Search this site
Embedded Files
Taiwan Math. School
  • Home
  • Programs
    • A-Number Theory and Representation Theory
    • B-Algebraic Geometry
    • C-Differential Geometry and Geometrical Analysis
    • D-Differential Equations and Stochastic Analysis
    • E-Scientific Computing
    • F-Interdisciplinary Studies
  • Course List
    • 2025
      • From Differential Geometry to tt* Geometry-(2)
      • Geometry, Algebra, and Topology with a view towards application and computa
    • 2024
      • Differential Forms in Algebraic Topology
      • Continuum Mechanics
      • From Differential Geometry to tt* Geometry-(1)
      • Normal Approximation and Related Topics
    • 2023
      • Grassmann Algebra
    • 2022
      • Real Analysis (Ⅱ)
      • Analytic Number Theory
      • Geometry and Quantum Field Theory
      • Introduction to Drinfeld Modules and Drinfeld Modular Varieties
      • Machine Learning for PDEs
    • 2021
      • Arithmetic Dynamics for Rational Dominant Self-maps of Projective Varieties
      • Real Analysis (I)
      • Algebraic Combinatorics (I)
      • Continuation Method: Theory and Application
      • Introduction to Riemann Surfaces
      • NTU Math Course
      • Algebraic Number Theory II
      • Complexity and Symbolic Dynamics of Dynamical Systems (Cancelled)
      • Multiscale Analysis of Random Processes (Cancelled)
      • Algebraic Combinatorics II
      • Topics in Geometric Measure Theory (Il)
      • Mathematical Foundation toward Artificial Intelligence in Medicine
    • 2020
      • Statistical Foundations of Medical AI: Survival Analysis
      • Statistical Foundations of Medical AI: Generalized Linear Model
      • Representation Theory: Mini course on Springer Fibers and Quiver Varieties
      • Symbolic Dynamics on Groups and Countable State Topological Markov Shifts
      • Topics in Geometric Measure Theory (I)
      • Statistical Foundations of Medical AI: Linear Regression
      • Algebraic Combinatorics
      • Algebraic Number Theory
      • Imaging Principles in Medical AI
      • Geometric Measure Theory Ⅱ
      • Topics on Drinfeld Modules and T-Motives Ⅱ
      • Dynamics in Network Systems
      • Advanced Course on Multi-Threaded Parallel Programming using OpenMP for Mul
      • Parallel Finite Element Method Using Supercomputer
    • 2019
      • Topics on Drinfeld Modules and T-Motives l
      • Dynamical System: Deterministic and Chaotic Behavior of Model Systems
      • Geometric Measure Theory I
      • 2019 NCTS Summer Course
        • Mathematical Modeling and Analysis of Infectious Diseases
        • MSRI SUMMER SCHOOL ON TORIC VARIETIES
      • Boltzmann Equations
      • Introduction to Machine Learning and Deep Learning with Python
      • Algebraic Surfaces
      • Introduction to Parallel Programming for Multicore/Manycore Clusters
    • 2018
      • Introduction to Automorphic Representations on GL(2)
      • Kinetic Equations and Related Topics
      • 2018 NCTS Summer Course
        • Fluid, Water Wave and Phase Transition Problems
        • Introduction to Parallel Computing (II)
        • Mathematical Modeling and Analysis of Infectious
      • Reaction-Diffusion and Mathematical Sciences
      • Lectures on Lagrangian Floer Theory
      • An Introduction to Geometric Measure Theory
      • Topics in Random Matrix Theory
      • Introduction to Parallel Programming for Multicore/Manycore Clusters
      • Scientific Computing and Machine Learning on Multi- and Manycore Architectu
      • Derived and Homological Algebraic GeometryWinter School
    • 2017
      • High-Performance Numerical Solvers
      • Derived Category in Algebraic Geometry
      • Kinetic Theory and Introduction to Shock Wave Theory​​
  • Media Archive
  • Overseas Opportunities
  • NCTS
Taiwan Math. School

Scientific Computing and Machine Learning on Multi- and Manycore Architectures

9:00 - 17:00, February 11 - 14, 2018

Room 301, Astronomy-Mathematics Building, NTU

Instructor:

Hartwig Anzt (Karlsruher Institut fur Technologie)

Organizers:

Weichung Wang (National Taiwan University)

Background & Purpose:

This course covers the fundamentals of designing and implementing numerical linear algebra operations and algorithms on modern multi- and manycore architectures. New trends in the direction of Machine Learning/ Deep Learning will also be covered. The course bridges between mathematical theory on linear solvers, iteration methods, and preconditioning and programming aspects like MPI, OpenMP and CUDA programming. The course splits into five parts:


Part I will start with an overview about HPC, current trends in high-end computing systems and environments, and continue with an introduction of common architecture designs and programming methodologies.

Part II covers programming techniques for multi- and manycore. Particular we will learn OpenMP and CUDA programming. Besides that, we will look at distributed memory systems and using MPI. A side aspect here is performance modeling and the introduction of tools that allow assessing the efficiency of implementations when running in parallel.

Part III will cover central routines and algorithms needed for scientific computing: BLAS, SpMV, linear solvers based on factorization and inversion routines, Singular Value Decompositions. Also, sparse solvers will be addressed.

Part IV we focus on batched routines as they are becoming increasingly popular and relevant. We look into batched BLAS efforts, hardware-specific optimization efforts, and sophisticated algorithms composed of batched routines.

Part V of the course is devoted to Machine Learning in the widest sense. We will in particular look at the concept of Deep Neural Networks (DNN), available ML libraries, and the performance of convolution kernels.

Part VI contains the presentation of the student projects. Each student chooses a topic in agreement with the lecturer and prepares a presentation along with a project class paper. This project accounts for 60% of the course grade. Although students are encouraged to come up with their own project ideas, a list containing possible topics will be distributed at the beginning of the course.

Each day contains two blocks: one morning block (3 hours) and one afternoon block (2 hours). While the morning block covers the more challenging theoretical background, the afternoon block aims at student involvement by containing practical examples, small exercises, and discussions. The students will have to complete 8 homework assignments covering the distinct topics.

Course Outline

You can also watch it on Youtube !

More Information...

(C) 2021 National Center for Theoretical Sciences 
Google Sites
Report abuse
Google Sites
Report abuse