Skip to content
GitLab
Projects
Groups
Snippets
/
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
SWIFT
SWIFTsim
Commits
45fa0e48
Commit
45fa0e48
authored
Jan 22, 2016
by
Matthieu Schaller
Browse files
Spell-checking
parent
12048375
Changes
1
Hide whitespace changes
Inline
Side-by-side
theory/paper_pasc/pasc_paper.tex
View file @
45fa0e48
...
...
@@ -94,7 +94,7 @@ strong scaling on more than 100\,000 cores.}
\swift
was designed from the bottom up to provide excellent
{
\em
strong scaling
}
on both commodity clusters (Tier-2 systems) and Top100-supercomputers
(Tier-0 systems), without relying on architecture-specific features
or specialized accel
l
erator hardware.
or specialized accelerator hardware.
This performance is due to three main computational approaches:
\begin{itemize}
...
...
@@ -107,7 +107,7 @@ strong scaling on more than 100\,000 cores.}
the task graph to decompose the simulation
domain such that the
{
\em
work
}
, as opposed to just the
{
\em
data
}
,
as is the case with most partitioning schemes, is equally distributed
ac
c
ross all nodes.
across all nodes.
\item
\textbf
{
Fully dynamic and asynchronous communication
}
,
in which communication is modelled as just another task in
...
...
@@ -289,7 +289,7 @@ analysis).
One of the main concerns when developing
\swift
was to break
with the branch-and-bound type parallelism inherent to parallel
codes using OpenMP and MPI, and the constant synchroni
z
ation
codes using OpenMP and MPI, and the constant synchroni
s
ation
between computational steps it results in.
If
{
\em
synchronisation
}
is the main problem, then
{
\em
asynchronicity
}
...
...
@@ -302,7 +302,7 @@ can be used to partition the work equitably over a set of
distributed-memory nodes using general-purpose graph partitioning
algorithms.
Finally, the necessary communication between nodes can itself be
modelled in a task-based way, interleaving communication seamlesly
modelled in a task-based way, interleaving communication seamles
s
ly
with the rest of the computation.
...
...
@@ -372,7 +372,7 @@ may be updated.
The task hierarchy is shown in Figure~
\ref
{
tasks
}
, where the particles in each
cell are first sorted (round tasks) before the particle densities
are computed (first layer of square tasks).
Ghost tasks (triangles) are used to ensure that all density coputations
Ghost tasks (triangles) are used to ensure that all density co
m
putations
on a cell of particles have completed before the force evaluation tasks
(second layer of square tasks) can be executed.
Once all the force tasks on a cell of particles have completed,
...
...
Write
Preview
Supports
Markdown
0%
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment