• Publications
  • Influence
SkelCL - A Portable Skeleton Library for High-Level GPU Programming
TLDR
We propose SkelCL -- a library providing so-called algorithmic skeletons that capture recurring patterns of parallel computation and communication, together with abstract vector data type and constructs for specifying data distribution. Expand
  • 126
  • 9
  • PDF
LIFT: A functional data-parallel IR for high-performance GPU code generation
TLDR
We introduce the LIFT IR, a new data-parallel IR which encodes OpenCL-specific constructs as functional patterns. Expand
  • 95
  • 7
  • PDF
Generating performance portable code using rewrite rules: from high-level functional expressions to high-performance OpenCL code
TLDR
We propose a novel approach aiming to combine high-level programming, code portability, and high-performance. Expand
  • 89
  • 7
  • PDF
Generating Performance Portable Code using Rewrite Rules
Computers have become increasingly complex with the emergence of heterogeneous hardware combining multicore CPUs and GPUs. These parallel systems exhibit tremendous computational power at the cost ofExpand
  • 13
  • 4
  • PDF
SkelCL: Enhancing OpenCL for High-Level Programming of Multi-GPU Systems
TLDR
We present the SkelCL high-level programming approach for systems with multiple GPUs and its implementation as a library on top of OpenCL. Expand
  • 31
  • 3
  • PDF
High performance stencil code generation with Lift
TLDR
This paper shows how complex multidimensional stencil code and optimizations are expressible in Lift, reusing its existing machinery for managing parallelism, memory hierarchy and optimizations. Expand
  • 48
  • 2
  • PDF
dOpenCL: Towards a Uniform Programming Approach for Distributed Heterogeneous Multi-/Many-Core Systems
TLDR
We present dOpenCL, an extended OpenCL API for using OpenCL in distributed, heterogeneous computing systems. Expand
  • 41
  • 2
  • PDF
Autotuning OpenCL Workgroup Size for Stencil Patterns
TLDR
We propose the use of machine learning-enabled autotuning to automatically predict workgroup sizes for stencil patterns on CPUs and multi-GPUs. Expand
  • 23
  • 2
  • PDF
Towards High-Level Programming of Multi-GPU Systems Using the SkelCL Library
TLDR
We present SkelCL – a high-level multi-GPU programming library that greatly simplifies programming for systems consisting of multiple GPUs. Expand
  • 19
  • 2
  • PDF
Runtime Code Generation and Data Management for Heterogeneous Computing in Java
TLDR
This paper presents a high-level parallel programming approach for the popular Java programming language based on array and functional programming to enable the use of parallel accelerators from Java. Expand
  • 14
  • 1
  • PDF