, H., Quéré, F., & Faure, J. (2020) · Physical Review X · doi:10.1103/physrevx.10.041064 · Cited by 38
Self-citationBlaclard, G., Vincenti, H., Lehé, R., & Vay, J.-L. (2017) · Physical review. E · doi:10.1103/physreve.96.033305 · Cited by 36
Self-citationAdaptive SIMD optimizations in particle-in-cell codes with fine-grain particle sorting
Beck, A., Dérouillat, J., Lobet, M., Farjallah, A., Massimo, F., Zemzemi, I., Perez, F., Vinci, T., & Grech, M. (2019) · Computer Physics Communications · doi:10.1016/j.cpc.2019.05.001 · Cited by 33
Self-citationPlasma propulsion modeling with particle-based algorithms
Taccogna, F., Cichocki, F., Eremin, D., Fubiani, G., & Garrigues, L. (2023) · Journal of Applied Physics · doi:10.1063/5.0153862 · Cited by 29
The magnetohydrodynamic-particle-in-cell module in athena++ : implementation and code tests
Xiaochen, S., & Bai, X. (2023) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stad1548 · Cited by 25
Garrigues, L., du Montcel, B. T., Fubiani, G., Bertomeu, F., Deluzet, F., & Narski, J. (2021) · Journal of Applied Physics · doi:10.1063/5.0044363 · Cited by 34
Evaluating and optimizing the NERSC workload on Knights Landing
Barnes, T., Cook, B., Deslippe, J. R., Doerfler, D. W., Friesen, B., He, Y., Kurth, T., Koskela, T., Lobet, M., Malas, T. B., et al. (2016) · eScholarship (California Digital Library) · doi:10.5555/3019057.3019062 · Cited by 22
“PICSAR is an open-source ParticleIn-Cell FORTRAN+Python library designed to provide highperformance subroutines optimized for many-integrated core architectures [40], [41] that can be interfaced with WARP.”
BackgroundSelf-citationInteraction of Ultraintense Radially-Polarized Laser Pulses with Plasma Mirrors
Zaïm, N., Guénot, D., Chopineau, L., Denoeud, A., Lundh, O., Vincenti, H., Quéré, F., & Faure, J. (2021) · HAL · Cited by 21
Self-citationSurmin, I., Bastrakov, S., Matveev, Z. A., Efimenko, E. S., Gonoskov, A. A., & Meyerov, I. B. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-49956-7_25 · Cited by 20
Two-step perfectly matched layer for arbitrary-order pseudo-spectral analytical time-domain methods
Shapoval, O. V., Vay, J.-L., & Vincenti, H. (2018) · Computer Physics Communications · doi:10.1016/j.cpc.2018.09.015 · Cited by 18
Self-citationFast-QSGS: A GPU accelerated program for structure generation of granular disordered media
Yang, G., Liu, T., Lu, X., & Wang, M. (2024) · Computer Physics Communications · doi:10.1016/j.cpc.2024.109241 · Cited by 16
Sub-laser-cycle control of relativistic plasma mirrors
Chopineau, L., Blaclard, G., Denoeud, A., Vincenti, H., Quéré, F., & Haessler, S. (2022) · Physical Review Research · doi:10.1103/physrevresearch.4.l012030 · Cited by 15
Self-citationFew-cycle laser wakefield acceleration on solid targets with controlled plasma scale length
Zaïm, N., Böhle, F., Bocoum, M., Vernier, A., Haessler, S., Davoine, X., Videau, L., Faure, J., & López-Martens, R. (2019) · Physics of Plasmas · doi:10.1063/1.5084783 · Cited by 15
A generalized massively parallel ultra-high order FFT-based Maxwell solver
Kallala, H., Vay, J.-L., & Vincenti, H. (2019) · Computer Physics Communications · doi:10.1016/j.cpc.2019.07.009 · Cited by 14
Self-citationEfficient data layouts for a three-dimensional electrostatic Particle-in-Cell code
Barsamian, Y., Hirstoaga, S. A., & Violard, É. (2018) · Journal of Computational Science · doi:10.1016/j.jocs.2018.06.004 · Cited by 13
“1) [6, Section 4.1.2.].”
BackgroundMethodInfluentialEfficient parallelization for 3d-3v sparse grid Particle-In-Cell: Shared memory architectures
Deluzet, F., Fubiani, G., Garrigues, L., Guillet, C., & Narski, J. (2023) · Journal of Computational Physics · doi:10.1016/j.jcp.2023.112022 · Cited by 13
Techniques to generate intense isolated attosecond pulses from relativistic plasma mirrors
Kallala, H., Quéré, F., & Vincenti, H. (2020) · Physical Review Research · doi:10.1103/physrevresearch.2.043007 · Cited by 12
Self-citationEfficient Data Structures for a Hybrid Parallel and Vectorized Particle-in-Cell Code
Barsamian, Y., Hirstoaga, S. A., & Violard, É. (2017) · IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum · doi:10.1109/ipdpsw.2017.74 · Cited by 8
“We compared our results to those of [6] and [20] and we obtained significant gains.”
MethodResultPlasma mirrors as a path to the Schwinger limit: theoretical and numerical developments
Vincenti, H., Clark, T. C., Fedeli, L., Martin, P., Sainte-Marie, A., & Zaïm, N. (2023) · The European Physical Journal Special Topics · doi:10.1140/epjs/s11734-023-00909-2 · Cited by 9
Self-citationEfficient Strict-Binning Particle-in-Cell Algorithm for Multi-core SIMD Processors
Barsamian, Y., Charguéraud, A., Hirstoaga, S. A., & Méhrenberger, M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-96983-1_53 · Cited by 7
“Rather than sorting, other algorithms rely on coarse-grained binning [5, 20, 19, 22].”
BackgroundMethodConvergence in nonlinear laser wakefield accelerators modeling in a Lorentz-boosted frame
Lee, P., & Vay, J.-L. (2018) · Computer Physics Communications · doi:10.1016/j.cpc.2018.12.013 · Cited by 4
Self-citationSingle Domain Multiple Decompositions for Particle-in-Cell simulations
Dérouillat, J., & Beck, A. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1596/1/012052 · Cited by 4
Analyzing Performance of Selected NESAP Applications on the Cori HPC System
Kurth, T., Arndt, W. D., Barnes, T., Cook, B., Deslippe, J. R., Doerfler, D. W., Friesen, B., He, Y., Koskela, T., Lobet, M., et al. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-67630-2_25 · Cited by 4
“WARP Accelerator PIC Gather, Sort, osiris [12, 45] Physics FFT, Solver”
MethodSelf-citationA Space and Bandwidth Efficient Multicore Algorithm for the Particle-in-Cell Method
Barsamian, Y., Charguéraud, A., & Ketterlin, A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-78024-5_13 · Cited by 3
“Remark: optimized PIC codes implement the accumulation of the charge into ρ using an intermediate data structure that enables vectorized processing of the four corners [25].”
MethodPerformance improvement of particle-in-cell method for numerical modelling of open magnetic system
Boronina, M., Черных, И. Г., Genrikh, E. A., & Вшивков, В. А. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1640/1/012014 · Cited by 3
A task programming implementation for the particle in cell code smilei
Massimo, F., Lobet, M., Dérouillat, J., Beck, A., Bouchard, G., Grech, M., Perez, F., & Vinci, T. (2022) · Platform for Advanced Scientific Computing Conference (PASC) · doi:10.1145/3539781.3539788 · Cited by 3
“To reduce the effects of load imbalance, a hybrid MPI+OpenMP parallelization of the PIC method was implemented in some codes [7, 10, 23, 25].”
MethodSelf-citationZemzemi, I. (2020) · theses.fr (ABES) · doi:10.70675/e87258a3zf40bz4309z8030z048bd0d0990c · Cited by 7
Matrix‑PIC: Harnessing Matrix Outer-product for High‑Performance Particle‑in‑Cell Simulations
Rao, Y., Cui, X., Xie, J., Pang, S., Feng, G., Wei, J., Chen, Z., & Lu, Y. (2026) · European Conference on Computer Systems · doi:10.1145/3767295.3769378 · Cited by 2
“…After processing all particles across cells in a rank, a VPU-driven pass reduces the rhocell contributions to the global current density arrays ( J 𝑥 , J 𝑦 , J 𝑧 Vincenti et al. [40], each rhocell ’s contiguous 8-element operations to write rhocell data to J 𝑥 , J 𝑦 , and J 𝑧”
Lobet, M., Massimo, F., Beck, A., Bouchard, G., Perez, F., Vinci, T., & Grech, M. (2022) · International Conference on High Performance Computing in Asia-Pacific Region Workshops (HPC Asia Workshops) · doi:10.1145/3503470.3503475 · Cited by 2
“The current projection is not vectorizable in the classical form (memory race when writing on the grid nodes) [33].”
BackgroundSelf-citationcuGMEC: A high-performance code for gyrokinetic-MHD hybrid simulation on GPUs with CUDA C++
LIU, S. Y., JIANG, P. Y., & FU, G. Y. (2026) · Computer Physics Communications · doi:10.1016/j.cpc.2026.110249 · Cited by 2
Performance Aspects of Collocated and Staggered Grids for Particle-in-Cell Plasma Simulation
Bastrakov, S., Surmin, I., Efimenko, E. S., Gonoskov, A. A., & Meyerov, I. B. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-62932-2_8 · Cited by 1
Pic-Vert : a particle-in-cell implementation for multi-core architectures
Barsamian, Y. (2018) · theses.fr (ABES) · doi:10.70675/a8e04c76z4a50z43b0z9a4fz23f3e5c3aaa3 · Cited by 2
“We exploit a recently-proposed, ingenious technique allowing to accumulate the charge on the 8 corners using SIMD instructions [87].”
MethodInfluentialSparse approach to accelerate Particle-In-Cell method in 3D
Guillet, C. (2023) · theses.fr (ABES) · doi:10.70675/e21b6a1az8f15z47fbzacd0zb84c39e0b593 · Cited by 1
Luthien: A Parallel PIC Code for Modeling the Interaction of Focused Electron Beams with Plasma
Berendeev, Е. А., & Volchok, E. P. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-81691-9_16
Черных, И. Г., Куликов, И. М., Vshivkov, V., Efimova, A. A., Weins, D., Chernoshtanov, I. S., & Boronina, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-81247-7_21
Silva-Cuevas, J. J., Zych, M., Peyen, K., Kabadshow, I., & Lobet, M. (2025) · Computer Physics Communications · doi:10.1016/j.cpc.2025.109647
Self-citationZaïm, N. (2019) · theses.fr (ABES) · doi:10.70675/921ba960zc4b1z405dza423z36f5e22e583b · Cited by 4
Physique attoseconde relativiste sur miroirs plasmas
Chopineau, L. (2019) · theses.fr (ABES) · doi:10.70675/84ff05f2zf363z461ezacbbzdf73a159ceee · Cited by 4
Kallala, H. (2020) · theses.fr (ABES) · doi:10.70675/3d908234zfe8dz42fez9ae1z02e6f7c08a6f · Cited by 1
“This implementation demonstrated an excellent weak scaling up to hundreds of thousands of cores [63].”
BackgroundMethodClassical and quantum description of plasma and radiation in strong fields
Niel, F. (2018) · theses.fr (ABES) · doi:10.70675/526e8f3bz7b93z449bza261z6ede59baabb8 · Cited by 1
Strong-field Quantum Electrodynamics in the extremely intense light of relativistic plasma mirrors
Sainte-Marie, A. (2023) · theses.fr (ABES) · doi:10.70675/790e1f45z02dez4d67z8180z6624057028bc · Cited by 1
Performance Analysis of a New Three-Dimensional Plasma Physics Solver
Черных, И. Г., Куликов, И. М., Chernoshtanov, I. S., Liseykina, T., Vshivkov, V., & Boronina, M. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-22051-6_31
Metadata
- Authors
- Vincenti, H., Lobet, M., Lehe, R., Sasanka, R., & Vay, J.-L.
- Affiliations
- Lawrence Berkeley National Laboratory (US)
- Intel (United States) (US)
- Corresponding author
- Vincenti, H.
- Venue
- Computer Physics Communications
- Publisher
- Elsevier BV
- Published
- 2017-01
- Volume
- 210
- Pages
- 145-154
- ISSN
- 0010-4655 (ISSN-L)
- OpenAlex
- W2238102822
- Cited by
- 48
- References
- 9
- Citations by year
- 2026: 2 · 2025: 2 · 2024: 2 · 2023: 5 · 2022: 3 · 2021: 4 · 2020: 6 · 2019: 8 · 2018: 8 · 2017: 5
- FWCI
- 12.12
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- www.elsevier.com/tdm/userlicense/1.0/ (tdm)
- www.elsevier.com/open-access/userlicense/1.0/ (am, 332 d)
- Locations
- Computer Physics Communications (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- eScholarship (California Digital Library) (submittedVersion)
- OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) (submittedVersion)
- HAL (submittedVersion)
- arXiv (Cornell University)
- Funders
- Marie Curie IOF fellowship PICSSAR (624543)
- Office of Science, Office of High Energy Physics, U.S. Dept. of Energy (DE-AC02-05CH11231)
- US-DOE SciDAC program ComPASS
- US-DOE program CAMPA
- Office of Science of the U.S. Department of Energy (DE-AC02-05CH11231)
- Topics
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Computer Graphics and Visualization Techniques
- Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Electromagnetic Scattering and Analysis
- Keywords
- SIMD vectorization, charge deposition, particle-in-cell code, vectorization, memory alignment, exascale computing, many-core processors, AVX-512, memory locality, Fortran 90, particle shape factor
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.