1 // Copyright (c) 2017-2018, Lawrence Livermore National Security, LLC. 2 // Produced at the Lawrence Livermore National Laboratory. LLNL-CODE-734707. 3 // All Rights reserved. See files LICENSE and NOTICE for details. 4 // 5 // This file is part of CEED, a collection of benchmarks, miniapps, software 6 // libraries and APIs for efficient high-order finite element and spectral 7 // element discretizations for exascale applications. For more information and 8 // source code availability see http://github.com/ceed. 9 // 10 // The CEED research is supported by the Exascale Computing Project 17-SC-20-SC, 11 // a collaborative effort of two U.S. Department of Energy organizations (Office 12 // of Science and the National Nuclear Security Administration) responsible for 13 // the planning and preparation of a capable exascale ecosystem, including 14 // software, applications, hardware, advanced system engineering and early 15 // testbed platforms, in support of the nation's exascale computing imperative. 16 17 #ifndef _ceed_cuda_compile_h 18 #define _ceed_cuda_compile_h 19 20 #include <ceed/ceed.h> 21 #include <cuda.h> 22 #include <nvrtc.h> 23 24 static inline CeedInt CeedDivUpInt(CeedInt numerator, CeedInt denominator) { 25 return (numerator + denominator - 1) / denominator; 26 } 27 28 CEED_INTERN int CeedCompileCuda(Ceed ceed, const char *source, CUmodule *module, 29 const CeedInt num_opts, ...); 30 31 CEED_INTERN int CeedGetKernelCuda(Ceed ceed, CUmodule module, const char *name, 32 CUfunction *kernel); 33 34 CEED_INTERN int CeedRunKernelCuda(Ceed ceed, CUfunction kernel, 35 const int grid_size, 36 const int block_size, void **args); 37 38 CEED_INTERN int CeedRunKernelAutoblockCuda(Ceed ceed, CUfunction kernel, 39 size_t size, void **args); 40 41 CEED_INTERN int CeedRunKernelDimCuda(Ceed ceed, CUfunction kernel, 42 const int grid_size, 43 const int block_size_x, const int block_size_y, 44 const int block_size_z, void **args); 45 46 CEED_INTERN int CeedRunKernelDimSharedCuda(Ceed ceed, CUfunction kernel, 47 const int grid_size, const int block_size_x, const int block_size_y, 48 const int block_size_z, const int shared_mem_size, void **args); 49 50 #endif // _ceed_cuda_compile_h 51