Amal Gueroudji

• PhD
• PostDoc Position at Argonne National Laboratory

The Workflows Community Summit gathered 111 participants from 18 countries to discuss emerging trends and challenges in scientific workflows, focusing on six key areas: time-sensitive workflows, AI-HPC convergence, multi-facility workflows, heterogeneous HPC environments, user experience, and FAIR computational workflows. The integration of AI and...

High-performance computing (HPC) applications and workflows are increasingly making use of custom data services to complement traditional parallel file systems with fast transient data management capabilities tailored to application specific needs. In the Mochi project we provide methodologies and tools that enable rapid development of custom HPC d...

A widening performance gap is separating CPU performance and IO bandwidth on large-scale systems. In some fields, such as weather forecast and nuclear fusion, numerical models generate such amounts of data that classical post hoc processing is not feasible anymore due to the limits in both storage capacity and IO performance. In situ approaches are...

A widening performance gap is separating CPU performance and IO bandwidth on large scale systems. In some fields such as weather forecast and nuclear fusion, numerical models generate such amounts of data that classical post hoc processing is not feasible anymore due to the limits in both storage capacity and IO performance. In situ approaches are...

Cutting-edge computing systems are getting more and more powerful, and as Ken Batcher stated, “a supercomputer is a device for turning compute-bound problems into I/O-bound problems”. Indeed scientists are writing more complex and accurate models that generate a huge amount of data. In many fields, writing all the generated data to disk is not an o...

Many companies, like Google and Microsft, often rewrite parts of their software using new programming languages because often these companies have to run their software on different architectures. Hardware architectures typically have different characteristics, so the same program can be very efficient on a given backend but less efficient on another. Th...

—Tiramisu is a new polyhedral compiler, that generates very fast code that outperforms highly optimized code written by expert programmers, and targets many hardware architectures (such as multi-cores, GPUs, FPGAs, distributed machines). WewillfocusourworkontheGPUbackendof Tiramisu. Graphic cards or GPUs are increasingly being used for general purp...