forked from lijiext/lammps
4366bfffd3
git-svn-id: svn://svn.icms.temple.edu/lammps-ro/trunk@5285 f3b2605a-c512-4ea7-a41b-209d697bcdaa |
||
---|---|---|
.. | ||
README | ||
VERSION.txt | ||
file_to_cstr.sh | ||
nvc_device.h | ||
nvc_macros.h | ||
nvc_texture.h | ||
nvd_device.h | ||
nvd_kernel.h | ||
nvd_macros.h | ||
nvd_mat.h | ||
nvd_memory.h | ||
nvd_texture.h | ||
nvd_timer.h | ||
ocl_device.h | ||
ocl_kernel.h | ||
ocl_mat.h | ||
ocl_texture.h | ||
ocl_timer.h | ||
ucl_arg_kludge.h | ||
ucl_basemat.h | ||
ucl_copy.h | ||
ucl_d_mat.h | ||
ucl_d_vec.h | ||
ucl_get_devices.cpp | ||
ucl_h_mat.h | ||
ucl_h_vec.h | ||
ucl_nv_kernel.h | ||
ucl_print.h | ||
ucl_types.h |
README
Geryon Copyright (2010) Sandia Corporation. Under the terms of Contract DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains certain rights in this software. This software is distributed under the Simplified BSD License. Geryon is intended to be a simple library for managing the CUDA Runtime, CUDA Driver, and OpenCL APIs with a consistent interface: * Change from one API to another by simply changing the namespace * Use multiple APIs in the same code * Lightweight (only include files - no build required) * Manage device query and selection * Simple vector and matrix containers * Simple routines for data copy and type casting * Simple routines for data I/O * Simple classes for managing device timing * Simple classes for managing kernel compilation and execution Geryon does not require building (although a Makefile is provided for testing purposes). The library is a set of header files that can be included with your code. Documentation and examples are provided at http://users.nccs.gov/~wb8/geryon/index.htm