Overview

Module cl

• Description
• Data Types
• Function Index
• Function Details

Description

The erlang api for OpenCL.

OpenCL (Open Computing Language) is an open royalty-free standard for general purpose parallel programming across CPUs, GPUs and other processors, giving software developers portable and efficient access to the power of these heterogeneous processing platforms.

OpenCL supports a wide range of applications, ranging from embedded and consumer software to HPC solutions, through a low-level, high-performance, portable abstraction. By creating an efficient, close-to-the-metal programming interface, OpenCL will form the foundation layer of a parallel computing ecosystem of platform-independent tools, middleware and applications.

OpenCL consists of an API for coordinating parallel computation across heterogeneous processors; and a cross-platform programming language with a well-specified computation environment. The OpenCL standard:

The specification is divided into a core specification that any OpenCL compliant implementation must support; a handheld/embedded profile which relaxes the OpenCL compliance requirements for handheld and embedded devices; and a set of optional extensions that are likely to move into the core specification in later revisions of the OpenCL specification.

The documentation is re-used with the following copyright:

Data Types

cl_addressing_mode()

cl_addressing_mode() = {none | clamp_to_edge | clamp | repeat}

cl_channel_order()

cl_channel_order() = r | a | rg | ra | rgb | rgba | rgba | bgra | argb | intensity | luminance | rx | rgx | rgbx | depth | depth_stencil

cl_channel_type()

cl_channel_type() = snorm_int8 | snorm_int16 | unorm_int8 | unorm_int16 | unorm_short_565 | unorm_short_555 | unorm_int_101010 | signed_int8 | signed_int16 | signed_int32 | unsigned_int8 | unsigned_int16 | unsigned_int32 | half_float | float | unorm_int24

cl_char()

cl_char() = integer()

cl_context()

cl_context() = {{object, 3, non_neg_integer()}}

cl_context_info()

cl_context_info() = {{reference_count, cl_uint()}, {devices, [cl_device()]}, {properties, [cl_int()]}}

cl_context_info_key()

cl_context_info_key() = {reference_count | devices | properties}

cl_device_id()

cl_device_id() = {{object, 2, non_neg_integer()}}

cl_device_info()

cl_device_info() = {cl_device_info_key(), term()}

cl_device_info_key()

cl_device_info_key() = {type | vendor_id | max_compute_units | max_work_item_dimensions | max_work_group_size | max_work_item_sizes | preferred_vector_width_char | preferred_vector_width_short | preferred_vector_width_int | preferred_vector_width_long | preferred_vector_width_float | preferred_vector_width_double | max_clock_frequency | address_bits | max_read_image_args | max_write_image_args | max_mem_alloc_size | image2d_max_width | image2d_max_height | image3d_max_width | image3d_max_height | image3d_max_depth | image_support | max_parameter_size | max_samplers | mem_base_addr_align | min_data_type_align_size | single_fp_config | global_mem_cache_type | global_mem_cacheline_size | global_mem_cache_size | global_mem_size | max_constant_buffer_size | max_constant_args | local_mem_type | local_mem_size | error_correction_support | profiling_timer_resolution | endian_little | available | compiler_available | execution_capabilities | queue_properties | name | vendor | driver_version | profile | version | extensions | platform}

cl_device_type()

cl_device_type() = {gpu | cpu | accelerator | all | default}

cl_device_types()

cl_device_types() = {cl_device_type() | [cl_device_type()]}

cl_double()

cl_double() = float()

cl_error()

cl_error() = {device_not_found | device_not_available | compiler_not_available | mem_object_allocation_failure | out_of_resources | out_of_host_memory | profiling_info_not_available | mem_copy_overlap | image_format_mismatch | image_format_not_supported | build_program_failure | map_failure | invalid_value | 'invalid_device type' | invalid_platform | invalid_device | invalid_context | invalid_queue_properties | invalid_command_queue | invalid_host_ptr | invalid_mem_object | invalid_image_format_descriptor | invalid_image_size | invalid_sampler | invalid_binary | invalid_build_options | invalid_program | invalid_program_executable | invalid_kernel_name | invalid_kernel_definition | invalid_kernel | invalid_arg_index | invalid_arg_value | invalid_arg_size | invalid_kernel_args | invalid_work_dimension | invalid_work_group_size | 'invalid_work_item size' | invalid_global_offset | invalid_event_wait_list | invalid_event | invalid_operation | invalid_gl_object | invalid_buffer_size | invalid_mip_level | unknown}

cl_event()

cl_event() = {{object, 9, non_neg_integer()}}

cl_filter_mode()

cl_filter_mode() = {nearest | linear}

cl_float()

cl_float() = float()

cl_half()

cl_half() = float()

cl_int()

cl_int() = integer()

cl_kernel()

cl_kernel() = {{object, 8, non_neg_integer()}}

cl_kernel_arg()

cl_kernel_arg() = integer() | float() | binary()

cl_long()

cl_long() = integer()

cl_mem()

cl_mem() = {{object, 5, non_neg_integer()}}

cl_mem_flag()

cl_mem_flag() = {read_write | write_only | read_only | use_host_ptr | alloc_host_ptr | copy_host_ptr}

cl_mem_object_type()

cl_mem_object_type() = buffer | image2d | image3d | image2d_array | image1d | image1d_array | image1d_buffer

cl_platform_id()

cl_platform_id() = {{object, 1, non_neg_integer()}}

cl_platform_info()

cl_platform_info() = {profile, string()} | {version, string()} | {name, string()} | {vendor, string()} | {extensions, string()}

cl_platform_info_key()

cl_platform_info_key() = profile | name | vendor | extensions

cl_program()

cl_program() = {{object, 7, non_neg_integer()}}

cl_queue()

cl_queue() = {{object, 4, non_neg_integer()}}

cl_queue_property()

cl_queue_property() = {out_of_order_exec_mode_enable | profiling_enabled}

cl_sampler()

cl_sampler() = {{object, 6, non_neg_integer()}}

cl_short()

cl_short() = integer()

cl_uchar()

cl_uchar() = non_neg_integer()

cl_uint()

cl_uint() = non_neg_integer()

cl_ulong()

cl_ulong() = non_neg_integer()

cl_ushort()

cl_ushort() = non_neg_integer()

start_arg()

start_arg() = {{debug, boolean()}}

Function Index

Function Details

async_build_program/3

async_compile_program/5

async_finish/1

async_flush/1

async_link_program/4

async_wait_for_event/1

Initiate an asynchronous wait operation.

build_program/3

Builds (compiles and links) a program executable from the program source or binary.

OpenCL allows program executables to be built using the source or the binary.

The build options are categorized as pre-processor options, options for math intrinsics, options that control optimization and miscellaneous options. This specification defines a standard set of options that must be supported by an OpenCL compiler when building program executables online or offline. These may be extended by a set of vendor- or platform-specific options.

Preprocessor Options

These options control the OpenCL preprocessor which is run on each program source before actual compilation. -D options are processed in the order they are given in the options argument to build_program/3.

-D name

Predefine name as a macro, with definition 1.

-D name=definition

The contents of definition are tokenized and processed as if they appeared during translation phase three in a #define directive. In particular, the definition will be truncated by embedded newline characters.

-I dir

Add the directory dir to the list of directories to be searched for header files.

Math Intrinsics Options

-cl-single-precision-constant

Treat double precision floating-point constant as single precision constant.

-cl-denorms-are-zero

This option controls how single precision and double precision denormalized numbers are handled. If specified as a build option, the single precision denormalized numbers may be flushed to zero and if the optional extension for double precision is supported, double precision denormalized numbers may also be flushed to zero. This is intended to be a performance hint and the OpenCL compiler can choose not to flush denorms to zero if the device supports single precision (or double precision) denormalized numbers.

This option is ignored for single precision numbers if the device does not support single precision denormalized numbers i.e. CL_FP_DENORM bit is not set in CL_DEVICE_SINGLE_FP_CONFIG.

This option is ignored for double precision numbers if the device does not support double precision or if it does support double precison but CL_FP_DENORM bit is not set in CL_DEVICE_DOUBLE_FP_CONFIG.

This flag only applies for scalar and vector single precision floating-point variables and computations on these floating-point variables inside a program. It does not apply to reading from or writing to image objects.

Optimization Options

-cl-opt-disable

This option disables all optimizations. The default is optimizations are enabled.

-cl-strict-aliasing

This option allows the compiler to assume the strictest aliasing rules.

The following options control compiler behavior regarding floating-point arithmetic. These options trade off between performance and correctness and must be specifically enabled. These options are not turned on by default since it can result in incorrect output for programs which depend on an exact implementation of IEEE 754 rules/specifications for math functions.

-cl-mad-enable

Allow a * b + c to be replaced by a mad. The mad computes a * b + c with reduced accuracy. For example, some OpenCL devices implement mad as truncate the result of a * b before adding it to c.

-cl-no-signed-zeros

Allow optimizations for floating-point arithmetic that ignore the signedness of zero. IEEE 754 arithmetic specifies the behavior of distinct +0.0 and -0.0 values, which then prohibits simplification of expressions such as x+0.0 or 0.0*x (even with -clfinite-math only). This option implies that the sign of a zero result isn't significant.

-cl-unsafe-math-optimizations

Allow optimizations for floating-point arithmetic that (a) assume that arguments and results are valid, (b) may violate IEEE 754 standard and (c) may violate the OpenCL numerical compliance requirements as defined in section 7.4 for single-precision floating-point, section 9.3.9 for double-precision floating-point, and edge case behavior in section 7.5. This option includes the -cl-no-signed-zeros and -cl-mad-enable options.

-cl-finite-math-only

Allow optimizations for floating-point arithmetic that assume that arguments and results are not NaNs or ±infinity. This option may violate the OpenCL numerical compliance requirements defined in in section 7.4 for single-precision floating-point, section 9.3.9 for double-precision floating-point, and edge case behavior in section 7.5.

-cl-fast-relaxed-math

Sets the optimization options -cl-finite-math-only and -cl-unsafe-math-optimizations. This allows optimizations for floating-point arithmetic that may violate the IEEE 754 standard and the OpenCL numerical compliance requirements defined in the specification in section 7.4 for single-precision floating-point, section 9.3.9 for double-precision floating-point, and edge case behavior in section 7.5. This option causes the preprocessor macro __FAST_RELAXED_MATH__ to be defined in the OpenCL program.

Options to Request or Suppress Warnings

-w

Inhibit all warning messages.

-Werror

Make all warnings into errors.

compile_program/5

context_info/0

List context info queries.

create_buffer/3

Equivalent to create_buffer(Context, Flags, Size, <<>>).

create_buffer/4

Creates a buffer object.

create_context/1

Creates an OpenCL context.

An OpenCL context is created with one or more devices. Contexts are used by the OpenCL runtime for managing objects such as command-queues, memory, program and kernel objects and for executing kernels on one or more devices specified in the context.

create_context_from_type/1

Create an OpenCL context from a device type that identifies the specific device(s) to use.

NOTE: create_context_from_type/1 may return all or a subset of the actual physical devices present in the platform and that match device_type.

create_image/5

create_image2d/7

create_image3d/9

create_kernel/2

Creates a kernal object.

create_kernels_in_program/1

Creates kernel objects for all kernel functions in a program object.

create_program_with_binary/3

Creates a program object for a context, and loads specified binary data into the program object.

OpenCL allows applications to create a program object using the program source or binary and build appropriate program executables. This allows applications to determine whether they want to use the pre-built offline binary or load and compile the program source and use the executable compiled/linked online as the program executable. This can be very useful as it allows applications to load and build program executables online on its first instance for appropriate OpenCL devices in the system. These executables can now be queried and cached by the application. Future instances of the application launching will no longer need to compile and build the program executables. The cached executables can be read and loaded by the application, which can help significantly reduce the application initialization time.

create_program_with_builtin_kernels/3

create_program_with_source/2

Creates a program object for a context, and loads the source code specified by the text strings in the strings array into the program object.

create_queue/3

Create a command-queue on a specific device.

'out_of_order_exec_mode_enable'

Determines whether the commands queued in the command-queue are executed in-order or out-of-order. If set, the commands in the command-queue are executed out-of-order. Otherwise, commands are executed in-order.

'profiling_enabled'

Enable or disable profiling of commands in the command-queue. If set, the profiling of commands is enabled. Otherwise profiling of commands is disabled. See clGetEventProfilingInfo for more information.

The OpenCL functions that are submitted to a command-queue are enqueued in the order the calls are made but can be configured to execute in-order or out-of-order. The properties argument in clCreateCommandQueue can be used to specify the execution order.

If the 'out_of_order_exec_mode_enable' property of a command-queue is not set, the commands enqueued to a command-queue execute in order. For example, if an application calls clEnqueueNDRangeKernel to execute kernel A followed by a clEnqueueNDRangeKernel to execute kernel B, the application can assume that kernel A finishes first and then kernel B is executed. If the memory objects output by kernel A are inputs to kernel B then kernel B will see the correct data in memory objects produced by execution of kernel A. If the 'out_of_order_exec_mode_enable' property of a commandqueue is set, then there is no guarantee that kernel A will finish before kernel B starts execution.

Applications can configure the commands enqueued to a command-queue to execute out-of-order by setting the 'out_of_order_exec_mode_enable' property of the command-queue. This can be specified when the command-queue is created or can be changed dynamically using clCreateCommandQueue. In out-of-order execution mode there is no guarantee that the enqueued commands will finish execution in the order they were queued. As there is no guarantee that kernels will be executed in order, i.e. based on when the clEnqueueNDRangeKernel calls are made within a command-queue, it is therefore possible that an earlier clEnqueueNDRangeKernel call to execute kernel A identified by event A may execute and/or finish later than a clEnqueueNDRangeKernel call to execute kernel B which was called by the application at a later point in time. To guarantee a specific order of execution of kernels, a wait on a particular event (in this case event A) can be used. The wait for event A can be specified in the event_wait_list argument to clEnqueueNDRangeKernel for kernel B.

In addition, a wait for events or a barrier command can be enqueued to the command-queue. The wait for events command ensures that previously enqueued commands identified by the list of events to wait for have finished before the next batch of commands is executed. The barrier command ensures that all previously enqueued commands in a command-queue have finished execution before the next batch of commands is executed.

create_sampler/4

Creates a sampler object.

create_sub_buffer/4

Creates a buffer object

create_sub_devices/2

device_info/0

Return a list of possible device info queries.

See also: get_device_info/2.

device_info_10/1

device_info_11/1

device_info_12/1

enqueue_barrier/1

A synchronization point that enqueues a barrier operation.

enqueue_barrier_with_wait_list/2

enqueue_copy_buffer/7

enqueue_copy_buffer_rect/11

enqueue_copy_buffer_to_image/7

enqueue_copy_image/6

enqueue_copy_image_to_buffer/7

enqueue_fill_buffer/6

enqueue_fill_image/6

enqueue_map_buffer/6

enqueue_map_image/6

enqueue_marker/1

Enqueues a marker command.

enqueue_marker_with_wait_list/2

enqueue_migrate_mem_objects/4

enqueue_nd_range_kernel/5

Enqueues a command to execute a kernel on a device.

Work-group instances are executed in parallel across multiple compute units or concurrently on the same compute unit.

enqueue_nd_range_kernel/6

enqueue_read_buffer/5

Enqueue commands to read from a buffer object to host memory.

Calling enqueue_read_buffer to read a region of the buffer object with the Buffer argument value set to host_ptr + offset, where host_ptr is a pointer to the memory region specified when the buffer object being read is created with CL_MEM_USE_HOST_PTR, must meet the following requirements in order to avoid undefined behavior:

• All commands that use this buffer object have finished execution before the read command begins execution
• The buffer object is not mapped
• The buffer object is not used by any command-queue until the read command has finished execution

enqueue_read_buffer_rect/10

enqueue_read_image/7

enqueue_task/3

Enqueues a command to execute a kernel on a device.

See also: enqueue_nd_range_kernel/5.

enqueue_task/4

enqueue_unmap_mem_object/3

enqueue_wait_for_events/2

Enqueues a wait for a specific event or a list of events to complete before any future commands queued in the command-queue are executed.

enqueue_write_buffer/6

Enqueue commands to write to a buffer object from host memory.

Calling enqueue_write_buffer to update the latest bits in a region of the buffer object with the Buffer argument value set to host_ptr + offset, where host_ptr is a pointer to the memory region specified when the buffer object being read is created with CL_MEM_USE_HOST_PTR, must meet the following requirements in order to avoid undefined behavior:

• The host memory region given by (host_ptr + offset, cb) contains the latest bits when the enqueued write command begins execution.
• The buffer object is not mapped
• The buffer object is not used by any command-queue until the read command has finished execution

enqueue_write_buffer/7

enqueue_write_buffer_rect/11

enqueue_write_image/8

enqueue_write_image/9

event_info/0

Returns all possible event_info items.

finish/1

Blocks until all previously queued OpenCL commands in a command-queue are issued to the associated device and have completed.

flush/1

Issues all previously queued OpenCL commands in a command-queue to the device associated with the command-queue.

get_context_info/1

Get all context info.

See also: get_context_info/2.

get_context_info/2

Query information about a context.

reference_count

Return the context reference count. The reference count returned should be considered immediately stale. It is unsuitable for general use in applications. This feature is provided for identifying memory leaks.

devices

Return the list of devices in context.

properties

Return the context properties.

get_device_ids/0

Equivalent to get_devive_ids(0, all).

get_device_ids/2

Obtain the list of devices available on a platform.

Platform

Refers to the platform ID returned by get_platform_ids or can be NULL. If platform is NULL, the behavior is implementation-defined.

Type

A list that identifies the type of OpenCL device. The device_type can be used to query specific OpenCL devices or all OpenCL devices available.

get_device_ids/2 may return all or a subset of the actual physical devices present in the platform and that match device_type.

get_device_info/1

Get all device info.

See also: get_device_info/2.

get_device_info/2

Get information about an OpenCL device.

'type'

The OpenCL device type. Currently supported values are one of or a combination of: CL_DEVICE_TYPE_CPU, CL_DEVICE_TYPE_GPU, CL_DEVICE_TYPE_ACCELERATOR, or CL_DEVICE_TYPE_DEFAULT.

'vendor_id'

A unique device vendor identifier. An example of a unique device identifier could be the PCIe ID.

'max_compute_units'

The number of parallel compute cores on the OpenCL device. The minimum value is 1.

'max_work_item_dimensions'

Maximum dimensions that specify the global and local work-item IDs used by the data parallel execution model. (@see enqueue_nd_range_kernel/5). The minimum value is 3.

'max_work_group_size'

Maximum number of work-items in a work-group executing a kernel using the data parallel execution model. (@see enqueue_nd_range_kernel/5). The minimum value is 1.

'max_work_item_sizes'

Maximum number of work-items that can be specified in each dimension of the work-group to enqueue_nd_range_kernel/5.

Returns n entries, where n is the value returned by the query for CL_DEVICE_MAX_WORK_ITEM_DIMENSIONS. The minimum value is (1, 1, 1).

'preferred_vector_width_TYPE'

Preferred native vector width size for built-in scalar types that can be put into vectors. The vector width is defined as the number of scalar elements that can be stored in the vector.

If the cl_khr_fp64 extension is not supported, CL_DEVICE_PREFERRED_VECTOR_WIDTH_DOUBLE must return 0.

'max_clock_frequency'

Maximum configured clock frequency of the device in MHz.

'address_bits'

The default compute device address space size specified as an unsigned integer value in bits. Currently supported values are 32 or 64 bits.

'max_read_image_args'

Max number of simultaneous image objects that can be read by a kernel. The minimum value is 128 if CL_DEVICE_IMAGE_SUPPORT is CL_TRUE.

'max_write_image_args'

Max number of simultaneous image objects that can be written to by a kernel. The minimum value is 8 if CL_DEVICE_IMAGE_SUPPORT is CL_TRUE.

'max_mem_alloc_size'

Max size of memory object allocation in bytes. The minimum value is max (1/4th of CL_DEVICE_GLOBAL_MEM_SIZE, 128*1024*1024)

'image2d_max_width'

Max width of 2D image in pixels. The minimum value is 8192 if CL_DEVICE_IMAGE_SUPPORT is CL_TRUE.

'image2d_max_height'

Max height of 2D image in pixels. The minimum value is 8192 if CL_DEVICE_IMAGE_SUPPORT is CL_TRUE.

'image3d_max_width'

Max width of 3D image in pixels. The minimum value is 2048 if CL_DEVICE_IMAGE_SUPPORT is CL_TRUE.

'image3d_max_height'

Max height of 3D image in pixels. The minimum value is 2048 if CL_DEVICE_IMAGE_SUPPORT is CL_TRUE.

'image3d_max_depth'

Max depth of 3D image in pixels. The minimum value is 2048 if CL_DEVICE_IMAGE_SUPPORT is CL_TRUE.

'image_support'

Is CL_TRUE if images are supported by the OpenCL device and CL_FALSE otherwise.

'max_parameter_size'

Max size in bytes of the arguments that can be passed to a kernel. The minimum value is 256.

'max_samplers'

Maximum number of samplers that can be used in a kernel. The minimum value is 16 if CL_DEVICE_IMAGE_SUPPORT is CL_TRUE.

'mem_base_addr_align'

Describes the alignment in bits of the base address of any allocated memory object.

'min_data_type_align_size'

The smallest alignment in bytes which can be used for any data type.

'single_fp_config'

Describes single precision floating-point capability of the device. This is a bit-field that describes one or more of the following values:

CL_FP_DENORM - denorms are supported

CL_FP_INF_NAN - INF and quiet NaNs are supported

CL_FP_ROUND_TO_NEAREST - round to nearest even rounding mode supported

CL_FP_ROUND_TO_ZERO - round to zero rounding mode supported

CL_FP_ROUND_TO_INF - round to +ve and -ve infinity rounding modes supported

CL_FP_FMA - IEEE754-2008 fused multiply-add is supported

The mandated minimum floating-point capability is CL_FP_ROUND_TO_NEAREST | CL_FP_INF_NAN.

'global_mem_cache_type'

Return type: cl_device_mem_cache_type

Type of global memory cache supported. Valid values are: CL_NONE, CL_READ_ONLY_CACHE, and CL_READ_WRITE_CACHE.

'global_mem_cacheline_size'

Size of global memory cache line in bytes.

'global_mem_cache_size'

Size of global memory cache in bytes.

'global_mem_size'

Size of global device memory in bytes.

'max_constant_buffer_size'

Max size in bytes of a constant buffer allocation. The minimum value is 64 KB.

'max_constant_args'

Max number of arguments declared with the __constant qualifier in a kernel. The minimum value is 8.

'local_mem_type'

Type of local memory supported. This can be set to CL_LOCAL implying dedicated local memory storage such as SRAM, or CL_GLOBAL.

'local_mem_size'

Size of local memory arena in bytes. The minimum value is 16 KB.

'error_correction_support'

Is CL_TRUE if the device implements error correction for the memories, caches, registers etc. in the device. Is CL_FALSE if the device does not implement error correction. This can be a requirement for certain clients of OpenCL.

'profiling_timer_resolution'

Describes the resolution of device timer. This is measured in nanoseconds.

'endian_little'

Is CL_TRUE if the OpenCL device is a little endian device and CL_FALSE otherwise.

'available'

Is CL_TRUE if the device is available and CL_FALSE if the device is not available.

'compiler_available'

Is CL_FALSE if the implementation does not have a compiler available to compile the program source. Is CL_TRUE if the compiler is available. This can be CL_FALSE for the embededed platform profile only.

'execution_capabilities'

Return type: cl_device_exec_capabilities

Describes the execution capabilities of the device. This is a bit-field that describes one or more of the following values:

CL_EXEC_KERNEL - The OpenCL device can execute OpenCL kernels.

CL_EXEC_NATIVE_KERNEL - The OpenCL device can execute native kernels.

The mandated minimum capability is CL_EXEC_KERNEL.

'queue_properties'

Describes the command-queue properties supported by the device. This is a bit-field that describes one or more of the following values:

'out_of_order_exec_mode_enable'

'profiling_enable'

These properties are described in the table for create_queue/3 . The mandated minimum capability is 'profiling_enable'.

'name'

Device name string.

'vendor'

Vendor name string.

'driver_version'

OpenCL software driver version string

'profile'

OpenCL profile string. Returns the profile name supported by the device (see note). The profile name returned can be one of the following strings:

FULL_PROFILE - if the device supports the OpenCL specification (functionality defined as part of the core specification and does not require any extensions to be supported).

EMBEDDED_PROFILE - if the device supports the OpenCL embedded profile.

'version'

OpenCL version string.

'extensions'

Returns a space separated list of extension names (the extension names themselves do not contain any spaces).

'platform'

The platform associated with this device.

get_event_info/1

Returns all specific information about the event object.

get_event_info/2

Returns specific information about the event object.

get_image_info/1

get_image_info/2

get_kernel_arg_info/1

get_kernel_arg_info/2

get_kernel_arg_info/3

Returns specific information about the kernel argument

get_kernel_info/1

Returns all information about the kernel object.

get_kernel_info/2

Returns specific information about the kernel object.

get_kernel_workgroup_info/2

Returns all information about the kernel object that may be specific to a device.

get_kernel_workgroup_info/3

Returns specific information about the kernel object that may be specific to a device.

get_mem_object_info/1

Used to get all information that is common to all memory objects (buffer and image objects).

get_mem_object_info/2

Used to get InfoType information that is common to all memory objects (buffer and image objects).

get_platform_ids/0

Obtain the list of platforms available.

get_platform_info/1

Get all information about the OpenCL platform.

See also: get_platform_info/2.

get_platform_info/2

Get specific information about the OpenCL platform.

name

Platform name string.

vendor

Platform vendor string.

profile

OpenCL profile string. Returns the profile name supported by the implementation. The profile name returned can be one of the following strings:

FULL_PROFILE - if the implementation supports the OpenCL specification (functionality defined as part of the core specification and does not require any extensions to be supported).

EMBEDDED_PROFILE - if the implementation supports the OpenCL embedded profile. The embedded profile is defined to be a subset for each version of OpenCL.

version

OpenCL version string. Returns the OpenCL version supported by the implementation.

extensions

Returns a space-separated list of extension names (the extension names themselves do not contain any spaces) supported by the platform. Extensions defined here must be supported by all devices associated with this platform.

get_program_build_info/2

Returns all build information for each device in the program object.

get_program_build_info/3

Returns specific build information for each device in the program object.

get_program_info/1

Returns all information about the program object.

get_program_info/2

Returns specific information about the program object.

get_queue_info/1

Returns all queue info.

get_queue_info/2

Return the specified queue info

get_sampler_info/1

Returns all information about the sampler object.

See also: get_sampler_info/2.

get_sampler_info/2

Returns InfoType information about the sampler object.

get_supported_image_formats/3

return a list of image formats [{Order,Type}]

image_info/0

kernel_arg_info/0

kernel_info/0

kernel_workgroup_info/0

link_program/4

mem_object_info/0

Returns a list of the possible mem info keys.

noop/0

Run a no operation towards the NIF object. This call can be used to messure the call overhead to the NIF objeect.

nowait_enqueue_nd_range_kernel/5

nowait_enqueue_task/3

nowait_enqueue_write_buffer/6

nowait_enqueue_write_image/8

platform_info/0

Returns a list of the possible platform info keys.

program_build_info/0

program_info/0

queue_info/0

Returns the list of possible queue info items.

release_context/1

Decrement the context reference count.

release_device/1

release_event/1

Decrements the event reference count.

release_kernel/1

Decrements the kernel reference count.

release_mem_object/1

Decrements the memory object reference count.

release_program/1

Decrements the program reference count.

release_queue/1

Decrements the command_queue reference count.

release_sampler/1

Decrements the sampler reference count.

retain_context/1

Increment the context reference count.

See also: create_context.

retain_device/1

retain_event/1

Increments the event reference count. NOTE: The OpenCL commands that return an event perform an implicit retain.

retain_kernel/1

Increments the program kernel reference count.

retain_mem_object/1

Increments the memory object reference count.

retain_program/1

Increments the program reference count.

retain_queue/1

Increments the command_queue reference count.

retain_sampler/1

Increments the sampler reference count.

sampler_info/0

set_kernel_arg/3

Used to set the argument value for a specific argument of a kernel.

For now set_kernel_arg handles integer and floats to set any other type use <<Foo:Bar/native...>> use the macros defined in cl.hrl to get it right (except for padding)

A kernel object does not update the reference count for objects such as memory, sampler objects specified as argument values by set_kernel_arg/3, Users may not rely on a kernel object to retain objects specified as argument values to the kernel.

set_kernel_arg_size/3

clErlang special to set kernel arg with size only (local mem etc)

set_queue_property/3

Function is deprecated and have been removed.

start/0

Equivalent to start([]).

Start the OpenCL application

start/1

Start the OpenCL application

stop/0

Equivalent to application:stop(cl).

Stop the OpenCL application

unload_compiler/0

Allows the implementation to release the resources allocated by the OpenCL compiler.

unload_platform_compiler/1

versions/0

Run a no operation towards the NIF object. This call can be used to messure the call overhead to the NIF objeect.

wait/1

wait/2

Waits for commands identified by event objects to complete.

wait_for_event/1

Equivalent to wait(Event, infinity).

wait_for_events/1

Overview

Generated by EDoc, Jan 19 2017, 13:55:09.