Go backward to
nCube Exercises
Go up to
Top
Go forward to
Ring Algorithm
Matrix Multiplication
Row-Column Oriented Algorithm
Load
A
[
i
]
on every processor
P
[
i
]
.
For all
P
[
i
]
do:
for
j
=0 to
N
-1 Receive
B
[
j
]
from root
C
[
i
][
j
]
=
A
[
i
]
*
B
[
j
]
Collect
C
[
i
]
Broadcasting of each
B
[
j
]
->
Step 2 takes
O(N logN)
time.
Author:
Wolfgang Schreiner
Last modification: November 15, 1996