Abstraction Library for Parallel Kernel Acceleration
**alpaka** - Abstraction Library for Parallel Kernel Acceleration

The alpaka library is a header-only C++11 abstraction library for accelerator development.

Its aim is to provide performance portability across accelerators through the abstraction (not hiding!) of the underlying levels of parallelism.

It is platform independent and supports the concurrent and cooperative use of multiple devices such as the hosts CPU as well as attached accelerators as for instance CUDA GPUs and Xeon Phis (currently native execution only). A multitude of accelerator back-end variants using CUDA, OpenMP (2.0/4.0), Boost.Fiber, std::thread and also serial execution is provided and can be selected depending on the device. Only one implementation of the user kernel is required by representing them as function objects with a special interface. There is no need to write special CUDA, OpenMP or custom threading code. Accelerator back-ends can be mixed within a device stream. The decision which accelerator back-end executes which kernel can be made at runtime.

The alpaka API is currently unstable (beta state).

The abstraction used is very similar to the CUDA grid-blocks-threads division strategy. Algorithms that should be parallelized have to be divided into a multi-dimensional grid consisting of small uniform work items. These functions are called kernels and are executed in parallel threads. The threads in the grid are organized in blocks. All threads in a block are executed in parallel and can interact via fast shared memory. Blocks are executed independently and can not interact in any way. The block execution order is unspecified and depends on the accelerator in use. By using this abstraction the execution can be optimally adapted to the available hardware.

Software License

alpaka is licensed under LGPLv3 or later.


The general documentation is located within the doc/markdown subfolder of the repository. The source code documentation is generated with doxygen.

Accelerator Back-ends

Accelerator Back-endLib/APIDevicesExecution strategy grid-blocksExecution strategy block-threads
Serialn/aHost CPU (single core)sequentialsequential (only 1 thread per block)
OpenMP 2.0+ blocksOpenMP 2.0+Host CPU (multi core)parallel (preemptive multitasking)sequential (only 1 thread per block)
OpenMP 2.0+ threadsOpenMP 2.0+Host CPU (multi core)sequentialparallel (preemptive multitasking)
OpenMP 4.0+ (CPU)OpenMP 4.0+Host CPU (multi core)parallel (undefined)parallel (preemptive multitasking)
std::thread std::thread Host CPU (multi core)sequentialparallel (preemptive multitasking)
Boost.Fiber boost::fibers::fiber Host CPU (single core)sequentialparallel (cooperative multitasking)
CUDA 7.0+CUDA 7.0+NVIDIA GPUs SM 2.0+parallel (undefined)parallel (lock-step within warps)

Supported Compilers

This library uses C++11 (or newer when available).

Accelerator Back-endgcc 4.9.2gcc 5.3gcc 6.1clang 3.5/3.6clang 3.7clang 3.8clang 3.9MSVC 2015.3
OpenMP 2.0+ blocks:white_check_mark::white_check_mark::white_check_mark::x::white_check_mark::white_check_mark::white_check_mark::white_check_mark:
OpenMP 2.0+ threads:white_check_mark::white_check_mark::white_check_mark::x::white_check_mark::white_check_mark::white_check_mark::white_check_mark:
OpenMP 4.0+ (CPU):white_check_mark::white_check_mark::white_check_mark::x::x::x::x::x:
std::thread :white_check_mark::white_check_mark::white_check_mark::white_check_mark::white_check_mark::white_check_mark::white_check_mark::white_check_mark:
Boost.Fiber :white_check_mark::white_check_mark::white_check_mark::white_check_mark::white_check_mark::white_check_mark::white_check_mark::white_check_mark:
CUDA 7.0+:white_check_mark: (nvcc 7.0+):white_check_mark: (nvcc 8.0+):x::x::x::white_check_mark: (native/nvcc 8.0+):white_check_mark: (native):x:


Boost 1.59+ is the only mandatory external dependency. The alpaka library itself just requires header-only libraries. However some of the accelerator back-end implementations require different boost libraries to be built.

When an accelerator back-end using Boost.Fiber is enabled, boost 1.62+ is required. boost-fiber, boost-context and all of its dependencies are required to be build in C++11 mode ./b2 cxxflags="-std=c++11".

When an accelerator back-end using CUDA is enabled, version 7.0 of the CUDA SDK is the minimum requirement. NOTE: When using nvcc as CUDA compiler, the CUDA accelerator back-end can not be enabled together with the Boost.Fiber accelerator back-end due to bugs in the nvcc compiler. NOTE: When using clang as a native CUDA compiler, the CUDA accelerator back-end can not be enabled together with any OpenMP accelerator back-end because this combination is currently unsupported.

When an accelerator back-end using OpenMP is enabled, the compiler and the platform have to support the corresponding minimum OpenMP version.


The library is header only so nothing has to be build. CMake 3.3.0+ is required to provide the correct defines and include paths. Just call ALPAKA_ADD_EXECUTABLE instead of CUDA_ADD_EXECUTABLE or ADD_EXECUTABLE and the difficulties of the CUDA nvcc compiler in handling .cu and .cpp files are automatically taken care of. Source files do not need any special file ending. Examples of how to utilize alpaka within CMake can be found in the example folder.

The whole alpaka library can be included with: #include <alpaka/alpaka.hpp> Code that is not intended to be utilized by the user is hidden in the detail namespace.


For a quick introduction, feel free to playback the recording of our presentation at GTC 2016:

  • E. Zenker, R. Widera, G. Juckeland et al., Porting the Plasma Simulation PIConGPU to Heterogeneous Architectures with Alpaka, video link (39 min)

Citing alpaka

Currently all authors of alpaka are scientists or connected with research. For us to justify the importance and impact of our work, please consider citing us accordingly in your derived work and publications:

% Peer-Reviewed Publication %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% Peer reviewed and accepted publication in
% "The Sixth International Workshop on
% Accelerators and Hybrid Exascale Systems (AsHES)"
% at the
% "30th IEEE International Parallel and Distributed
% Processing Symposium" in Chicago, IL, USA
author = {Erik Zenker and Benjamin Worpitz and Ren{\'{e}} Widera
and Axel Huebl and Guido Juckeland and
Andreas Kn{\"{u}}pfer and Wolfgang E. Nagel and Michael Bussmann},
title = {Alpaka - An Abstraction Library for Parallel Kernel Acceleration},
archivePrefix = "arXiv",
eprint = {1602.08477},
keywords = {Computer science;CUDA;Mathematical Software;nVidia;OpenMP;Package;
performance portability;Portability;Tesla K20;Tesla K80},
day = {23},
month = {May},
year = {2016},
publisher = {IEEE Computer Society},
url = {},
% Original Work: Benjamin Worpitz' Master Thesis %%%%%%%%%%
author = {Benjamin Worpitz},
title = {Investigating performance portability of a highly scalable
particle-in-cell simulation code on various multi-core
school = {{Technische Universit{\"{a}}t Dresden}},
month = {Sep},
year = {2015},
type = {Master Thesis},
doi = {10.5281/zenodo.49768},
url = {}


Maintainers and Core Developers

  • Benjamin Worpitz (original author)
  • Erik Zenker
  • Rene Widera

Former Members, Contributions and Thanks

  • Dr. Michael Bussmann
  • Axel Huebl