1 / 9

Parallel Algorithms: Morph

Parallel Algorithms: Morph. Robert Vitolo CS474. WHAT IT DOES. The Morph program is designed to take two singular images and blend them together in a manner where both images appear increasingly translucent.

lali
Download Presentation

Parallel Algorithms: Morph

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Parallel Algorithms:Morph Robert Vitolo CS474

  2. WHAT IT DOES The Morph program is designed to take two singular images and blend them together in a manner where both images appear increasingly translucent. These images are layered on top of one another, allowing each to be displayed simultaneously.

  3. EXAMPLE: Ayers Rock

  4. EXAMPLE: Bricks

  5. EXAMPLE: Morphed Image

  6. HOW IT WORKS Manipulates the RGB values of corresponding pairs of pixels (those that occupy the same general position) in the two images, gradually changing the RGB values of one to match that of the other image and refreshing the image with each pass.

  7. SEQUENTIAL versus PARALLEL • Sequential: • Performs the algorithm in a linear fashion, transforming each pair of points in the image, one after the next • Parallel: • Uses the same basic code, but utilizes a Parallel.For loop, enabling the processing of multiple pairs of points at a time

  8. SPEED-UP • Sequential Processing Time: 11,000 ms • Parallel (2 Cores): 10,000 ms • Speedup factor: 1.1x • Parallel (4 Cores): 6,100 ms • Speedup Factor: 1.8x • Parallel (8 Cores): 4,900 ms • Speedup Factor: 2.24x

  9. SPEED-UP • Suboptimal speedup, possible reasons? • Only a small part of the algorithm is parallelized • File I/O takes up a significant amount of time • Implications • Major potential for improvements in CPU and time intensive tasks, such as video encoding speed and filter processing through utilization of multiple cores.

More Related