From 05f202a75e1910ab53eb045c1c46456bcc57afed Mon Sep 17 00:00:00 2001 From: Anthony Scemama Date: Fri, 15 Nov 2019 15:47:04 +0100 Subject: [PATCH] En marche --- Manuscript/ExPerspective.bib | 10 ++++++++++ Manuscript/ExPerspective.tex | 11 +++++++++-- 2 files changed, 19 insertions(+), 2 deletions(-) diff --git a/Manuscript/ExPerspective.bib b/Manuscript/ExPerspective.bib index f4bd1fd..e482277 100644 --- a/Manuscript/ExPerspective.bib +++ b/Manuscript/ExPerspective.bib @@ -1707,3 +1707,13 @@ publisher = {John Wiley {\&} Sons, Ltd}, doi = {10.1002/jcc.24713} } + +@article{Sce13b, + author = {Scemama, Anthony and Giner, Emmanuel}, + title = {{An efficient implementation of Slater-Condon rules}}, + journal = {arXiv}, + year = {2013}, + month = {Nov}, + eprint = {1311.6244}, + url = {https://arxiv.org/abs/1311.6244} +} diff --git a/Manuscript/ExPerspective.tex b/Manuscript/ExPerspective.tex index c8cb24f..58b6d7e 100644 --- a/Manuscript/ExPerspective.tex +++ b/Manuscript/ExPerspective.tex @@ -334,8 +334,15 @@ It would surely stimulate further theoretical developments in excited-state meth \alert{ To keep on with Moore's ``Law'' in the early 2000's, computer manufacturers had no other choice than to propose multi-core chips to avoid an explosion of the energy requirements. Doubling the number of floating-point operations per second (flops/s) by doubling the number of CPU cores only requires to double the required energy, while doubling the frequency multiplies the required energy by a factor close to 8. -This bifuraction in hardware design implied a \emph{Change of paradigm}\cite{Sut05} in the implementation and design of computational algorithms, which needed to express a large degree of parallelism to benefit from a significant acceleration. -Fifteen years later, the community has made the effort of redesigning the methods with parallel-friendly algorithms,\cite{Val10,Cle10,Gar17b,Pen16,Kri13,Sce13} but the next generation of supercomputers is going to generalize the presence of accelerators (graphical processing units, GPUs), leading to a new software crisis. +This bifuraction in hardware design implied a \emph{change of paradigm}\cite{Sut05} in the implementation and design of computational algorithms, which needed to express a large degree of parallelism to benefit from a significant acceleration. +Fifteen years later, the community has made a significant effort of redesigning the methods with parallel-friendly algorithms.\cite{Val10,Cle10,Gar17b,Pen16,Kri13,Sce13} +In particular, the change of paradigm to reach FCI accuracy with SCI methods came +from the use of determinant-driven algorithms which were considered for long as inefficient +with respect to integral-driven algorithms. +The first important element making these algorithms efficient is the introduction of new bit manipulation instructions (BMI) in the hardware of modern processors that enable an extremely fast evaluation of Slater-Condon rules\cite{Sce13b} for the direct calculation of +the Hamiltonian matrix elements over arbitrary determinants. +Then massive parallelism can be harnessed to perform the sparse matrix-vector multiplications required in Davidson's algorithm, and to compute the second-order perturbative correction with semi-stochatic algorithms.\cite{Gar17b,Sha17} +The next generation of supercomputers is going to generalize the presence of accelerators (graphical processing units, GPUs), leading to a new software crisis. Fortunately, some authors have already prepared this transition.\cite{Dep11,Kim18,Sny15,Ufi08,Kal17} }