Giter Club home page Giter Club logo

rocfft's Introduction

rocFFT

rocFFT is a software library for computing Fast Fourier Transforms (FFT) written in HIP. It is part of AMD's software ecosystem based on ROCm. In addition to AMD GPU devices, the library can also be compiled with the CUDA compiler using HIP tools for running on Nvidia GPU devices.

Installing pre-built packages

Download pre-built packages either from ROCm's package servers or by clicking the github releases tab and downloading the source, which could be more recent than the pre-build packages. Release notes are available for each release on the releases tab.

  • sudo apt update && sudo apt install rocfft

Dependencies

rocFFT requires python3 libraries to be present at runtime. These are typically present by default in most Linux distributions.

Building from source

rocFFT is compiled with hipcc and uses cmake. There are a number of options that can be provided to cmake to customize the build, but the following commands will build a shared library for supported AMD GPUs:

mkdir build && cd build
cmake -DCMAKE_CXX_COMPILER=hipcc -DCMAKE_C_COMPILER=hipcc .. 
make -j

A static library can be compiled by using the option -DBUILD_SHARED_LIBS=off

To use the hip-clang compiler, one must specify -DUSE_HIP_CLANG=ON -DHIP_COMPILER=clang to cmake. rocFFT enables use of indirect function calls by default and requires ROCm 4.3 or higher to build successfully. -DROCFFT_CALLBACKS_ENABLED=off may be specified to cmake to disable those calls on older ROCm compilers, though callbacks will not work correctly in this configuration.

There are several clients included with rocFFT:

  1. rocfft-rider runs general transforms and is useful for performance analysis;
  2. rocfft-test runs various regression tests; and
  3. various small samples are included.

Clients are not built by default. To build them:

Client CMake option Dependencies
rocfft-rider -DBUILD_CLIENTS_RIDER=on Boost program options
rocfft-test -DBUILD_CLIENTS_TESTS=on Boost program options, FFTW, Google Test
samples -DBUILD_CLIENTS_SAMPLES=on Boost program options, FFTW

To build all of the above clients, use -DBUILD_CLIENTS=on. The build process will download and build Google Test and FFTW if they are not installed.

Clients may be built separately from the main library. For example, one may build all the clients with an existing rocFFT library by invoking cmake from within the rocFFT-src/clients folder:

mkdir build && cd build
cmake -DCMAKE_CXX_COMPILER=hipcc -DCMAKE_C_COMPILER=hipcc -DCMAKE_PREFIX_PATH=/path/to/rocFFT-lib ..
make -j

To install the client dependencies on Ubuntu, run:

sudo apt install libgtest-dev libfftw3-dev libboost-program-options-dev`

We use version 1.11 of Google Test (gtest).

install.sh is a bash script that will install dependencies on certain Linux distributions, such as Ubuntu, CentOS, RHEL, Fedora, and SLES and invoke cmake. However, the preferred method for compiling rocFFT is to call cmake directly.

Library and API Documentation

Please refer to the library documentation for current documentation.

Examples

Examples may be found in the clients/samples subdirectory.

Contribution Rules

Source code formatting

  • C++ source code must be formatted with clang-format with .clang-format

  • Python source code must be formatted with yapf --style pep8

rocfft's People

Contributors

af-ayala avatar amcamd avatar amdkila avatar arvindcheru avatar bragadeesh avatar cgmb avatar cheyennegoh avatar darkbuck avatar eidenyoshida avatar eng-flavio-teixeira avatar evetsso avatar feizheng10 avatar hchevanne avatar lawruble13 avatar malcolmroberts avatar mdnauta avatar memmett avatar mhbliao avatar mkuron avatar pruthvistony avatar raramakr avatar rmalavally avatar rosenrodt avatar saadrahim avatar solaslin avatar timmyliu avatar tingxingdong avatar yoichiyoshida avatar zaliu avatar zhang2amd avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.