Consolidated Schedule, Fall 2016

The schedule below is tentative and will be tweaked as we go along in the semester. There are five main components (columns): Lectures (and the notes), readings, labs, discussions and weekly assignments. The video of the lectures will be available under Canvas.


Month Day Week Lecture Reading Discussions Labs Assignment
Posted Due
Aug 23 Tue 1 Intro, expectations/logistics (slides) Quinn Ch 3 D00 (groups) L00 (taking notes)    
25 Thu  
30 Tue 2 OpenMP (slides from Quinn) Quinn Ch17 D01 (L01 report) L01 (Measuring & Plotting) PA1 (warmup)
Sept 1 Thu   PA1
6 Tue 3 Sieve of Eratosthenes (slides) Quinn Ch 5 D02 (L02 Report) L02 (Mandelbrot revisited)  
8 Thu  
13 Tue 4 OpenMP Tasks (slides)   D03 (L03 Report) L03 (OpenMP Tasks) PA2 (Sieve)
15 Thu   PA2
20 Tue 5 Caching, Blocking & Locality (slides)
Knapsack DP (slides)
3-C, Roofline
Knapsack
   
22 Thu  
27 Tue 6 Memory-efficient knapsack
Cray Basics
  D04 (L04 Report) L04 (Running PA1 on the Cray)  
29 Thu    
Oct 4 Tue 7 Midterm Review       PA3 (KPDP)  
6 Thu Midterm (in class, no lab)
11 Tue 8 Dependence Analysis
Wavefront Parallelization (slides)
        PA3
13 Thu  
18 Tue 9 MPI Introduction (slides from Quinn)   L05 (MPI basics) PA4 (MPI J2D)
20 Thu   PA4
25 Tue 10        
27 Thu Wavefront parallelization (contd.)  
Nov 1 Tue 11 Intro to GPUs & CUDA (slides )   L06 (GPUs & CUDA) PA5 (CUDA)
3 Thu   PA5
8 Tue 12 Performance and Efficiency Quinn Ch 7 L07 (Plotting and analyzing data)  
10 Thu
15 Tue 13 Wavefront parallelization (contd.)
Back Propagation Learning in CUDA
  L08 (Wavefront Parallelization Exercises) PA6 (BPL)
17 Thu   Report
22 Tue 14 Thanksgiving break (no classes)
24 Thu
29 Tue 15 Sorting Matrix Mult         PA6
Dec 1 Thu  
6 Tue 16 Review        
8 Thu    
12 Mon Final Exam (6:20-8:20 pm)