1# libCEED: the CEED API Library 2 3[](https://travis-ci.org/CEED/libCEED) 4[](https://codecov.io/gh/CEED/libCEED/) 5[](https://opensource.org/licenses/BSD-2-Clause) 6[](https://codedocs.xyz/CEED/libCEED/) 7 8## Code for Efficient Extensible Discretization 9 10This repository contains an initial low-level API library for the efficient 11high-order discretization methods developed by the ECP co-design [Center for 12Efficient Exascale Discretizations (CEED)](http://ceed.exascaleproject.org). 13While our focus is on high-order finite elements, the approach is mostly 14algebraic and thus applicable to other discretizations in factored form, as 15explained in the API documentation portion of the [Doxygen documentation](https://codedocs.xyz/CEED/libCEED/md_doc_libCEEDapi.html). 16 17One of the challenges with high-order methods is that a global sparse matrix is 18no longer a good representation of a high-order linear operator, both with 19respect to the FLOPs needed for its evaluation, as well as the memory transfer 20needed for a matvec. Thus, high-order methods require a new "format" that still 21represents a linear (or more generally non-linear) operator, but not through a 22sparse matrix. 23 24The goal of libCEED is to propose such a format, as well as supporting 25implementations and data structures, that enable efficient operator evaluation 26on a variety of computational device types (CPUs, GPUs, etc.). This new operator 27description is based on algebraically [factored form](https://codedocs.xyz/CEED/libCEED/md_doc_libCEEDapi.html), 28which is easy to incorporate in a wide variety of applications, without significant 29refactoring of their own discretization infrastructure. 30 31The repository is part of the [CEED software suite][ceed-soft], a collection of 32software benchmarks, miniapps, libraries and APIs for efficient exascale 33discretizations based on high-order finite element and spectral element methods. 34See http://github.com/ceed for more information and source code availability. 35 36The CEED research is supported by the [Exascale Computing Project][ecp] 37(17-SC-20-SC), a collaborative effort of two U.S. Department of Energy 38organizations (Office of Science and the National Nuclear Security 39Administration) responsible for the planning and preparation of a [capable 40exascale ecosystem](https://exascaleproject.org/what-is-exascale), including 41software, applications, hardware, advanced system engineering and early testbed 42platforms, in support of the nation’s exascale computing imperative. 43 44For more details on the CEED API see http://ceed.exascaleproject.org/ceed-code/. 45 46## Building 47 48The CEED library, `libceed`, is a C99 library with no external dependencies. It 49can be built using 50 51 make 52 53or, with optimization flags 54 55 make OPT='-O3 -march=skylake-avx512 -ffp-contract=fast' 56 57These optimization flags are used by all languages (C, C++, Fortran) and this 58makefile variable can also be set for testing and examples (below). 59 60The library attempts to automatically detect support for the AVX 61instruction set using gcc-style compiler options for the host. 62Support may need to be manually specified via 63 64 make AVX=1 65 66or 67 68 make AVX=0 69 70if your compiler does not support gcc-style options, if you are cross 71compiling, etc. 72 73## Testing 74 75The test suite produces [TAP](https://testanything.org) output and is run by: 76 77 make test 78 79or, using the `prove` tool distributed with Perl (recommended) 80 81 make prove 82 83## Backends 84 85There are multiple supported backends, which can be selected at runtime in the examples: 86 87| CEED resource | Backend | 88| :----------------------- | :------------------------------------------------ | 89| `/cpu/self/ref/serial` | Serial reference implementation | 90| `/cpu/self/ref/blocked` | Blocked refrence implementation | 91| `/cpu/self/tmpl` | Backend template, delegates to `/cpu/self/ref/blocked` | 92| `/cpu/self/avx/serial` | Serial AVX implementation | 93| `/cpu/self/avx/blocked` | Blocked AVX implementation | 94| `/cpu/self/xsmm/serial` | Serial LIBXSMM implementation | 95| `/cpu/self/xsmm/blocked` | Blocked LIBXSMM implementation | 96| `/cpu/occa` | Serial OCCA kernels | 97| `/gpu/occa` | CUDA OCCA kernels | 98| `/omp/occa` | OpenMP OCCA kernels | 99| `/ocl/occa` | OpenCL OCCA kernels | 100| `/gpu/cuda` | Pure CUDA kernels | 101| `/gpu/magma` | CUDA MAGMA kernels | 102 103 104The `/cpu/self/*/serial` backends process one element at a time and are intended for meshes 105with a smaller number of high order elements. The `/cpu/self/*/blocked` backends process 106blocked batches of eight interlaced elements and are intended for meshes with higher numbers 107of elements. 108 109The `/cpu/self/ref/*` backends are written in pure C and provide basic functionality. 110 111The `/cpu/self/avx/*` backends rely upon AVX instructions to provide vectorized CPU performance. 112 113The `/cpu/self/xsmm/*` backends relies upon the [LIBXSMM](http://github.com/hfp/libxsmm) package 114to provide vectorized CPU performance. 115 116The `/*/occa` backends rely upon the [OCCA](http://github.com/libocca/occa) package to provide 117cross platform performance. 118 119The `/gpu/cuda` backend provides GPU performance strictly using CUDA. 120 121The `/gpu/magma` backend relies upon the [MAGMA](https://bitbucket.org/icl/magma) package. 122 123## Examples 124 125libCEED comes with several examples of its usage, ranging from standalone C 126codes in the `/examples/ceed` directory to examples based on external packages, 127such as MFEM, PETSc, and Nek5000. Nek5000 v18.0 or greater is required. 128 129To build the examples, set the `MFEM_DIR`, `PETSC_DIR` and `NEK5K_DIR` variables 130and run: 131 132```console 133# libCEED examples on CPU and GPU 134cd examples/ceed 135make 136./ex1 -ceed /cpu/self 137./ex1 -ceed /gpu/occa 138cd ../.. 139 140# MFEM+libCEED examples on CPU and GPU 141cd examples/mfem 142make 143./bp1 -ceed /cpu/self -no-vis 144./bp1 -ceed /gpu/occa -no-vis 145cd ../.. 146 147# PETSc+libCEED examples on CPU and GPU 148cd examples/petsc 149make 150./bp1 -ceed /cpu/self 151./bp1 -ceed /gpu/occa 152cd ../.. 153 154# Nek+libCEED examples on CPU and GPU 155cd examples/nek5000 156./make-nek-examples.sh 157./run-nek-example.sh -ceed /cpu/self -b 3 158./run-nek-example.sh -ceed /gpu/occa -b 3 159cd ../.. 160``` 161 162The above code assumes a GPU-capable machine with the OCCA backend 163enabled. Depending on the available backends, other Ceed resource specifiers can 164be provided with the `-ceed` option. 165 166## Benchmarks 167 168A sequence of benchmarks for all enabled backends can be run using 169 170```console 171make benchmarks 172``` 173 174The results from the benchmarks are stored inside the `benchmarks/` directory 175and they can be viewed using the commands (requires python with matplotlib): 176 177```console 178cd benchmarks 179python postprocess-plot.py petsc-bp1-*-output.txt 180python postprocess-plot.py petsc-bp3-*-output.txt 181``` 182 183Using the `benchmarks` target runs a comprehensive set of benchmarks which may 184take some time to run. Subsets of the benchmarks can be run using targets such 185as `make bench-petsc-bp1`, or `make bench-petsc-bp3`. 186 187For more details about the benchmarks, see 188[`benchmarks/README.md`](benchmarks/README.md) 189 190 191## Install 192 193To install libCEED, run 194 195 make install prefix=/usr/local 196 197or (e.g., if creating packages), 198 199 make install prefix=/usr DESTDIR=/packaging/path 200 201Note that along with the library, libCEED installs kernel sources, e.g. OCCA 202kernels are installed in `$prefix/lib/okl`. This allows the OCCA backend to 203build specialized kernels at run-time. In a normal setting, the kernel sources 204will be found automatically (relative to the library file `libceed.so`). 205However, if that fails (e.g. if `libceed.so` is moved), one can copy (cache) the 206kernel sources inside the user OCCA directory, `~/.occa` using 207 208 $(OCCA_DIR)/bin/occa cache ceed $(CEED_DIR)/lib/okl/*.okl 209 210This will allow OCCA to find the sources regardless of the location of the CEED 211library. One may occasionally need to clear the OCCA cache, which can be accomplished 212by removing the `~/.occa` directory or by calling `$(OCCA_DIR)/bin/occa clear -a`. 213 214### pkg-config 215 216In addition to library and header, libCEED provides a [pkg-config][pkg-config1] 217file that can be used to easily compile and link. [For example][pkg-config2], if 218`$prefix` is a standard location or you set the environment variable 219`PKG_CONFIG_PATH`, 220 221 cc `pkg-config --cflags --libs ceed` -o myapp myapp.c 222 223will build `myapp` with libCEED. This can be used with the source or 224installed directories. Most build systems have support for pkg-config. 225 226## Contact 227 228You can reach the libCEED team by emailing [ceed-users@llnl.gov](mailto:ceed-users@llnl.gov) 229or by leaving a comment in the [issue tracker](https://github.com/CEED/libCEED/issues). 230 231## Copyright 232 233The following copyright applies to each file in the CEED software suite, unless 234otherwise stated in the file: 235 236> Copyright (c) 2017, Lawrence Livermore National Security, LLC. Produced at the 237> Lawrence Livermore National Laboratory. LLNL-CODE-734707. All Rights reserved. 238 239See files LICENSE and NOTICE for details. 240 241[ceed-soft]: http://ceed.exascaleproject.org/software/ 242[ecp]: https://exascaleproject.org/exascale-computing-project 243[pkg-config1]: https://en.wikipedia.org/wiki/Pkg-config 244[pkg-config2]: https://people.freedesktop.org/~dbn/pkg-config-guide.html#faq 245
){kind=link}
){kind=link}
){kind=link}
){kind=link}