Aug 23, 2021 · This paper addresses the important question of how to compose these code versions into a single program that (near-)optimally discriminates them across ...

We present a simple and highly-composable strategy which requires that the (dynamic) program property used to discriminate between code ver- sions conforms with ...

Feb 17, 2021 · This paper addresses the important question of how to compose these code versions into a single program that (near-)optimally discriminates them across ...

Dataset Sensitive Autotuning of Multi-versioned Code Based on Monotonic Properties: Autotuning in Futhark. August 2021. DOI:10.1007/978-3-030-83978-9_1.

This thesis investigates the feasibility of the Futhark programming language to map k-means and its generalization, mixture models, to efficient GPU code ...

We apply our tuning strategy to the incremental-flattening transformation supported by the publicly-available Futhark compiler and compare with a previous black ...

Dataset Sensitive Autotuning of Multi-versioned Code Based on Monotonic Properties - Autotuning in Futhark. Munksgaard P, Breddam S, Henriksen T, Gieseke F ...

We apply our tuning strategy to the incremental-flattening transformation supported by the publicly-available Futhark compiler and compare with a previous black ...

Jun 27, 2015 · SC22. Dataset Sensitive Autotuning of Multi-versioned Code Based on Monotonic Properties. Presented at TFP 2021. Experience report: Type-safe ...

Feb 12, 2021 · Dataset Sensitive Autotuning of Multi-Versioned Code based on Monotonic Properties · A general method for finding the near-optimal* tuning ...