pith. sign in

arxiv: 1907.01199 · v1 · pith:TAAI22OKnew · submitted 2019-07-02 · 💻 cs.DC

Asynchronous Communications Library for the Parallel-in-Time Solution of Black-Scholes Equation

Qinmeng Zou , Guillaume Gbikpi-Benissan , Frederic Magoules This is my paper

Pith reviewed 2026-05-25 11:00 UTC · model grok-4.3

classification 💻 cs.DC
keywords asynchronous iterative schemesparareal algorithmsBlack-Scholes equationparallel-in-time methodsresource managementconvergence detectionnumerical computations
0
0 comments X

The pith

An asynchronous communication library enables elegant handling of resource management and convergence detection for asynchronous parareal algorithms on the Black-Scholes equation.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper shows that an asynchronous communication library makes it possible to implement both classical and asynchronous parareal algorithms for the time-dependent Black-Scholes equation. The library addresses the usual difficulties with resource management and convergence detection in asynchronous iterative schemes. Experiments confirm that the resulting implementation is available and efficient. A sympathetic reader would care because asynchronous schemes can deliver high efficiency on parallel systems, yet practical issues with resources and stopping criteria often block their use. If correct, the work makes such methods more practical for solving time-dependent financial models.

Core claim

The paper establishes that the asynchronous communication kernel library for iterative algorithms can be used to implement asynchronous parareal algorithms for the time-dependent Black-Scholes equation by elegantly tackling the problems of resource management and convergence detection, with experiments proving the availability and efficiency of the application.

What carries the argument

The asynchronous communication kernel library for iterative algorithms, which supplies the mechanisms for communication, resource management, and convergence detection in parareal methods.

If this is right

  • Both classical and asynchronous parareal algorithms become easier to code for time-dependent problems.
  • The standard difficulties of resource management and convergence detection are resolved through the library.
  • Experiments confirm availability and efficiency for the Black-Scholes equation.
  • Asynchronous iterative schemes can achieve higher efficiency once these implementation barriers are lowered.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same library approach could be tested on other time-dependent partial differential equations in finance or physics.
  • Performance on very large parallel systems might reveal additional scaling advantages.
  • The method could be combined with different coarse and fine solvers to improve overall accuracy or speed.

Load-bearing premise

That the asynchronous communication library can elegantly handle resource management and convergence detection when the asynchronous parareal method is applied to the time-dependent Black-Scholes equation.

What would settle it

An implementation or experiment in which resource management and convergence detection still require substantial custom code beyond the library would show the claim of elegant handling to be incorrect.

Figures

Figures reproduced from arXiv: 1907.01199 by Frederic Magoules, Guillaume Gbikpi-Benissan, Qinmeng Zou.

Figure 1
Figure 1. Figure 1: Time domain of the parareal scheme [5] is a multi-threaded library aiming at the execution of asynchronous iterative algorithms based on Java, followed by a centralized volatility tolerant extension named JaceV [4]. Re￾cently, they have developed some P2P and decentralized versions to enlarge the applicable scope [3, 7]. Additionally, CRAC [9] is another library designed to build the asynchronous applicati… view at source ↗
read the original abstract

The advent of asynchronous iterative scheme gives high efficiency to numerical computations. However, it is generally difficult to handle the problems of resource management and convergence detection. This paper uses JACK2, an asynchronous communication kernel library for iterative algorithms, to implement both classical and asynchronous parareal algorithms, especially the latter. We illustrate the measures whereby one can tackle the problems above elegantly for the time-dependent case. Finally, experiments are presented to prove the availability and efficiency of such application.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript describes the use of the JACK2 asynchronous communication kernel library to implement both classical and asynchronous parareal algorithms for solving the time-dependent Black-Scholes equation. It focuses on elegantly addressing resource management and convergence detection issues in asynchronous iterative schemes and claims that experiments demonstrate the availability and efficiency of the approach.

Significance. If the implementation details and experimental results hold, the work offers a practical software contribution to parallel-in-time methods by showing how an asynchronous library can handle key challenges in parareal algorithms for time-dependent PDEs in finance. It is framed as an existence claim via implementation rather than a formal derivation or parameter-free result.

major comments (2)
  1. [Abstract] Abstract: the assertion that 'experiments are presented to prove the availability and efficiency of such application' is not accompanied by any quantitative data, speedup factors, convergence rates, error analysis, or comparison to classical parareal; this is load-bearing for the central claim that JACK2 enables efficient handling of the problems.
  2. [Introduction/Method description] The weakest assumption (that JACK2 elegantly handles resource management and convergence detection for asynchronous parareal on the time-dependent Black-Scholes PDE) is stated but not demonstrated with concrete code snippets, pseudocode, or measured overheads in the provided text.
minor comments (2)
  1. [Title and Abstract] Clarify in the title and abstract whether the Black-Scholes model is the standard European option PDE or a time-dependent variant with explicit time dependence in coefficients.
  2. [Experiments] The manuscript would benefit from a table or figure summarizing the experimental setup (grid sizes, number of processors, iteration counts) to make the efficiency claims reproducible.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed review and constructive feedback on our manuscript. We address the major comments point by point below, proposing revisions to improve clarity and support for our claims.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the assertion that 'experiments are presented to prove the availability and efficiency of such application' is not accompanied by any quantitative data, speedup factors, convergence rates, error analysis, or comparison to classical parareal; this is load-bearing for the central claim that JACK2 enables efficient handling of the problems.

    Authors: Abstracts are designed to be brief summaries, and the detailed quantitative results, including speedup factors, convergence rates, and comparisons, are presented in the experimental section of the manuscript. However, to better highlight the central claim, we will revise the abstract to include a concise mention of key quantitative outcomes from the experiments. revision: yes

  2. Referee: [Introduction/Method description] The weakest assumption (that JACK2 elegantly handles resource management and convergence detection for asynchronous parareal on the time-dependent Black-Scholes PDE) is stated but not demonstrated with concrete code snippets, pseudocode, or measured overheads in the provided text.

    Authors: The manuscript provides a description of how JACK2 is used to address resource management and convergence detection. To make the demonstration more concrete as suggested, we will add pseudocode examples and report on measured overheads in the revised manuscript. revision: yes

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper describes a software implementation of classical and asynchronous parareal algorithms using the JACK2 library for the time-dependent Black-Scholes PDE, with experiments to demonstrate availability and efficiency. There is no derivation chain, no fitted parameters presented as predictions, no self-referential equations, and no load-bearing self-citations of uniqueness theorems. The central claims rest on implementation existence and empirical results rather than any reduction of outputs to inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Based solely on the abstract, no free parameters, axioms, or invented entities are identifiable or stated.

pith-pipeline@v0.9.0 · 5603 in / 1007 out tokens · 27044 ms · 2026-05-25T11:00:06.482548+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

18 extracted references · 18 canonical work pages

  1. [1]

    Fastsparsematrix-vectormultiplicationongraphics processingunitforfiniteelementanalysis

    A.-K.C.AhamedandF.Magoulès. Fastsparsematrix-vectormultiplicationongraphics processingunitforfiniteelementanalysis. In 14th IEEE Int. Conf. on High Performance Computing and Communications, Liverpool, UK, June 25-27, 2012. IEEE, 2012

    work page 2012

  2. [2]

    A.-K. C. Ahamed and F. Magoulès. Iterative methods for sparse linear systems on graphics processing unit. In 14th IEEE Int. Conf. on High Performance Computing and Communications, Liverpool, UK, June 25-27, 2012. IEEE, 2012

    work page 2012

  3. [3]

    J. M. Bahi, R. Couturier, and P. Vuillemin. JaceP2P: an environment for asynchronous computations on peer-to-peer networks. InProc. of 2006 IEEE Int. Conf. on Cluster Computing, pages 1–10, 2006

    work page 2006

  4. [4]

    J. M. Bahi, R. Couturier, and P. Vuillemin. JaceV: A programming and execution environment for asynchronous iterative computations on volatile nodes. InProc. of 7th Int. Conf. VECPAR, Rio de Janeiro, Brazil, June 10-13, 2006, pages 79–92. Springer, 2007

    work page 2006

  5. [5]

    J. M. Bahi, S. Domas, and K. Mazouzi. Jace: a Java environment for distributed asynchronous iterative computations. InProc. of 12th Euromicro Conf. on Para. Dist. and Network-Based Proc., 2004, pages 350–357, 2004

    work page 2004

  6. [6]

    parareal

    G. Bal and Y. Maday. A “parareal” time discretization for non-linear pde’s with applica- tion to the pricing of an american put. In L. F. Pavarino and A. Toselli, editors,Recent Developments in Domain Decomposition Methods, pages 189–202. Springer, 2002

    work page 2002

  7. [7]

    Charr, R

    J.-C. Charr, R. Couturier, and D. Laiymani. JACEP2P-V2: A fully decentralized and fault tolerant environment for executing parallel iterative asynchronous applications on volatile distributed architectures. In Proc. of 4th Int. Conf. GPC 2009, Geneva, Switzerland, May 4-8, 2009, pages 446–458. Springer, 2009

    work page 2009

  8. [8]

    Chazan and W

    D. Chazan and W. Miranker. Chaotic relaxation.Linear Algebra and its Applications, 2(2):199–222, 1969

    work page 1969

  9. [9]

    Couturier and S

    R. Couturier and S. Domas. CRAC: a grid environment to solve scientific applica- tions with asynchronous iterative algorithms. InProc. of 2007 IEEE Int. Parallel and Distributed Processing Symposium, pages 1–8, 2007

    work page 2007

  10. [10]

    pararéel

    J.-L. Lions, Y. Maday, and G. Turinici. Résolution d’EDP par un schéma en temps “pararéel”. CRAS. Série I, Mathématique, 332(7):661–668, 2001

    work page 2001

  11. [11]

    Magoulès and A.-K

    F. Magoulès and A.-K. C. Ahamed. Alinea: An advanced linear algebra library for massivelyparallelcomputationsongraphicsprocessingunits. The International Journal of High Performance Computing Applications, 29(3):284–310, 2015

    work page 2015

  12. [12]

    Magoulès, A.-K

    F. Magoulès, A.-K. C. Ahamed, and R. Putanowicz. Auto-tuned Krylov methods on cluster of graphics processing unit. International Journal of Computer Mathematics, 92(6):1222–1250, 2015

    work page 2015

  13. [13]

    Magoulès, A.-K

    F. Magoulès, A.-K. C. Ahamed, and R. Putanowicz. Fast iterative solvers for large compressed-sparse row linear systems on graphics processing unit.Pollack Periodica, 10(1):3–18, 2015

    work page 2015

  14. [14]

    Magoulès and G

    F. Magoulès and G. Gbikpi-Benissan. JACK: an asynchronous communication kernel library for iterative algorithms.The Journal of Supercomputing, 73(8):3468–3487, 2017

    work page 2017

  15. [15]

    Magoulès, D

    F. Magoulès, D. B. Szyld, and C. Venet. Asynchronous optimized Schwarz methods with and without overlap.Numerische Mathematik, 137:199–227, 2017. 7

    work page 2017

  16. [16]

    Magoulès and C

    F. Magoulès and C. Venet. Asynchronous iterative sub-structuring methods.Mathe- matics and Computers in Simulation, (in press)

    work page

  17. [17]

    W. L. Miranker and W. Liniger. Parallel methods for the numerical integration of ordinary differential equations.Mathematics of Computation, 21:303–320, 1967

    work page 1967

  18. [18]

    Nievergelt

    J. Nievergelt. Parallel methods for integrating ordinary differential equations.Commun. ACM, 7(12):731–733, 1964. 8

    work page 1964