commit 31178f9f60bb33ba83999c532047ef4cc4ef754e
parent 7e752e7ec175e07d9ee806f65c750773bab7e22f
Author: Anders Damsgaard <anders@adamsgaard.dk>
Date: Tue, 2 Jun 2020 11:42:43 +0200
Add abstract to brcon2020 post
Diffstat:
2 files changed, 32 insertions(+), 2 deletions(-)
diff --git a/pages/005-energy-efficient-programming.html b/pages/005-energy-efficient-programming.html
@@ -22,7 +22,22 @@ href="gopher://bitreich.org/1/scm/sacc">sacc(1)</a>.</p>
my thougts on scientific software development during the <a
href="gopher://bitreich.org/1/con/2020">2020 brcon</a>, and how
consistent use of low-level programming languages can benefit
-scientific model development and energy efficiency.</a></p>
+scientific model development and energy efficiency. Full abstract:</a></p>
+
+<blockquote>Numerical models are used extensively for simulating
+complex physical systems including fluid flows, astronomical events,
+weather, and climate. Many researchers struggle to bring their
+model developments from single-computer, interpreted languages to
+parallel high-performance computing (HPC) systems. There are
+initiatives to make interpreted languages such as MATLAB, Python,
+and Julia feasible for HPC programming. In this talk I argue that
+the computational overhead is far costlier than any potential
+development time saved. Instead, doing model development in C and
+unix tools from the start minimizes porting headaches between
+platforms, reduces energy use on all systems, and ensures reproducibility
+of results.</blockquote>
+
+<p>You can check out the slides and audio here:</p>
<ul>
<li><a href="https://adamsgaard.dk/pub/energy-efficient-programming.md">slides (markdown)</a></li>
diff --git a/pages/005-energy-efficient-programming.txt b/pages/005-energy-efficient-programming.txt
@@ -16,7 +16,22 @@ choice is [6]sacc(1).
I presented my thougts on scientific software development during
the [7]2020 brcon, and how consistent use of low-level programming
languages can benefit scientific model development and energy
-efficiency.
+efficiency. Full abstract:
+
+ Numerical models are used extensively for simulating complex
+ physical systems including fluid flows, astronomical events,
+ weather, and climate. Many researchers struggle to bring their
+ model developments from single-computer, interpreted languages to
+ parallel high-performance computing (HPC) systems. There are
+ initiatives to make interpreted languages such as MATLAB, Python,
+ and Julia feasible for HPC programming. In this talk I argue that
+ the computational overhead is far costlier than any potential
+ development time saved. Instead, doing model development in C and
+ unix tools from the start minimizes porting headaches between
+ platforms, reduces energy use on all systems, and ensures
+ reproducibility of results.
+
+You can check out the slides and audio here:
- [8]slides (markdown)
- [9]audio (ogg)
