Fri 30 Oct 2015 11:37 - 12:00 at Grand Station 2 - 10. Empirical Studies & Approximation Chair(s): John Field

We present Topaz, a new task-based language for computations that execute on approximate computing platforms that may occasionally produce arbitrarily inaccurate results. Topaz maps tasks onto the approximate hardware and integrates the generated results into the main computation. To prevent unacceptably inaccurate task results from corrupting the main computation, Topaz deploys a novel outlier detection mechanism that recognizes and precisely reexecutes outlier tasks. Outlier detection enables Topaz to work effectively with approximate hardware platforms that have complex fault characteristics, including platforms with bit pattern dependent faults (in which the presence of faults may depend on values stored in adjacent memory cells). Our experimental results show that, for our set of benchmark applications, outlier detection enables Topaz to deliver acceptably accurate results (less than 1% error) on our target approximate hardware platforms. Depending on the application and the hardware platform, the overall energy savings range from 5 to 13 percent. Without outlier detection, only one of the applications produces acceptably accurate results.

Fri 30 Oct

10:30 - 12:00: OOPSLA - 10. Empirical Studies & Approximation at Grand Station 2
Chair(s): John FieldGoogle
oopsla2015144619740000010:30 - 10:52
Markus Völteritemis, Germany, Arie van DeursenDelft University of Technology, Netherlands, Bernd Kolbitemis AG, Stephan Eberleitemis AG
DOI Pre-print Media Attached
oopsla2015144619875000010:52 - 11:15
Crista LopesUniversity of California, Irvine, Joel OssherUniversity of California, Irvine
DOI Pre-print Media Attached File Attached
oopsla2015144620010000011:15 - 11:37
Luis MastrangeloUniversity of Lugano, Switzerland, Luca PonzanelliUniversity of Lugano, Switzerland, Andrea MocciUniversity of Lugano, Switzerland, Michele LanzaUniversity of Lugano, Switzerland, Matthias HauswirthUniversity of Lugano, Switzerland, Nate NystromUniversity of Lugano, Switzerland
DOI Media Attached
oopsla2015144620145000011:37 - 12:00
Sara AchourMassachusetts Institute of Technology, USA, Martin RinardMassachusetts Institute of Technology, USA
DOI Media Attached