Skip to content

Booksellers & Trade Customers: Sign up for online bulk buying at trade.atlanticbooks.com for wholesale discounts

Booksellers: Create Account on our B2B Portal for wholesale discounts

GPGPU Computing with OpenCL

by Bernhard Manfred Gruber
Save 13% Save 13%
Current price ₹5,350.00
Original price ₹6,165.00
Original price ₹6,165.00
Original price ₹6,165.00
(-13%)
₹5,350.00
Current price ₹5,350.00

Imported Edition - Ships in 18-21 Days

Free Shipping in India on orders above Rs. 500

Request Bulk Quantity Quote
+91
Book cover type: Paperback
  • ISBN13: 9783656829843
  • Binding: Paperback
  • Subject: N/A
  • Publisher: Grin Verlag
  • Publisher Imprint: Grin Verlag
  • Publication Date:
  • Pages: 132
  • Original Price: USD 62.9
  • Language: English
  • Edition: N/A
  • Item Weight: 336 grams
  • BISAC Subject(s): Languages / General and Programming / General

Bachelor Thesis from the year 2013 in the subject Computer Science - Programming, grade: 1.0, University of Applied Sciences Oberösterreich, Hagenberg, course: Software Engineering, language: English, abstract: This thesis provides an introduction into programming for GPUs using OpenCL. After a historical overview of how graphic cards have evolved, the peculiarities of GPU and CPU hardware are discussed. Based on this knowledge, OpenCL is introduced as an API supporting all kinds of processing hardware. A deeper look into OpenCL's execution and memory model, which allows handling heterogeneous hardware, is rounded off by a simple, yet full example code. The thesis then continues with several implementations of standard algorithms for the GPU. The chosen problems start with matrix multiplication and go along with the all-prefix sum and sorting. As the first problem already offers parallelism naturally, performance analysis and optimization is focused during the first implementation chapter. The all-prefix sum and sorting are both problems being more dicult to split into independent pieces of work. Techniques will be discussed to tackle such kind of problems. Each GPU implementation is benchmarked and compared with one or more traditional CPU approaches. As GPUs and CPUs have different hardware architectures, appropriate algorithms and optimizations have been chosen to solve the problems by exploiting the underlying platform at best.

Trusted for over 49 years

Family Owned Company

Secure Payment

All Major Credit Cards/Debit Cards/UPI & More Accepted

New & Authentic Products

India's Largest Distributor

Need Support?

Whatsapp Us