CS140 Assignment 1: Research a Parallel Language
Due January 10, 2011 Problem
Ever since the first parallel computers were built in the 1980s, people have invented new programming languages (and extensions of old programming languages) for them. There's a
January 21, 2011
Administrivia
Expectations and Confidence
Homework #1 Homework #2 Moving forward Read the materials provided. If you need help come work with me!
Hw1 MPI Communication
void powerMethod(int dims[2], double* splitA, double* x, int my_rank
+
Game of Life!
February 11, 2011
+ Administrivia
Midterms Soon Hw4 Soon Watch Jeopardy!
+ Today
Talk about the basic concepts behind the game of life. Look at the Matlab code to get some ideas. Discuss possible parallelization strategies. What the he
CS 140 Assignment 4:
Cilkified Inner Products
Assigned January 31, 2011
Due by 11:59 pm Monday, February 7
The purpose of this assignment is to gain familiarity with Cilk+ constructs and tools, as well as to think about different ways of parallelizing an
Triton Shared Compute Cluster
(TSCC) Quick Start
Burak Himmetoglu
Supercomputing Consultant
Enterprise Technology Services &
Center for Scientific Computing
University of California
Santa Barbara
e-mail: [email protected]
General Information
Performanc
Complexity Measures
for
Parallel Computation
Complexity Measures for Parallel Computation
Problem parameters:
n index of problem size
p number of processors
Algorithm parameters:
tp running time on p processors
t1 time on 1 processor = sequential time
Floating-Point vs. Graphs, November 2016
38 Terateps
93 Petaflops
P A
=
L
x
U
1
2
4
7
3
93 Peta / 38 Tera is about 2400.
1
6
5
Floating-Point vs. Graphs, November 2016
38 Terateps
93 Petaflops
P A
=
L
x
U
1
2
4
7
3
6
Nov 2016: 93 Peta / 38 Tera
~ 2,400
No
CS 140 : Feb 6, 2017
Multicore (and Shared Memory)
Programming with Cilk Plus
Multicore and shared memory
Cilk Plus and the divide & conquer paradigm
Data races
Analyzing performance in Cilk Plus
Thanks to Charles E. Leiserson for some of these slides
1
M
CS 140 : Feb 8, 2017
Cilk Scheduling & Applications
Analyzing quicksort
Optional: Master method for solving
divide-and-conquer recurrences
Tips on parallelism and overheads
Greedy scheduling and parallel slackness
Cilk runtime
Thanks to Charles E. Le
www.cilk.com
How to Survive the Multicore Software Revolution (or at Least Survive the Hype)
CharlesE.Leiserson IlyaB.Mirman
Pagei
www.cilk.com
Contents
Preface. iv 1. TheEmergenceofMulticoreSoftware. 1 Thefreelunchisover. 1 Themulticoresoftwaretria
CS 140 : Jan 31 Feb 7, 2011 Multicore (and Shared Memory) Programming with Cilk+
Multicore and NUMA architectures Multithreaded Programming Cilk+ as a concurrency platform Divide and conquer paradigm for Cilk+
Thanks to Charles E. Leiserson for some of t
CS 140 Assignment 2: Matrix-Vector Multiplication and the Power Method
Assigned January 10, 2011 Due by 11:59 pm Wednesday, January 19
This assignment is to write a parallel program to multiply a matrix by a vector, and to use this routine in an implement
CS 140 Assignment 3: Simulating the N-body Problem
Assigned January 19, 2010 Due by 11:59 pm Monday, January 31
This assignment is to write an MPI program to simulate a large number of astronomical bodies (stars and planets) moving under the inuence of gr
CS 140 Assignment 4:
Cilkified Inner Products
Assigned January 31, 2011
Due by 11:59 pm Monday, February 7
The purpose of this assignment is to gain familiarity with Cilk+ constructs and tools, as well as to think about different ways of parallelizing an
CS 140 Assignment 5: Life in the Fast Lane
Assigned February 7, 2010 Due by 11:59 pm Friday, February 18
The object of this problem is to implement a cellular automaton called the Game of Life in Cilk+, and to tune it to get maximum performance. The progr
CS 140 Midterm 1 - 8 February 2010 Name Perm#
Problem 1 [20 points total] In Lake Wobegon, all the women are strong, all the men are goodlooking, and all the children are above average. Well, everyone cant be above average-but here well count how many are
Complexity Measures for Parallel Computation
Several possible models! Several
Execution time and parallelism: Work / Span Model Total cost of moving data: Communication Volume Model Detailed models that try to capture time for moving data: Latency / Band
CS 140 : Matrix multiplication CS
Matrix multiplication I : parallel issues Matrix multiplication II: cache issues
Thanks to Jim Demmel and Kathy Yelick (UCB) for some of these slides
Communication volume model Communication
Network of p processors
Eac
CS 140 : Matrix multiplication
Warmup: Matrix times vector: communication volume
Matrix multiplication I : parallel issues
Matrix multiplication II: cache issues
Thanks to Jim Demmel and Kathy Yelick (UCB) for some of these slides
Matrix-Matrix Multipl