Citations¶

EXESS prints a citation summary at the end of each calculation. The complete set of citations is provided below, along with their BibTeX entries.

Main EXESS citation¶

Galvez Vallejo, J. L.; Snowdon, C.; Stocks, R.; Kazemian, F.; Yan Yu, F. C.; Seidl, C.; Seeger, Z.; Alkan, M.; Poole, D.; Westheimer, B. M.; Basha, M.; De La Pierre, M.; Rendell, A.; Izgorodina, E. I.; Gordon, M. S.; Barca, G. M. J. Toward an Extreme-Scale Electronic Structure System. The Journal of Chemical Physics 2023, 159 (4), 044112. https://doi.org/10.1063/5.0156399.

@article{galvez_vallejo_exess_jcp,
  title = {Toward an extreme-scale electronic structure system},
  volume = {159},
  issn = {0021-9606},
  url = {https://doi.org/10.1063/5.0156399},
  doi = {10.1063/5.0156399},
  number = {4},
  urldate = {2023-11-28},
  journal = {The Journal of Chemical Physics},
  author = {Galvez Vallejo, Jorge L. and Snowdon, Calum and Stocks, Ryan and Kazemian, Fazeleh and Yan Yu, Fiona Chuo and Seidl, Christopher and Seeger, Zoe and Alkan, Melisa and Poole, David and Westheimer, Bryce M. and Basha, Mehaboob and De La Pierre, Marco and Rendell, Alistair and Izgorodina, Ekaterina I. and Gordon, Mark S. and Barca, Giuseppe M. J.},
  month = jul,
  year = {2023},
  pages = {044112}
}

Fragmentation papers¶

Stocks, R.; Vallejo, J. L. G.; Yu, F. C. Y.; Snowdon, C.; Palethorpe, E.; Kurzak, J.; Bykov, D.; Barca, G. M. J. Breaking the Million-Electron and 1 EFLOP/s Barriers: Biomolecular-Scale Ab Initio Molecular Dynamics Using MP2 Potentials. In SC24: International Conference for High Performance Computing, Networking, Storage and Analysis; 2024; pp 1-12. https://doi.org/10.1109/SC41406.2024.00015.
Barca, G. M. J.; Snowdon, C.; Vallejo, J. L. G.; Kazemian, F.; Rendell, A. P.; Gordon, M. S. Scaling Correlated Fragment Molecular Orbital Calculations on Summit; IEEE Computer Society, 2022; pp 72-85.
Barca, G. M. J.; Vallejo, J. L. G.; Poole, D. L.; Alkan, M.; Stocks, R.; Rendell, A. P.; Gordon, M. S. Enabling Large-Scale Correlated Electronic Structure Calculations: Scaling the RI-MP2 Method on Summit. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis; SC ‘21; Association for Computing Machinery: New York, NY, USA, 2021; pp 1-15. https://doi.org/10.1145/3458817.3476222.
Barca, G. M. J.; Poole, D. L.; Vallejo, J. L. G.; Alkan, M.; Bertoni, C.; Rendell, A. P.; Gordon, M. S. Scaling the Hartree-Fock Matrix Build on Summit. In SC20: International Conference for High Performance Computing, Networking, Storage and Analysis; 2020; pp 1-14. https://doi.org/10.1109/SC41405.2020.00085.

@inproceedings{stocks_breaking_2024,
  title = {Breaking the {Million}-{Electron} and 1 {{EFLOP}}/s {Barriers}: {Biomolecular}-{Scale} {Ab Initio} {Molecular} {Dynamics} {Using} {{MP2}} {Potentials}},
  shorttitle = {Breaking the {Million}-{Electron} and 1 {{EFLOP}}/s {Barriers}},
  booktitle = {{{SC24}}: {{International Conference}} for {{High Performance Computing}}, {{Networking}}, {{Storage}} and {{Analysis}}},
  author = {Stocks, Ryan and Vallejo, Jorge L. Galvez and Yu, Fiona C. Y. and Snowdon, Calum and Palethorpe, Elise and Kurzak, Jakub and Bykov, Dmytro and Barca, Giuseppe M. J.},
  year = {2024},
  month = nov,
  pages = {1--12},
  publisher = {IEEE},
  address = {Atlanta, GA, USA},
  doi = {10.1109/SC41406.2024.00015},
  urldate = {2025-06-16},
  isbn = {979-8-3503-5291-7},
  langid = {english}
}

@inproceedings{barca_fmo_sc22,
  title = {Scaling {Correlated} {Fragment} {Molecular} {Orbital} {Calculations} on {Summit}},
  isbn = {978-1-66545-444-5},
  url = {https://www.computer.org/csdl/proceedings-article/sc/2022/544400a072/1I0bSLKTsKA},
  language = {English},
  urldate = {2022-11-21},
  publisher = {IEEE Computer Society},
  author = {Barca, Giuseppe M. J. and Snowdon, Calum and Vallejo, Jorge L. Galvez and Kazemian, Fazeleh and Rendell, Alistair P. and Gordon, Mark S.},
  month = nov,
  year = {2022},
  note = {ISSN: 2167-4337},
  pages = {72--85}
}

@inproceedings{barca_rimp2_summit_sc21,
  address = {New York, NY, USA},
  series = {{SC} '21},
  title = {Enabling large-scale correlated electronic structure calculations: scaling the {RI}-{MP2} method on summit},
  isbn = {978-1-4503-8442-1},
  shorttitle = {Enabling large-scale correlated electronic structure calculations},
  url = {https://doi.org/10.1145/3458817.3476222},
  doi = {10.1145/3458817.3476222},
  urldate = {2021-11-01},
  booktitle = {Proceedings of the {International} {Conference} for {High} {Performance} {Computing}, {Networking}, {Storage} and {Analysis}},
  publisher = {Association for Computing Machinery},
  author = {Barca, Giuseppe M. J. and Vallejo, Jorge L. Galvez and Poole, David L. and Alkan, Melisa and Stocks, Ryan and Rendell, Alistair P. and Gordon, Mark S.},
  month = nov,
  year = {2021},
  pages = {1--15}
}

@inproceedings{barca_fock_build_summit_sc20,
  title = {Scaling the {Hartree}-{Fock} {Matrix} {Build} on {Summit}},
  doi = {10.1109/SC41405.2020.00085},
  booktitle = {{SC20}: {International} {Conference} for {High} {Performance} {Computing}, {Networking}, {Storage} and {Analysis}},
  author = {Barca, G. M. J. and Poole, D. L. and Vallejo, J. L. G. and Alkan, M. and Bertoni, C. and Rendell, A. P. and Gordon, Mark S.},
  month = nov,
  year = {2020},
  pages = {1--14}
}

RI methodologies (energies and gradients)¶

Stocks, R.; Palethorpe, E.; Barca, G. M. J. Multi-GPU RI-HF Energies and Analytic Gradients - toward High-Throughput Ab Initio Molecular Dynamics. J. Chem. Theory Comput. 2024, 20 (17), 7503-7515. https://doi.org/10.1021/acs.jctc.4c00877.
Stocks, R.; Palethorpe, E.; Barca, G. M. J. High-Performance Multi-GPU Analytic RI-MP2 Energy Gradients. J. Chem. Theory Comput. 2024, 20 (6), 2505-2519. https://doi.org/10.1021/acs.jctc.3c01424.

@article{stocks_rihf_2024,
  title = {Multi-{{GPU RI-HF}} {Energies} and {Analytic} {Gradients} --- toward {High}-{Throughput} {Ab} {Initio} {Molecular} {Dynamics}},
  volume = {20},
  issn = {1549-9618},
  url = {https://doi.org/10.1021/acs.jctc.4c00877},
  doi = {10.1021/acs.jctc.4c00877},
  urldate = {2025-06-16},
  journal = {Journal of Chemical Theory and Computation},
  author = {Stocks, Ryan and Palethorpe, Elise and Barca, Giuseppe M. J.},
  month = aug,
  year = {2024},
  number = {17},
  pages = {7503--7515},
  langid = {english}
}

@article{stocks_rimp2_grad_2024,
  title = {High-{Performance} {Multi}-{GPU} {Analytic} {RI}-{MP2} {Energy} {Gradients}},
  volume = {20},
  issn = {1549-9618, 1549-9626},
  url = {https://pubs.acs.org/doi/10.1021/acs.jctc.3c01424},
  doi = {10.1021/acs.jctc.3c01424},
  language = {en},
  number = {6},
  urldate = {2024-06-24},
  journal = {Journal of Chemical Theory and Computation},
  author = {Stocks, Ryan and Palethorpe, Elise and Barca, Giuseppe M. J.},
  month = mar,
  year = {2024},
  pages = {2505--2519}
}

KSDFT methodologies¶

Stocks, R.; Barca, G. M. J. Efficient Algorithms for GPU Accelerated Evaluation of the DFT Exchange-Correlation Functional. J. Chem. Theory Comput. 2025. https://doi.org/10.1021/acs.jctc.5c01229.

@article{stocks_dft_2025,
  title = {Efficient {Algorithms} for {{GPU}} {Accelerated} {Evaluation} of the {{DFT}} {Exchange}-{Correlation} {Functional}},
  issn = {1549-9618},
  url = {https://doi.org/10.1021/acs.jctc.5c01229},
  doi = {10.1021/acs.jctc.5c01229},
  urldate = {2025-10-16},
  journal = {Journal of Chemical Theory and Computation},
  publisher = {American Chemical Society},
  author = {Stocks, Ryan and Barca, Giuseppe M. J.},
  month = oct,
  year = {2025},
  langid = {english}
}

General SCF routines¶

Palethorpe, E.; Barca, G. M. J. High-Performance, High-Angular-Momentum J Engine on Graphics Processing Units. J. Chem. Theory Comput. 2025, 21 (19), 9388-9403. https://doi.org/10.1021/acs.jctc.5c00775.
Palethorpe, E.; Stocks, R.; Barca, G. M. J. Advanced Techniques for High-Performance Fock Matrix Construction on GPU Clusters. J. Chem. Theory Comput. 2024, 20 (23), 10424-10442. https://doi.org/10.1021/acs.jctc.4c00994.
Galvez Vallejo, J. L.; Barca, G. M. J.; Gordon, M. S. High-Performance GPU-Accelerated Evaluation of Electron Repulsion Integrals. Molecular Physics 2022, 0 (0), e2112987. https://doi.org/10.1080/00268976.2022.2112987.
Barca, G. M. J.; Alkan, M.; Galvez-Vallejo, J. L.; Poole, D. L.; Rendell, A. P.; Gordon, M. S. Faster Self-Consistent Field (SCF) Calculations on GPU Clusters. J. Chem. Theory Comput. 2021, 17 (12), 7486-7503. https://doi.org/10.1021/acs.jctc.1c00720.
Barca, G. M. J.; Galvez-Vallejo, J. L.; Poole, D. L.; Rendell, A. P.; Gordon, M. S. High-Performance, Graphics Processing Unit-Accelerated Fock Build Algorithm. J. Chem. Theory Comput. 2020, 16 (12), 7232-7238. https://doi.org/10.1021/acs.jctc.0c00768.

@article{palethorpe_j_engine_2025,
  title = {High-{Performance}, {High}-{Angular}-{Momentum} {{J}} {Engine} on {Graphics} {Processing} {Units}},
  volume = {21},
  issn = {1549-9618},
  url = {https://doi.org/10.1021/acs.jctc.5c00775},
  doi = {10.1021/acs.jctc.5c00775},
  urldate = {2025-10-16},
  journal = {Journal of Chemical Theory and Computation},
  publisher = {American Chemical Society},
  author = {Palethorpe, Elise and Barca, Giuseppe M. J.},
  month = oct,
  year = {2025},
  number = {19},
  pages = {9388--9403},
  abstract = {Efficient evaluation of electron repulsion integrals (ERIs) involving high-angular-momentum Gaussian basis functions is computationally challenging on graphical processing units (GPUs), as traditional recurrence-based integral algorithms generate numerous intermediates, causing significant register pressure and memory bottlenecks. In this Article, we present a high-performance, high-angular-momentum Coulomb-matrix (J) engine specifically optimized for GPU execution. Our approach introduces a GPU-optimized McMurchie-Davidson recurrence algorithm combined with a tailored integral batching scheme, designed specifically to jointly minimize intermediate storage requirements and redundant computation. By strategically partitioning high-angular-momentum ERIs classes into several carefully selected sub-batches, our approach transitions the associated integral evaluation kernels from memory-bound to compute-bound regimes, significantly enhancing computational throughput and reducing time to solution. Implemented in the Extreme-scale Electronic Structure System (EXESS), our algorithm achieves individual kernel speedups of up to 9\texttimes{} and improves overall J-matrix formation performance by up to 64\% across a variety of increasing-size chemical systems, including polyglycine chains, water clusters, and boron nitride crystals, when using the cc-pVQZ quadruple-{$\zeta$} basis set on an NVIDIA A100 GPU.},
  langid = {english}
}

@article{palethorpe_fock_build_2024,
  title = {Advanced {Techniques} for {High}-{Performance} {{Fock}} {Matrix} {Construction} on {{GPU}} {Clusters}},
  volume = {20},
  copyright = {https://doi.org/10.15223/policy-029},
  issn = {1549-9618},
  url = {https://doi.org/10.1021/acs.jctc.4c00994},
  doi = {10.1021/acs.jctc.4c00994},
  urldate = {2025-06-16},
  journal = {Journal of Chemical Theory and Computation},
  publisher = {American Chemical Society},
  author = {Palethorpe, Elise and Stocks, Ryan and Barca, Giuseppe M. J.},
  month = dec,
  year = {2024},
  number = {23},
  pages = {10424--10442},
  abstract = {This Article presents two optimized multi-GPU algorithms for Fock matrix construction, building on the work of Ufimtsev and Martinez [ J. Chem. Theory Comput. 2009, 5, 1004--1015] and Barca et al. [ J. Chem. Theory Comput. 2021, 17, 7486--7503]. The novel algorithms, opt-UM and opt-Brc, introduce significant enhancements, including improved integral screening, exploitation of sparsity and symmetry, a linear scaling exchange matrix assembly algorithm, and extended capabilities for Hartree--Fock calculations up to f-type angular momentum functions. Opt-Brc excels for smaller systems and for highly contracted triple-{$\zeta$} basis sets, while opt-UM is advantageous for large molecular systems. Performance benchmarks on NVIDIA A100 GPUs show that our algorithms in the EXtreme-scale Electronic Structure System (EXESS), when combined, outperform all current GPU and CPU Fock build implementations in TeraChem, QUICK, GPU4PySCF, LibIntX, ORCA, and Q-Chem. The implementations were benchmarked on linear and globular systems and average speed ups across three double-{$\zeta$} basis sets of 1.4\texttimes, 8.4\texttimes, and 9.4\texttimes{} were observed compared to TeraChem, QUICK, and GPU4PySCF respectively. An increased average speedup of 2.1\texttimes{} over TeraChem is observed when using four A100 GPUs. Strong scaling analysis reveals over 91\% parallel efficiency on four GPUs for opt-Brc, making it typically faster for multi-GPU execution. Single-compute-node comparisons with CPU-based software like ORCA and Q-Chem show speedups of up to 42\texttimes{} and 31\texttimes, respectively, enhancing power efficiency by up to 18\texttimes.},
  langid = {english}
}

@article{galvez_vallejo_integrals_2022,
  title = {High-performance {GPU}-accelerated evaluation of electron repulsion integrals},
  volume = {0},
  issn = {0026-8976},
  url = {https://doi.org/10.1080/00268976.2022.2112987},
  doi = {10.1080/00268976.2022.2112987},
  number = {0},
  urldate = {2022-10-03},
  journal = {Molecular Physics},
  author = {Galvez Vallejo, Jorge Luis and Barca, Giuseppe M.J. and Gordon, Mark S.},
  month = aug,
  year = {2022},
  note = {Publisher: Taylor \& Francis},
  pages = {e2112987}
}

@article{barca_scf_2021,
  title = {Faster {Self}-{Consistent} {Field} ({SCF}) {Calculations} on {GPU} {Clusters}},
  volume = {17},
  issn = {1549-9618},
  url = {https://doi.org/10.1021/acs.jctc.1c00720},
  doi = {10.1021/acs.jctc.1c00720},
  number = {12},
  urldate = {2024-06-24},
  journal = {Journal of Chemical Theory and Computation},
  author = {Barca, Giuseppe M. J. and Alkan, Melisa and Galvez-Vallejo, Jorge L. and Poole, David L. and Rendell, Alistair P. and Gordon, Mark S.},
  month = dec,
  year = {2021},
  note = {Publisher: American Chemical Society},
  pages = {7486--7503}
}

@article{barca_fock_build_2021,
  title = {High-{Performance}, {Graphics} {Processing} {Unit}-{Accelerated} {Fock} {Build} {Algorithm}},
  volume = {16},
  issn = {1549-9618},
  url = {https://doi.org/10.1021/acs.jctc.0c00768},
  doi = {10.1021/acs.jctc.0c00768},
  number = {12},
  urldate = {2021-03-15},
  journal = {Journal of Chemical Theory and Computation},
  author = {Barca, Giuseppe M. J. and Galvez-Vallejo, Jorge L. and Poole, David L. and Rendell, Alistair P. and Gordon, Mark S.},
  month = dec,
  year = {2020},
  note = {Publisher: American Chemical Society},
  pages = {7232--7238}
}

Commented citation block¶

The citation page includes a commented Q-Next citation block. It is reproduced here for completeness:

Seidl, C.; Barca, G. M. J. Q-Next: A Fast, Parallel, and Diagonalization-Free Alternative to Direct Inversion of the Iterative Subspace. J. Chem. Theory Comput. 2022, 18 (7), 4164-4176. https://doi.org/10.1021/acs.jctc.2c00073.

@article{q-next-2022,
  title = {Q-{Next}: {A} {Fast}, {Parallel}, and {Diagonalization}-{Free} {Alternative} to {Direct} {Inversion} of the {Iterative} {Subspace}},
  volume = {18},
  issn = {1549-9618},
  shorttitle = {Q-{Next}},
  url = {https://doi.org/10.1021/acs.jctc.2c00073},
  doi = {10.1021/acs.jctc.2c00073},
  number = {7},
  urldate = {2022-10-03},
  journal = {Journal of Chemical Theory and Computation},
  author = {Seidl, Christopher and Barca, Giuseppe M. J.},
  month = jul,
  year = {2022},
  note = {Publisher: American Chemical Society},
  pages = {4164--4176}
}