Programming Massively Parallel Processors with CUDA

Michael Garland, of NVIDIA Research, discusses sorting methods in order to make searching, categorization, and building of data structures in parallel easier. (April 20, 2010)

15. Optimizing Parallel GPU Performance (May 20, 2010)

Jun 9th, 2010 4s

John Nicholis discusses how to optimize with Parallel GPU Performance. (May 20, 2010)

14. Path Planning System on the GPU (May 18, 2010)

Jun 9th, 2010 3s

Avi Bleiweiss delivers a lecture on the path planning system on the GPU. (May 18, 2010)

6. Parallel Patterns I (April 15, 2010)

May 27th, 2010 2s

Students are taught how to effectively program massively parallel processors using the CUDA C programming language. Students also develop familiarity with the language itself and are exposed to the architecture of modern GPUs. (April 15, 2010)

12. NVIDIA OptiX: Ray Tracing on the GPU (May 11, 2010)

May 26th, 2010 4s

Steven Parker, Director of High Performance Computing and Computational Graphics at NVIDIA, speaks about ray tracing. (May 11, 2010)

13. Future of Throughput (May 13, 2010)

May 26th, 2010 4s

William Dally guest-lectures on the end of denial architecture and the rise of throughput computing. (May 13, 2010)

11. The Fermi Architecture (May 6, 2010)

May 17th, 2010 4s

Michael C Shebanow, Principal Research Scientist with NVIDIA Research, talks about the new Fermi architecture. This next generation CUDA architecture, code named "Fermi" is the most advanced GPU computing architecture ever built. (May 6, 2010)

10. Solving Partial Differential Equations with CUDA (May 4, 2010)

May 17th, 2010 3s

Jonathan Cohen, a Senior Research Scientist at NVIDIA Research, talks about solving partial differential equations with CUDA. (May 4, 2010)

9. Sparse Matrix Vector Operations (April 29, 2010)

May 17th, 2010 2s

Nathan Bell from NVIDIA Research talks about sparse matrix-vector multiplication on throughput-oriented processors. (April 29, 2010)

8. Introduction to Thrust (April 27, 2010)

May 17th, 2010 2s

Nathan Bell of NVIDIA Research talks about Thrust, a productivity library for CUDA. (April 27, 2010)

7. Parallel Patterns II (April 22, 2010)

May 17th, 2010 2s

David Tarjan continues his discussion on parallel patterns. (April 22, 2010)

5. Performance Considerations (April 13, 2010)

Apr 21st, 2010 3s

Lukas Biewald of Delores Labs, discusses performance considerations including: memory coalescing, shared memory bank conflicts, control-flow divergence, occupancy, and kernel launch overheads. (April 13, 2010)

4. CUDA Memories (April 8, 2010)

Apr 21st, 2010 3s

Jared Hoberock of NVIDIA lectures on CUDA memory spaces for CS 193G: Programming Massively Parallel Processors. (April 8, 2010)

3. CUDA Threads & Atomics (April 6, 2010)

Apr 15th, 2010 2s

Atomic operations in CUDA and the associated hardware are discussed. (April 6, 2010)

2. Introduction to CUDA (April 1, 2010)

Apr 14th, 2010 4s

science, technology, computer science, CS, software engineering, programming, parallel processors, CUDA, language, code, Computers, coding, MP0, MP1, hardware, software, memory management, GPU, CPU, memory, parallel code, kernel, threads, launc