目录
- cilkImport the Cilk version of MiniFE9年前
- cudaFix for atomicAdd compialtion issue interference.8年前
- kokkosUpdate for Kokkos 3.06年前
- mklImport MiniFE version written to Intel's MKL library9年前
- nvamgImport NV-AMG version of MiniFE from Mantevo9年前
- openmp-opt-knl-memkindImplementation using memkind for *some* parts of CSR matrix9年前
- openmp-opt-knlSmall ~4% improvement in performance, hint to use large pages for the Vector allocations and then shift the offset.9年前
- openmp-optEnable MPI_THREAD_MULTIPLE8年前
- openmpImport the basic OpenMP variant of MiniFE9年前
- openmp45-optUpdate for restrict keywords9年前
- openmp45Makefile to build OpenMP4.5 on a GPU platform.8年前
- qthreadsmodern versions of qthreads provide qthread/qthread.h not qthread.h8年前
- refImport miniFE Reference 2.0 from the Mantevo Release Website9年前
- .gitignoreadd initial .gitignore8年前
- LICENSEMake formatting a little better8年前
- README.FIRSTNicer format for README.8年前
- README.mdAdded reference5年前
邀请码
miniFE Finite Element Mini-Application
MiniFE is an proxy application for unstructured implicit finite element codes. It is similar to HPCCG and pHPCCG but provides a much more complete vertical covering of the steps in this class of applications. MiniFE also provides support for computation on multicore nodes, including pthreads and Intel Threading Building Blocks (TBB) for homogeneous multicore and CUDA for GPUs. Like HPCCG and pHPCCG, MiniFE is intended to be the “best approximation to an unstructured implicit finite element or finite volume application, but in 8000 lines or fewer.”
License Information
MiniFE is licensed under the LGPL-3. See LICENSE for more information.
Additional Information
Please see the README.FIRST which accompanies the MiniFE source code.
For more details about miniFE and a comparison with an application code, please see the following reference:
P.T. Lin, M.A. Heroux, R.F. Barrett, and A.B. Williams, “Assessing a mini-application as a performance proxy for a finite element method engineering application,” Concurrency and Computation: Practice and Experience, 27(17):5374–5389, 2015. DOI: 10.1002/cpe.3587