Closed editorialbot closed 1 year ago
Hello humans, I'm @editorialbot, a robot that can help you with some common editorial tasks.
For a list of things I can do to help you, just type:
@editorialbot commands
For example, to regenerate the paper pdf after making changes in the paper's md or bib files, type:
@editorialbot generate pdf
Software report:
github.com/AlDanial/cloc v 1.88 T=0.11 s (581.4 files/s, 179243.0 lines/s)
-------------------------------------------------------------------------------
Language files blank comment code
-------------------------------------------------------------------------------
C++ 21 2259 2095 8546
Python 10 302 467 1426
C/C++ Header 14 552 582 1039
YAML 11 139 400 932
TeX 1 0 0 220
Markdown 2 25 0 66
make 2 14 12 37
Bourne Shell 1 0 1 1
-------------------------------------------------------------------------------
SUM: 62 3291 3557 12267
-------------------------------------------------------------------------------
gitinspector failed to run statistical information for the repository
Wordcount for paper.md
is 1915
Reference check summary (note 'MISSING' DOIs are suggestions that need verification):
OK DOIs
- None
MISSING DOIs
- 10.1115/1.4054554 may be a valid DOI for title: Thermophysical analysis of microconfined turbulent flow regimes at supercritical fluid conditions in heat transfer applications
- 10.1016/j.jcp.2019.01.007 may be a valid DOI for title: Numerically stable formulations of convective terms for turbulent compressible flows
- 10.1137/s003614450036757x may be a valid DOI for title: Strong stability-preserving high-order time discretization methods
- 10.1109/mcse.2013.47 may be a valid DOI for title: Survey of multiscale and multiphysics applications and communities
- 10.1016/j.cpc.2020.107262 may be a valid DOI for title: HTR solver: an open-source Exascale-oriented task-based multi-GPU high-order code for hypersonic aerothermodynamics
- 10.1016/j.pecs.2020.100877 may be a valid DOI for title: Transcritical diffuse-interface hydrodynamics of propellants in high-pressure combustors of chemical propulsion systems
- 10.1007/s00158-022-03293-y may be a valid DOI for title: Rapid aerodynamic shape optimization under uncertainty using a stochastic gradient approach
- 10.1063/1.869966 may be a valid DOI for title: Direct numerical simulation of turbulent channel flow up to Re_τ=590
- 10.1146/annurev.fluid.010908.165248 may be a valid DOI for title: Uncertainty quantification and polynomial chaos techniques in computational fluid dynamics
- 10.1016/j.jocs.2016.11.001 may be a valid DOI for title: OpenSBLI: a framework for the automated derivation and parallel execution of finite difference solvers on a range of computer architectures
- 10.1109/tim.2022.3165790 may be a valid DOI for title: Superheterodyne microwave system for the detection of bioparticles with coplanar electrodes on a microfluidic platform
- 10.1016/0021-9991(92)90227-p may be a valid DOI for title: Boundary conditions for direct simulations of compressible viscous flows
- 10.1016/j.cpc.2021.107906 may be a valid DOI for title: STREAmS: a high-fidelity accelerated solver for direct numerical simulation of compressible turbulent flows
INVALID DOIs
- None
:point_right::page_facing_up: Download article proof :page_facing_up: View article proof on GitHub :page_facing_up: :point_left:
Old list and needs to be ignored.
Review checklist for @thomasgillis
Conflict of interest
- [x] I confirm that I have read the JOSS conflict of interest (COI) policy and that: I have no COIs with reviewing this work or that any perceived COIs have been waived by JOSS for the purpose of this review.
Code of Conduct
- [x] I confirm that I read and will adhere to the JOSS code of conduct.
General checks
- [x] Repository: Is the source code for this software available at the https://gitlab.com/ProjectRHEA/flowsolverrhea?
- [x] License: Does the repository contain a plain-text LICENSE file with the contents of an OSI approved software license?
- [ ] Contribution and authorship: Has the submitting author (@lluisjofre) made major contributions to the software? Does the full list of paper authors seem appropriate and complete?
- [x] Substantial scholarly effort: Does this submission meet the scope eligibility described in the JOSS guidelines
Functionality
- [ ] Installation: Does installation proceed as outlined in the documentation?
- [ ] Functionality: Have the functional claims of the software been confirmed?
- [ ] Performance: If there are any performance claims of the software, have they been confirmed? (If there are no claims, please check off this item.)
Documentation
- [ ] A statement of need: Do the authors clearly state what problems the software is designed to solve and who the target audience is?
- [ ] Installation instructions: Is there a clearly-stated list of dependencies? Ideally these should be handled with an automated package management solution.
- [ ] Example usage: Do the authors include examples of how to use the software (ideally to solve real-world analysis problems).
- [ ] Functionality documentation: Is the core functionality of the software documented to a satisfactory level (e.g., API method documentation)?
- [ ] Automated tests: Are there automated tests or manual steps described so that the functionality of the software can be verified?
- [ ] Community guidelines: Are there clear guidelines for third parties wishing to 1) Contribute to the software 2) Report issues or problems with the software 3) Seek support
Software paper
- [ ] Summary: Has a clear description of the high-level functionality and purpose of the software for a diverse, non-specialist audience been provided?
- [ ] A statement of need: Does the paper have a section titled 'Statement of need' that clearly states what problems the software is designed to solve, who the target audience is, and its relation to other work?
- [ ] State of the field: Do the authors describe how this software compares to other commonly-used packages?
- [ ] Quality of writing: Is the paper well written (i.e., it does not require editing for structure, language, or writing quality)?
- [ ] References: Is the list of references complete, and is everything cited appropriately that should be cited (e.g., papers, datasets, software)? Do references in the text use the proper citation syntax?
Thanks for your work in the software @lluisjofre, here is a list of my comments. I don't think I have access to your issues, so couldn't open a new one on the target repo :-)
The paper is 1900 words while the limit is at 1000, maybe you will want to reduce it. There are plenty of non-relevant details that could go away and you might want to tighten your english a bit more.
I would definitely rewrite your sections summary
, statement of the need
, etc. to make them more explicit about what you do and others do or don't.
I also have specific questions:
N
and Re
should either be detailed or refer to a citation (and I have N ~ Re^3
in mind).using namespace std;
in headers or enforcing a MPI_Barrier
before stopping a timer.:point_right::page_facing_up: Download article proof :page_facing_up: View article proof on GitHub :page_facing_up: :point_left:
Some preliminary comments on the code before I get it installed.
I will continue my review once these items are addressed.
@lluisjofre please have a look into the comments above.
Dear @diehlpk,
Thanks for organizing the review. We have started making modifications to the paper and code following the indications from the reviewers. How much time do we have to make the modifications?
Thanks for your time and attention.
Best, Lluis
Dear @diehlpk,
Thanks for organizing the review. We have started making modifications to the paper and code following the indications from the reviewers. How much time do we have to make the modifications?
Thanks for your time and attention.
Best, Lluis
@lluisjofre you are welcome. I do not have a strict schedule yet. However, if you could address all the issues within 6 weeks would be good. I would appreciate if you report any progress here, so the reviewers could look at them.
@lluisjofre just checking on the progress you made?
Dear @diehlpk,
We have completed answering the comments/questions raised by the 2 reviewers. Responses are available in the PDF file attached to this message.
Thanks for your time and attention.
Best, Lluis response_to_reviewers_4637.pdf
Hi @ctdegroot, @thomasgillis could you please have a look at the comments above?
Reminder set for @ctdegroot in 2 weeks
Reminder set for @thomasgillis in 2 weeks
Hi @ctdegroot, @thomasgillis could you please have a look at the comments above?
Hi @ctdegroot, @thomasgillis could you please have a look at the comments above?
Hi, thanks for the heads-up. I will look at this over the coming week
Thanks, I will look at it in the next week as well.
Hi @ctdegroot, @thomasgillis could you please have a look at the comments above?
Hi @ctdegroot, @thomasgillis could you please have a look at the comments above?
Hi @ctdegroot, @thomasgillis could you please have a look at the comments above?
I am working on this but the installation instructions are still very much lacking. It doesn't seem like this comment was addressed.
@editorialbot generate pdf
:point_right::page_facing_up: Download article proof :page_facing_up: View article proof on GitHub :page_facing_up: :point_left:
Thanks for the updated version of the software as well as the work put in it. Here is a list of the additional comments I have. Let me know if you have further questions
general comments
is your code 2D or 3D? Please mention it. The distributed computing need on a 2D code is difficult to support with the architectures nowadays though.
I understand timing in parallel with MPI
but it seems that there is still an issue there. From the code below I still don't understand the need of MPI_Barrier()
. If you remove it you would get an exact timing and the code would work the same way (production or not) as you have the MPI_Allreduce
. There is no need for this Barrier
if I understood your code correctly.
// https://gitlab.com/ProjectRHEA/flowsolverrhea/-/blob/master/src/ParallelTimer.cpp#L34
// function stop()
MPI_Barrier(MPI_COMM_WORLD);
time_array[str][1] = getTime_cpu();
time_array[str][2] = time_array[str][1] - time_array[str][0];
// [...]
ltime = time_array[str][2];
MPI_Allreduce(<ime,&maxtime,1,MPI_DOUBLE,MPI_MAX,MPI_COMM_WORLD);
MPI_Allreduce(<ime,&mintime,1,MPI_DOUBLE,MPI_MIN,MPI_COMM_WORLD);
MPI_Allreduce(<ime,&avgtime,1,MPI_DOUBLE,MPI_SUM,MPI_COMM_WORLD);
Fig1: this figure is still very puzzling to me. I don't fully understand what you did: which testcase, how many unknowns per rank, which time-integration, etc. Additionally:
a traditional way of presenting results is to begin with "times-to-solution" (and for you, energy to solution), if you replace your figure by that, then the ratio makes sense. There is no need to have a figure for a ratio, you can simply put it in the text. Also how do you get the energy information? Was it on 1 node?
on the right: you did a weak scalability so you should mention it before, in the first part of the paragraph (where you mention the strong scalability). Usually the weak scalability metric is referred to as the "efficiency" as the number is between 0 and 1 and not the "speedup".
I disagree to say that your CPU and CPU+GPU code scale the same. If you compute the parallel percentage of the software from the scalability study I guess you will find a factor 2 there (or close). Also you mention 90%
in the text but we are unable to verify that claim with the graduation of the figure.
the CI/CD you have added seems very short to me. It looks like you only check the solution on a problem in 1D? I cannot really check that box, sorry. Maybe add some details.
more subjective comments
I understand your strategy to produce reproducible science. However I am not sure that the fact of adding a test
folder with some testcase justifies that adjective in the title. To me the results (of a paper, presentation, etc) can be reproducible (and should be!), but I am not sure what it means to have a "reproducible software".
To reproduce results, you need the source code but also the same infrastructure etc. For example one could argue that a CI/CD suite increases reproducibility while the test
folder does not. Changing the title would also change the acronym which is maybe not a suitable option at this point.
"is named RHEA, which stands for open-source Reproducible Hybrid-architecture flow solver Engineered for Academia, and is inspired by the Titaness great Mother of the ancient Greek Gods, and goddess of female fertility, motherhood and generation. Her name was RHEA and means flow and ease, representing the eternal flow of time and generations with ease." I understand that the choice of a name for a software is personal, but I don't think that this level of details is relevant here. Also the information stated here repeats the title.
@lluisjofre can you please have a look?
@lluisjofre can you please have a look?
Dear @diehlpk,
We have completed answering the comments/questions raised by the 2 reviewers. Responses are available in the PDF files attached to this message. The git repository has been correspondingly updated.
Thanks for your time and attention.
Best, Lluis
@ctdegroot can you please have a look?
@thomasgillis can you please have a look?
thanks for the update (and the time spent on it!). I still have one comment on the scalability claim, the rest looks good to me.
As previously explained I disagree on the assertion "the solver presents similar speedups in terms of strong scalability when running on CPUs and CPUs+GPUs".
Scalability is independent from the speed as it's a ratio of time-to-solution. instead scalability comes from the percentage of your program that can be run in parallel.
From the figures, we can roughly estimate that at a ratio of 32
the speedup is
2^(4.25) = 19
for the CPU+GPU -> 97.8% of parallelization -> serial % = 2.2%2^(4.75) = 27
for the CPU only -> 99.4% of parallelization -> serial % = 0.6%
There is still a factor of 3-4 (roughly done, I agree) between the two implementations if my calculations are correct.
I would therefore not claim that the scalability is similar but rather say that the scalability is above xx%
/xx
speedup in both cases and that the CPU has a higher parallelization percentage (and therefore scalability) than the GPU+CPU.
it would be interesting to explain the why of this but I guess it's outside of the scope of the present paper.Dear @thomasgillis and @diehlpk,
We agree with your comment @thomasgillis. We have subsequently modified the manuscript as: "Second, as shown in Figure 1, on BSC for a fixed-problem size and noting that on CPUs+GPUs the solver is roughly faster, the solver presents strong scalability speedups above 80% and 60%, respectively, when running on CPUs and CPUs+GPUs up to 32 nodes (640 cores and 128 GPUs)." The git repository has been correspondingly updated.
Thanks for your time and attention.
Best, Lluis
@thomasgillis does this satisfy you?
@thomasgillis does this satisfy you? yes, thank you
@thomasgillis Can you please have a look at your check list. There are some unchecked boxes.
@thomasgillis Can you please have a look at your check list. There are some unchecked boxes.
@editorialbot generate pdf
@editorialbot check references
:point_right::page_facing_up: Download article proof :page_facing_up: View article proof on GitHub :page_facing_up: :point_left:
@editorialbot check references
@ctdegroot How is your review going?
Reference check summary (note 'MISSING' DOIs are suggestions that need verification):
OK DOIs
- None
MISSING DOIs
- 10.1115/1.4054554 may be a valid DOI for title: Thermophysical analysis of microconfined turbulent flow regimes at supercritical fluid conditions in heat transfer applications
- 10.1063/1.3676783 may be a valid DOI for title: Grid-point requirements for large eddy simulation: Chapman’s estimates revisited
- 10.1016/j.jcp.2019.01.007 may be a valid DOI for title: Numerically stable formulations of convective terms for turbulent compressible flows
- 10.1137/s003614450036757x may be a valid DOI for title: Strong stability-preserving high-order time discretization methods
- 10.1109/mcse.2013.47 may be a valid DOI for title: Survey of multiscale and multiphysics applications and communities
- 10.1016/j.cpc.2020.107262 may be a valid DOI for title: HTR solver: an open-source Exascale-oriented task-based multi-GPU high-order code for hypersonic aerothermodynamics
- 10.1016/j.pecs.2020.100877 may be a valid DOI for title: Transcritical diffuse-interface hydrodynamics of propellants in high-pressure combustors of chemical propulsion systems
- 10.1007/s00158-022-03293-y may be a valid DOI for title: Rapid aerodynamic shape optimization under uncertainty using a stochastic gradient approach
- 10.1063/1.869966 may be a valid DOI for title: Direct numerical simulation of turbulent channel flow up to Re_τ=590
- 10.1146/annurev.fluid.010908.165248 may be a valid DOI for title: Uncertainty quantification and polynomial chaos techniques in computational fluid dynamics
- 10.1016/j.jocs.2016.11.001 may be a valid DOI for title: OpenSBLI: a framework for the automated derivation and parallel execution of finite difference solvers on a range of computer architectures
- 10.1109/tim.2022.3165790 may be a valid DOI for title: Superheterodyne microwave system for the detection of bioparticles with coplanar electrodes on a microfluidic platform
- 10.1016/0021-9991(92)90227-p may be a valid DOI for title: Boundary conditions for direct simulations of compressible viscous flows
- 10.1016/j.cpc.2021.107906 may be a valid DOI for title: STREAmS: a high-fidelity accelerated solver for direct numerical simulation of compressible turbulent flows
- Errored finding suggestions for "Riemann Solvers and Numerical Methods for Fluid Dy...", please try later
INVALID DOIs
- None
Reference check summary (note 'MISSING' DOIs are suggestions that need verification):
OK DOIs
- None
MISSING DOIs
- 10.1115/1.4054554 may be a valid DOI for title: Thermophysical analysis of microconfined turbulent flow regimes at supercritical fluid conditions in heat transfer applications
- 10.1063/1.3676783 may be a valid DOI for title: Grid-point requirements for large eddy simulation: Chapman’s estimates revisited
- 10.1016/j.jcp.2019.01.007 may be a valid DOI for title: Numerically stable formulations of convective terms for turbulent compressible flows
- 10.1137/s003614450036757x may be a valid DOI for title: Strong stability-preserving high-order time discretization methods
- 10.1109/mcse.2013.47 may be a valid DOI for title: Survey of multiscale and multiphysics applications and communities
- Errored finding suggestions for "HTR solver: an open-source Exascale-oriented task-...", please try later
- 10.1016/j.pecs.2020.100877 may be a valid DOI for title: Transcritical diffuse-interface hydrodynamics of propellants in high-pressure combustors of chemical propulsion systems
- 10.1007/s00158-022-03293-y may be a valid DOI for title: Rapid aerodynamic shape optimization under uncertainty using a stochastic gradient approach
- 10.1063/1.869966 may be a valid DOI for title: Direct numerical simulation of turbulent channel flow up to Re_τ=590
- 10.1146/annurev.fluid.010908.165248 may be a valid DOI for title: Uncertainty quantification and polynomial chaos techniques in computational fluid dynamics
- 10.1016/j.jocs.2016.11.001 may be a valid DOI for title: OpenSBLI: a framework for the automated derivation and parallel execution of finite difference solvers on a range of computer architectures
- 10.1109/tim.2022.3165790 may be a valid DOI for title: Superheterodyne microwave system for the detection of bioparticles with coplanar electrodes on a microfluidic platform
- 10.1016/0021-9991(92)90227-p may be a valid DOI for title: Boundary conditions for direct simulations of compressible viscous flows
- 10.1016/j.cpc.2021.107906 may be a valid DOI for title: STREAmS: a high-fidelity accelerated solver for direct numerical simulation of compressible turbulent flows
INVALID DOIs
- None
@lluisjofre please add all the missing DOIs to the paper.
@ctdegroot How is your review going?
Submitting author: !--author-handle-->@lluisjofre<!--end-author-handle-- (Lluis Jofre) Repository: https://gitlab.com/ProjectRHEA/flowsolverrhea Branch with paper.md (empty if default branch): master Version: v1.0.0 Editor: !--editor-->@diehlpk<!--end-editor-- Reviewers: @ctdegroot, @thomasgillis Archive: 10.5281/zenodo.7525886
Status
Status badge code:
Reviewers and authors:
Please avoid lengthy details of difficulties in the review thread. Instead, please create a new issue in the target repository and link to those issues (especially acceptance-blockers) by leaving comments in the review thread below. (For completists: if the target issue tracker is also on GitHub, linking the review thread in the issue or vice versa will create corresponding breadcrumb trails in the link target.)
Reviewer instructions & questions
@ctdegroot & @thomasgillis, your review will be checklist based. Each of you will have a separate checklist that you should update when carrying out your review. First of all you need to run this command in a separate comment to create the checklist:
The reviewer guidelines are available here: https://joss.readthedocs.io/en/latest/reviewer_guidelines.html. Any questions/concerns please let @diehlpk know.
✨ Please start on your review when you are able, and be sure to complete your review in the next six weeks, at the very latest ✨
Checklists
📝 Checklist for @ctdegroot
📝 Checklist for @thomasgillis