pith. sign in

arxiv: 2605.02217 · v1 · submitted 2026-05-04 · 💻 cs.DC

Leveraging Teaching on Demand: Approaching HPC to Undergrads

S. Catal\'an , R. Carratal\'a-S\'aez , S. Iserte This is my paper

Pith reviewed 2026-05-08 18:33 UTC · model grok-4.3

classification 💻 cs.DC
keywords HPC educationRaspberry Pi clusterundergraduate teachinghands-on learningteaching on demandcluster managementsupercomputing
0
0 comments X

The pith

A Raspberry Pi cluster course with teaching on demand equips undergraduates with practical HPC skills for their careers.

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

The paper presents a non-mandatory course in which engineering students build and run their own Raspberry Pi clusters to learn the fundamentals of high-performance computing. Topics include hardware, networking, software tools, performance evaluation, and cluster management, with an added teaching-on-demand feature that lets students select extra material based on their own interests. The authors share complete instructions for reproducing the course and evaluate its success by measuring gains in student knowledge and self-reported readiness to apply the skills professionally. A reader would care because HPC expertise is increasingly required in industry while standard degree programs often omit it entirely.

Core claim

Leveraging the low cost and versatility of Raspberry Pi devices together with student-driven topic selection allows a compact, hands-on course to deliver core supercomputing knowledge and leave participants confident they can use those abilities in their mid-term professional careers.

What carries the argument

The teaching-on-demand component, which lets attendees choose fields to explore according to their interests and pairs it with the concrete task of assembling and operating a Raspberry Pi cluster.

If this is right

  • Students receive practical exposure to hardware setup, networking, software tools, performance measurement, and cluster management.
  • The methodology meets its stated objectives of raising HPC knowledge and career readiness.
  • Other instructors can replicate the entire course using the detailed materials the authors provide.
  • Direct, build-your-own experience increases student engagement compared with lecture-only formats.

Where Pith is reading between the lines

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

  • The same low-cost hardware approach could help other universities add specialized computing topics without needing expensive equipment.
  • Pairing the course with access to a real institutional cluster afterward might strengthen skill retention.
  • The student-choice element could be adapted to teach other hands-on subjects where curricula currently lag industry demand.

Load-bearing premise

That motivation and confidence gained from building and operating a small, affordable cluster will produce lasting, transferable skills that students can apply later in professional settings that use large-scale systems.

What would settle it

A follow-up survey or interview of former students several years after the course to determine whether they have actually worked with or managed real high-performance computing resources in jobs or graduate studies.

Figures

Figures reproduced from arXiv: 2605.02217 by R. Carratal\'a-S\'aez, S. Catal\'an, S. Iserte.

Figure 1
Figure 1. Figure 1: Course curriculum overview. 4.1.4. Design of the course A crucial aspect when creating a course is the number of available resources in terms of material, budget, and people. In this course, we propose using a low￾cost cluster to guarantee a hands-on experience to the attendees, while keeping a reasonable budget. The required hardware to assemble each of the clusters is described in view at source ↗
Figure 2
Figure 2. Figure 2: A Raspberry Pi cluster assembled during the course. Note that the 3D-printed view at source ↗
Figure 3
Figure 3. Figure 3: Temperature during a LAMMPS execution with different frequencies. view at source ↗
Figure 4
Figure 4. Figure 4: Answers of ISQ2 and FSQ2. From our teaching experience through the past years, we observed a lack of HPC knowledge among the students. This was an opinion before starting the course, but now we have evidence that exposes that it was true, taking into account what can be observed in view at source ↗
Figure 5
Figure 5. Figure 5: Answers of ISQ1 and FSQ1. HPC interest has increased among attendees. Regarding the HPC interest and awareness, view at source ↗
Figure 6
Figure 6. Figure 6: Answers of ISQ3 and FSQ3. Overall HPC knowledge has increased after the course view at source ↗
Figure 9
Figure 9. Figure 9: Answers of FSQ7 and FSQ8. Note that only second edition answers are provided, view at source ↗
Figure 11
Figure 11. Figure 11: reports the questionnaire answers, showing in orange the influence over posterior training selection by the attendees, and in green, the impact in their current studies and/or the professional environment; the light tonalities refer to the first edition and darker tones to the second one. am not studying CS want to continue in STEM related fields not sure how don't believe it has direct impact in the soci… view at source ↗
read the original abstract

High Performance Computing (HPC) is a highly demanded discipline in companies and institutions. However, as students and also afterwards as professors, we observed a lack of HPC related content in the engineering degrees at our university, including Computer Science. Thus, we designed and offered the engineering students a non-mandatory course entitled ``Build you own Raspberry Pi cluster employing Raspberry Pi'' to provide the students with HPC skills. With this course, we covered the basics of supercomputing (hardware, networking, software tools, performance evaluation, cluster management, etc.). This was possible thanks to leveraging the flexibility and versatility of Raspberry Pi devices, and the students' motivation that arose from the hands-on experience. Moreover, the course included a ``Teaching on demand'' component to let the attendees choose a field to explore, based on their own interests. In this paper, we offer all the details to let anyone fully reproduce the course. Besides, we analyze and evaluate the methodology that let us fulfill our objectives: increase the students' HPC skills and knowledge in such a way that they feel capable of utilizing it in their mid-term professional career.

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

1 major / 3 minor

Summary. The manuscript describes the design and delivery of a non-mandatory undergraduate engineering course titled 'Build your own Raspberry Pi cluster' that introduces HPC fundamentals (hardware, networking, software tools, performance evaluation, cluster management) via hands-on Raspberry Pi clusters, augmented by a student-driven 'Teaching on Demand' component. The authors supply detailed, reproducible course materials and evaluate the approach through accounts of student motivation and post-course self-reported readiness, claiming that the methodology successfully increases HPC skills for mid-term professional use.

Significance. If the hands-on Raspberry Pi methodology demonstrably produces transferable HPC skills, the work supplies a low-cost, fully documented template for addressing gaps in undergraduate HPC education. The reproducibility of the course outline and the student-choice element are practical strengths that could aid adoption by other instructors. The current evaluation, however, limits the strength of claims about durable professional applicability.

major comments (1)
  1. [Evaluation section] Evaluation section (and abstract): The claim that the course 'let us fulfill our objectives: increase the students' HPC skills and knowledge in such a way that they feel capable of utilizing it in their mid-term professional career' is supported only by descriptive accounts of motivation and post-course self-perception. No pre/post quantitative skill metrics, objective assessments, control groups, retention checks, or longitudinal follow-up on real-world application are reported, leaving the central claim of transferable professional readiness only partially substantiated.
minor comments (3)
  1. [Abstract] Abstract: 'Build you own' contains a typographical error and should read 'Build your own'.
  2. [Abstract] Abstract and course-description sections: The phrase 'etc.' and the list of covered topics are vague; an explicit enumerated list or table of topics, tools, and activities would strengthen reproducibility.
  3. [Course design] Throughout: Consider adding a concise table summarizing weekly schedule, hardware requirements, and assessment methods to improve clarity for readers wishing to replicate the course.

Simulated Author's Rebuttal

1 responses · 1 unresolved

We thank the referee for their constructive feedback on the evaluation of our course methodology. We address the major comment below and will make revisions to the manuscript to better align our claims with the available evidence.

read point-by-point responses

  1. Referee: [Evaluation section] Evaluation section (and abstract): The claim that the course 'let us fulfill our objectives: increase the students' HPC skills and knowledge in such a way that they feel capable of utilizing it in their mid-term professional career' is supported only by descriptive accounts of motivation and post-course self-perception. No pre/post quantitative skill metrics, objective assessments, control groups, retention checks, or longitudinal follow-up on real-world application are reported, leaving the central claim of transferable professional readiness only partially substantiated.

    Authors: We agree with the referee that our evaluation relies on descriptive accounts of student motivation and post-course self-perception rather than quantitative pre/post metrics or longitudinal studies. This is a limitation of the work, as the course was designed primarily as an educational intervention with a focus on providing reproducible materials and a flexible 'Teaching on Demand' approach. We will revise the abstract and the Evaluation section to moderate the claims, stating that the course successfully engaged students and led to self-reported increases in confidence regarding HPC skills for potential professional use, while noting the absence of objective assessments as a direction for future work. We will expand the description of the evaluation methodology to include more specifics on student feedback collection. We believe this addresses the concern while preserving the practical value of the documented course template. revision: yes

standing simulated objections not resolved
  • We are unable to provide pre/post quantitative skill metrics, objective assessments, control groups, retention checks, or longitudinal follow-up on real-world application, as these were not part of the original course design and data collection.

Circularity Check

0 steps flagged

No circularity: purely descriptive educational report with no derivations or predictions

full rationale

The paper describes the design, delivery, and observed outcomes of a hands-on HPC course using Raspberry Pi clusters plus a 'Teaching on Demand' component. It reports student motivation and self-reported readiness from the course activities themselves. No equations, predictive models, fitted parameters, or first-principles derivations appear in the abstract or context. Central claims rest on direct observation of the implemented course rather than any reduction to self-citations, self-definitions, or inputs-by-construction. This is a standard descriptive methodology paper whose evaluation chain is self-contained and non-circular.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on the domain assumption that hands-on cluster building plus student choice reliably produces lasting professional readiness; no free parameters or invented entities are introduced.

axioms (1)
  • domain assumption Hands-on experience with affordable hardware increases student engagement and perceived capability in technical computing topics
    Invoked throughout the course design and evaluation sections to justify the Raspberry Pi approach and teaching-on-demand component.

pith-pipeline@v0.9.0 · 5505 in / 1218 out tokens · 49051 ms · 2026-05-08T18:33:55.955304+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

58 extracted references · 8 canonical work pages

  1. [1]

    core topics

    RELATED WORK In the recent past, we can find many efforts from the HPC community to convey the supercomputing philosophy to CS and other engineering students. 5 Within these efforts, we can find platforms to simulate HPC environments and help students to understand the different needs and infrastructures [11], and extra courses to provide them with essent...

  2. [2]

    Computer Structure

    METHODOLOGY In this section, we describe the proposed course. First, we present the course goals, a high-level curriculum description, the course design, and the recruitment and selection criteria; then, details regarding the contents of the course are provided and discussed; lastly, we include an evaluation of the syllabus. 4.1. Overview Broadly speaking...

    2018

  3. [3]

    hands- on

    COURSE EVALUATION: DISCUSSION AND LESSONS LEARNT The remaining results extracted from the surveys and the course experience itself are summarized and discussed in this section. Are students motivated to learn? Motivation is vital for learning, and university students have it. However, we (as lecturers) do not always find a way to keep it alive. In Figure ...

  4. [4]

    Not at all

    FOLLOW-UP: IMPACT OF ATTENDING THE COURSE In the first quarter of the year 2021 (respectively two and three years af- ter the first and second edition), the authors sent a short questionnaire to the 34 participants of both editions of the course to follow-up on the impact and in- fluence of attending it. The questionnaire was composed of two questions tha...

    2021

  5. [5]

    hands-on

    CONCLUSIONS HPC necessity and importance are unquestionable, and we have realized that there is a lack of related content in the engineering syllabus of the UJI, particularly in CS subjects. Motivated students and an increasing necessity of HPC knowledge in the job market, moved us to propose the course. Combining the “hands-on” experience and the “on-dem...

  6. [6]

    hands-on

    FUTURE WORK We are satisfied with the results derived from completing the course and will offer subsequent editions of it. We plan to look for funding from technological companies so we can include a small competition at the end of the course in which a general challenge is proposed, following the spirit of student cluster competitions. Moreover, we are w...

    2020

  7. [7]

    Carratal´ a-S´ aez, S

    R. Carratal´ a-S´ aez, S. Iserte, S. Catal´ an, Teaching on Demand: an HPC Experience, in: Proceedings of EduHPC 2019: Workshop on Education for High Performance Computing - Held in conjunction with SC19: The International Conference for High Performance Computing, Networking, Storage and Analysis, 2019, pp. 32–41

    2019

  8. [8]

    G. V. Wilson, A glossary of parallel computing terminology, IEEE Concur- rency (out of print) 1 (01) (1993) 52–67.doi:10.1109/88.219862

    work page doi:10.1109/88.219862 1993

  9. [9]

    HPC Wiki, https://hpc-wiki.info/hpc/HPC-Dictionary, accessed: March 2021

    2021

  10. [10]

    HPC Glossary (The University of Tennessee), https://www.nics.tennessee.edu/hpc-glossary, accessed: March 2021

    2021

  11. [11]

    HPC Glossary of Terms (Pomona College), https://www.pomona.edu/administration/hpc/access-guidelines/glossary, accessed: March 2021. 39

    2021

  12. [12]

    Saffran, G

    J. Saffran, G. Garcia, M. A. Souza, P. H. Penna, M. Castro, L. F. W. G´ oes, H. C. Freitas, A low-cost energy-efficient raspberry pi cluster for data min- ing algorithms, in: F. Desprez, P.-F. Dutot, C. Kaklamanis, L. Marchal, K. Molitorisz, L. Ricci, V. Scarano, M. A. Vega-Rodr´ ıguez, A. L. Var- banescu, S. Hunold, S. L. Scott, S. Lankes, J. Weidendorfe...

    2016

  13. [13]

    M. F. Cloutier, C. Paradis, V. M. Weaver, A raspberry pi cluster in- strumented for fine-grained power measurement, Electronics 5 (4).doi: 10.3390/electronics5040061. URLhttps://www.mdpi.com/2079-9292/5/4/61

    work page doi:10.3390/electronics5040061 2079

  14. [14]

    Hajji, F

    W. Hajji, F. P. Tso, Understanding the performance of low power raspberry pi cloud for big data, Electronics 5 (2).doi:10.3390/electronics50200 29. URLhttps://www.mdpi.com/2079-9292/5/2/29

    work page doi:10.3390/electronics50200 2079

  15. [15]

    Doucet, J

    K. Doucet, J. Zhang, Learning cluster computing by creating a raspberry pi cluster, in: Proceedings of the SouthEast Conference, ACM SE ’17, Asso- ciation for Computing Machinery, New York, NY, USA, 2017, p. 191–194. doi:10.1145/3077286.3077324. URLhttps://doi.org/10.1145/3077286.3077324

    work page doi:10.1145/3077286.3077324 2017

  16. [16]

    Mappuji, N

    A. Mappuji, N. Effendy, M. Mustaghfirin, F. Sondok, R. P. Yuniar, S. P. Pangesti, Study of raspberry pi 2 quad-core cortex-a7 cpu cluster as a mini supercomputer, in: 2016 8th International Conference on Information Technology and Electrical Engineering (ICITEE), 2016, pp. 1–4.doi: 10.1109/ICITEED.2016.7863250

    work page doi:10.1109/iciteed.2016.7863250 2016

  17. [17]

    Lasserre, R

    A. Lasserre, R. Namyst, P.-A. Wacrenier, Easypap: a framework for learn- ing parallel programming, in: EduPar-20: 10th NSF/TCPP Workshop on Parallel and Distributed Computing Education (EduPar-20), 2020, pp. 276–283. 40

    2020

  18. [18]

    Marzulo, C

    L. Marzulo, C. Bianchini, L. Santiago, V. Ferreira, B. Goldstein, F. Fran¸ ca, Teaching high performance computing through parallel programming marathons, in: 2019 IEEE International Parallel and Distributed Process- ing Symposium Workshops (IPDPSW), 2019, pp. 296–303

    2019

  19. [19]

    Prasad, K

    S. Prasad, K. Kant, Y. Robert, A. Chtchelkanova, S. Das, A. La Salle, R. Le Blanc, A. Rosenberg, F. Dehne, M. Lumsdaine, S. Sahni, M. Gouda, D. Padua, B. Shirazi, A. Gupta, M. Parashar, A. Sussman, J. Jaja, V. Prasanna, C. Weems, J. Wu, Nsf/ieee-tcpp curriculum initiative on parallel and distributed computing - core topics for undergraduates, in: SIGCSE’1...

    work page doi:10.1145/1953163.1953336 2011

  20. [20]

    Holmes, I

    V. Holmes, I. Kureshi, Developing High Performance Computing Resources for Teaching Cluster and Grid Computing Courses, Procedia Computer Science 51 (2015) 1714–1723

    2015

  21. [21]

    L´ opez, E

    P. L´ opez, E. Baydal, Teaching high-performance service in a cluster com- puting course, Journal of Parallel and Distributed Computing 117 (2018) 138–147

    2018

  22. [22]

    A. A. Datti, H. A. Umar, J. Galadanci, A Beowulf Cluster for Teaching and Learning, Procedia Computer Science 70 (2015) 62–68

    2015

  23. [23]

    Sterling, T

    T. Sterling, T. Sterling, D. J. Becker, D. Savarese, J. E. Dorband, U. A. Ranawake, C. V. Packer, Beowulf: A Parallel Workstation For Scientific Computation, in Proceedings of the 24th International Conference on Par- allel Processing 1 (1995) 11—-14

    1995

  24. [24]

    Alvarez, E

    L. Alvarez, E. Ayguade, F. Mantovani, Teaching HPC Systems and Parallel 41 Programming with Small Scale Clusters of Embedded SoCs, in: Workshop on Education for High Performance Computing (EduHPC), 2018, pp. 1–10

    2018

  25. [25]

    Adams, S

    J. Adams, S. J. Matthews, E. Shoop, D. Toth, J. Wolfer, Using Inexpen- sive Microclusters and Accessible Materials for Cost-Effective Parallel and Distributed Computing Education, The Journal of Computational Science Education 8 (3) (2017) 2–10

    2017

  26. [26]

    Vaughan-Nichols, Build your own supercomputer out of Rasp- berry Pi boards (2013)

    Steven J. Vaughan-Nichols, Build your own supercomputer out of Rasp- berry Pi boards (2013). URLhttps://www.zdnet.com/article/build-your-own-supercomput er-out-of-raspberry-pi-boards/

    2013

  27. [27]

    URLhttps://youtu.be/DN_cqiSg8jU

    Eva Havelkova, Parallel computing demonstrations on Wee Archie (2018). URLhttps://youtu.be/DN_cqiSg8jU

    2018

  28. [28]

    URLhttps://csinparallel.org/csinparallel/raspberry_pi.html

    Teaching PDC Using the Raspberry Pi. URLhttps://csinparallel.org/csinparallel/raspberry_pi.html

  29. [29]

    URLhttps://magpi.raspberrypi.org/articles/build-a-raspberry -pi-cluster-computer

    PJ Evans, Build a Raspberry Pi cluster computer (2020). URLhttps://magpi.raspberrypi.org/articles/build-a-raspberry -pi-cluster-computer

    2020

  30. [30]

    R. P. Foundation, Raspberry pi model 4b,https://www.raspberrypi.or g/products/raspberry-pi-4-model-b/

  31. [31]

    Eadline, High Performance Computing for Dummies, Wiley Publishing, 2009

    D. Eadline, High Performance Computing for Dummies, Wiley Publishing, 2009

    2009

  32. [32]

    Severance, K

    C. Severance, K. Dowd, High Performance Computing, O’Reilly Media, Inc, 1998

    1998

  33. [33]

    URLhttp://link.springer.com/10.1007/978-981-10-3731-3 42

    ASC Community, The Student Supercomputer Challenge Guide, Springer Singapore, Singapore, 2018. URLhttp://link.springer.com/10.1007/978-981-10-3731-3 42

    work page doi:10.1007/978-981-10-3731-3 2018

  34. [34]

    A. C. : Bj¨ orn-S¨ oren Gigler, A. Verbeek, Financing the future of supercom- puting: How to increase the investments in high performance computing in Europe, European Investment Bank, 2018

    2018

  35. [35]

    Obama, Executive Order - Creating a National Strategic Computing Initiative, Vol

    B. Obama, Executive Order - Creating a National Strategic Computing Initiative, Vol. 29, The White House, 2015

    2015

  36. [36]

    Joseph, J

    E. Joseph, J. Wu, S. Conway, S. Tichenor, Benchmarking Industrial Use of High Performance Computing for Innovation, The Council on competitive- ness, 2008

    2008

  37. [37]

    BSC - Computing with you,https://www.bsc.es/discover-bsc/compu ting-with-you

  38. [38]

    TACC - Tours,https://www.tacc.utexas.edu/education/tours

  39. [39]

    Banchelli, F

    F. Banchelli, F. Mantovani, Filling the gap between education and indus- try: evidence-based methods for introducing undergraduate students to hpc, in: 2018 IEEE/ACM Workshop on Education for High-Performance Computing (EduHPC), 2018, pp. 41–50

    2018

  40. [40]

    Neelima, J

    B. Neelima, J. Li, Introducing high performance computing concepts into engineering undergraduate curriculum: A success story, in: Proceedings of the Workshop on Education for High-Performance Computing, EduHPC ’15, ACM, New York, NY, USA, 2015, pp. 6:1–6:8

    2015

  41. [41]

    Chaudhury, A

    B. Chaudhury, A. Varma, Y. Keswani, Y. Bhatnagar, S. Parikh, Let’s HPC: A web-based platform to aid parallel, distributed and high performance computing education, Journal of Parallel and Distributed Computing 118 (2018) 213–232

    2018

  42. [42]

    J. L. Hennessy, D. A. Patterson, Computer Architecture: A Quantitative Approach, 6th Edition, Morgan Kaufmann Publishers Inc, 2017

    2017

  43. [43]

    TOP500 List,https://www.top500.org

  44. [44]

    LINPACK library,https://www.netlib.org/linpack/. 43

  45. [45]

    A Portable Implementation of the High-Performance Linpack Benchmark for Distributed-Memory Computers,https://www.netlib.org/benchma rk/hpl/

  46. [46]

    Marenostrum Supercomputer from the Barcelona Supercomputing Center (BSC),https://www.bsc.es/marenostrum/marenostrum, accessed: March 2021

    2021

  47. [47]

    Raspbian free operating system based on debian optimized for the rasp- berry pi hardware.,https://raspbian.org

  48. [48]

    NFS protocol,http://nfs.sourceforge.net/

  49. [49]

    Plimpton, Short-Range Molecular Dynamics, Journal of Computational Physics 117 (6) (1997) 1–42

    S. Plimpton, Short-Range Molecular Dynamics, Journal of Computational Physics 117 (6) (1997) 1–42

    1997

  50. [50]

    OpenMP,https://www.openmp.org/

  51. [51]

    W. D. Gropp, W. Gropp, E. Lusk, A. Skjellum, A. D. F. E. E. Lusk, Using MPI: portable parallel programming with the message-passing interface, Vol. 1, MIT press, 1999

    1999

  52. [52]

    Mpich,https://www.mpich.org/

  53. [53]

    Openmpi,https://www.open-mpi.org/

  54. [54]

    L. Zhou, S. Guo, Thermal management of arm socs using linux cpufreq as cooling device, in: COMPUTER MODELLING & NEW TECHNOLO- GIES, 2015, pp. 162–167

    2015

  55. [55]

    A. B. Yoo, M. A. Jette, M. Grondona, SLURM: Simple Linux Utility for Resource Management, in: D. Feitelson, L. Rudolph, U. Schwiegelshohn (Eds.), Job Scheduling Strategies for Parallel Processing: 9th International Workshop, JSSPP 2003, Seattle, WA, USA, June 24, 2003. Revised Paper, Springer Berlin Heidelberg, Berlin, Heidelberg, 2003, pp. 44–60.doi: 10....

    work page doi:10.1007/10968987_3 2003

  56. [56]

    N. J. Nersessian, Conceptual change in science and in science education, Synthese 80 (1) (1989) 163–183

    1989

  57. [57]

    M. P. Clough, Using the laboratory to enhance student learning, Learning science and the science of learning (2002) 85–94

    2002

  58. [58]

    step by step

    C. Garc´ ıa, Los grados de Ciencias solo captan a una de cada 10 alumnas en la UJI, El Peri´ odico Mediterr´ aneo. URLhttps://www.elperiodicomediterraneo.com/noticias/castell on/grados-ciencias-solo-captan-10-alumnas-uji_1204005.html 45 Appendix A. User guide In this appendix, we present a “step by step” guide detailing the tasks pro- posed in the course....