\internal_

Returns the size (width, height) of the image.

AMD platforms have a bug when using struct assignment. this affects algorithms like fill() when used with pairs/tuples. see: https://community.amd.co

\internal_

Enqueues a command to read data from \p image to host memory. \see_opencl_ref{clEnqueueReadImage}

Enqueues a command to copy \p size bytes of data from \p src_ptr to \p dst_ptr. \opencl_version_warning{2,0} \see_opencl2_ref{clEnqueueSVMMemcpy}

Enqueues a command to write data from host memory to \p buffer. The copy is performed asynchronously. \see_opencl_ref{clEnqueueWriteBuffer} \see cop

Returns a pointer to the \c cl_image_format object.

Creates a shared OpenCL/OpenGL context for the currently active OpenGL context. Once created, the shared context can be used to create OpenCL memory

Returns the build log.

Returns the number of compute units in the device.

create a lambda context for kernel with args

Returns a vector containing all of the compute devices on the system. For example, to print out the name of each OpenCL-capable device available on t

Enqueues a command to copy data from \p src_buffer to \p dst_buffer. \see_opencl_ref{clEnqueueCopyBuffer} \see copy()

Enqueues a command to map \p buffer into the host address space. Event associated with map operation is returned through \p map_buffer_event parameter

Enqueues a command to copy \p size bytes of data from \p src_ptr to \p dst_ptr. The operation is performed asynchronously. \opencl_version_warning{2,

Enqueues a command to write data from host memory to \p image. \see_opencl_ref{clEnqueueWriteImage}

returns true if the device is an amd cpu or gpu

Enqueues a command to acquire the specified OpenGL memory objects. \see_opencl_ref{clEnqueueAcquireGLObjects}

Enqueues a command to release the specified OpenGL memory objects. \see_opencl_ref{clEnqueueReleaseGLObjects}

Returns the origin of the image (\c 0, \c 0).

Returns the origin of the texture (\c 0, \c 0).

Returns the number of elements in the vector.

generic square function definition

Returns the type of the device.

Blocks until the computation is complete.

Returns a C-string description of the error.

Returns the binary for the program.

clEnqueueSVMMemcpy() operation does not work on AMD devices. This affects copy() algorithm. see: https://community.amd.com/thread/190585

Given a total number of values (count), a number of values to process per thread (vtp), and a number of threads to execute per block (tpb), this funct

\internal_

Generates \p z random numbers and discards them.

Enqueues a command to fill \p buffer with \p pattern. \see_opencl_ref{clEnqueueFillBuffer} \opencl_version_warning{1,2} \see fill()

Enqueues a command to fill \p image with \p fill_color. \see_opencl_ref{clEnqueueFillImage} \opencl_version_warning{1,2}

Enqueues a command to read data from \p buffer to host memory. The copy will be performed asynchronously. \see_opencl_ref{clEnqueueReadBuffer} \see

Enqueues a command to fill \p size bytes of data at \p svm_ptr with \p pattern. \opencl_version_warning{2,0} \see_opencl2_ref{clEnqueueSVMMemFill}

Enqueues a command to map \p svm_ptr to the host memory space. \opencl_version_warning{2,0} \see_opencl2_ref{clEnqueueSVMMap}