Sökning: "GPU Computation"

Visar resultat 6 - 10 av 51 uppsatser innehållade orden GPU Computation.

  1. 6. Integration of a Cycle-approximate Model Into a Cycle-accurate Environment

    Master-uppsats, Lunds universitet/Institutionen för datavetenskap

    Författare :Andreas Hansson; [2021]
    Nyckelord :C ; Modelling; Memory requests; Coroutines; GPU; AXI; Technology and Engineering;

    Sammanfattning : Software models can simulate hardware components to varying degrees of ac- curacy. On the extreme ends, there are purely functional models which have no concept of time and execute requests right away, and cycle-accurate models which capture all the implementation details and clock the time they take. LÄS MER

  3. 7. GPU-Assisted Collision Avoidance for Trajectory Optimization : Parallelization of Lookup Table Computations for Robotic Motion Planners Based on Optimal Control

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Abhiraj Bishnoi; [2021]
    Nyckelord :Motion Planning; Robotics; Trajectory Optimization; GPGPU; Parallel Programming;

    Sammanfattning : One of the biggest challenges associated with optimization based methods forrobotic motion planning is their extreme sensitivity to a good initial guess,especially in the presence of local minima in the cost function landscape.Additional challenges may also arise due to operational constraints, robotcontrollers sometimes have very little time to plan a trajectory to perform adesired function. LÄS MER

  4. 8. Pushing the boundary of Semantic Image Segmentation

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Shipra Jain; [2020]
    Nyckelord :Deep Learning; computer vision; semantic segmentation; metric learning; contrastive learning; Djup lärning; datorsyn; semantisk segmentering; metrisk inlärning; kontrastivt lärande;

    Sammanfattning : The state-of-the-art object detection and image classification methods can perform impressively on more than 9k classes. In contrast, the number of classes in semantic segmentation datasets are fairly limited. This is not surprising , when the restrictions caused by the lack of labeled data and high computation demand are considered. LÄS MER

  5. 9. AES - kryptering med cuda : Skillnader i beräkningshastighet mellan AES-krypteringsmetoderna ECB och CTR vid implementering med Cuda-ramverket.

    Kandidat-uppsats, Jönköping University/JTH, Datateknik och informatik

    Författare :Pontus Vidén; Viktor Henningsson; [2020]
    Nyckelord :GPGPU; CTR; ECB; Cuda; AES; parallellisering; GPGPU-ramverk; processorer; AES-krypteringsmetod; Amazon EC2 P3; AWS;

    Sammanfattning : Purpose – The purpose of this study is partly to illustrate how the AES encryption methods ECB and CTR affect the computational speed when using the GPGPU framework Cuda, but also to clarify the advantages and disadvantages between the different AES encryption modes. Method – A preliminary study was conducted to obtain empirical data on the AES encryption modes ECB and CTR. LÄS MER

  7. 10. Programmable Address Generation Unit for Deep Neural Network Accelerators

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Muhammad Jazib Khan; [2020]
    Nyckelord :Address Generation Unit; Deep Neural Network Accelerators; Very Long Instruction Word; Application Specific Instruction Processor; Hardware-Software Co-design; Adressgenereringsenhet; Deep Neural Network Accelerators; Mycket långt instruktionsord; Applikationsspecifik instruktionsprocessor; Hårdvaruprogramvara Samdesign;

    Sammanfattning : The Convolutional Neural Networks are getting more and more popular due to their applications in revolutionary technologies like Autonomous Driving, Biomedical Imaging, and Natural Language Processing. With this increase in adoption, the complexity of underlying algorithms is also increasing. LÄS MER