WEP522: The Evolution of the Universe in a Computer: A Walk through the World of Supercomputers
What can computer simulations show us about the creation of our universe? This lecture will describe the steps towards the creation of self-consistent computer simulations of the evolution of the universe, from soon after the Big Bang to the formation of realistic stellar systems like the Milky Way.
Creating simulations of this complexity is a multi-scale problem of vast proportions. The first step has been the Millennium Simulation, one of the largest and most successful numerical simulations of the Universe ever carried out. Now we are in the midst of the next step, where this is carried to a much higher level of physical fidelity on the latest supercomputing platforms.
Overall, this will illustrate how the role of mathematics is essential in this endeavor, using demonstrations of computer simulations produced in collaboration with Volker Springel.
The talk will be preceded by a brief history of the role of supercomputers in enhancing progress in mathematics. Moving through the exciting history of supercomputing, we will touch upon the top supercomputers of its time and its important applications. This will be followed by a stimulating story about a supercomputer simulation that has proven the validity of a theory that was proposed 40 years ago: simulating the evolution of the universe.
|WEP735: Emerging programming models in high performance computing and big data analytics||
Most HPC current systems are clusters of shared memory nodes. Such SMP nodes can be small multi-core CPUs up to large many-core CPUs. Parallel programming of such systems will require knowledge in shared memory parallelization inside of each node using OpenMP and the distributed memory parallelization across multiple nodes connected with a high-speed network; using message passing (MPI).
Lately, the largest supercomputing systems became heterogeneous where nodes are built from multi-core processors and accelerators such as NVIDIA GPUs and Intel Xeon Phi, providing an aggregate node performance of more than one TeraFlop/s. This tremendous computational power can only be efficiently and easily utilized with the appropriate programming models such as OpenACC.
Furthermore, with the tremendous increase in compute power of supercomputers in addition to other electronic devices, there has been lately an increased emphasis on big data and data analytics. Among the big data technologies you'll need to know are the Apache Software Foundations' Java-based Hadoop programming framework that can run applications on systems with thousands of nodes; and the MapReduce software framework, which consists of a Map function that distributes work to different nodes and a Reduce function that gathers results and resolves them into a single value.
This brief history enables attendees to absorb the role of supercomputers in enhancing the science of mathematics.
The first part thoroughly addresses all the related aspects of supercomputing.
In the second part, several applications of supercomputing are explored. The first application is a supercomputer simulation that has proven the validity of a theory that was proposed 40 years ago for the evolution of the universe. A second application considers wave propagation through solids. Computing this is important in understanding many areas, such as earthquake wave propagation and finding oil.
The Mystery of Pi in the Pyramids
|This lecture sheds light on the most notable wonders of the great Egyptian Pyramids over time. The topic will be approached historically, scientifically and philosophically, and will be followed by a consideration of the latest theories in this field. The major emphasis will be on the mysterious numerical connections found in these works with the digital Pi and how nowadays supercomputers are racing to break the latest records in terms of Pi calculations.|
|WEP068: Steps to the Supercomputer World||This is a brief history that enables attendees to absorb the role of supercomputers in enhancing the Science of Math.|
|WEP233: Hybrid Computing at KAUST||
This course cover the following topics :