Sökning: "högprestandaberäkningar"

Hittade 5 uppsatser innehållade ordet högprestandaberäkningar.

1. 1. Using GPU-aware message passing to accelerate high-fidelity fluid simulations

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

   Författare :Jacob Wahlgren; [2022]
   Nyckelord :high-performance computing; computational fluid dynamics; spectral element method; graphical processing units; message passing interface; högprestandaberäkningar; beräkningsströmningsdynamik; spektralelementmetoden; grafikprocessorer; meddelandeförmedlingsgränssnitt;

   Sammanfattning : Motivated by the end of Moore’s law, graphics processing units (GPUs) are replacing general-purpose processors as the main source of computational power in emerging supercomputing architectures. A challenge in systems with GPU accelerators is the cost of transferring data between the host memory and the GPU device memory. LÄS MER

3. 2. An Evaluation of TensorFlow as a Programming Framework for HPC Applications

   Master-uppsats, KTH/Beräkningsvetenskap och beräkningsteknik (CST); KTH/Parallelldatorcentrum, PDC

   Författare :Wei Der Chien; [2018]
   Nyckelord :HPC; GPU; TensorFlow;

   Sammanfattning : In recent years, deep-learning, a branch of machine learning gained increasing popularity due to their extensive applications and performance. At the core of these application is dense matrix-matrix multiplication. Graphics Processing Units (GPUs) are commonly used in the training process due to their massively parallel computation capabilities. LÄS MER

4. 3. Record Types in Scala: Design and Evaluation

   Master-uppsats, KTH/Skolan för datavetenskap och kommunikation (CSC)

   Författare :Olof Karlsson; [2017]
   Nyckelord :Records; Types; Scala; Programming Languages;

   Sammanfattning : A record type is a data type consisting of a collection of named fields that combines the flexibility of associative arrays in some dynamically typed languages with the safety guarantees and possible runtime performance of static typing. The structural typing of records is especially suitable for handling semi-structured data such as JSON and XML making efficient records an attractive choice for high-performance computing and large- scale data analytics. LÄS MER

5. 4. Disc : Approximative Nearest Neighbor Search using Ellipsoids for Photon Mapping on GPUs

   Kandidat-uppsats, KTH/Skolan för datavetenskap och kommunikation (CSC)

   Författare :Marcus Bergholm; Viktor Kronvall; [2016]
   Nyckelord :photon mapping; k-nearest neighbors; ellipsoid; gpu; parallel;

   Sammanfattning : Recent development in Graphics Processing Units (GPUs) has enabled inexpensive high-performance computing for general-purpose applications. The K-Nearest Neighbors problem is widely used in applications ranging from classification to gathering of photons in the Photon Mapping algorithm. LÄS MER

7. 5. Scalable Computation of Long-Range Potentialsfor Molecular Dynamics

   Master-uppsats, KTH/Numerisk analys, NA

   Författare :Christoph Rachinger; [2013]
   Nyckelord :;

   Sammanfattning : To calculate long-range potentials in a molecular dynamics simulation, a naive approach using direct particle interactions needs a computational work of order O(N2). This is infeasible for larger simulations. LÄS MER