This talk presents an overview of Morocco's emerging HPC ecosystem, highlighting national initiatives, key infrastructure developments, and the growing collaborations that drive computational research and innovation. A particular focus will be given to Toubkal, Morocco's flagship supercomputer, which represents a major step forward in national computing capacity and supports applications in...
The newly established High-Performance Computing and Big Data Analytics (HPC-BDA) Centre of Excellence at Addis Ababa Science and Technology University (AASTU) represents Ethiopia’s bold entry into the continental cyber-infrastructure landscape, complementing South Africa’s CHPC and NICIS. Anchored in state-of-the-art laboratories spanning Business Analytics, HPC & Cloud Systems,...
computer architecture targetting RAM chips
Highly parallel computation algorithms on structured data can remain
inside the memory chip, removing the need to pass all the data across a
bus to a CPU chip and back.
This can save a great deal of power for very little added complexity of
the RAM chip itself.
As a proof of concept, this computer architecture is implemented inside
an...
The current paradigm in HPC for AI has shifted from simple "data parallelism" to multi-dimensional (3D) parallelism and heterogeneous co-execution. In this talk, we will discuss optimization and placement patterns for training and inference workloads. For Training, we will focus on topology-aware placement that minimizes inter-node communication latency using 3D parallelism. For inference, We...
Water scarcity and non-revenue water remain pressing issues in South Africa, exacerbated by environmental changes. The CSIR's Smart Water and Waste Water Institute (SWWWI), in collaboration with Spectrum Access and Management Innovation (SAMI), proposes an innovative Smart Water Network Management solution to address these challenges. The solution integrates a Dynamic Hydraulic Model (DHM)...
Urban areas across South Africa face increasing pressure to plan for sustainable growth and service delivery amid rapid change. The Urban and Regional Dynamics research group at the CSIR develops city- and provincial-level simulation and decision-support tools to assist planners and policymakers in exploring long-term urban development scenarios. These models integrate spatial, economic, and...
The use of gamification has gained popularity in higher education, which offers a valuable learning experience and improved skills acquisition by incorporating game-based mechanisms such as points, badges, leaderboards, and challenges. The use of gamification in education enhances student engagement and motivation by making learning more interactive and fun, improves learning outcomes,...
This talk is focused on providing an overview of the Artificial Intelligence, Data Science and Natural Language Processing fields. The audience will be given a view of use cases and solutions that are being worked on at CSIR. This will be followed by an overview of the impact that CHPC infrastructure has contributed to our NLP initiatives. Lastly, we will briefly share perspectives to enable...
The session will provide an opportunity for HPC Educators to share their plans, challenges, and ideas for HPC education curricula, tools, and resources with the broader HPC Educator community.
The FAIR principles have become the best practice for sharing artifacts, such as data, with the public. Findable, Accessible, Interoperable, and Reusable each seem straightforward, but as implementation details are worked through many difficult decisions and unclear meanings are revealed. This talk will look at common practices and challenges with implementing these principles when sharing...
Title: Training ML algorithms on resource-constrained devices - a memory/storage perspective
Summray:
Deploying ML/AI algorithms on the edge is necessary for applications (e.g., security and surveillance,
industrial IoT, autonomous vehicles, healthcare use cases, ...) requiring low latency, data privacy or reduced costs. However, most edge devices are not equipped with powerful memory...
Title: Scalable Data Management Techniques for AI workloads
Abstract: The advent of complex AI workflows that involve large learning models (training using data/pipeline/tensor parallelism, retrieval augmented generation, chaining) has prompted the need for scalable system-level building blocks that enable running them efficiently at large scale on high end machines. Of particular interest...
This session is an opportunity for members of the HPC Ecosystems Community and those that identify as associates / affiliates to convene in-person. The session will allow time for members to discuss matters relating to HPC Ecosystems Project as well as broader African HPC and emerging HPC community topics. The 90-minute session will include 60-minutes of prepared talks from members of the...
This presentation will focus on the collaborative, quantitative co-design approach to the deployment of large-scale computing services adopted by the STFC DiRAC HPC Facility in the UK (www.dirac.ac.uk). Over the past 15 years, successive generations of DiRAC services have demonstrated how workflow-centred co-design can maximise the scientific impact of computing investments. The co-design of...
There is a great need to develop computing infrastructure to support the increased application of data science and health informatics across Africa which includes robust data sharing and federated computing, whilst fostering research collaboration. The Global Alliance for Genomics and Health (GA4GH; https://www.ga4gh.org/) aims to promote responsible data sharing standards through the use of...
The proliferation of Artificial Intelligence (AI), data-driven research, and digital transformation has increased the global demand for powerful computing infrastructures capable of processing and analyzing enormous volumes of data. High-Performance Computing (HPC) has emerged as the cornerstone of this evolution, enabling researchers to perform complex simulations, accelerate model training,...
In this session we'll walk through the rapid evolution of the AI workloads, and learn key insights on how next gen Hardware and Software will look like.
The 2019 White Paper on Science, Technology, and Innovation in South Africa
emphasises the core themes of inclusivity, transformation, and partnerships. Following
the introductory discussion with the farmers, it became clear that the majority of them have
an urgent need for up-to-date soil-health data and assistance with managing their crops
in order to maximize their profits. Addressing...
Learning from scientific simulations often relies not on the raw quantities calculated, but instead from derived values. For example, air pressures in a weather simulation in isolation are not as interesting as the air pressure gradient. If the gradients are roughly parallel, you have straight-line winds. If the gradient is rotating around a point, it is a cyclone storm. Other uses, such as...
High-Performance Computing (HPC) systems play a pivotal role in modern scientific research, enabling complex simulations, data analysis, and large-scale modelling across disciplines such as climate science, genomics, physics, and engineering. As these systems grow in scale and sophistication, the efficient scheduling and allocation of computational resources become crucial for ensuring optimal...
As artificial intelligence drives more and more innovation in industry and science with the emergence of Large-Language Models (LLMs), the demand for such computing resources is growing substantially. This development poses major challenges for supercomputing centres around the world, as they need to provide state-of-the-art AI resources while meeting their sustainability goals and...
This talk aims to unpack the rising trend of converging technologies in the HPC, Cloud & AI disciplines of emerging hi-tech. At first the speaker will bring to the audiences attention not only the opportunity for new, technology-driven industrial development, but will argue for the business imperative of adopting, expanding and developing internal capabilities around these technologies....
The complexity of the HPC I/O stack combined with gaps in the state-of-the-art profiling tools creates a barrier that does not help end-users and scientific application developers solve the I/O performance problems they encounter. To bridge this gap, we introduce Dristhi, a multi-source interactive analysis framework that empowers users to visualize I/O traces, identify bottlenecks, and gain a...
