Title Member Names Put your group members name
Title Member Names Put your group member’s name here, click on View -> Master -> Slide Master. ECE 408/CS 483, University of Illinois, Urbana-Champaign
Give an overview of your design; include the final flow charts of your algorithms, and discuss how parallelism is exploited in them. DESIGN OVERVIEW Put your group member’s name here, click on View -> Master -> Slide Master. ECE 408/CS 483, University of Illinois, Urbana-Champaign
Describe in more detail the kernels and functions you created. Trace the data flow through each kernel, describing any data marshaling where applicable. IMPLEMENTATION Put your group member’s name here, click on View -> Master -> Slide Master. ECE 408/CS 483, University of Illinois, Urbana-Champaign
What is your testing procedure to make sure your implementation is robust and correct? For cases where the accuracy may be compromised in order to use the single-precision hardware and/or to achieve higher level of parallelism, provide an acceptance test for your output. VERIFICATION Put your group member’s name here, click on View -> Master -> Slide Master. ECE 408/CS 483, University of Illinois, Urbana-Champaign
Did you achieve your performance goals? What went well with CUDA in terms of the performance gained? What hindered performance? Given enough development time, what is the best performance you think you could ultimately achieve with this application on the current generation of GPUs? What are the features in the toolset or hardware that would allow you to increase performance even more? PERFORMANCE Put your group member’s name here, click on View -> Master -> Slide Master. ECE 408/CS 483, University of Illinois, Urbana-Champaign
CONCLUSIONS Put your group member’s name here, click on View -> Master -> Slide Master. ECE 408/CS 483, University of Illinois, Urbana-Champaign
- Slides: 6