Futhark is a purely functional data-parallel array language that offers a machine-neutral
programming model and an optimising compiler that generates OpenCL code for GPUs …

Compilation techniques for nested-parallel applications that can adapt to hardware and
dataset characteristics are vital for unlocking the power of modern hardware. This paper …

We show how to compile high-level functional array-processing programs, drawn from
image processing and machine learning, into C code that runs as fast as hand-written C …

We present a type system for expressing size constraints on array types in an ML-style type
system. The goal is to detect shape mismatches at compile-time, while being simpler than …

Commodity many-core hardware is now mainstream, but parallel programming models are
still lagging behind in efficiently utilizing the application parallelism. There are (at least) two …

We present a higher-order module system for the purely functional data-parallel array
language Futhark. The module language has the property that it is completely eliminated at …

We present and evaluate an implementation technique for regular segmented reductions on
GPUs. Existing techniques tend to be either consistent in performance but relatively …

We present the first formalization and metatheory of language soundness for a user-
schedulable language, the widely used array processing language Halide. User …

General-purpose massively parallel processors, such as GPUs, have become common, but
are difficult to program. Pure functional programming can be a solution, as it guarantees …

This case study examines the data-parallel functional implementation of three algorithms:
generation of quasi-random Sobol numbers, breadth-first search, and calibration of Heston …