GPU

This article is a stub. You can help by expanding it.

Introduction

A graphics processing unit (GPU) is a processor for handling graphics data, but can be used for other types of software as well.

See also CUDA.

For more information, see the Wikipedia article.

Software

• Category GPU at Hackage

• accelerate-cuda library: Accelerate backend for NVIDIA GPUs

• cuda library: FFI binding to the CUDA interface for programming NVIDIA GPUs

• GPipe library: A functional graphics API for programmable GPUs

• shady-graphics library: Functional GPU programming - DSEL & compiler

• Obsidian library: Embedded language for GPU Programming

• shady-gen library: Functional GPU programming - DSEL & compiler

Links

• Parallel and Concurrent Programming in Haskell, Chapter 6. GPU Programming with Accelerate

• GPU Programming in Haskell (video)

• GPU programming with Accelerate (PDF slides)

• How to write hybrid CPU/GPU programs with Haskell (blog)

• GPU Programming in Functional Languages, A Comparison of Haskell GPU Embedded Domain Specic Languages (PDF)

• Obsidian: GPU Programming in Haskell (PDF)

• GPU Kernels as Data-Parallel Array Computations in Haskell (PDF)

• Beauty And The Beast: Exploiting GPUs In Haskell (PDF)

• Financial Software on GPUs: Between Haskell and Fortran (PDF)

• Haskell on the GPU, Game of Life (video)