Stan Math Library
5.0.0
Automatic Differentiation
|
The API to access the methods and values in opencl_context_base.
Definition at line 210 of file opencl_context.hpp.
#include <opencl_context.hpp>
Public Member Functions | |
opencl_context ()=default | |
std::string | description () const |
Returns the description of the OpenCL platform and device that is used. | |
std::string | capabilities () const |
Returns the description of the OpenCL platforms and devices that are available. | |
cl::Context & | context () noexcept |
Returns the reference to the OpenCL context. | |
cl::CommandQueue & | queue () noexcept |
Returns the reference to the active OpenCL command queue for the device. | |
opencl_context_base::map_base_opts & | base_opts () noexcept |
Returns a copy of the map of kernel defines. | |
int | max_thread_block_size () noexcept |
Returns the maximum thread block size defined by CL_DEVICE_MAX_WORK_GROUP_SIZE for the device in the context. | |
opencl_context_base::tuning_struct & | tuning_opts () noexcept |
Returns the thread block size for the Cholesky Decompositions L_11. | |
std::vector< cl::Device > & | device () noexcept |
Returns a vector containing the OpenCL device used to create the context. | |
std::vector< cl::Platform > & | platform () noexcept |
Returns a vector containing the OpenCL platform used to create the context. | |
bool & | in_order () noexcept |
Return a bool representing whether the write to the OpenCL device are blocking. | |
void | select_device (int platform_id, int instance_id) |
Selects the OpenCL device to use from now on. | |
void | register_kernel_cache (cl::Kernel *cache) |
Registers a cached kernel. | |
Private Attributes | |
tbb::concurrent_vector< cl::Kernel * > | kernel_caches_ |