OpenMP/CUDA 강의 모음 (슬라이드 & YouTube 링크)

멀티코어프로그래밍 (Multi-core Programming)

* 모든 강의는 YouTube [재생목록]에서 보실 수 있습니다. 

* 강의와 관련된 실습문제 및 해설은 [재생목록]에서 보실 수 있습니다.
* 강의에 사용된 코드들은 [Git repository]에서 받으실 수 있습니다.

* 과목 홈페이지 [link]
* FAQ page [link]
  - notion link로 구버전의 Internet Explorer 에서는 안보일 수 있습니다 (최신 브라우저 권장)

---

Lecture 1. Why Parallel Computing? [slides] [video]

  - What is and Why parallel computing?
  - Why parallel programming?

Lecture 2. Introduction to Parallel Computing [slides] [video]
  - Flynn’s Taxonomy (SIMD and MIMD)
  - Nondeterminism

  - Performance of Parallel Computing

---

Lecture 3. OpenMP Overview [slides] [video]
  - What is OpenMP?
  - Hello OpenMP!

Lecture 4. Introduction to OpenMP (1/3) [slides]
  - Parallel construct [Video]

  - Work-sharing construct [Video]
  - Scope of variables [Video]

Lecture 5. Introduction to OpenMP (2/3) [slides]

  - Barrier [Video]
  - Crtical section [Video]
  - Locking [Video]

Lecture 6. Introduction to OpenMP (3/3) [slides]
  - Reduction clause [Video]
  - Scheduling clauses [Video]
  - Nested parallelism [Video]

 

---

Lecture 7. Introduction to GPGPU/CUDA [slides] [video 1][video 2]
  - Heterogeneous Parallel Computing with CUDA

Lecture 8. [CUDA] Thread and Execution Model [slides]
  - Hello CUDA! [Video]
  - The basic workflow of CUDA Program [Video]
  - CUDA Thread Hierarchy [Video]
  - Organizing threads [Video]
  - CUDA Execution Model [Video]

Lecture 9. CUDA Memory Model [slides]
  - CUDA memory hierarchy [Video]

  - Memory model & Performance [Video]

  - Using shared memory [Video1] [Video2]

Lecture 10. Maximizing Memory Throughput [slides]
  - for Global memory [Video]

  - for Shared memory [Video]

Lecture 11. Synchronization & Concurrent execution [slides]
  - Synchronization [Video]
  - CUDA stream & Concurrent execution [Video]
  - CUDA Event [Video]

Lecture 12. Get More Power! [slides]
  - Multi-GPUs [Video]
  - Heterogeneous Computing [Video]

---

CUDA 학습자를 위한 도서를 출판하였습니다.
교재가 필요하신 분들은 [도서링크]를 참고하세요.