Programming Massively Parallel Processors with CUDA

Programming Massively Parallel Processors with CUDA

Follow Programming Massively Parallel Processors with CUDA
Share on
Copy link to clipboard

Virtually all semiconductor market domains, including PCs, game consoles, mobile handsets, servers, supercomputers, and networks, are converging to concurrent platforms. There are two important reasons for this trend. First, these concurrent processors can potentially offer more effective use of chi…

Stanford University


    • Jun 9, 2010 LATEST EPISODE
    • infrequent NEW EPISODES
    • 58m AVG DURATION
    • 16 EPISODES


    More podcasts from Stanford University

    University Public Worship 2017
    University Public Worship 2017

    infrequent

    University Public Worship 2018 - 2020
    University Public Worship 2018 - 2020

    monthly

    Commencement
    Commencement

    infrequent

    Colonial and Revolutionary America
    Colonial and Revolutionary America

    infrequent

    Stanford A Cappella
    Stanford A Cappella

    infrequent

    Clinical Anatomy Heritage Collection
    Clinical Anatomy Heritage Collection

    infrequent

    Stanford Law
    Stanford Law

    infrequent

    Health Library
    Health Library

    infrequent

    Hasso Plattner Institute of Design
    Hasso Plattner Institute of Design

    infrequent

    Search for episodes from Programming Massively Parallel Processors with CUDA with a specific topic:

    Latest episodes from Programming Massively Parallel Processors with CUDA

    16. Parallel Sorting (April 20, 2010)

    Play Episode Listen Later Jun 9, 2010 66:00


    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)

    parallel sorting michael garland
    15. Optimizing Parallel GPU Performance (May 20, 2010)

    Play Episode Listen Later Jun 9, 2010 74:15


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

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

    Play Episode Listen Later Jun 9, 2010 50:15


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

    planning system gpu
    6. Parallel Patterns I (April 15, 2010)

    Play Episode Listen Later May 27, 2010 37:23


    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)

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

    Play Episode Listen Later May 26, 2010 69:27


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

    director nvidia ray tracing high performance computing optix steven parker
    13. Future of Throughput (May 13, 2010)

    Play Episode Listen Later May 26, 2010 73:13


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

    throughput
    11. The Fermi Architecture (May 6, 2010)

    Play Episode Listen Later May 17, 2010 72:34


    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)

    architecture gpu fermi cuda principal research scientist
    10. Solving Partial Differential Equations with CUDA (May 4, 2010)

    Play Episode Listen Later May 17, 2010 64:46


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

    senior research scientist cuda jonathan cohen partial differential equations
    9. Sparse Matrix Vector Operations (April 29, 2010)

    Play Episode Listen Later May 17, 2010 38:33


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

    matrix operations vector sparse nathan bell
    8. Introduction to Thrust (April 27, 2010)

    Play Episode Listen Later May 17, 2010 44:29


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

    thrust cuda nathan bell
    7. Parallel Patterns II (April 22, 2010)

    Play Episode Listen Later May 17, 2010 41:30


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

    patterns parallel
    5. Performance Considerations (April 13, 2010)

    Play Episode Listen Later Apr 21, 2010 59:46


    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)

    performance considerations
    4. CUDA Memories (April 8, 2010)

    Play Episode Listen Later Apr 21, 2010 57:48


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

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

    Play Episode Listen Later Apr 15, 2010 49:49


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

    atomic threads cuda atomics
    2. Introduction to CUDA (April 1, 2010)

    Play Episode Listen Later Apr 14, 2010 75:40


    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, launch, thread b

    computers cs cpu gpu cuda mp1
    1. Introduction to Massively Parallel Computing (March 30, 2010)

    Play Episode Listen Later Apr 9, 2010 67:34


    Jared Hoberock of NVIDIA gives the introductory lecture to CS 193G: Programming Massively Parallel Processors. (March 30, 2010)

    nvidia massively parallel computing

    Claim Programming Massively Parallel Processors with CUDA

    In order to claim this podcast we'll send an email to with a verification link. Simply click the link and you will be able to edit tags, request a refresh, and other features to take control of your podcast page!

    Claim Cancel