1. J.M.H.M Jayamaha
SEU/IS/10/PS/104
PS0372

2.  What is Parallel Algorithm
 What is Linear Algebra
 Dense Matrix Algorithms
◦ Matrix-Vector Multiplication
 Solving a System of Linear Equations
◦ A Simple Gaussian Elimination Algorithm
 Parallel Implementation with 1-D Partitioning

3.  In computer science, a parallel algorithm, as
opposed to a traditional serial algorithm, is
an algorithm which can be executed a piece
at a time on many different processing
devices, and then combined together again at
the end to get the correct result.
(wikipedia.org)

4.  Linear algebra is the branch of mathematics
concerning vector spaces and linear
mappings between such spaces. It includes
the study of lines, planes, and subspaces, but
is also concerned with properties common to
all vector spaces.

5.  dense or full matrices that have no or few
known usable zero entries.
 In numerical analysis, a sparse matrix is
a matrix in which most of the elements are
zero

6.  This slide addresses the problem of multiplying a dense
n x n matrix A with an n x 1 vector x to yield the n x 1
result vector y.
 serial algorithm for this problem
◦ 1. procedure MAT_VECT ( A, x, y)
◦ 2. begin
◦ 3. for i := 0 to n - 1 do
◦ 4. begin
◦ 5. y[i]:=0;
◦ 6. for j := 0 to n - 1 do
◦ 7. y[i] := y[i] + A[i, j] x x[j];
◦ 8. endfor;
◦ 9. end MAT_VECT

7.  The sequential algorithm requires n2
multiplications and additions. Assuming that a
multiplication and addition pair takes unit time, the
sequential run time is
W = n2
 At least three distinct parallel formulations of
matrix-vector multiplication are possible,
depending on whether rowwise 1-D, columnwise
1-D, or a 2-D partitioning is used.

8.  This slide details the parallel algorithm for matrix-
vector multiplication using rowwise block 1-D
partitioning. The parallel algorithm for columnwise
block 1-D partitioning is similar and has a similar
expression for parallel run time
 Next Figure shows the Multiplication of an n x n
matrix with an n x 1 vector using rowwise block 1-
D partitioning. For the one-row-per-process case,
p = n

10.  First, consider the case in which the n x n matrix is
partitioned among n processes so that each process
stores one complete row of the matrix.
 Figure (a) Process Pi initially owns x[i] and A[i, 0], A[i, 1],
..., A[i, n-1] and is responsible for computing y[i].
 Vector x is multiplied with each row of the matrix
(Algorithm); hence, every process needs the entire
vector.
 Since each process starts with only one element of x, an
all-to-all broadcast is required to distribute all the
elements to all the processes

11.  This section discusses the problem of solving a system
of linear equations of the form
 In matrix notation, this system is written as Ax = b
 Here A is a dense n x n matrix of coefficients such that
A [i , j ] = ai , j , b is an n x 1 vector [b 0 , b 1 , ..., bn -1 ]T
,and x is the desired solution vector [x 0 , x 1 , ..., xn -1 ]T

12.  A system of equations Ax = b is usually solved in two
stages. First, through a series of algebraic
manipulations, the original system of equations is
reduced to an upper-triangular system of the form
 We write this as Ux = y , where U is a unit upper-
triangular matrix – one in which all sub diagonal entries
are zero and all principal diagonal entries are equal to
one.

13.  A serial Gaussian elimination algorithm that converts
the system of linear equations Ax = b to a unit upper-
triangular system Ux = y . The matrix U occupies the
upper-triangular locations of A . This algorithm
assumes that A [k , k ] ≠ 0 when it is used as a divisor
on lines 6 and 7.
 The serial Gaussian elimination algorithm has three
nested loops.
 Several variations of the algorithm exist, depending on
the order in which the loops are arranged

14.  Algorithm shows one variation of Gaussian elimination
◦ 1. procedure GAUSSIAN_ELIMINATION (A, b, y)
◦ 2. begin
◦ 3. for k := 0 to n - 1 do /* Outer loop */
◦ 4. begin
◦ 5. for j := k + 1 to n - 1 do
◦ 6. A[k, j] := A[k, j]/A[k, k]; /* Division step */
◦ 7. y[k] := b[k]/A[k, k];
◦ 8. A[k, k] := 1;
◦ 9. for i := k + 1 to n - 1 do
◦ 10. begin
◦ 11. for j := k + 1 to n - 1 do
◦ 12. A[i, j] := A[i, j] - A[i, k] x A[k,
j]; /* Elimination step */
◦ 13. b[i] := b[i] - A[i, k] x y[k];
◦ 14. A[i, k] := 0;
◦ 15. endfor; /* Line 9 */
◦ 16. endfor; /* Line 3 */
◦ 17. end GAUSSIAN_ELIMINATION

15.  For k varying from 0 to n - 1, the Gaussian elimination
procedure systematically eliminates variable x [k ] from
equations k + 1 to n - 1 so that the matrix of
coefficients becomes upper triangular.
 As shown in Algorithm , in the k th iteration of the
outer loop (starting on line 3), an appropriate multiple
of the k th equation is subtracted from each of the
equations k + 1 to n- 1 (loop starting on line 9).
 The multiples of the k th equation (or the k th row of
matrix A ) are chosen such that the k th coefficient
becomes zero in equations k + 1 to n - 1 eliminating x
[k ] from these equations.

16.  A typical computation in Gaussian elimination
 The k th iteration of the outer loop does not involve any
computation on rows 1 to k - 1 or columns 1 to k - 1.
Thus, at this stage, only the lower-right (n - k ) x (n - k
) sub-matrix of A (the shaded portion in Figure) is
computationally active.

17.  Gaussian elimination involves approximately n 2 /2
divisions (line 6) and approximately (n 3 /3) - (n 2 /2)
subtractions and multiplications (line 12).
 we assume that each scalar arithmetic operation takes
unit time. With this assumption, the sequential run time
of the procedure is approximately 2n 3 /3 (for large n );

18.  We now consider a parallel implementation of Algorithm
, in which the coefficient matrix is rowwise 1-D
partitioned among the processes.
 A parallel implementation of this algorithm with
columnwise 1-D partitioning is very similar.
 We first consider the case in which one row is assigned
to each process, and the n x n coefficient matrix A is
partitioned along the rows among n processes labeled
from P0 to Pn -1

19.  Gaussian elimination steps during the iteration
corresponding to k = 3 for an 8 x 8 matrix partitioned
rowwise among eight processes.

20.  Algorithm show that A [k , k + 1], A [k , k + 2], ..., A [k ,
n - 1] are divided by A [k , k ] (line 6) at the beginning
of the k th iteration. All matrix elements participating in
this operation (shown by the shaded portion of the
matrix in Figure (a) ) belong to the same process.

21.  In the second computation step of the algorithm (the
elimination step of line 12), the modified (after division)
elements of the k th row are used by all other rows of
the active part of the matrix
 As Figure (b) shows, this requires a one-to-all
broadcast of the active part of the k th row to the
processes storing rows k + 1 to n - 1.
 Finally, the computation A [i , j ] := A [i , j ] - A [i , k ] x
A [k , j ] takes place in the remaining active portion of
the matrix, which is shown shaded in Figure (c) .

22.  The computation step corresponding to Figure (a) in the
k th iteration requires n - k – 1 divisions at process Pk
 Similarly, the computation step of Figure (c) involves
n - k – 1 multiplications and subtractions in the k th
iteration at all processes Pi , such that k < i < n .
Assuming a single arithmetic operation takes unit time,
the total time spent in computation in the k th iteration
is 3(n - k - 1).
 Figures (a) and (c) in this parallel implementation of
Gaussian elimination is,
which is equal to 3n (n - 1)/2.

23.  The communication step of Figure (b) takes time
(ts +tw (n -k -1)) log n
 the total communication time
 This cost is asymptotically higher than the sequential
run time of this algorithm. Hence, this parallel
implementation is not cost-optimal.

24.  Introduction to parallel computing second edition by
Ananth Grama, Snshul Gupta , George Karypis, Vipin
Kumar
 https://en.wikipedia.org/wiki/Parallel_algorithm (2015-
11-18)
 https://en.wikipedia.org/wiki/Linear_algebra (2015-
11-18)