2018 High Performance Scientific Computing

Font size  SML

Register update notification mail Add to favorite lecture list
Academic unit or major
Graduate major in Computer Science
Yokota Rio 
Course component(s)
Day/Period(Room No.)
Mon1-2(W831)  Thr1-2(W831)  
Course number
Academic year
Offered quarter
Syllabus updated
Lecture notes updated
Language used
Access Index

Course description and aims

This course will equip students with the necessary knowledge and skills to develop fast algorithms and their massively parallel implementation on modern supercomputers using parallel programming techniques such as SIMD, OpenMP, MPI, and CUDA. The course will cover how to use various linear algebra libraries for parallel execution on both CPUs and GPUs. Tutorials on how to use debuggers and profilers in a massively parallel environment will also be given. Demonstration of performance primitives such as MapReduce and graph partitioning tools will be given, along with tips on how to execute deep learning frameworks on large GPU supercomputers.

Student learning outcomes

By the end of this course, students will be able to
1. Use SIMD vectorization, shared memory parallelization via OpenMP, and distributed memory parallelization via MPI
2. Program GPUs using OpenACC, CUDA, and OpenCL
3. Understand how high performance numerical libraries function, and will be able to use them appropriately
4. Debug and profile code in a parallel environment by using parallel debuggers and profilers
5. Use performance primitives such as ModernGPU and MapReduce to achieve high performance with minimal effort
6. Use graph partitioning tools and deep learning frameworks on massively parallel computers


Vectorization, Shared memory parallelism, Distributed memory parallelism, GPU programming, Numerical libraries, Matrix Multiplication, Linear solvers, FFT, Parallel debugger, Parallel profilers, Graph partitioning, Deep Learning

Competencies that will be developed

Intercultural skills Communication skills Specialist skills Critical thinking skills Practical and/or problem-solving skills
- -

Class flow

From the second lecture, the class will proceed interactively under the assumption that course materials for that week have been read.

Course schedule/Required learning

  Course schedule Required learning
Class 1 How to use TSUBAME Login to Tokyo Tech's supercomputer TSUBAME and learn how to use libraries and the job scheduler
Class 2 Shared memory parallelization Use pthreads and OpenMP to achieve shared memory parallelization
Class 3 Distributed memory parallelization Use MPI to achieve distributed memory parallelization
Class 4 SIMD parallelization Use SSE, AVX, and AVX512 to achieve SIMD vectorization
Class 5 GPU programming Use OpenACC, CUDA, and OpenCL to program GPUs
Class 6 Multi-GPU programming Combine CUDA and MPI to use multiple GPUs on TSUBAME
Class 7 Cache blocking Use BLISLAB and CUBLAS as an example to practice cache blocking
Class 8 Numerical libraries Understand how LAPACK, SCALAPACK, and FFTW work, and learn to use them appropriately
Class 9 Fast linear solvers Understand how to choose the appropriate solvers in PETSc and Trilinos
Class 10 I/O libraries Use NetCDF, HDF5, MPI-IO to read and write on large parallel file systems
Class 11 Parallel debugger Use CUDA-GDB, Valgrind, TotalView to debug parallel code
Class 12 Parallel profiler Use gprof, VTune, PAPI, Tau, Vampire to profile parallel code
Class 13 Performance primitives Learn how to use performance primitives such as ModernGPU and MapReduce
Class 14 Graph partitioning Use METIS and ParMETIS to partition a large graph in parallel
Class 15 Deep Learning Use ChainerMN to train a large neural network on a parallel computer



Reference books, course materials, etc.


Assessment criteria and methods

Evaluation is based on written reports (40%) and final report (60%).

Related courses

  • Numerical Analysis
  • Basic Application of Computing and Mathematical Sciences

Prerequisites (i.e., required knowledge, skills, courses, etc.)


Page Top