1# libCEED: Efficient Extensible Discretization 2 3[![GitHub Actions][github-badge]][github-link] 4[![GitLab-CI][gitlab-badge]][gitlab-link] 5[![Code coverage][codecov-badge]][codecov-link] 6[![BSD-2-Clause][license-badge]][license-link] 7[![Documentation][doc-badge]][doc-link] 8[![JOSS paper][joss-badge]][joss-link] 9[![Binder][binder-badge]][binder-link] 10 11## Summary and Purpose 12 13libCEED provides fast algebra for element-based discretizations, designed for performance portability, run-time flexibility, and clean embedding in higher level libraries and applications. 14It offers a C99 interface as well as bindings for Fortran, Python, Julia, and Rust. 15While our focus is on high-order finite elements, the approach is mostly algebraic and thus applicable to other discretizations in factored form, as explained in the [user manual](https://libceed.org/en/latest/) and API implementation portion of the [documentation](https://libceed.org/en/latest/api/). 16 17One of the challenges with high-order methods is that a global sparse matrix is no longer a good representation of a high-order linear operator, both with respect to the FLOPs needed for its evaluation, as well as the memory transfer needed for a matvec. 18Thus, high-order methods require a new "format" that still represents a linear (or more generally non-linear) operator, but not through a sparse matrix. 19 20The goal of libCEED is to propose such a format, as well as supporting implementations and data structures, that enable efficient operator evaluation on a variety of computational device types (CPUs, GPUs, etc.). 21This new operator description is based on algebraically [factored form](https://libceed.org/en/latest/libCEEDapi/#finite-element-operator-decomposition), which is easy to incorporate in a wide variety of applications, without significant refactoring of their own discretization infrastructure. 22 23The repository is part of the [CEED software suite](http://ceed.exascaleproject.org/software/), a collection of software benchmarks, miniapps, libraries and APIs for efficient exascale discretizations based on high-order finite element and spectral element methods. 24See <http://github.com/ceed> for more information and source code availability. 25 26The CEED research is supported by the [Exascale Computing Project](https://exascaleproject.org/exascale-computing-project) (17-SC-20-SC), a collaborative effort of two U.S. Department of Energy organizations (Office of Science and the National Nuclear Security Administration) responsible for the planning and preparation of a [capable exascale ecosystem](https://exascaleproject.org/what-is-exascale), including software, applications, hardware, advanced system engineering and early testbed platforms, in support of the nation’s exascale computing imperative. 27 28For more details on the CEED API see the [user manual](https://libceed.org/en/latest/). 29 30% gettingstarted-inclusion-marker 31 32## Building 33 34The CEED library, `libceed`, is a C99 library with no required dependencies, and with Fortran, Python, Julia, and Rust interfaces. 35It can be built using: 36 37``` 38make 39``` 40 41or, with optimization flags: 42 43``` 44make OPT='-O3 -march=skylake-avx512 -ffp-contract=fast' 45``` 46 47These optimization flags are used by all languages (C, C++, Fortran) and this makefile variable can also be set for testing and examples (below). 48 49The library attempts to automatically detect support for the AVX instruction set using gcc-style compiler options for the host. 50Support may need to be manually specified via: 51 52``` 53make AVX=1 54``` 55 56or: 57 58``` 59make AVX=0 60``` 61 62if your compiler does not support gcc-style options, if you are cross compiling, etc. 63 64To enable CUDA support, add `CUDA_DIR=/opt/cuda` or an appropriate directory to your `make` invocation. 65To enable HIP support, add `HIP_DIR=/opt/rocm` or an appropriate directory. 66To store these or other arguments as defaults for future invocations of `make`, use: 67 68``` 69make configure CUDA_DIR=/usr/local/cuda HIP_DIR=/opt/rocm OPT='-O3 -march=znver2' 70``` 71 72which stores these variables in `config.mk`. 73 74## Additional Language Interfaces 75 76The Fortran interface is built alongside the library automatically. 77 78Python users can install using: 79 80``` 81pip install libceed 82``` 83 84or in a clone of the repository via `pip install .`. 85 86Julia users can install using: 87 88``` 89$ julia 90julia> ] 91pkg> add LibCEED 92``` 93 94See the [LibCEED.jl documentation](http://ceed.exascaleproject.org/libCEED-julia-docs/dev/) for more information. 95 96Rust users can include libCEED via `Cargo.toml`: 97 98```toml 99[dependencies] 100libceed = { git = "https://github.com/CEED/libCEED", branch = "main" } 101``` 102 103See the [Cargo documentation](https://doc.rust-lang.org/cargo/reference/specifying-dependencies.html#specifying-dependencies-from-git-repositories) for details. 104 105## Testing 106 107The test suite produces [TAP](https://testanything.org) output and is run by: 108 109``` 110make test 111``` 112 113or, using the `prove` tool distributed with Perl (recommended): 114 115``` 116make prove 117``` 118 119## Backends 120 121There are multiple supported backends, which can be selected at runtime in the examples: 122 123| CEED resource | Backend | Deterministic Capable | 124| :--- | :--- | :---: | 125|| 126| **CPU Native** | 127| `/cpu/self/ref/serial` | Serial reference implementation | Yes | 128| `/cpu/self/ref/blocked` | Blocked reference implementation | Yes | 129| `/cpu/self/opt/serial` | Serial optimized C implementation | Yes | 130| `/cpu/self/opt/blocked` | Blocked optimized C implementation | Yes | 131| `/cpu/self/avx/serial` | Serial AVX implementation | Yes | 132| `/cpu/self/avx/blocked` | Blocked AVX implementation | Yes | 133|| 134| **CPU Valgrind** | 135| `/cpu/self/memcheck/*` | Memcheck backends, undefined value checks | Yes | 136|| 137| **CPU LIBXSMM** | 138| `/cpu/self/xsmm/serial` | Serial LIBXSMM implementation | Yes | 139| `/cpu/self/xsmm/blocked` | Blocked LIBXSMM implementation | Yes | 140|| 141| **CUDA Native** | 142| `/gpu/cuda/ref` | Reference pure CUDA kernels | Yes | 143| `/gpu/cuda/shared` | Optimized pure CUDA kernels using shared memory | Yes | 144| `/gpu/cuda/gen` | Optimized pure CUDA kernels using code generation | No | 145|| 146| **HIP Native** | 147| `/gpu/hip/ref` | Reference pure HIP kernels | Yes | 148| `/gpu/hip/shared` | Optimized pure HIP kernels using shared memory | Yes | 149| `/gpu/hip/gen` | Optimized pure HIP kernels using code generation | No | 150|| 151| **MAGMA** | 152| `/gpu/cuda/magma` | CUDA MAGMA kernels | No | 153| `/gpu/cuda/magma/det` | CUDA MAGMA kernels | Yes | 154| `/gpu/hip/magma` | HIP MAGMA kernels | No | 155| `/gpu/hip/magma/det` | HIP MAGMA kernels | Yes | 156|| 157| **OCCA** | 158| `/*/occa` | Selects backend based on available OCCA modes | Yes | 159| `/cpu/self/occa` | OCCA backend with serial CPU kernels | Yes | 160| `/cpu/openmp/occa` | OCCA backend with OpenMP kernels | Yes | 161| `/gpu/cuda/occa` | OCCA backend with CUDA kernels | Yes | 162| `/gpu/hip/occa`~ | OCCA backend with HIP kernels | Yes | 163 164The `/cpu/self/*/serial` backends process one element at a time and are intended for meshes with a smaller number of high order elements. 165The `/cpu/self/*/blocked` backends process blocked batches of eight interlaced elements and are intended for meshes with higher numbers of elements. 166 167The `/cpu/self/ref/*` backends are written in pure C and provide basic functionality. 168 169The `/cpu/self/opt/*` backends are written in pure C and use partial e-vectors to improve performance. 170 171The `/cpu/self/avx/*` backends rely upon AVX instructions to provide vectorized CPU performance. 172 173The `/cpu/self/memcheck/*` backends rely upon the [Valgrind](http://valgrind.org/) Memcheck tool to help verify that user QFunctions have no undefined values. 174To use, run your code with Valgrind and the Memcheck backends, e.g. `valgrind ./build/ex1 -ceed /cpu/self/ref/memcheck`. 175A 'development' or 'debugging' version of Valgrind with headers is required to use this backend. 176This backend can be run in serial or blocked mode and defaults to running in the serial mode if `/cpu/self/memcheck` is selected at runtime. 177 178The `/cpu/self/xsmm/*` backends rely upon the [LIBXSMM](http://github.com/hfp/libxsmm) package to provide vectorized CPU performance. 179If linking MKL and LIBXSMM is desired but the Makefile is not detecting `MKLROOT`, linking libCEED against MKL can be forced by setting the environment variable `MKL=1`. 180 181The `/gpu/cuda/*` backends provide GPU performance strictly using CUDA. 182 183The `/gpu/hip/*` backends provide GPU performance strictly using HIP. 184They are based on the `/gpu/cuda/*` backends. 185ROCm version 4.2 or newer is required. 186 187The `/gpu/*/magma/*` backends rely upon the [MAGMA](https://bitbucket.org/icl/magma) package. 188To enable the MAGMA backends, the environment variable `MAGMA_DIR` must point to the top-level MAGMA directory, with the MAGMA library located in `$(MAGMA_DIR)/lib/`. 189By default, `MAGMA_DIR` is set to `../magma`; to build the MAGMA backends with a MAGMA installation located elsewhere, create a link to `magma/` in libCEED's parent directory, or set `MAGMA_DIR` to the proper location. 190MAGMA version 2.5.0 or newer is required. 191Currently, each MAGMA library installation is only built for either CUDA or HIP. 192The corresponding set of libCEED backends (`/gpu/cuda/magma/*` or `/gpu/hip/magma/*`) will automatically be built for the version of the MAGMA library found in `MAGMA_DIR`. 193 194Users can specify a device for all CUDA, HIP, and MAGMA backends through adding `:device_id=#` after the resource name. 195For example: 196 197> - `/gpu/cuda/gen:device_id=1` 198 199The `/*/occa` backends rely upon the [OCCA](http://github.com/libocca/occa) package to provide cross platform performance. 200To enable the OCCA backend, the environment variable `OCCA_DIR` must point to the top-level OCCA directory, with the OCCA library located in the `${OCCA_DIR}/lib` (By default, `OCCA_DIR` is set to `../occa`). 201 202Additionally, users can pass specific OCCA device properties after setting the CEED resource. 203For example: 204 205> - `"/*/occa:mode='CUDA',device_id=0"` 206 207Bit-for-bit reproducibility is important in some applications. 208However, some libCEED backends use non-deterministic operations, such as `atomicAdd` for increased performance. 209The backends which are capable of generating reproducible results, with the proper compilation options, are highlighted in the list above. 210 211## Examples 212 213libCEED comes with several examples of its usage, ranging from standalone C codes in the `/examples/ceed` directory to examples based on external packages, such as MFEM, PETSc, and Nek5000. 214Nek5000 v18.0 or greater is required. 215 216To build the examples, set the `MFEM_DIR`, `PETSC_DIR`, and `NEK5K_DIR` variables and run: 217 218``` 219cd examples/ 220``` 221 222% running-examples-inclusion-marker 223 224```console 225# libCEED examples on CPU and GPU 226cd ceed/ 227make 228./ex1-volume -ceed /cpu/self 229./ex1-volume -ceed /gpu/cuda 230./ex2-surface -ceed /cpu/self 231./ex2-surface -ceed /gpu/cuda 232cd .. 233 234# MFEM+libCEED examples on CPU and GPU 235cd mfem/ 236make 237./bp1 -ceed /cpu/self -no-vis 238./bp3 -ceed /gpu/cuda -no-vis 239cd .. 240 241# Nek5000+libCEED examples on CPU and GPU 242cd nek/ 243make 244./nek-examples.sh -e bp1 -ceed /cpu/self -b 3 245./nek-examples.sh -e bp3 -ceed /gpu/cuda -b 3 246cd .. 247 248# PETSc+libCEED examples on CPU and GPU 249cd petsc/ 250make 251./bps -problem bp1 -ceed /cpu/self 252./bps -problem bp2 -ceed /gpu/cuda 253./bps -problem bp3 -ceed /cpu/self 254./bps -problem bp4 -ceed /gpu/cuda 255./bps -problem bp5 -ceed /cpu/self 256./bps -problem bp6 -ceed /gpu/cuda 257cd .. 258 259cd petsc/ 260make 261./bpsraw -problem bp1 -ceed /cpu/self 262./bpsraw -problem bp2 -ceed /gpu/cuda 263./bpsraw -problem bp3 -ceed /cpu/self 264./bpsraw -problem bp4 -ceed /gpu/cuda 265./bpsraw -problem bp5 -ceed /cpu/self 266./bpsraw -problem bp6 -ceed /gpu/cuda 267cd .. 268 269cd petsc/ 270make 271./bpssphere -problem bp1 -ceed /cpu/self 272./bpssphere -problem bp2 -ceed /gpu/cuda 273./bpssphere -problem bp3 -ceed /cpu/self 274./bpssphere -problem bp4 -ceed /gpu/cuda 275./bpssphere -problem bp5 -ceed /cpu/self 276./bpssphere -problem bp6 -ceed /gpu/cuda 277cd .. 278 279cd petsc/ 280make 281./area -problem cube -ceed /cpu/self -degree 3 282./area -problem cube -ceed /gpu/cuda -degree 3 283./area -problem sphere -ceed /cpu/self -degree 3 -dm_refine 2 284./area -problem sphere -ceed /gpu/cuda -degree 3 -dm_refine 2 285 286cd fluids/ 287make 288./navierstokes -ceed /cpu/self -degree 1 289./navierstokes -ceed /gpu/cuda -degree 1 290cd .. 291 292cd solids/ 293make 294./elasticity -ceed /cpu/self -mesh [.exo file] -degree 2 -E 1 -nu 0.3 -problem Linear -forcing mms 295./elasticity -ceed /gpu/cuda -mesh [.exo file] -degree 2 -E 1 -nu 0.3 -problem Linear -forcing mms 296cd .. 297``` 298 299For the last example shown, sample meshes to be used in place of `[.exo file]` can be found at <https://github.com/jeremylt/ceedSampleMeshes> 300 301The above code assumes a GPU-capable machine with the CUDA backends enabled. 302Depending on the available backends, other CEED resource specifiers can be provided with the `-ceed` option. 303Other command line arguments can be found in [examples/petsc](https://github.com/CEED/libCEED/blob/main/examples/petsc/README.md). 304 305% benchmarks-marker 306 307## Benchmarks 308 309A sequence of benchmarks for all enabled backends can be run using: 310 311``` 312make benchmarks 313``` 314 315The results from the benchmarks are stored inside the `benchmarks/` directory and they can be viewed using the commands (requires python with matplotlib): 316 317``` 318cd benchmarks 319python postprocess-plot.py petsc-bps-bp1-*-output.txt 320python postprocess-plot.py petsc-bps-bp3-*-output.txt 321``` 322 323Using the `benchmarks` target runs a comprehensive set of benchmarks which may take some time to run. 324Subsets of the benchmarks can be run using the scripts in the `benchmarks` folder. 325 326For more details about the benchmarks, see the `benchmarks/README.md` file. 327 328## Install 329 330To install libCEED, run: 331 332``` 333make install prefix=/path/to/install/dir 334``` 335 336or (e.g., if creating packages): 337 338``` 339make install prefix=/usr DESTDIR=/packaging/path 340``` 341 342To build and install in separate steps, run: 343 344``` 345make for_install=1 prefix=/path/to/install/dir 346make install prefix=/path/to/install/dir 347``` 348 349The usual variables like `CC` and `CFLAGS` are used, and optimization flags for all languages can be set using the likes of `OPT='-O3 -march=native'`. 350Use `STATIC=1` to build static libraries (`libceed.a`). 351 352To install libCEED for Python, run: 353 354``` 355pip install libceed 356``` 357 358with the desired setuptools options, such as `--user`. 359 360### pkg-config 361 362In addition to library and header, libCEED provides a [pkg-config](https://en.wikipedia.org/wiki/Pkg-config) file that can be used to easily compile and link. 363[For example](https://people.freedesktop.org/~dbn/pkg-config-guide.html#faq), if `$prefix` is a standard location or you set the environment variable `PKG_CONFIG_PATH`: 364 365``` 366cc `pkg-config --cflags --libs ceed` -o myapp myapp.c 367``` 368 369will build `myapp` with libCEED. 370This can be used with the source or installed directories. 371Most build systems have support for pkg-config. 372 373## Contact 374 375You can reach the libCEED team by emailing [ceed-users@llnl.gov](mailto:ceed-users@llnl.gov) or by leaving a comment in the [issue tracker](https://github.com/CEED/libCEED/issues). 376 377## How to Cite 378 379If you utilize libCEED please cite: 380 381``` 382@article{libceed-joss-paper, 383 author = {Jed Brown and Ahmad Abdelfattah and Valeria Barra and Natalie Beams and Jean Sylvain Camier and Veselin Dobrev and Yohann Dudouit and Leila Ghaffari and Tzanio Kolev and David Medina and Will Pazner and Thilina Ratnayaka and Jeremy Thompson and Stan Tomov}, 384 title = {{libCEED}: Fast algebra for high-order element-based discretizations}, 385 journal = {Journal of Open Source Software}, 386 year = {2021}, 387 publisher = {The Open Journal}, 388 volume = {6}, 389 number = {63}, 390 pages = {2945}, 391 doi = {10.21105/joss.02945} 392} 393 394@misc{libceed-user-manual, 395 author = {Abdelfattah, Ahmad and 396 Barra, Valeria and 397 Beams, Natalie and 398 Brown, Jed and 399 Camier, Jean-Sylvain and 400 Dobrev, Veselin and 401 Dudouit, Yohann and 402 Ghaffari, Leila and 403 Kolev, Tzanio and 404 Medina, David and 405 Pazner, Will and 406 Ratnayaka, Thilina and 407 Thompson, Jeremy L and 408 Tomov, Stanimire}, 409 title = {{libCEED} User Manual}, 410 month = jul, 411 year = 2021, 412 publisher = {Zenodo}, 413 version = {0.9.0}, 414 doi = {10.5281/zenodo.5077489} 415} 416``` 417 418For libCEED's Python interface please cite: 419 420``` 421@InProceedings{libceed-paper-proc-scipy-2020, 422 author = {{V}aleria {B}arra and {J}ed {B}rown and {J}eremy {T}hompson and {Y}ohann {D}udouit}, 423 title = {{H}igh-performance operator evaluations with ease of use: lib{C}{E}{E}{D}'s {P}ython interface}, 424 booktitle = {{P}roceedings of the 19th {P}ython in {S}cience {C}onference}, 425 pages = {85 - 90}, 426 year = {2020}, 427 editor = {{M}eghann {A}garwal and {C}hris {C}alloway and {D}illon {N}iederhut and {D}avid {S}hupe}, 428 doi = {10.25080/Majora-342d178e-00c} 429} 430``` 431 432The BiBTeX entries for these references can be found in the `doc/bib/references.bib` file. 433 434## Copyright 435 436The following copyright applies to each file in the CEED software suite, unless otherwise stated in the file: 437 438> Copyright (c) 2017, Lawrence Livermore National Security, LLC. Produced at the 439> Lawrence Livermore National Laboratory. LLNL-CODE-734707. All Rights reserved. 440 441See files LICENSE and NOTICE for details. 442 443[github-badge]: https://github.com/CEED/libCEED/workflows/C/Fortran/badge.svg 444[github-link]: https://github.com/CEED/libCEED/actions 445[gitlab-badge]: https://gitlab.com/libceed/libCEED/badges/main/pipeline.svg?key_text=GitLab-CI 446[gitlab-link]: https://gitlab.com/libceed/libCEED/-/pipelines?page=1&scope=all&ref=main 447[codecov-badge]: https://codecov.io/gh/CEED/libCEED/branch/main/graphs/badge.svg 448[codecov-link]: https://codecov.io/gh/CEED/libCEED/ 449[license-badge]: https://img.shields.io/badge/License-BSD%202--Clause-orange.svg 450[license-link]: https://opensource.org/licenses/BSD-2-Clause 451[doc-badge]: https://readthedocs.org/projects/libceed/badge/?version=latest 452[doc-link]: https://libceed.org/en/latest/?badge=latest 453[joss-badge]: https://joss.theoj.org/papers/10.21105/joss.02945/status.svg 454[joss-link]: https://doi.org/10.21105/joss.02945 455[binder-badge]: http://mybinder.org/badge_logo.svg 456[binder-link]: https://mybinder.org/v2/gh/CEED/libCEED/main?urlpath=lab/tree/examples/python/tutorial-0-ceed.ipynb 457
