Registration - room E3 at KTH Main campus Room: E3 at KTH Main campus

Welcome to PDC and the Summer School

• Erwin Laure (PDC-HPC)

Room: E3

High-Performance Computer Architecture

• Erik Hagersten

Room: E3

High-Performance Computer Architecture

• Erik Hagersten

Room: E3

High-Performance Computer Architecture

• Erik Hagersten

Room: E3

Concepts and Algorithms for Scientific Computing

• Michael Hanke

Room: E3 In this talk we will present of what Scientific Computing is and what the challenges are. In particular, we will discuss the "simulation pipeline". The present and future of Scientific Computing is massively parallel. Consequences for modelling and examples for algorithm contruction for scalable computing are given.

Concepts and Algorithms for Scientific Computing

• Michael Hanke

Room: E3

Introduction to PDC's Environment Room: E3

Shared memory programming, OpenMP

• Christoph Kessler

Room: E3 Two common ways of speeding up programs are to use processes or threads executing in parallel. The second week of the Summer School presents process-based parallel computing using MPI. In this lecture parallelization using threads will be discussed. Threads can be managed in different ways, e.g. using a low level library, like the POSIX threads library. The lecture deals with OpenMP, which is a more convenient way to use threads. OpenMP is a specification for a set of compiler directives, library routines, and environment variables that can be used to specify shared memory parallelism in Fortran and C/C++ programs. The threaded program can be executed on a shared memory computer (e.g. a multi- core processor). Typically, the iterations of a time consuming loop are shared among a team of threads, each thread working on part of the iterations. The loop is parallelized by writing a directive in the code and a compiler or a pre- processor will generate parallel code. Using short code examples, the lecture covers the most important OpenMP-constructs, how to use them and how not to use them. A few more realistic examples are presented as well.

Shared memory programming, OpenMP

• Christoph Kessler

Room: E3

Shared memory programming, OpenMP

• Christoph Kessler

Room: E3

Lab: Programming Exercises on OpenMP

• Stefano Markidis
• Niclas Jansson (CSC/NA)

Room: Röd and Ora Lab-rooms

Lab: Programming Exercises on OpenMP

• Stefano Markidis
• Niclas Jansson (CSC/NA)

Room: Röd and Ora Lab-rooms

Shared memory programming, OpenMP

• Christoph Kessler

Room: E3

Shared memory programming, OpenMP

• Christoph Kessler

Room: E3

Lab: OpenMP Advanced Project

• Stefano Markidis
• Niclas Jansson (CSC/NA)

Room: Röd and Ora Lab-rooms

Lab: OpenMP Advanced Project

• Stefano Markidis
• Niclas Jansson (CSC/NA)

Room: Röd and Ora Lab-rooms

GPU Architectures

• Szilard Pall

Room: E3

Introduction to CUDA Room: E3

Lab: CUDA

• Szilard Pall

Room: Röd and Ora Lab-rooms

Lab: CUDA

• Szilard Pall

Room: Röd and Ora Lab-rooms

Wrap up: GPU Programming

• Szilard Pall

Room: E3

MPI: Introduction, Basic Concepts, Point-to-Point Communication

• Erwin Laure (PDC-HPC)

Room: E3

MPI - Point-to-Point Communication

• Erwin Laure (PDC-HPC)

Room: E3

Lab: MPI Part 1 Room: Röd and Ora Lab-rooms

Lab: MPI Part 1 Room: Röd and Ora Lab-rooms

MPI - Collective Communication

• Erwin Laure (PDC-HPC)

Room: E3

MPI - Intermediate MPI

• Erwin Laure (PDC-HPC)

Room: E3

Lab: MPI Part 2 Room: Röd and Ora Lab-rooms

Performance Engineering

• Pekka Manninen

Room: E3

Performance Engineering

• Pekka Manninen

Room: E3

Lab: Performance Engineering Room: Röd and Ora Lab-rooms

Lab: Performance Engineering Room: Röd and Ora Lab-rooms

Wrap up: Performance Engineering

• Pekka Manninen

Room: E3

MPI: Advanced Concepts

• Erwin Laure (PDC-HPC)

Room: E3

MPI: Advanced Concepts

• Erwin Laure (PDC-HPC)

Room: E3

Case Study: Energy Efficiency in Scientific Computing

• Enrique Quintana Ortí

Room: E3 Energy consumption is a crucial challenge that the high performance computing community will have to face to efficiently leverage the Exascale systems that will be available at the end of this decade. In this talk we will motivate the roots of the power wall, and introduce a "recipe" of measures that are being implemented in hardware as well as scientific applications in order to reduce energy consumption: 1) Selection of energy efficient hardware 2) Dynamic voltage-frequency scaling 3) Dynamic concurrency throttling 4) Suppression of polling 5) Approximate computing 6) Near threshold voltage computing 7) Use of energy proportional hardware 8) Virtualization of computational resources

Lab: MPI Part 3

The Future of Computing - Towards the Post Moore’s Law Era

• Stefano Markidis

Room: E3 This lecture presents the Moore's law and discusses its future focusing on future emerging technologies in computing.

The Future of Computing - Towards the Post Moore’s Law Era

• Stefano Markidis

Room: E3

Case Study: State of the Art Parallel Computing enables new Science breakthroughs

• Alison Lowndes (Nvidia)

Room: E3 NVIDIAs Alison Lowndes will provide an overview of NVIDIA's latest hardware and software offering and how this enables discovery and insight via parallel scientific visual computing. She will also cover recent progress in algorithms and papers that should be of great interest Alison Lowndes Deep Learning Solutions Architect & Community Manager EMEA| NVIDIA (UK) Recent mature graduate in Artificial Intelligence (University of Leeds), combining technical and theoretical computer science with a physics background. Completed a thorough empirical study of deep learning, specifically with GPU technology, covering the entire history and technical aspects of GPGPU with underlying mathematics. After 25+ years in international project management and entrepreneurship, Alison now manages the Deep Learning and AI developer community across EMEAI and advises on a wide range of applications of deep learning.

Course Evaluation Room: E3 In class course evaluation

Open Lab and Project Work Room: Röd and Ora Lab-rooms