OpenCL Runtime

Version Queries

pyopencl.VERSION

Gives the numeric version of PyOpenCL as a variable-length tuple of integers. Enables easy version checks such as VERSION >= (0, 93).

pyopencl.VERSION_STATUS

A text string such as “rc4” or “beta” qualifying the status of the release.

pyopencl.VERSION_TEXT

The full release name (such as “0.93rc4”) in string form.

pyopencl.get_cl_header_version()

Return a variable-length tuple of integers representing the version of the OpenCL header against which PyOpenCL was compiled.

New in version 0.92.

Error Reporting

class pyopencl.Error

Base class for all PyOpenCL exceptions.

class pyopencl.MemoryError
class pyopencl.LogicError
class pyopencl.RuntimeError

Constants

Warning

This set of PyOpenCL documentation is incomplete because it was generated on a PyOpenCL build that did not support OpenGL.

class pyopencl.addressing_mode
CLAMP
CLAMP_TO_EDGE
MIRRORED_REPEAT

Available with OpenCL 1.1.

New in version 0.92.

NONE
REPEAT
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.affinity_domain_ext
L1_CACHE

Available with the cl_ext_device_fission extension.

New in version 2011.1.

L2_CACHE

Available with the cl_ext_device_fission extension.

New in version 2011.1.

L3_CACHE

Available with the cl_ext_device_fission extension.

New in version 2011.1.

L4_CACHE

Available with the cl_ext_device_fission extension.

New in version 2011.1.

NEXT_FISSIONABLE

Available with the cl_ext_device_fission extension.

New in version 2011.1.

NUMA

Available with the cl_ext_device_fission extension.

New in version 2011.1.

to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.channel_order
A
BGRA
INTENSITY
LUMINANCE
R
RA
RG
RGB
RGBA
RGBx

Available with OpenCL 1.1.

New in version 0.92.

RGx

Available with OpenCL 1.1.

New in version 0.92.

Rx

Available with OpenCL 1.1.

New in version 0.92.

to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.channel_type
FLOAT
HALF_FLOAT
SIGNED_INT16
SIGNED_INT32
SIGNED_INT8
SNORM_INT16
SNORM_INT8
UNORM_INT16
UNORM_INT8
UNORM_INT_101010
UNORM_SHORT_555
UNORM_SHORT_565
UNSIGNED_INT16
UNSIGNED_INT32
UNSIGNED_INT8
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.command_execution_status
COMPLETE
QUEUED
RUNNING
SUBMITTED
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.command_queue_info
CONTEXT
DEVICE
PROPERTIES
REFERENCE_COUNT
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.command_queue_properties
OUT_OF_ORDER_EXEC_MODE_ENABLE
PROFILING_ENABLE
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.command_type
ACQUIRE_GL_OBJECTS
BARRIER

Available with OpenCL 1.2.

New in version 2011.2.

COPY_BUFFER
COPY_BUFFER_RECT

Available with OpenCL 1.1.

New in version 0.92.

COPY_BUFFER_TO_IMAGE
COPY_IMAGE
COPY_IMAGE_TO_BUFFER
FILL_BUFFER

Available with OpenCL 1.2.

New in version 2011.2.

FILL_IMAGE

Available with OpenCL 1.2.

New in version 2011.2.

MAP_BUFFER
MAP_IMAGE
MARKER
MIGRATE_MEM_OBJECTS

Available with OpenCL 1.2.

New in version 2011.2.

NATIVE_KERNEL
NDRANGE_KERNEL
READ_BUFFER
READ_BUFFER_RECT

Available with OpenCL 1.1.

New in version 0.92.

READ_IMAGE
RELEASE_GL_OBJECTS
TASK
UNMAP_MEM_OBJECT
USER

Available with OpenCL 1.1.

New in version 0.92.

WRITE_BUFFER
WRITE_BUFFER_RECT

Available with OpenCL 1.1.

New in version 0.92.

WRITE_IMAGE
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.context_info
DEVICES
INTEROP_USER_SYNC

Available with OpenCL 1.2.

New in version 2011.2.

NUM_DEVICES

Available with OpenCL 1.1.

New in version 0.92.

PROPERTIES
REFERENCE_COUNT
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.context_properties
OFFLINE_DEVICES_AMD

Available with the cl_amd_offline_devices extension.

New in version 2011.1.

PLATFORM
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.device_affinity_domain
L1_CACHE

Available with OpenCL 1.2.

New in version 2011.2.

L2_CACHE

Available with OpenCL 1.2.

New in version 2011.2.

L3_CACHE

Available with OpenCL 1.2.

New in version 2011.2.

L4_CACHE

Available with OpenCL 1.2.

New in version 2011.2.

NEXT_PARTITIONABLE
NUMA

Available with OpenCL 1.2.

New in version 2011.2.

to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.device_exec_capabilities
KERNEL
NATIVE_KERNEL
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.device_fp_config
CORRECTLY_ROUNDED_DIVIDE_SQRT

Available with OpenCL 1.2.

New in version 2011.2.

DENORM
FMA
INF_NAN
ROUND_TO_INF
ROUND_TO_NEAREST
ROUND_TO_ZERO
SOFT_FLOAT

Available with OpenCL 1.1.

New in version 0.92.

to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.device_info
ADDRESS_BITS
AFFINITY_DOMAINS_EXT

Available with the cl_ext_device_fission extension.

New in version 2011.1.

AVAILABLE
BOARD_NAME_AMD

Available with the cl_amd_device_attribute_query extension.

New in version 2013.2.

BUILT_IN_KERNELS

Available with OpenCL 1.2.

New in version 2011.2.

COMPILER_AVAILABLE
COMPUTE_CAPABILITY_MAJOR_NV

Available with the cl_nv_device_attribute_query extension.

New in version 0.92.

COMPUTE_CAPABILITY_MINOR_NV

Available with the cl_nv_device_attribute_query extension.

New in version 0.92.

DOUBLE_FP_CONFIG

Available with the cl_khr_fp64 extension.

New in version 2011.1.

DRIVER_VERSION
ENDIAN_LITTLE
ERROR_CORRECTION_SUPPORT
EXECUTION_CAPABILITIES
EXTENSIONS
GLOBAL_FREE_MEMORY_AMD

Available with the cl_amd_device_attribute_query extension.

New in version 2013.2.

GLOBAL_MEM_CACHELINE_SIZE
GLOBAL_MEM_CACHE_SIZE
GLOBAL_MEM_CACHE_TYPE
GLOBAL_MEM_CHANNELS_AMD

Available with the cl_amd_device_attribute_query extension.

New in version 2013.2.

GLOBAL_MEM_CHANNEL_BANKS_AMD

Available with the cl_amd_device_attribute_query extension.

New in version 2013.2.

GLOBAL_MEM_CHANNEL_BANK_WIDTH_AMD

Available with the cl_amd_device_attribute_query extension.

New in version 2013.2.

GLOBAL_MEM_SIZE
GPU_OVERLAP_NV

Available with the cl_nv_device_attribute_query extension.

New in version 0.92.

HALF_FP_CONFIG

Available with the cl_khr_fp16 extension.

New in version 2011.1.

HOST_UNIFIED_MEMORY

Available with OpenCL 1.1.

New in version 0.92.

IMAGE2D_MAX_HEIGHT
IMAGE2D_MAX_WIDTH
IMAGE3D_MAX_DEPTH
IMAGE3D_MAX_HEIGHT
IMAGE3D_MAX_WIDTH
IMAGE_MAX_ARRAY_SIZE

Available with OpenCL 1.2.

New in version 2011.2.

IMAGE_MAX_BUFFER_SIZE

Available with OpenCL 1.2.

New in version 2011.2.

IMAGE_SUPPORT
INTEGRATED_MEMORY_NV

Available with the cl_nv_device_attribute_query extension.

New in version 0.92.

KERNEL_EXEC_TIMEOUT_NV

Available with the cl_nv_device_attribute_query extension.

New in version 0.92.

LINKER_AVAILABLE

Available with OpenCL 1.2.

New in version 2011.2.

LOCAL_MEM_BANKS_AMD

Available with the cl_amd_device_attribute_query extension.

New in version 2013.2.

LOCAL_MEM_SIZE
LOCAL_MEM_SIZE_PER_COMPUTE_UNIT_AMD

Available with the cl_amd_device_attribute_query extension.

New in version 2013.2.

LOCAL_MEM_TYPE
MAX_ATOMIC_COUNTERS_EXT

Available with the cl_ext_atomic_counters_64 extension.

New in version 2013.2.

MAX_CLOCK_FREQUENCY
MAX_COMPUTE_UNITS
MAX_CONSTANT_ARGS
MAX_CONSTANT_BUFFER_SIZE
MAX_MEM_ALLOC_SIZE
MAX_PARAMETER_SIZE
MAX_READ_IMAGE_ARGS
MAX_SAMPLERS
MAX_WORK_GROUP_SIZE
MAX_WORK_ITEM_DIMENSIONS
MAX_WORK_ITEM_SIZES
MAX_WRITE_IMAGE_ARGS
MEM_BASE_ADDR_ALIGN
MIN_DATA_TYPE_ALIGN_SIZE
NAME
NATIVE_VECTOR_WIDTH_CHAR

Available with OpenCL 1.1.

New in version 0.92.

NATIVE_VECTOR_WIDTH_DOUBLE

Available with OpenCL 1.1.

New in version 0.92.

NATIVE_VECTOR_WIDTH_FLOAT

Available with OpenCL 1.1.

New in version 0.92.

NATIVE_VECTOR_WIDTH_HALF

Available with OpenCL 1.1.

New in version 0.92.

NATIVE_VECTOR_WIDTH_INT

Available with OpenCL 1.1.

New in version 0.92.

NATIVE_VECTOR_WIDTH_LONG

Available with OpenCL 1.1.

New in version 0.92.

NATIVE_VECTOR_WIDTH_SHORT

Available with OpenCL 1.1.

New in version 0.92.

OPENCL_C_VERSION

Available with OpenCL 1.1.

New in version 0.92.

PARENT_DEVICE

Available with OpenCL 1.2.

New in version 2011.2.

PARENT_DEVICE_EXT

Available with the cl_ext_device_fission extension.

New in version 2011.1.

PARTITION_AFFINITY_DOMAIN

Available with OpenCL 1.2.

New in version 2011.2.

PARTITION_MAX_SUB_DEVICES

Available with OpenCL 1.2.

New in version 2011.2.

PARTITION_PROPERTIES

Available with OpenCL 1.2.

New in version 2011.2.

PARTITION_STYLE_EXT

Available with the cl_ext_device_fission extension.

New in version 2011.1.

PARTITION_TYPE

Available with OpenCL 1.2.

New in version 2011.2.

PARTITION_TYPES_EXT

Available with the cl_ext_device_fission extension.

New in version 2011.1.

PLATFORM
PREFERRED_INTEROP_USER_SYNC

Available with OpenCL 1.2.

New in version 2011.2.

PREFERRED_VECTOR_WIDTH_CHAR
PREFERRED_VECTOR_WIDTH_DOUBLE
PREFERRED_VECTOR_WIDTH_FLOAT
PREFERRED_VECTOR_WIDTH_HALF

Available with OpenCL 1.1.

New in version 0.92.

PREFERRED_VECTOR_WIDTH_INT
PREFERRED_VECTOR_WIDTH_LONG
PREFERRED_VECTOR_WIDTH_SHORT
PRINTF_BUFFER_SIZE

Available with OpenCL 1.2.

New in version 2011.2.

PROFILE
PROFILING_TIMER_OFFSET_AMD

Available with the cl_amd_device_attribute_query extension.

New in version 2013.2.

PROFILING_TIMER_RESOLUTION
QUEUE_PROPERTIES
REFERENCE_COUNT

Available with OpenCL 1.2.

New in version 2011.2.

REFERENCE_COUNT_EXT

Available with the cl_ext_device_fission extension.

New in version 2011.1.

REGISTERS_PER_BLOCK_NV

Available with the cl_nv_device_attribute_query extension.

New in version 0.92.

SIMD_INSTRUCTION_WIDTH_AMD

Available with the cl_amd_device_attribute_query extension.

New in version 2013.2.

SIMD_PER_COMPUTE_UNIT_AMD

Available with the cl_amd_device_attribute_query extension.

New in version 2013.2.

SIMD_WIDTH_AMD

Available with the cl_amd_device_attribute_query extension.

New in version 2013.2.

SINGLE_FP_CONFIG
TOPOLOGY_AMD

Available with the cl_amd_device_attribute_query extension.

New in version 2013.2.

TYPE
VENDOR
VENDOR_ID
VERSION
WARP_SIZE_NV

Available with the cl_nv_device_attribute_query extension.

New in version 0.92.

WAVEFRONT_WIDTH_AMD

Available with the cl_amd_device_attribute_query extension.

New in version 2013.2.

to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.device_local_mem_type
GLOBAL
LOCAL
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.device_mem_cache_type
NONE
READ_ONLY_CACHE
READ_WRITE_CACHE
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.device_partition_property
BY_AFFINITY_DOMAIN

Available with OpenCL 1.2.

New in version 2011.2.

BY_COUNTS

Available with OpenCL 1.2.

New in version 2011.2.

BY_COUNTS_LIST_END
EQUALLY

Available with OpenCL 1.2.

New in version 2011.2.

to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.device_partition_property_ext
BY_AFFINITY_DOMAIN

Available with the cl_ext_device_fission extension.

New in version 2011.1.

BY_COUNTS

Available with the cl_ext_device_fission extension.

New in version 2011.1.

BY_NAMES

Available with the cl_ext_device_fission extension.

New in version 2011.1.

EQUALLY

Available with the cl_ext_device_fission extension.

New in version 2011.1.

PARTITION_BY_COUNTS_LIST_END

Available with the cl_ext_device_fission extension.

New in version 2011.1.

PARTITION_BY_NAMES_LIST_END

Available with the cl_ext_device_fission extension.

New in version 2011.1.

PROPERTIES_LIST_END

Available with the cl_ext_device_fission extension.

New in version 2011.1.

to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.device_type
ACCELERATOR
ALL
CPU
CUSTOM

Available with OpenCL 1.2.

New in version 2011.2.

DEFAULT
GPU
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.event_info
COMMAND_EXECUTION_STATUS
COMMAND_QUEUE
COMMAND_TYPE
CONTEXT

Available with OpenCL 1.1.

New in version 0.92.

REFERENCE_COUNT
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.filter_mode
LINEAR
NEAREST
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.gl_context_info

Only available when PyOpenCL is compiled with GL support. See have_gl().

to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.image_info
ARRAY_SIZE

Available with OpenCL 1.2.

New in version 2011.2.

BUFFER

Available with OpenCL 1.2.

New in version 2011.2.

DEPTH
ELEMENT_SIZE
FORMAT
HEIGHT
NUM_MIP_LEVELS

Available with OpenCL 1.2.

New in version 2011.2.

NUM_SAMPLES

Available with OpenCL 1.2.

New in version 2011.2.

ROW_PITCH
SLICE_PITCH
WIDTH
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.kernel_arg_access_qualifier
NONE

Available with OpenCL 1.2.

New in version 2011.2.

READ_ONLY

Available with OpenCL 1.2.

New in version 2011.2.

READ_WRITE

Available with OpenCL 1.2.

New in version 2011.2.

WRITE_ONLY

Available with OpenCL 1.2.

New in version 2011.2.

to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.kernel_arg_address_qualifier
CONSTANT

Available with OpenCL 1.2.

New in version 2011.2.

GLOBAL

Available with OpenCL 1.2.

New in version 2011.2.

LOCAL

Available with OpenCL 1.2.

New in version 2011.2.

PRIVATE

Available with OpenCL 1.2.

New in version 2011.2.

to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.kernel_arg_info
ACCESS_QUALIFIER

Available with OpenCL 1.2.

New in version 2011.2.

ADDRESS_QUALIFIER

Available with OpenCL 1.2.

New in version 2011.2.

NAME
TYPE_NAME

Available with OpenCL 1.2.

New in version 2011.2.

to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.kernel_info
ATTRIBUTES

Available with OpenCL 1.2.

New in version 2011.2.

CONTEXT
FUNCTION_NAME
NUM_ARGS
PROGRAM
REFERENCE_COUNT
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.kernel_work_group_info
COMPILE_WORK_GROUP_SIZE
GLOBAL_WORK_SIZE

Available with OpenCL 1.2.

New in version 2011.2.

LOCAL_MEM_SIZE
PREFERRED_WORK_GROUP_SIZE_MULTIPLE

Available with OpenCL 1.1.

New in version 0.92.

PRIVATE_MEM_SIZE

Available with OpenCL 1.1.

New in version 0.92.

WORK_GROUP_SIZE
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.map_flags
READ
WRITE
WRITE_INVALIDATE_REGION

Available with OpenCL 1.2.

New in version 2011.2.

to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.mem_flags
ALLOC_HOST_PTR
COPY_HOST_PTR
HOST_NO_ACCESS
HOST_READ_ONLY
HOST_WRITE_ONLY

Available with OpenCL 1.2.

New in version 2011.2.

READ_ONLY
READ_WRITE
USE_HOST_PTR
USE_PERSISTENT_MEM_AMD

Available with the cl_amd_device_memory_flags extension.

New in version 2011.1.

WRITE_ONLY
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.mem_info
ASSOCIATED_MEMOBJECT

Available with OpenCL 1.1.

New in version 0.92.

CONTEXT
FLAGS
HOST_PTR
MAP_COUNT
OFFSET

Available with OpenCL 1.1.

New in version 0.92.

REFERENCE_COUNT
SIZE
TYPE
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.mem_migration_flags
CONTENT_UNDEFINED

Available with OpenCL 1.2.

New in version 2011.2.

HOST

Available with OpenCL 1.2.

New in version 2011.2.

to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.mem_object_type
BUFFER
IMAGE1D

Available with OpenCL 1.2.

New in version 2011.2.

IMAGE1D_ARRAY

Available with OpenCL 1.2.

New in version 2011.2.

IMAGE1D_BUFFER

Available with OpenCL 1.2.

New in version 2011.2.

IMAGE2D
IMAGE2D_ARRAY

Available with OpenCL 1.2.

New in version 2011.2.

IMAGE3D
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.migrate_mem_object_flags_ext
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.platform_info
EXTENSIONS
NAME
PROFILE
VENDOR
VERSION
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.profiling_info
END
QUEUED
START
SUBMIT
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.program_binary_type
COMPILED_OBJECT

Available with OpenCL 1.2.

New in version 2011.2.

EXECUTABLE

Available with OpenCL 1.2.

New in version 2011.2.

LIBRARY

Available with OpenCL 1.2.

New in version 2011.2.

NONE

Available with OpenCL 1.2.

New in version 2011.2.

to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.program_build_info
BINARY_TYPE

Available with OpenCL 1.2.

New in version 2011.2.

LOG
OPTIONS
STATUS
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.program_info
BINARIES
BINARY_SIZES
CONTEXT
DEVICES
KERNEL_NAMES

Available with OpenCL 1.2.

New in version 2011.2.

NUM_DEVICES
NUM_KERNELS

Available with OpenCL 1.2.

New in version 2011.2.

REFERENCE_COUNT
SOURCE
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.program_kind
BINARY
SOURCE
UNKNOWN
bit_length
conjugate
denominator
imag
name
numerator
real
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.sampler_info
ADDRESSING_MODE
CONTEXT
FILTER_MODE
NORMALIZED_COORDS
REFERENCE_COUNT
to_string(value)

Returns a str representing value.

New in version 0.91.

class pyopencl.status_code
BUILD_PROGRAM_FAILURE
COMPILER_NOT_AVAILABLE
COMPILE_PROGRAM_FAILURE

Available with OpenCL 1.2.

New in version 2011.2.

DEVICE_NOT_AVAILABLE
DEVICE_NOT_FOUND
DEVICE_PARTITION_FAILED

Available with OpenCL 1.2.

New in version 2011.2.

DEVICE_PARTITION_FAILED_EXT
EXEC_STATUS_ERROR_FOR_EVENTS_IN_WAIT_LIST

Available with OpenCL 1.1.

New in version 0.92.

IMAGE_FORMAT_MISMATCH
IMAGE_FORMAT_NOT_SUPPORTED
INVALID_ARG_INDEX
INVALID_ARG_SIZE
INVALID_ARG_VALUE
INVALID_BINARY
INVALID_BUFFER_SIZE
INVALID_BUILD_OPTIONS
INVALID_COMMAND_QUEUE
INVALID_COMPILER_OPTIONS

Available with OpenCL 1.2.

New in version 2011.2.

INVALID_CONTEXT
INVALID_DEVICE
INVALID_DEVICE_PARTITION_COUNT

Available with OpenCL 1.2.

New in version 2011.2.

INVALID_DEVICE_TYPE
INVALID_EVENT
INVALID_EVENT_WAIT_LIST
INVALID_GLOBAL_OFFSET
INVALID_GLOBAL_WORK_SIZE

Available with OpenCL 1.1.

New in version 0.92.

INVALID_GL_OBJECT
INVALID_HOST_PTR
INVALID_IMAGE_DESCRIPTOR

Available with OpenCL 1.2.

New in version 2011.2.

INVALID_IMAGE_FORMAT_DESCRIPTOR
INVALID_IMAGE_SIZE
INVALID_KERNEL
INVALID_KERNEL_ARGS
INVALID_KERNEL_DEFINITION
INVALID_KERNEL_NAME
INVALID_LINKER_OPTIONS

Available with OpenCL 1.2.

New in version 2011.2.

INVALID_MEM_OBJECT
INVALID_MIP_LEVEL
INVALID_OPERATION
INVALID_PARTITION_COUNT_EXT
INVALID_PARTITION_NAME_EXT
INVALID_PLATFORM
INVALID_PROGRAM
INVALID_PROGRAM_EXECUTABLE
INVALID_QUEUE_PROPERTIES
INVALID_SAMPLER
INVALID_VALUE
INVALID_WORK_DIMENSION
INVALID_WORK_GROUP_SIZE
INVALID_WORK_ITEM_SIZE
KERNEL_ARG_INFO_NOT_AVAILABLE

Available with OpenCL 1.2.

New in version 2011.2.

LINKER_NOT_AVAILABLE

Available with OpenCL 1.2.

New in version 2011.2.

Available with OpenCL 1.2.

New in version 2011.2.

MAP_FAILURE
MEM_COPY_OVERLAP
MEM_OBJECT_ALLOCATION_FAILURE
MISALIGNED_SUB_BUFFER_OFFSET

Available with OpenCL 1.1.

New in version 0.92.

OUT_OF_HOST_MEMORY
OUT_OF_RESOURCES
PLATFORM_NOT_FOUND_KHR

Available with the cl_khr_icd extension.

New in version 2011.1.

PROFILING_INFO_NOT_AVAILABLE
SUCCESS
to_string(value)

Returns a str representing value.

New in version 0.91.

Platforms, Devices and Contexts

pyopencl.get_platforms()

Return a list of Platform instances.

class pyopencl.Platform
info

Lower case versions of the platform_info constants may be used as attributes on instances of this class to directly query info attributes.

get_info(param)

See platform_info for values of param.

get_devices(device_type=device_type.ALL)

Return a list of devices matching device_type. See device_type for values of device_type.

Changed in version 2013.2: This used to raise an exception if no matching devices were found. Now, it will simply return an empty list.

from_int_ptr((int)int_ptr_value) → Platform :

(static method) Return a new Python object referencing the C-level cl_platform_id object at the location pointed to by int_ptr_value. The relevant clRetain*() function will be called.

New in version 2013.2.

int_ptr

Return an integer corresponding to the pointer value of the underlying cl_platform_id. Use from_int_ptr() to turn back into a Python object.

New in version 2013.2.

Instances of this class are hashable, and two instances of this class may be compared using “==” and ”!=”. (Hashability was added in version 2011.2.)

class pyopencl.Device
info

Lower case versions of the device_info constants may be used as attributes on instances of this class to directly query info attributes.

get_info(param)

See device_info for values of param.

from_int_ptr((int)int_ptr_value) → Device :

(static method) Return a new Python object referencing the C-level cl_device_id object at the location pointed to by int_ptr_value. The relevant clRetain*() function will be called.

New in version 2013.2.

int_ptr

Return an integer corresponding to the pointer value of the underlying cl_device_id. Use from_int_ptr() to turn back into a Python object.

New in version 2013.2.

Two instances of this class may be compared using ==” and ”!=”.

class pyopencl.Context(devices=None, properties=None, dev_type=None)

Create a new context. properties is a list of key-value tuples, where each key must be one of context_properties. At most one of devices and dev_type may be not None, where devices is a list of Device instances, and dev_type is one of the device_type constants. If neither is specified, a context with a dev_type of device_type.DEFAULT is created.

Note

Calling the constructor with no arguments will fail for recent CL drivers that support the OpenCL ICD. If you want similar, just-give-me-a-context-already behavior, we recommend create_some_context(). See, e.g. this explanation by AMD.

Note

For context_properties.CL_GL_CONTEXT_KHR, context_properties.CL_EGL_DISPLAY_KHR, context_properties.CL_GLX_DISPLAY_KHR, context_properties.CL_WGL_HDC_KHR, and context_properties.CL_CGL_SHAREGROUP_KHR context_properties.CL_CGL_SHAREGROUP_APPLE the value in the key-value pair is a PyOpenGL context or display instance.

Changed in version 0.91.2: Constructor arguments dev_type added.

info

Lower case versions of the context_info constants may be used as attributes on instances of this class to directly query info attributes.

get_info(param)

See context_info for values of param.

create_sub_devices(properties)

properties is an array of one (or more) of the forms:

[ dpp.EQUALLY, 8]
[ dpp.BY_COUNTS, 5, 7, 9, dpp.PARTITION_BY_COUNTS_LIST_END]
[ dpp.BY_NAMES, 5, 7, 9, dpp.PARTITION_BY_NAMES_LIST_END]
[ dpp.BY_AFFINITY_DOMAIN, dad.L1_CACHE]

where dpp represents device_partition_property and dad represent device_affinity_domain.

PROPERTIES_LIST_END_EXT is added automatically.

Only available with CL 1.2.

New in version 2011.2.

create_sub_devices_ext(properties)

properties is an array of one (or more) of the forms:

[ dppe.EQUALLY, 8]
[ dppe.BY_COUNTS, 5, 7, 9, dppe.PARTITION_BY_COUNTS_LIST_END]
[ dppe.BY_NAMES, 5, 7, 9, dppe.PARTITION_BY_NAMES_LIST_END]
[ dppe.BY_AFFINITY_DOMAIN, ad.L1_CACHE]

where dppe represents device_partition_property_ext and ad represent affinity_domain_ext.

PROPERTIES_LIST_END_EXT is added automatically.

Only available with the cl_ext_device_fission extension.

New in version 2011.1.

from_int_ptr((int)int_ptr_value) → Context :

(static method) Return a new Python object referencing the C-level cl_context object at the location pointed to by int_ptr_value. The relevant clRetain*() function will be called.

New in version 2013.2.

int_ptr

Return an integer corresponding to the pointer value of the underlying cl_context. Use from_int_ptr() to turn back into a Python object.

New in version 2013.2.

Instances of this class are hashable, and two instances of this class may be compared using “==” and ”!=”. (Hashability was added in version 2011.2.)

pyopencl.create_some_context(interactive=True)

Create a Context ‘somehow’.

If multiple choices for platform and/or device exist, interactive is True, and sys.stdin.isatty() is also True, then the user is queried about which device should be chosen. Otherwise, a device is chosen in an implementation-defined manner.

Command Queues and Events

class pyopencl.CommandQueue(context, device=None, properties=None)

Create a new command queue. properties is a bit field consisting of command_queue_properties values.

if device is None, one of the devices in context is chosen in an implementation-defined manner.

A CommandQueue may be used as a context manager, like this:

with cl.CommandQueue(self.cl_context) as queue:
    enqueue_stuff(queue, ...)

finish() is automatically called at the end of the context.

New in version 2013.1: Context manager capability.

info

Lower case versions of the command_queue_info constants may be used as attributes on instances of this class to directly query info attributes.

get_info(param)

See command_queue_info for values of param.

set_property(prop, enable)

See command_queue_properties for possible values of prop. enable is a bool.

Unavailable in OpenCL 1.1 and newer.

flush()
finish()
from_int_ptr((int)int_ptr_value) → CommandQueue :

(static method) Return a new Python object referencing the C-level cl_command_queue object at the location pointed to by int_ptr_value. The relevant clRetain*() function will be called.

New in version 2013.2.

int_ptr

Return an integer corresponding to the pointer value of the underlying cl_command_queue. Use from_int_ptr() to turn back into a Python object.

New in version 2013.2.

Instances of this class are hashable, and two instances of this class may be compared using “==” and ”!=”. (Hashability was added in version 2011.2.)

class pyopencl.Event
info

Lower case versions of the event_info constants may be used as attributes on instances of this class to directly query info attributes.

profile.info

Lower case versions of the profiling_info constants may be used as attributes on the attribute profile of this class to directly query profiling info.

For example, you may use evt.profile.end instead of evt.get_profiling_info(pyopencl.profiling_info.END).

get_info(param)

See event_info for values of param.

get_profiling_info(param)

See profiling_info for values of param. See profile for an easier way of obtaining the same information.

wait()
from_int_ptr((int)int_ptr_value) → Event :

(static method) Return a new Python object referencing the C-level cl_event object at the location pointed to by int_ptr_value. The relevant clRetain*() function will be called.

New in version 2013.2.

int_ptr

Return an integer corresponding to the pointer value of the underlying cl_event. Use from_int_ptr() to turn back into a Python object.

New in version 2013.2.

Instances of this class are hashable, and two instances of this class may be compared using “==” and ”!=”. (Hashability was added in version 2011.2.)

pyopencl.wait_for_events(events)
pyopencl.enqueue_barrier(queue, wait_for=None)

Enqueues a barrier operation. which ensures that all queued commands in command_queue have finished execution. This command is a synchronization point.

New in version 0.91.5.

Changed in version 2011.2: Takes wait_for and returns an Event

pyopencl.enqueue_marker(queue, wait_for=None)

Returns an Event.

Changed in version 2011.2: Takes wait_for.

class pyopencl.UserEvent(context)

A subclass of Event. Only available with OpenCL 1.1 and newer.

New in version 0.92.

set_status(status)

See command_execution_status for possible values of status.

class pyopencl.NannyEvent

Transfers between host and device return events of this type. They hold a reference to the host-side buffer and wait for the transfer to complete when they are freed. Therefore, they can safely release the reference to the object they’re guarding upon destruction.

A subclass of Event.

New in version 2011.2.

get_ward()
wait()

In addition to performing the same wait as Event.wait(), this method also releases the reference to the guarded object.

Memory

class pyopencl.MemoryObject
info

Lower case versions of the mem_info constants may be used as attributes on instances of this class to directly query info attributes.

hostbuf
get_info(param)

See mem_info for values of param.

release()
get_host_array(shape, dtype, order="C")

Return the memory object’s associated host memory area as a numpy.ndarray of the given shape, dtype and order.

from_int_ptr((int)arg1) → object :

(static method) Return a new Python object referencing the C-level cl_mem object at the location pointed to by int_ptr_value. The relevant clRetain*() function will be called.

New in version 2013.2.

int_ptr

Return an integer corresponding to the pointer value of the underlying cl_mem. Use from_int_ptr() to turn back into a Python object.

New in version 2013.2.

Instances of this class are hashable, and two instances of this class may be compared using “==” and ”!=”. (Hashability was added in version 2011.2.)

pyopencl.enqueue_migrate_mem_objects(queue, mem_objects, flags=0, wait_for=None)
Parameters:flags – from mem_migration_flags

New in version 2011.2.

Only available with CL 1.2.

pyopencl.enqueue_migrate_mem_object_ext(queue, mem_objects, flags=0, wait_for=None)
Parameters:flags – from migrate_mem_object_flags_ext

New in version 2011.2.

Only available with the cl_ext_migrate_memobject extension.

Buffers

class pyopencl.Buffer(context, flags, size=0, hostbuf=None)

Create a Buffer. See mem_flags for values of flags. If hostbuf is specified, size defaults to the size of the specified buffer if it is passed as zero.

Buffer inherits from MemoryObject.

Note

Python also defines a type of buffer object, and PyOpenCL interacts with those, too, as the host-side target of enqueue_copy(). Make sure to always be clear on whether a Buffer or a Python buffer object is needed.

Note that actual memory allocation in OpenCL may be deferred. Buffers are attached to a Context and are only moved to a device once the buffer is used on that device. That is also the point when out-of-memory errors will occur. If you’d like to be sure that there’s enough memory for your allocation, either use enqueue_migrate_mem_objects() (if available) or simply perform a small transfer to the buffer. See also pyopencl.tools.ImmediateAllocator.

get_sub_region(origin, size, flags=0)

Only available in OpenCL 1.1 and newer.

__getitem__(slc)

slc is a slice object indicating from which byte index range a sub-buffer is to be created. The flags argument of get_sub_region() is set to the same flags with which self was created.

pyopencl.enqueue_fill_buffer(queue, mem, pattern, offset, size, wait_for=None)
Parameters:pattern – a buffer object (likely a numpy.ndarray)

Returns a new pyopencl.Event. wait_for may either be None or a list of pyopencl.Event instances for whose completion this command waits before starting exeuction.

Only available with CL 1.2.

New in version 2011.2.

Image Formats

class pyopencl.ImageFormat([channel_order, channel_type])
channel_order

See channel_order for possible values.

channel_data_type

See channel_type for possible values.

channel_count

New in version 0.91.5.

dtype_size

New in version 0.91.5.

itemsize

New in version 0.91.5.

__repr__()

Returns a str representation of the image format.

New in version 0.91.

Instances of this class are hashable, and two instances of this class may be compared using “==” and ”!=”. (Hashability was added in version 2011.2.)

Changed in version 0.91: Constructor arguments added.

Changed in version 2013.2: ImageFormat was made comparable and hashable

pyopencl.get_supported_image_formats(context, flags, image_type)

See mem_flags for possible values of flags and mem_object_type for possible values of image_type.

Images

Image(context, flags, format, shape=None, pitches=None, hostbuf=None, is_array=False, buffer=None):

See mem_flags for values of flags. shape is a 2- or 3-tuple. format is an instance of ImageFormat. pitches is a 1-tuple for 2D images and a 2-tuple for 3D images, indicating the distance in bytes from one scan line to the next, and from one 2D image slice to the next.

If hostbuf is given and shape is None, then hostbuf.shape is used as the shape parameter.

Image inherits from MemoryObject.

Note

If you want to load images from numpy.ndarray instances or read images back into them, be aware that OpenCL images expect the x dimension to vary fastest, whereas in the default (C) order of numpy arrays, the last index varies fastest. If your array is arranged in the wrong order in memory, there are two possible fixes for this:

  • Convert the array to Fortran (column-major) order using numpy.asarray().
  • Pass ary.T.copy() to the image creation function.

New in version 0.91.

Changed in version 2011.2: Added is_array and buffer, which are only available on CL 1.2 and newer.

pyopencl.info

Lower case versions of the mem_info and image_info constants may be used as attributes on instances of this class to directly query info attributes.

pyopencl.shape

Return the value of the shape constructor argument as a tuple.

pyopencl.get_image_info(param)

See image_info for values of param.

pyopencl.release()

Instances of this class are hashable, and two instances of this class may be compared using “==” and ”!=”. (Hashability was added in version 2011.2.)

pyopencl.image_from_array(ctx, ary, num_channels=None, mode="r", norm_int=False)

Build a 2D or 3D Image from the numpy.ndarray ary. If num_channels is greater than one, the last dimension of ary must be identical to num_channels. ary must be in C order. If num_channels is not given, it defaults to 1 for scalar types and the number of entries for Vector Types.

The ImageFormat is chosen as the first num_channels components of “RGBA”.

Parameters:mode – “r” or “w” for read/write

Note

When reading from the image object, the indices passed to read_imagef are in the reverse order from what they would be when accessing ary from Python.

If norm_int is True, then the integer values are normalized to a floating point scale of 0..1 when read.

New in version 2011.2.

pyopencl.enqueue_fill_image(queue, mem, color, origin, region, wait_for=None)
Parameters:color – a buffer object (likely a numpy.ndarray)

Returns a new pyopencl.Event. wait_for may either be None or a list of pyopencl.Event instances for whose completion this command waits before starting exeuction.

Only available with CL 1.2.

New in version 2011.2.

Transfers

pyopencl.enqueue_copy(queue, dest, src, **kwargs)

Copy from Image, Buffer or the host to Image, Buffer or the host. (Note: host-to-host copies are unsupported.)

The following keyword arguments are available:

Parameters:
  • wait_for – (optional, default empty)
  • is_blocking – Wait for completion. Defaults to True. (Available on any copy involving host memory)
Returns:

A NannyEvent if the transfer involved a host-side buffer, otherwise an Event.

Note

Two types of ‘buffer’ occur in the arguments to this function, Buffer and ‘host-side buffers’. The latter are defined by Python and commonly called buffer objects. Make sure to always be clear on whether a Buffer or a Python buffer object is needed.

Transfer Buffer ↔ host

Parameters:device_offset – offset in bytes (optional)

Note

The size of the transfer is controlled by the size of the of the host-side buffer. If the host-side buffer is a numpy.ndarray, you can control the transfer size by transfering into a smaller ‘view’ of the target array, like this:

cl.enqueue_copy(queue, large_dest_numpy_array[:15], src_buffer)

Transfer BufferBuffer

Parameters:
  • byte_count – (optional) If not specified, defaults to the size of the source in versions 2012.x and earlier, and to the minimum of the size of the source and target from 2013.1 on.
  • src_offset – (optional)
  • dest_offset – (optional)

Rectangular Buffer ↔ host transfers (CL 1.1 and newer)

Parameters:
  • buffer_origintuple of int of length three or shorter. (mandatory)
  • host_origintuple of int of length three or shorter. (mandatory)
  • regiontuple of int of length three or shorter. (mandatory)
  • buffer_pitchestuple of int of length two or shorter. (optional, “tightly-packed” if unspecified)
  • host_pitchestuple of int of length two or shorter. (optional, “tightly-packed” if unspecified)

Transfer Image ↔ host

Parameters:
  • origintuple of int of length three or shorter. (mandatory)
  • regiontuple of int of length three or shorter. (mandatory)
  • pitchestuple of int of length two or shorter. (optional)

Transfer BufferImage

Parameters:
  • offset – offset in buffer (mandatory)
  • origintuple of int of length three or shorter. (mandatory)
  • regiontuple of int of length three or shorter. (mandatory)

Transfer ImageImage

Parameters:
  • src_origintuple of int of length three or shorter. (mandatory)
  • dest_origintuple of int of length three or shorter. (mandatory)
  • regiontuple of int of length three or shorter. (mandatory)

Returns a new pyopencl.Event. wait_for may either be None or a list of pyopencl.Event instances for whose completion this command waits before starting exeuction.

New in version 2011.1.

Mapping Memory into Host Address Space

class pyopencl.MemoryMap
release(queue=None, wait_for=None)
pyopencl.enqueue_map_buffer(queue, buf, flags, offset, shape, dtype, order="C", strides=None, wait_for=None, is_blocking=True)

wait_for may either be None or a list of pyopencl.Event instances for whose completion this command waits before starting exeuction. shape, dtype, and order have the same meaning as in numpy.empty(). See map_flags for possible values of flags. strides, if given, overrides order.

Returns:a tuple (array, event). array is a numpy.ndarray representing the host side of the map. Its .base member contains a MemoryMap.

Changed in version 2011.1: is_blocking now defaults to True.

Changed in version 2013.1: order now defaults to “C”.

Changed in version 2013.2: Added strides argument.

pyopencl.enqueue_map_image(queue, buf, flags, origin, region, shape, dtype, order="C", strides=None, wait_for=None, is_blocking=True)

wait_for may either be None or a list of pyopencl.Event instances for whose completion this command waits before starting exeuction. shape, dtype, and order have the same meaning as in numpy.empty(). See map_flags for possible values of flags. strides, if given, overrides order.

Returns:a tuple (array, event). array is a numpy.ndarray representing the host side of the map. Its .base member contains a MemoryMap.

Changed in version 2011.1: is_blocking now defaults to True.

Changed in version 2013.1: order now defaults to “C”.

Changed in version 2013.2: Added strides argument.

Samplers

class pyopencl.Sampler(context, normalized_coords, addressing_mode, filter_mode)

normalized_coords is a bool indicating whether to use coordinates between 0 and 1 (True) or the texture’s natural pixel size (False). See addressing_mode and filter_mode for possible argument values.

info

Lower case versions of the sampler_info constants may be used as attributes on instances of this class to directly query info attributes.

get_info(param)

See sampler_info for values of param.

from_int_ptr((int)int_ptr_value) → Sampler :

(static method) Return a new Python object referencing the C-level cl_sampler object at the location pointed to by int_ptr_value. The relevant clRetain*() function will be called.

New in version 2013.2.

int_ptr

Return an integer corresponding to the pointer value of the underlying cl_sampler. Use from_int_ptr() to turn back into a Python object.

New in version 2013.2.

Instances of this class are hashable, and two instances of this class may be compared using “==” and ”!=”. (Hashability was added in version 2011.2.)

Programs and Kernels

class pyopencl.Program(context, src)
class pyopencl.Program(context, devices, binaries)

binaries must contain one binary for each entry in devices.

info

Lower case versions of the program_info constants may be used as attributes on instances of this class to directly query info attributes.

get_info(param)

See program_info for values of param.

get_build_info(device, param)

See program_build_info for values of param.

build(options=[], devices=None)

options is a string of compiler flags. Returns self.

By default, built binaries are cached in an on-disk cache called pyopencl-compiler-cache-vN-uidNAME-pyVERSION in the directory returned by tempfile.gettempdir(). By setting the environment variable PYOPENCL_NO_CACHE to any non-empty value, this caching is suppressed. Any options found in the environment variable PYOPENCL_BUILD_OPTIONS will be appended to options.

Changed in version 2011.1: options may now also be a list of str.

Changed in version 2013.1: Added PYOPENCL_NO_CACHE. Added PYOPENCL_BUILD_OPTIONS.

compile(self, options=[], devices=None, headers=[])
Parameters:headers – a list of tuples (name, program).

Only available with CL 1.2.

New in version 2011.2.

kernel_name

Kernel objects can be produced from a built (see build()) program simply by attribute lookup.

Note

The program_info attributes live in the same name space and take precedence over Kernel names.

all_kernels()

Returns a list of all Kernel objects in the Program.

static from_int_ptr((int)int_ptr_value) → _Program :

(static method) Return a new Python object referencing the C-level cl_program object at the location pointed to by int_ptr_value. The relevant clRetain*() function will be called.

New in version 2013.2.

int_ptr

Return an integer corresponding to the pointer value of the underlying cl_program. Use from_int_ptr() to turn back into a Python object.

New in version 2013.2.

Instances of this class are hashable, and two instances of this class may be compared using “==” and ”!=”. (Hashability was added in version 2011.2.)

pyopencl.create_program_with_built_in_kernels(context, devices, kernel_names)

Only available with CL 1.2.

New in version 2011.2.

Only available with CL 1.2.

New in version 2011.2.

pyopencl.unload_platform_compiler(platform)

Only available with CL 1.2.

New in version 2011.2.

class pyopencl.Kernel(program, name)
info

Lower case versions of the kernel_info constants may be used as attributes on instances of this class to directly query info attributes.

get_info(param)

See kernel_info for values of param.

get_work_group_info(param, device)

See kernel_work_group_info for values of param.

get_arg_info(arg_index, param)

See kernel_arg_info for values of param.

Only available in OpenCL 1.2 and newer.

set_arg(self, index, arg)

arg may be

  • None: This may be passed for __global memory references to pass a NULL pointer to the kernel.

  • Anything that satisfies the Python buffer interface, in particular numpy.ndarray, str, or numpy‘s sized scalars, such as numpy.int32 or numpy.float64.

    Note

    Note that Python’s own int or float objects will not work out of the box. See Kernel.set_scalar_arg_dtypes() for a way to make them work. Alternatively, the standard library module struct can be used to convert Python’s native number types to binary data in a str.

  • An instance of MemoryObject. (e.g. Buffer, Image, etc.)

  • An instance of LocalMemory.

  • An instance of Sampler.

set_args(self, *args)

Invoke set_arg() on each element of args in turn.

New in version 0.92.

set_scalar_arg_dtypes(arg_dtypes)

Inform the wrapper about the sized types of scalar Kernel arguments. For each argument, arg_dtypes contains an entry. For non-scalars, this must be None. For scalars, it must be an object acceptable to the numpy.dtype constructor, indicating that the corresponding scalar argument is of that type.

After invoking this function with the proper information, most suitable number types will automatically be cast to the right type for kernel invocation.

Note

The information set by this rountine is attached to a single kernel instance. A new kernel instance is created every time you use program.kernel attribute access. The following will therefore not work:

prg = cl.Program(...).build()
prg.kernel.set_scalar_arg_dtypes(...)
prg.kernel(queue, n_globals, None, args)
__call__(queue, global_size, local_size, *args, global_offset=None, wait_for=None, g_times_l=False)

Use enqueue_nd_range_kernel() to enqueue a kernel execution, after using set_args() to set each argument in turn. See the documentation for set_arg() to see what argument types are allowed. Returns a new pyopencl.Event. wait_for may either be None or a list of pyopencl.Event instances for whose completion this command waits before starting exeuction.

None may be passed for local_size.

If g_times_l is specified, the global size will be multiplied by the local size. (which makes the behavior more like Nvidia CUDA) In this case, global_size and local_size also do not have to have the same number of dimensions.

Note

__call__() is not thread-safe. It sets the arguments using set_args() and then runs enqueue_nd_range_kernel(). Another thread could race it in doing the same things, with undefined outcome. This issue is inherited from the C-level OpenCL API. The recommended solution is to make a kernel (i.e. access prg.kernel_name, which corresponds to making a new kernel) for every thread that may enqueue calls to the kernel.

A solution involving implicit locks was discussed and decided against on the mailing list in October 2012.

Changed in version 0.92: local_size was promoted to third positional argument from being a keyword argument. The old keyword argument usage will continue to be accepted with a warning throughout the 0.92 release cycle. This is a backward-compatible change (just barely!) because local_size as third positional argument can only be a tuple or None. tuple instances are never valid Kernel arguments, and None is valid as an argument, but its treatment in the wrapper had a bug (now fixed) that prevented it from working.

Changed in version 2011.1: Added the g_times_l keyword arg.

capture_call(filename, queue, global_size, local_size, *args, global_offset=None, wait_for=None, g_times_l=False)

This method supports the exact same interface as __call__(), but instead of invoking the kernel, it writes a self-contained PyOpenCL program to filename that reproduces this invocation. Data and kernel source code will be packaged up in filename‘s source code.

This is mainly intended as a debugging aid. For example, it can be used to automate the task of creating a small, self-contained test case for an observed problem. It can also help separate a misbehaving kernel from a potentially large or time-consuming outer code.

To use, simply change:

evt = my_kernel(queue, gsize, lsize, arg1, arg2, ...)

to:

evt = my_kernel.capture_call("bug.py", queue, gsize, lsize, arg1, arg2, ...)

New in version 2013.1.

from_int_ptr((int)int_ptr_value) → Kernel :

(static method) Return a new Python object referencing the C-level cl_kernel object at the location pointed to by int_ptr_value. The relevant clRetain*() function will be called.

New in version 2013.2.

int_ptr

Return an integer corresponding to the pointer value of the underlying cl_kernel. Use from_int_ptr() to turn back into a Python object.

New in version 2013.2.

Instances of this class are hashable, and two instances of this class may be compared using “==” and ”!=”. (Hashability was added in version 2011.2.)

class pyopencl.LocalMemory(size)

A helper class to pass __local memory arguments to kernels.

New in version 0.91.2.

size

The size of local buffer in bytes to be provided.

pyopencl.enqueue_nd_range_kernel(queue, kernel, global_work_size, local_work_size, global_work_offset=None, wait_for=None, g_times_l=False)

Returns a new pyopencl.Event. wait_for may either be None or a list of pyopencl.Event instances for whose completion this command waits before starting exeuction.

If g_times_l is specified, the global size will be multiplied by the local size. (which makes the behavior more like Nvidia CUDA) In this case, global_size and local_size also do not have to have the same number of dimensions.

Changed in version 2011.1: Added the g_times_l keyword arg.

pyopencl.enqueue_task(queue, kernel, wait_for=None)

Returns a new pyopencl.Event. wait_for may either be None or a list of pyopencl.Event instances for whose completion this command waits before starting exeuction.

GL Interoperability

Functionality in this section is only available when PyOpenCL is compiled with GL support. See have_gl().

New in version 0.91.

pyopencl.have_gl()

Return True if PyOpenCL was compiled with OpenGL interoperability, otherwise False.

pyopencl.get_gl_sharing_context_properties()

Return a list of context_properties that will allow a newly created context to share the currently active GL context.

pyopencl.get_apple_cgl_share_group()

Get share group handle for current CGL context.

Apple OS X only.

New in version 2011.1.

class pyopencl.GLBuffer(context, flags, bufobj)

GLBuffer inherits from MemoryObject.

gl_object
class pyopencl.GLRenderBuffer(context, flags, bufobj)

GLRenderBuffer inherits from MemoryObject.

gl_object
class pyopencl.GLTexture(context, flags, texture_target, miplevel, texture, dims)

dims is either 2 or 3. GLTexture inherits from Image.

gl_object
get_gl_texture_info(param)

See gl_texture_info for values of param. Only available when PyOpenCL is compiled with GL support. See have_gl().

pyopencl.enqueue_acquire_gl_objects(queue, mem_objects, wait_for=None)

mem_objects is a list of MemoryObject instances. Returns a new pyopencl.Event. wait_for may either be None or a list of pyopencl.Event instances for whose completion this command waits before starting exeuction.

pyopencl.enqueue_release_gl_objects(queue, mem_objects, wait_for=None)

mem_objects is a list of MemoryObject instances. Returns a new pyopencl.Event. wait_for may either be None or a list of pyopencl.Event instances for whose completion this command waits before starting exeuction.

pyopencl.get_gl_context_info_khr(properties, param_name, platform=None)

Get information on which CL device corresponds to a given GL/EGL/WGL/CGL device.

See the Context constructor for the meaning of properties and gl_context_info for param_name.

Changed in version 2011.2: Accepts the platform argument. Using platform equal to None is deprecated as of PyOpenCL 2011.2.