The parameters of the model are:
parameter | description |
---|---|
W | total number of work units in job |
Pl | lower bound on number of processors |
Pu | upper bound on number of processors |
Bl | lower bound on number of barriers |
Bu | upper bound on number of barriers |
wi | mean number of work units per barrier |
wstd | standard deiation of number of work units per barrier |
ui | mean compute time of a work unit |
ustd | standard deiation of compute time of work units |
Rigid jobs:
This is P work units running on P processors for T time, with no
additional structure.
It is expressed by
Pl = Pu = P
W = wi = P
wstd = 0
Bl = Bu = 0
ui = T
ustd = 0, or another value to express imbalance
Workpile:
This is an unstructured collection of multiple work units.
It is expressed by
Pl = some minimum number or 1
Pu = some maximum number or the system size
W = wi = the number of work units, which should be larger
than Pu
wstd = 0
Bl = Bu = 0
ui = average granularity
ustd = 0, or another value to express imbalance
Fork-join:
In this class of applications the degree of parallelism varies during
the execution, which is partitioned into a set of discrete steps.
It is expressed by
Pl = some minimum number or 1, or fixed at P
Pu = some maximum number or the system size, or fixed at P
Bl = Bu = number of phases in the application
wi = degree of parallelism in phase i, subject to
Pl <= wi <= Pu
wstd = variability in degrees of parallelism
W = w0 + ... + wB
ui = grain of phase i
ustd = 0, or another value to express imbalance