arrayfire
general purpose GPU library
ArrayFire is a high performance software library for parallel computing with an easy-to-use API. Its array based function set makes parallel programming simple. ArrayFire's multiple backends (CUDA, OpenCL and native CPU) make it platform independent and highly portable.
homepage ↗ github: google/googletest
Available in
| Overlay | Newest | Ebuilds | Last activity | |
|---|---|---|---|---|
| science gitweb ↗ | 3.8.0 | 1 | 4 d | details › |
Versions & arches
Use flags of 3.8.0
- examples Install examples, usually source code
- +cache cache kernals to disk.
- cuda Build CUDA backend.
- doc Add extra documentation (API, Javadoc, etc). It is recommended to enable per package instead of globally
- mkl Build against static MKL.
- nonfree build.
- opencl build OpenCL backend.
- test Enable dependencies and/or preparations necessary to run tests (usually controlled by FEATURES=test but can be toggled independently)
- +trace enable additional traces during logging.
Runtime dependencies of 3.8.0
show 22 lines
cuda?
(
)
mkl?
(
)
opencl?
(
)