BEGIN:VCALENDAR VERSION:2.0 PRODID:-//CERN//INDICO//EN BEGIN:VEVENT SUMMARY:Questions and Discussion DTSTART;VALUE=DATE-TIME:20231207T100000Z DTEND;VALUE=DATE-TIME:20231207T103000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1968@events.chpc.ac.za DESCRIPTION:Speakers: Q&A ()\nhttps://events.chpc.ac.za/event/125/contribu tions/1968/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1968/ END:VEVENT BEGIN:VEVENT SUMMARY:® Next DC Design for Generative AI workloads & HPC DTSTART;VALUE=DATE-TIME:20231205T115000Z DTEND;VALUE=DATE-TIME:20231205T121000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1975@events.chpc.ac.za DESCRIPTION:Speakers: Pramod Venkatesh ()\nThe evolution of data center (D C) design over the years has been pivotal in shaping the digital landscape \, particularly with the rise of Web 2.0 and now\, the advent of Generativ e AI. Initially\, the growth of Web 2.0 was underpinned by technologies th at focused on increasing data storage capacities and improving network ban dwidth to support burgeoning internet services and cloud computing. As we step into the era of Generative AI\, the demands on DCs have dramatically escalated\, requiring not just enhanced storage and connectivity\, but als o unprecedented computational power and energy efficiency. The new DC desi gns are poised to future-proof themselves by adopting cutting-edge technol ogies like advanced cooling systems\, AI-driven automation for operational efficiency\, and modular designs for scalable expansion.\n\nhttps://event s.chpc.ac.za/event/125/contributions/1975/ LOCATION:Skukuza 1-1-2+4 - Ndau + Nari URL:https://events.chpc.ac.za/event/125/contributions/1975/ END:VEVENT BEGIN:VEVENT SUMMARY:® Investigating machine learning techniques for precipitation fo recast in Brazil DTSTART;VALUE=DATE-TIME:20231206T093000Z DTEND;VALUE=DATE-TIME:20231206T094500Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-2008@events.chpc.ac.za DESCRIPTION:Speakers: Fabio Porto ()\nExtreme events of rainfall in Brazil are observing significant increase in the frequency and in the strength o f their occurrence. Recent events in the southeast part of the country led to casualties\, property damage\, and huge impact in the cities and their urban lives. Governments are installing alarms in endangered parts of the towns\, preparing evacuation instructions and event deallocating people t rying to avoid human loss in the next known-come large event. \nIn other t o support these initiatives\, we are developing different projects aiming at constructing predictive models to forecast the occurrence of strong rai nfall. The Rionowcast project is being carried on in a collaboration betwe en academic institutions in the Rio de Janeiro state and the Operation Cen ter of Rio de Janeiro (COR). The idea is to build AI spatio-temporal model s using a variety of data sources providing historical and real-time infor mation about the weather conditions in Rio de Janeiro. Data sources includ e: rain gauges\, weather stations\, radio-sonda\; ocean buoys\; satellite products\, radar products and numerical models. We are trying with differe nt DL model architectures from transformers to GNN\; from global to local models and ensembles\; and physical informed networks. \nIn order to foste r the collaboration among the different research groups\, we are using the Gypscie framework that supports data and model management and dataflow ex ecution.\nDuring the Digital Earth Session of the CHPC National Conference \, we intend to briefly present theses initiatives\n\nhttps://events.chpc. ac.za/event/125/contributions/2008/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/2008/ END:VEVENT BEGIN:VEVENT SUMMARY:® The Cambridge Open Zettascale Lab is hosting Dawn\, the UK’s fastest artificial intelligence (AI) supercomputer DTSTART;VALUE=DATE-TIME:20231207T121000Z DTEND;VALUE=DATE-TIME:20231207T123000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-2010@events.chpc.ac.za DESCRIPTION:Speakers: Paul Calleja (Cambridge University)\nDawn has been c reated via a highly innovative long-term co-design partnership between the University of Cambridge\, UK Research & Innovation\, the UK Atomic Energy Authority and global tech leaders Intel and Dell Technologies. This partn ership brings highly valuable technology first-mover status and inward inv estment into the UK technology sector. Dawn\, supported by UK Research and Innovation (UKRI)\, will vastly increase the country's AI and simulation compute capacity for both fundamental research and industrial use\, accele rating research discovery and driving growth within the UK knowledge econo my. It is expected to drive significant advancements in healthcare\, green fusion energy development and climate modelling. In this talk\, there wil l be opportunities for South African Scientists to develop a framework on access to Dawn and doing benchmarks for some of the applications relevant to South Africa. So do attend\, you might just win yourself part of the Di rector’s Discretionary time on Dawn.\n\nhttps://events.chpc.ac.za/event/ 125/contributions/2010/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/2010/ END:VEVENT BEGIN:VEVENT SUMMARY:® I/O behavior of scientific deep learning workloads DTSTART;VALUE=DATE-TIME:20231206T121000Z DTEND;VALUE=DATE-TIME:20231206T123000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1971@events.chpc.ac.za DESCRIPTION:Speakers: Hariharan Devarajan (Lawrence Livermore National Lab oratory)\nDeep learning has been shown as a successful method for various tasks\, and its popularity results in numerous open-source deep learning s oftware tools. Deep learning has been applied to a broad spectrum of scien tific domains such as cosmology\, particle physics\, computer vision\, fus ion\, and astrophysics. Scientists have performed a great deal of work to optimize the computational performance of deep learning frameworks. Howeve r\, the same cannot be said for I/O performance. As deep learning algorith ms rely on big-data volume and variety to effectively train neural network s accurately\, I/O is a significant bottleneck on large-scale distributed deep learning training.\n \nIn this talk\, I aim to provide a detailed inv estigation of the I/O behavior of various scientific deep learning workloa ds running on the Theta cluster at Argonne Leadership Computing Facility. In this talk\, I present DLIO\, a novel representative benchmark suite bui lt based on the I/O profiling of the selected workloads. DLIO can be utili zed to accurately emulate the I/O behavior of modern scientific deep learn ing applications. Using DLIO\, application developers and system software solution architects can identify potential I/O bottlenecks in their applic ations and guide optimizations to boost the I/O performance leading to low er training times by up to 6.7x.\n\nhttps://events.chpc.ac.za/event/125/co ntributions/1971/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1971/ END:VEVENT BEGIN:VEVENT SUMMARY:® Mango-IO: I/O Metrics Consistency Analysis DTSTART;VALUE=DATE-TIME:20231206T115000Z DTEND;VALUE=DATE-TIME:20231206T121000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1970@events.chpc.ac.za DESCRIPTION:Speakers: Radita Liem (RWTH Aachen\, Germany)\nPerformance too ls are inseparable from complex HPC applications’ performance analysis a nd engineering life cycles. Due to the application’s complexity\, variou s performance analysis tools are created to serve different analysis purpo ses and provide a deeper look at certain aspects of the applications. Alth ough these tools might operate differently\, having coherent information a nd consistent metrics across all tools is mandatory for ensuring analysis continuity. It is common for performance analysts to switch their usual pe rformance tools due to various reasons and limitations. In this work\, we look specifically at the I/O performance analysis tools landscape and intr oduce Mango-IO to verify the result consistencies between tools and provid e tool-agnostic metrics calculation methods. Our analysis and case study p rovides lesson learned and guideline for ensuring measurement continuity a nd comparability.\n\nhttps://events.chpc.ac.za/event/125/contributions/197 0/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1970/ END:VEVENT BEGIN:VEVENT SUMMARY:® Enable Fundamental Cacheability for Distributed Deep Learning T raining DTSTART;VALUE=DATE-TIME:20231206T113000Z DTEND;VALUE=DATE-TIME:20231206T115000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1969@events.chpc.ac.za DESCRIPTION:Speakers: Ali Butt (Virginia Tech)\nDeep learning training (DL T) applications exhibit unique I/O workload behaviors that pose new challe nges for storage system design. DLT is I/O intensive since data samples ne ed to be fetched continuously from a remote storage. Accelerators such as GPUs have been extensively used to support these applications. As accelera tors become more powerful and more data-hungry\, the I/O performance lags behind. This creates a crucial performance bottleneck\, especially in dist ributed DLT. At the same time\, the exponentially growing dataset sizes ma ke it impossible to store these datasets entirely in memory. While today ’s DLT frameworks typically use a random sampling policy that treat all samples uniformly equally\, recent findings indicate that not all samples are equally important and different data samples contribute differently to wards improving the accuracy of a model. This observation creates an oppor tunity for DLT I/O optimizations by exploiting the data locality enabled b y importance sampling.\n\nIn this talk\, I’ll present the design of SHAD E\, a new DLT-aware caching system that detects fine-grained importance va riations at per-sample level and leverages the variance to make informed c aching decisions for a distributed DLT job. SHADE adopts a novel\, rank-ba sed approach\, which captures the relative importance of data samples acro ss different mini-batches. SHADE then dynamically updates the importance s cores of all samples during training. With these techniques\, SHADE manage s to significantly improve the cache hit ratio\nof the DLT job\, and thus\ , improves the job’s training performance.\n\nhttps://events.chpc.ac.za/ event/125/contributions/1969/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1969/ END:VEVENT BEGIN:VEVENT SUMMARY:® Integrating WRF and Hydrology Models for Improved Urban Flood F orecasting in Pune using HPC: A Comprehensive Approach for the Indian Metr opolis DTSTART;VALUE=DATE-TIME:20231206T094500Z DTEND;VALUE=DATE-TIME:20231206T100000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-2009@events.chpc.ac.za DESCRIPTION:Speakers: Manoj Khare ()\nPune is the second largest city in t he Indian state of Maharashtra\, situated over a complex topographical reg ion on the leeward side of the Western Ghats\, India. Recently\, Pune City has been experiencing frequent heavy to extreme rainfall events\, causing urban floods\, threatening lives\, and heavy socio-economic damage. The r ecent decade has witnessed the adverse effects of urban foods on daily lif e by destroying infrastructure\, water-logging that triggers foods\, disru pting transportation\, and resulting in the loss of lives and property. An efficient early warning system is a crucial requirement that remains chal lenging using a high-resolution numerical weather prediction (NWP) model. The complexity increases manifold\, particularly if the forecast has to be made on an urban scale to mitigate its adverse impacts.\nAn attempt is ma de to develop a coupled modelling system that integrates the Weather Resea rch and Forecasting (WRF) model with Hydrological to enhance urban flood f orecasting capabilities for an Indian city. Extensive work has been done t o set up the WRF model through sensitivity analysis of domain setup\, para meterisation schemes\, land-use information\, and initial conditions for r ainfall event forecasting over Pune. Model performance has been validated against various observations available through ground-based and satellite measurements. The rainfall forecast obtained from the WRF model at a very high resolution of 0.5 km has been provided to the hydrology model to simu late surface runoff\, stormwater discharge\, and depth in urban regions. T he developed coupled system was calibrated against past rainfall flood eve nts over Pune. This calibration ensured that the model represented the act ual behaviour of the system and the rainfall distribution in the sub-catch ments. This coupled system was used for simulations of recent floods of 20 22 and showed a good agreement with observations. Such coupling of hydro-m et systems can be a helpful tool to enhance urban flood forecasting. For t his work\, WRF model simulations were performed on HPC (PARAM series) usin g around 1900 processors.\n\nhttps://events.chpc.ac.za/event/125/contribut ions/2009/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/2009/ END:VEVENT BEGIN:VEVENT SUMMARY:Land surface model TerM: design\, applications and HPC aspects DTSTART;VALUE=DATE-TIME:20231206T090000Z DTEND;VALUE=DATE-TIME:20231206T091500Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1910@events.chpc.ac.za DESCRIPTION:Speakers: Victor Stepanenko (Moscow State University)\nTerrest rial model (TerM) is the land surface scheme developed jointly at the Inst itute of Numerical Mathematics RAS and Moscow State University. It has bee n originally a part of INM-CM Easth system model and SL-AV weather forecas ting system\, and is responsible for providing fluxes of radiation\, heat\ , moisture and greenhouse gases to the atmosphere from the land surface. T erM uses multilayer soil\, snow and lake models\, vegetation controls on e vaporation and energy exchange\, terrestrial carbon and methane cycles. Te rM is currently implemented also in a standalone mode\, enabling more flex ibility in land surface research. The standalone TerM includes advanced ri ver routing scheme\, and can be used in single-column\, regional and globa l domains of arbitrary longitude-latitude regular mesh\, forced by meteoro logical observations\, reanalysis\, or climate models data. It is suppleme nted with preprocessing system supplying external data on land cover types \, soil\, lakes\, rivers\, etc. To increase the model performance\, an aut omatic calibration system is developed. The model is implemented for multi core systems using MPI+OpenMP technologies. We present examples of the Ter M application for hydrological and carbon cycle studies.\n\nhttps://events .chpc.ac.za/event/125/contributions/1910/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1910/ END:VEVENT BEGIN:VEVENT SUMMARY:Data Management on HPC Workloads: Accelerating outcomes while pres erving data for future examination and collaboration DTSTART;VALUE=DATE-TIME:20231206T123000Z DTEND;VALUE=DATE-TIME:20231206T125000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1972@events.chpc.ac.za DESCRIPTION:Speakers: Miguel Castro (Spectralogic)\nProvide attendees with a detailed view of the Long-Term Digital Archive solution implemented at CSIR. \n\nThis solution enables CSIR to provide a high performance\, highl y scalable\, integrated archive ecosystem that allows internal departments and external organisations to collaborate\, archive and preserve data dri ven research in support of National Science and Strategic priorities.\n\nT he importance of arriving at the right data management strategy becomes pa ramount as the size of HPC datasets continues its inexorable march towards zettabytes.\n\nhttps://events.chpc.ac.za/event/125/contributions/1972/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1972/ END:VEVENT BEGIN:VEVENT SUMMARY:Question and Discussions DTSTART;VALUE=DATE-TIME:20231207T123000Z DTEND;VALUE=DATE-TIME:20231207T130000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1993@events.chpc.ac.za DESCRIPTION:Speakers: Q&A ()\nTBC\n\nhttps://events.chpc.ac.za/event/125/c ontributions/1993/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1993/ END:VEVENT BEGIN:VEVENT SUMMARY:Build diversified computing infrastructure\, unleash data value\, promote scientific\, technological\, and economic development DTSTART;VALUE=DATE-TIME:20231207T115000Z DTEND;VALUE=DATE-TIME:20231207T121000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1991@events.chpc.ac.za DESCRIPTION:Speakers: Zekelman Zhang ()\nTBC\n\nhttps://events.chpc.ac.za/ event/125/contributions/1991/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1991/ END:VEVENT BEGIN:VEVENT SUMMARY:Simplifying HPC/AI Storage Using Industry Standard Protocol DTSTART;VALUE=DATE-TIME:20231207T113000Z DTEND;VALUE=DATE-TIME:20231207T115000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1967@events.chpc.ac.za DESCRIPTION:Speakers: Scott Howard ()\nTBC\n\nhttps://events.chpc.ac.za/ev ent/125/contributions/1967/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1967/ END:VEVENT BEGIN:VEVENT SUMMARY:Questions DTSTART;VALUE=DATE-TIME:20231206T125000Z DTEND;VALUE=DATE-TIME:20231206T130000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1989@events.chpc.ac.za DESCRIPTION:https://events.chpc.ac.za/event/125/contributions/1989/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1989/ END:VEVENT BEGIN:VEVENT SUMMARY:® South Africa’s Operational Ocean Forecasting Developments DTSTART;VALUE=DATE-TIME:20231206T101500Z DTEND;VALUE=DATE-TIME:20231206T103000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1949@events.chpc.ac.za DESCRIPTION:Speakers: Giles Fearon ()\nAlgoa Bay is situated at the edge o f the Agulhas Current\, where it transitions from being relatively stable\ , to unstable as the continental shelf broadens in the downstream directio n. As one of South Africa’s largest bays it provides a degree of shelter from the southern hemisphere’s most powerful western boundary current a nd is being utilized for offshore ship refueling operations. The environme ntal risks involved\, the highly dynamic offshore boundary and the good ne twork of measurements in the bay have led to it being identified as a pilo t site for the development of an operational forecast system that would su pport stakeholders and decision makers in the case of coastal hazards. To this end\, a step by step approach was followed in order to produce a down scaled forecast system optimized for this region and that can be readily c onfigured for other key locations around the coastline. The first step was to evaluate and intercompare various global models as potential boundary conditions. The next step was to develop high-resolution\, limited duratio n hindcast CROCO/ROMS simulations\, using different ocean boundary forcing s and resolution atmospheric products. Comparisons with temperature record ers and ADCPs at various locations within the bay reveal the differences i n the skill of the different models and that their ensemble mean performs best. The tools for the modelling approach have been ‘dockerized’ for the ease of implementation and interoperability of the system. Using this dockerized workflow\, a second bay-scale operational forecast system has b een implemented for the South West Cape Coast region\, which is home to a lucrative aquaculture industry that are periodically impacted by severe ha rmful algal blooms (HABs). These limited area forecast systems are being i ncorporated into a tool to initialize operational OpenDrift particle track ing simulations with various site-specific applications (e.g. oil spills\, search and rescue and HAB advection). The operational system will be inte grated into the National Oceans and Coastal Information Management Systems (OCIMS) in support of various decision support tools which promote good g overnance of the coastal environment.\n\nhttps://events.chpc.ac.za/event/1 25/contributions/1949/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1949/ END:VEVENT BEGIN:VEVENT SUMMARY:Supermicro Vendor Talk (Title to be confirmed) DTSTART;VALUE=DATE-TIME:20231207T094000Z DTEND;VALUE=DATE-TIME:20231207T100000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1966@events.chpc.ac.za DESCRIPTION:Speakers: Roger Crighton ()\nTBC\n\nhttps://events.chpc.ac.za/ event/125/contributions/1966/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1966/ END:VEVENT BEGIN:VEVENT SUMMARY:Boost Performance with Accelerated HPC and AI DTSTART;VALUE=DATE-TIME:20231207T092000Z DTEND;VALUE=DATE-TIME:20231207T094000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1965@events.chpc.ac.za DESCRIPTION:Speakers: Claudio Polla (Mr)\nThe NVIDIA Accelerated Compute P latform offers a complete end-to-end stack and suite of optimized products \, infrastructure\, and services to deliver unmatched performance\, effici ency\, ease of adoption\, and responsiveness for scientific workloads. NVI DIA’s full-stack architectural approach ensures scientific applications execute with optimal performance\, fewer servers\, and use less energy\, r esulting in faster insights at dramatically lower costs for high-performan ce computing (HPC) and AI workflows.\n\nhttps://events.chpc.ac.za/event/12 5/contributions/1965/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1965/ END:VEVENT BEGIN:VEVENT SUMMARY:Dell - Bringing AI to your Data DTSTART;VALUE=DATE-TIME:20231207T090000Z DTEND;VALUE=DATE-TIME:20231207T092000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1964@events.chpc.ac.za DESCRIPTION:Speakers: Ryan Rautenbach (Dell)\nComprehensive view into Dell ’s AI strategy\, Why Dell for AI\, and our individual products\, solutio ns\, partnerships\, and services for multiple use cases in any location.\n \nhttps://events.chpc.ac.za/event/125/contributions/1964/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1964/ END:VEVENT BEGIN:VEVENT SUMMARY:NGEI’s Initiatives from DSI Regarding the Sovereign Quantum Comp uting Decal Plan DTSTART;VALUE=DATE-TIME:20231205T092000Z DTEND;VALUE=DATE-TIME:20231205T094000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1918@events.chpc.ac.za DESCRIPTION:Speakers: Coral Featherstone (CSIR)\nI will briefly discuss th e history of how scientific focus areas are coordinated through the use of the national development plan\, aligned scientific white papers\, and the decadal plans that are built from the resulting insight. I will also disc uss the current academic landscape of quantum computing in South Africa.\n \nI will discuss the CSIR and how the clusters within the organisation ali gn with the decadal plan. Two units in particular are involved in computin g research and are therefore aligned with quantum computing research\, whi le other units within the CSIR offer unique insights and potential to expl ore the applications of quantum computing. Researchers within the Centre f or High Performance Computing (CHPC)\, and the Nextgen enterprises and ins titutions units within the CSIR are working on making quantum computing re search available and applicable to South Africans. The two units are worki ng with each other\, other suitable clusters within the CSIR\, and quantum -orientated academic institutions\, and industry.\n\nThe quantum computing community in South Africa is too small to work in isolation and working t ogether in a coordinated manner is essential. If we work together we will find applicable uses of quantum computing as applied to local problems tha t are unique to South Africans. There are many examples of uniquely South African problems applicable to quantum computers that would be ignored by international scientists. As just one example\, applying quantum computing to optimisation problems\, such as finding\, predicting\, and treating st rains of HIV that are only found in South Africa.\n\nThe universities are providing additional quantum computing research topics\, and academic grou ps such as the quantum computing working group also contribute white paper s that guide the next round of policy making. Both the universities and th e CSIR provide the DSI with indications on how to apply the focus areas as suggested in the decadal plan.\n\nAligning quantum computing research wit h the focus areas within the decadal plan will help fund and coordinate ca refully pre-identified critical research that helps South Africa with iden tified problems and potential threats.\n\nhttps://events.chpc.ac.za/event/ 125/contributions/1918/ LOCATION:Skukuza 1-1-2+4 - Ndau + Nari URL:https://events.chpc.ac.za/event/125/contributions/1918/ END:VEVENT BEGIN:VEVENT SUMMARY:Questions DTSTART;VALUE=DATE-TIME:20231205T125000Z DTEND;VALUE=DATE-TIME:20231205T130000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1936@events.chpc.ac.za DESCRIPTION:Speakers: Questions ()\nQuestions\n\nhttps://events.chpc.ac.za /event/125/contributions/1936/ LOCATION:Skukuza 1-1-2+4 - Ndau + Nari URL:https://events.chpc.ac.za/event/125/contributions/1936/ END:VEVENT BEGIN:VEVENT SUMMARY:Questions DTSTART;VALUE=DATE-TIME:20231205T102000Z DTEND;VALUE=DATE-TIME:20231205T103000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1934@events.chpc.ac.za DESCRIPTION:Speakers: Questions ()\nQuestions\n\nhttps://events.chpc.ac.za /event/125/contributions/1934/ LOCATION:Skukuza 1-1-2+4 - Ndau + Nari URL:https://events.chpc.ac.za/event/125/contributions/1934/ END:VEVENT BEGIN:VEVENT SUMMARY:Questions DTSTART;VALUE=DATE-TIME:20231206T143000Z DTEND;VALUE=DATE-TIME:20231206T145000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1926@events.chpc.ac.za DESCRIPTION:Speakers: Questions ()\nTBC\n\nhttps://events.chpc.ac.za/event /125/contributions/1926/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1926/ END:VEVENT BEGIN:VEVENT SUMMARY:A multifaceted framework of understanding and synthesises of the d igital artefacts and its impact on the ICT ecosystem DTSTART;VALUE=DATE-TIME:20231206T141000Z DTEND;VALUE=DATE-TIME:20231206T143000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1925@events.chpc.ac.za DESCRIPTION:Speakers: Ricardo Harry (CSIR)\nTBC\n\nhttps://events.chpc.ac. za/event/125/contributions/1925/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1925/ END:VEVENT BEGIN:VEVENT SUMMARY:The influence of national culture dimensions on Agile roles in the South African Software Development Context DTSTART;VALUE=DATE-TIME:20231206T135000Z DTEND;VALUE=DATE-TIME:20231206T141000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1924@events.chpc.ac.za DESCRIPTION:Speakers: Kirwin Matthews (University of Cape Town)\nAbstract — Culture influences how agile frameworks are implemented\, and agility is said to be suitable in contexts where flexibility and spontaneity are e mphasized. While past studies have investigated the influence of national culture on Agile implementations in Western and Eastern contexts\, studies focusing on a South African software development context is limited. Furt hermore\, few studies have focused on the effect of cultural differences w ithin software engineering in general. The purpose of this study is to des cribe how national culture influences Agile roles within the South African software development context. The study was interpretive and was executed using a qualitative\, semi- structured interview research strategy direct ed at Agile practitioners in South African software development teams. The thematic analysis technique was used to analyze the data. Ten proposition s have been formulated to highlight how national culture dimensions influe nce Agile roles.\nIndex Terms— Agile Software Development\, National Cul ture\, Agile Roles\, South Africa.\n\nhttps://events.chpc.ac.za/event/125/ contributions/1924/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1924/ END:VEVENT BEGIN:VEVENT SUMMARY:Emerging Leadership Practices in deploying Digital Research Infras tructure in Africa DTSTART;VALUE=DATE-TIME:20231206T133000Z DTEND;VALUE=DATE-TIME:20231206T135000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1923@events.chpc.ac.za DESCRIPTION:Speakers: Mervyn Christoffels (CHPC)\nTo adopt a universal dig ital leadership paradigm for Africa would mean having to ignore previous r esearch that indicates the link between the African cultural context and i ts influence on shaping decisions and behavioural patterns within organisa tions. Similarly\, to ignore the emerging digital leadership paradigm enti rely would deprive Africa of a wide variety of leadership management theor ies and practices that have already been developed and proved effective. I n order to bridge the differences between the two noted positions\, a nove l conceptual framework will be developed in this proposed study. This fram ework will synthesise the best scientific facets of both the emerging digi tal leadership paradigm and the African leadership context with an African -based value system (i.e.\, the framework will use crossvergence. In this way\, the proposed study aims to explore a new digital leadership paradigm that is specifically focused on addressing the unique African digital sce nario.\n\nhttps://events.chpc.ac.za/event/125/contributions/1923/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1923/ END:VEVENT BEGIN:VEVENT SUMMARY:From Grassroots to Greatness: Unleashing HPC Potential in Africa DTSTART;VALUE=DATE-TIME:20231205T122000Z DTEND;VALUE=DATE-TIME:20231205T123000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1922@events.chpc.ac.za DESCRIPTION:Speakers: Nilesh Jain (Deep Learning Indaba𝕏)\nThe Deep Lea rning Indaba\, founded in 2017\, serves as a community dedicated to foster ing Artificial Intelligence capabilities and promoting knowledge sharing a cross Africa. As part of this endeavor\, Deep Learning Indaba𝕏 events h ave been established in several participating countries. A Deep Learning I ndaba𝕏 represents a locally-organized "Indaba" or conference aimed at e nsuring the widespread dissemination of knowledge and capacity in machine learning across the African continent. As of 2023\, Indaba𝕏 events have taken place in 36 African countries.\n\nThe Deep Learning Indaba and Inda ba𝕏 have provided an invaluable platform for the emergence and growth o f various research communities with shared interests. Grassroots communiti es like Masakhane\, Ro'ya\, and Sisonke Biotik have cultivated networks of localized expertise in AI applications for language\, computer vision\, a nd healthcare respectively. These organisations prioritise the "community first" principle\, valuing it even above objectives like research publicat ion. As the African proverb wisely suggests\, "If you want to go fast\, go alone\; if you want to go far\, go together." These communities embody th e essence of African AI development\, and their impact stands to be enhanc ed through the utilization of High-Performance Computing (HPC).\n\nThe glo bal AI revolution has spurred the creation of numerous startups. The Deep Learning Indaba platforms have been instrumental in showcasing African AI startups and creating opportunities for talent acquisition and business ne tworking. While African AI-focused companies like InstaDeep have firmly es tablished themselves in the private sector\, the potential for further AI industry development in Africa remains substantial. Lelapa AI serves as an other recent example of a South African AI company that has generated sign ificant attention and anticipation. Support from HPC for startups holds th e potential to facilitate their transition from the early stages of growth and experimentation to achieving sustainable expansion at a faster pace.\ n\nDuring this talk\, we will spotlight success stories\, share published research from these communities\, and delve into the challenges they have encountered. Finally\, we will emphasize how the convergence of grassroots efforts\, small businesses\, strategic partnerships\, and the untapped po tential of HPC can collectively ignite the next wave of African innovation – an innovation "for Africans\, by Africans."\n\nhttps://events.chpc.ac .za/event/125/contributions/1922/ LOCATION:Skukuza 1-1-2+4 - Ndau + Nari URL:https://events.chpc.ac.za/event/125/contributions/1922/ END:VEVENT BEGIN:VEVENT SUMMARY:® Building a Knowledge Democracy: The Deep Learning IndabaX Story DTSTART;VALUE=DATE-TIME:20231205T121000Z DTEND;VALUE=DATE-TIME:20231205T122000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1921@events.chpc.ac.za DESCRIPTION:Speakers: Lydia de Lange (Deep Learning Indaba𝕏 ZA)\nThe De ep Learning Indaba was founded in 2017 as a community for growing Artifici al Intelligence capability and knowledge sharing across Africa. To extend the impact of the community\, "Deep Learning Indaba𝕏" events have been launched in multiple participating nations. A Deep Learning Indaba𝕏\, o r "Indaba𝕏\," represents a locally-organised conference aimed at democr atizing machine learning expertise and capability across the African conti nent. As of 2023\, these Indaba𝕏 events have been conducted in 36 Afric an countries.\n\nThe South African Deep Learning Indaba𝕏 ("Indaba𝕏 Z A") first took place in 2018 and has since united students\, researchers\, and industry practitioners in a collaborative atmosphere. Indaba𝕏 ZA s erves as a platform for attendees to meet and engage with grassroots commu nities and small businesses. Indaba𝕏 ZA is a volunteer-driven event and would not be possible without support from partners including the CHPC\, NiTheCS and the DSI-NRF Centre of Excellence in Mathematical and Statistic al Science (CoE-MaSS). \n\nOne of the highlights of the Indaba𝕏 ZA is t he hackathon\, where concerted efforts have been made over time to encoura ge more active student participation in the event. Complementing this is a dedicated "fundamentals" track spanning 3 days\, with the aim of cultivat ing foundational skills and lowering the barrier to entry for new members of the community. Furthermore\, initial strides have been taken towards in corporating practical\, hands-on training into the programme.\n\nThis talk will provide a review of the Indaba𝕏 ZA journey thus far\, shedding li ght on its impact\, community diversity and emerging trends within the fie ld. Moreover\, we will touch on our shared vision with partners like the C HPC and how we can explore avenues for deeper collaboration. For example\, there is a great opportunity to provide a platform for the CHPC to introd uce participants to compute and training resources. Our mutual goal remain s the upliftment of young minds in the realm of AI research\, paving the w ay for a future generation of skilled and empowered individuals across the country and the continent.\n\nhttps://events.chpc.ac.za/event/125/contrib utions/1921/ LOCATION:Skukuza 1-1-2+4 - Ndau + Nari URL:https://events.chpc.ac.za/event/125/contributions/1921/ END:VEVENT BEGIN:VEVENT SUMMARY:® Distributed Deep Learning in HPC: Challenges and Opportunities DTSTART;VALUE=DATE-TIME:20231205T123000Z DTEND;VALUE=DATE-TIME:20231205T125000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1920@events.chpc.ac.za DESCRIPTION:Speakers: Albert Kahira (Julich Supercomputing Center)\nLarge- scale training of Deep Learning Models (DL) in High Performance Computing( HPC) systems has become increasingly common to achieve faster training tim e for larger models and datasets by alleviating memory constraints. Traini ng DL models in these systems cuts weeks or even months of training to mer e hours and facilitates faster prototyping and research in DL. Importantly \, training some of the larger models is only possible through these large -scale machines. This talk will provide participants with a foundational u nderstanding of the concepts and techniques involved in Deep Learning in H PC as well as challenges and opportunities for research in the area.\n\nht tps://events.chpc.ac.za/event/125/contributions/1920/ LOCATION:Skukuza 1-1-2+4 - Ndau + Nari URL:https://events.chpc.ac.za/event/125/contributions/1920/ END:VEVENT BEGIN:VEVENT SUMMARY:Machine Learning in Cosmology DTSTART;VALUE=DATE-TIME:20231205T113000Z DTEND;VALUE=DATE-TIME:20231205T115000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1919@events.chpc.ac.za DESCRIPTION:Speakers: Yin-Zhe Ma (University of KwaZulu-Natal)\nCosmology\ , the understanding of the evolution of entire Universe\, has progressed v ery fast in the past several decades with the advances of modern telescope s. I will give a brief overview of the modern cosmology of the last centur y and highlight its phenomenal successes and distinctive challenges. I wil l then explain how and why the use of Machine Learning technique can help unravel these mysteries and exploit the uncharted territories of the early Universe. In particular\, I will give several cases of using machine lear ning to constrain primordial non-Gaussian fluctuations in the cosmic micro wave background radiation\, and studying the epoch of reionization.\n\nhtt ps://events.chpc.ac.za/event/125/contributions/1919/ LOCATION:Skukuza 1-1-2+4 - Ndau + Nari URL:https://events.chpc.ac.za/event/125/contributions/1919/ END:VEVENT BEGIN:VEVENT SUMMARY:® Roadmap of Quantum Computing in a South African Context DTSTART;VALUE=DATE-TIME:20231205T090000Z DTEND;VALUE=DATE-TIME:20231205T092000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1917@events.chpc.ac.za DESCRIPTION:Speakers: Francesco Petruccione (UKZN)\nTBC\n\nhttps://events. chpc.ac.za/event/125/contributions/1917/ LOCATION:Skukuza 1-1-2+4 - Ndau + Nari URL:https://events.chpc.ac.za/event/125/contributions/1917/ END:VEVENT BEGIN:VEVENT SUMMARY:Materials research within the Excalibur Project: Is it time to exp loit Quantum Computers? DTSTART;VALUE=DATE-TIME:20231205T100000Z DTEND;VALUE=DATE-TIME:20231205T102000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1916@events.chpc.ac.za DESCRIPTION:Speakers: Scott Woodley (UCL)\nExascale computing is coming an d given the large anticipated power consumption it is prudent to first ens ure both the users and the software are exascale ready before investing in the hardware. The [Excalibur][1] Project is UK's response to this challen ge\, which funds a range of hardware and software projects and train the n ext generation of Research Software Engineers. One of these funded Excalib ur projects is called [QEVEC][2]\, which seeks to determine whether quantu m computers could potentially be employed as accelerators for classical HP C. Part of the QEVEC project has targeted the use of D-wave annealers (qua ntum computers) to tackle problems\, in the field of computational chemist ry and materials science\, that are intractable on classical computers.\n\ nIn this talk\, I will show how the relative energy of defective graphene structures can be calculated by using a quantum annealer. This simple syst em is used to guide the audience through the steps needed to translate a c hemical structure (a set of atoms) and energy model to a representation th at can be implemented on quantum annealers (a set of qubits). I discuss in detail how different energy contributions can be included in the model an d what their effect is on the final result. The code used to run the simul ation on D-Wave quantum annealers is made available as a Jupyter Notebook - more details can be found in our recent [publication][3]. The first part of this talk is designed to be a quick-start guide for the computational chemists interested in running their first quantum annealing simulations. The methodology outlined in this talk represents the foundation for simula ting more complex systems\, such as solid solutions and disordered systems \, which I will go on to discuss and show latest results for three differe nt solid solutions\, to demonstrate the versatility of our developed metho d. Each system has interesting technological applications: N-doped graphen e in catalysis and energy materials\, Al$_{\\delta}$Ga$_{1-\\delta}$N in o ptoelectronics and Mo$_\\delta$W$_{1-\\delta}$ used as structural componen ts in nuclear and rocket systems because of their high high-temperature st rength\, high melting point\, and good corrosion resistance. Time permitti ng\, I will also present an overview of the Excalibur [PAX-HPC][4] project . \n\n\n [1]: https://excalibur.ac.uk/\n [2]: https://excalibur.ac.uk/pr ojects/qevec/\n [3]: http://doi.org/10.1063/5.0151346\n [4]: https://exc alibur.ac.uk/projects/pax-hpc-particles-at-exascale/\n\nhttps://events.chp c.ac.za/event/125/contributions/1916/ LOCATION:Skukuza 1-1-2+4 - Ndau + Nari URL:https://events.chpc.ac.za/event/125/contributions/1916/ END:VEVENT BEGIN:VEVENT SUMMARY:Leveraging Quantum Machine Learning for Enhanced Biophotonics Appl ications DTSTART;VALUE=DATE-TIME:20231205T094000Z DTEND;VALUE=DATE-TIME:20231205T100000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1915@events.chpc.ac.za DESCRIPTION:Speakers: Kelvin Mpofu (CSIR)\nRecent advancements in the inte rdisciplinary realms of machine learning (ML) and quantum computing (QC) h ave paved the way for innovative approaches in biophotonics\, an establish ed field that utilizes light-based technologies to probe biological substa nces. Quantum machine learning (QML)\, an emerging frontier\, amalgamates quantum computing's superior processing capabilities with machine learning 's predictive power\, offering unprecedented opportunities in biophotonics applications ranging from medical diagnostics to cellular microscopy. Thi s talk explores the symbiotic integration of ML\, QC\, and QML within the context of biophotonics. We begin by providing a foundational overview of machine learning algorithms\, emphasizing their application in image and s ignal processing tasks common in biophotonics\, such as feature extraction from complex biological datasets and pattern recognition in biomolecular structures. We then delve into the quantum computing paradigm\, elucidatin g how its intrinsic properties — such as superposition and entanglement — can dramatically accelerate computational tasks pertinent to biophoton ics. The crux of our discussion centers on quantum machine learning\, wher e we dissect how QML algorithms harness quantum states to perform data enc oding\, processing\, and learning at a scale and speed beyond the reach of classical computers. We present a critical analysis of the current state of QML\, highlighting how its implementation could revolutionize biophoton ics by enabling the analysis of voluminous and high-dimensional datasets m ore efficiently\, thereby facilitating real-time monitoring and decision-m aking in clinical settings. To illustrate the practical implications of QM L in biophotonics\, we showcase cutting-edge applications\, such as the qu antum-enhanced detection of biophotonic signals\, the optimization of biop hotonic setups\, and the quantum-assisted imaging systems that provide sup er-resolved images. The challenges of integrating QML in biophotonics are also discussed\, including the current technological limitations of quantu m hardware and the need for specialized quantum algorithms tailored to bio photonic data. We conclude by forecasting the future directions of QML in biophotonics\, contemplating the potential breakthroughs and transformativ e impacts on healthcare\, biological research\, and beyond. Our synthesis not only underscores the transformative potential of QML in biophotonics b ut also calls for a concerted effort to overcome existing barriers\, thus charting a course towards a quantum-enhanced era in biological science and medicine.\n\nhttps://events.chpc.ac.za/event/125/contributions/1915/ LOCATION:Skukuza 1-1-2+4 - Ndau + Nari URL:https://events.chpc.ac.za/event/125/contributions/1915/ END:VEVENT BEGIN:VEVENT SUMMARY:Numerical simulation of atmospheric boundary layer turbulence on H PC systems DTSTART;VALUE=DATE-TIME:20231206T100000Z DTEND;VALUE=DATE-TIME:20231206T101500Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1912@events.chpc.ac.za DESCRIPTION:Speakers: Evgeny Mortikov (Lomonosov Moscow State University)\ nWe discuss the development of the unified framework for the numerical sim ulation of the atmospheric boundary layer turbulence. The model developed at the Lomonosov Moscow State University combines DNS (Direct Numerical Si mulation)\, LES (Large-Eddy Simulation) and RANS (Reynolds-Averaged Navier -Stokes) approaches for turbulence modelling and allows high-resolution si mulations on HPC systems by using MPI\, OpenMP and CUDA. The code is struc tured in a such way as to separate the solution of high-level “numerical ” and “physical” problems from the code related to parallelization o r low-level algorithm optimization highly dependent on the computational a rchitecture. The principal advantage of such separation is the ability to tune the code for different architectures without modifying the high-level and problem specific part of the code. The efficiency of the model implem entation and the challenges of using heterogeneous architecture of modern HPC are discussed. A particular emphasis is placed on the code optimizatio ns relevant for problems of aerosol and chemistry transport in urban envir onment. We show how the DNS- and LES- simulations may be used to improve current boundary-layer processes parameterizations used in Earth system mo dels.\n\nhttps://events.chpc.ac.za/event/125/contributions/1912/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1912/ END:VEVENT BEGIN:VEVENT SUMMARY:® The Development of An Adaptive Mesh Atmospheric Model - Fluidit y-Atmosphere DTSTART;VALUE=DATE-TIME:20231206T091500Z DTEND;VALUE=DATE-TIME:20231206T093000Z DTSTAMP;VALUE=DATE-TIME:20260520T005132Z UID:indico-contribution-616-1911@events.chpc.ac.za DESCRIPTION:Speakers: Jinxi Li ()\nThis study presents the development of a three-dimensional unstructured adaptive finite-element model (Fluidity-A tmosphere) for atmospheric research. To improve the computational efficien cy\, a LSTM-based three-dimensional unstructured mesh generator is propose d to predict the evolution of the adaptive mesh. To evaluate the performan ce of adaptive meshes and physical parameterisations in Fluidity-Atmospher e\, a series of idealized test cases have been setup and the unstructured tetrahedral meshes are adapted automatically with the specified fields in time and space.\n\nhttps://events.chpc.ac.za/event/125/contributions/1911/ LOCATION:Skukuza 1-1-2 - Ndau URL:https://events.chpc.ac.za/event/125/contributions/1911/ END:VEVENT END:VCALENDAR