http://mw.hh.se/wg211/index.php?action=history&feed=atom&title=WG211%2FM26BodoWG211/M26Bodo - Revision history2026-10-26T17:10:27ZRevision history for this page on the wikiMediaWiki 1.43.5http://mw.hh.se/wg211/index.php?title=WG211/M26Bodo&diff=2934&oldid=prevSven-Bodo: added abstract2026-10-14T08:22:47Z<p>added abstract</p>
<p><b>New page</b></p><div>'''Code Generation in the Mirror --- on Generating ONNX for Scientific Codes'''<br />
<br />
'''Sven-Bodo Scholz'''<br />
<br />
Many new architectures have been created aiming at improved AI computations.<br />
These machines promise faster computations or lower power consumption in comparison to standard hardware.<br />
Given that AI computations are mainly based on a small set of linear algebra operations it should be possible to<br />
leverage the benefits of these architectures for scientific computation as well. In a first attempt to do so, we look into<br />
the feasibility of leveraging Open Neural Network Exchange (ONNX) as an intermediate representation which<br />
is supported by a rather wide range of accelerator platforms.<br />
<br />
The key challenge here is that ONNX is on a rather high level of abstraction which seems to to turn the code generation task <br />
into a code analysis task. This talk presents an idea to address this analysis task by a combination of functional abstraction <br />
and ONNX code generation. We present our first experiences when turning scientific applications written in SaC into ONNX programs.</div>Sven-Bodo