clinfo

NAME

SYNOPSIS

DESCRIPTION

OPTIONS

-a, --all-props

try to retrieve all properties, even those not officially supported (e.g. because they require specific extensions), but only show them if the property could be retrieved successfully; see also the LIMITATIONS section below; note that even though this may reveal hidden properties, there is no guarantee that the returned values are meaningful, nor that the corresponding feature is actually available at all;

-A, --always-all-props

like -a, but also show errors;

--human

produce human-friendly output; this is the default (except as noted below);

--raw

produce machine-friendly output; this is the default if clinfo is invoked with a name that contains the string “raw”;

--json

outputs the raw data (cf. the --raw option) in JSON format; support for this option is experimental, as the representation of some of the values is not finalized;

--offline

shows also offline devices for platforms that expose this feature;

--null-platform

tries to handle the NULL platform as a normal platform, retrieving and showing its properties and devices; this is in addition to the NULL platform behavior tests done at the end, and can be useful on systems where there are no ICD platforms, but there is a platform hard-coded in the OpenCL library itself;

-l, --list

list platforms and devices by name, with no (other) properties;

-dplatform_index:device_index

--device platform_index:device_index only show properties for the specified device in the specified platform;

--prop property-name

only show properties whose symbolic name matches (contains as a substring) the given property-name; the name is normalized as upper-case and with minus sign (-) replaced by underscore signs (_); when this flag is specified, raw mode is forced;

-h, -?

show usage;

--version, -v

show program version.

CONFORMING TO

EXTENSIONS

cl_khr_device_uuid

for the UUID, LUID and node mask of the device;

cl_khr_extended_versioning

for the extended platform, device, extension and IL versioned properties backported from OpenCL 3.0 to previous OpenCL versions;

cl_khr_fp16, cl_khr_fp64, cl_amd_fp64, cl_APPLE_fp64_basic_ops

for information about support for half-precision and double-precision floating-point data types;

cl_khr_image2d_from_buffer

for information about the base address and pitch alignment requirements of buffers to be used as base for 2D images;

cl_khr_il_program

for information about the supported IL (Intermediate Language) representations;

cl_khr_spir

for information about the supported SPIR (Standard Portable Intermediate Representation) versions;

cl_khr_icd

for the suffix of vendor extensions functions;

cl_khr_subgroup_named_barrier

for the maximum number of named sub-group barriers;

cl_khr_terminate_context, cl_arm_controlled_kernel_termination

for the terminate capabilities for the device;

cl_ext_device_fission

for device fission support in OpenCL 1.1 devices;

cl_khr_pci_bus_info

for the PCI bus information (see also cl_nv_device_attribute_query and cl_amd_device_attribute_query)

cl_ext_atomic_counters_32

cl_ext_atomic_counters_64 for the atomic counter extension;

cl_ext_cxx_for_opencl

for the version of the C++ for OpenCL language supported by the device compiler;

cl_amd_device_attribute_query

for AMD-specific device attributes;

cl_amd_object_metadata

to show the maximum number of keys supported by the platform;

cl_amd_offline_devices

to show offline devices exposed by the platform, if requested (see --offline option);

cl_amd_copy_buffer_p2p

to show the number and IDs of available P2P devices;

cl_amd_svm

cl_arm_shared_virtual_memory for Shared Virtual Memory (SVM) capabilities in OpenCL 1.2 devices;

cl_arm_core_id

to show the (potentially sparse) list of the core IDs that the device may return;

cl_arm_job_slot_selection

to show the (potentially sparse) list of available job slots for command submission;

cl_arm_scheduling_controls

to show the supported work scheduling controls and the available sets of register allocations;

cl_nv_device_attribute_query

for NVIDIA-specific device attributes;

cl_intel_device_attribute_query

for Intel-specific device attributes;

cl_intel_exec_by_local_thread

for the Intel extension allowing CPU devices to run kernels as part of the current host thread;

cl_intel_advanced_motion_estimation

for the version of the Intel Motion Estimation accelerator version;

cl_intel_device_side_avc_motion_estimation

for the version and supported features of Intel's device-side AVC Motion;

cl_intel_planar_yuv

for the maximum dimensions of planar YUV images;

cl_intel_simultaneous_sharing

for simultaneous CL/GL/DirectX context sharing (only partial support);

cl_intel_required_subgroup_size

to enumerate allowed sub-group sizes;

cl_intel_command_queue_families

to enumerate the available command queues and their properties and capabilities;

cl_altera_device_temperature

for the Altera extension to query the core temperature of the device;

cl_qcom_ext_host_ptr

for the QUALCOMM extension to query page size and required padding in external memory allocation.

NOTES

•

supported device partition types and domains as obtained using the cl_ext_device_fission extension typically match the ones obtained using the core OpenCL 1.2 device partition feature;

•

the preferred work-group size multiple matches the NVIDIA warp size (on NVIDIA devices) or the AMD wavefront width (on AMD devices).

clGetPlatformInfo()

by trying to show the platform name;

clGetDeviceIDs()

by trying to enumerate devices; the corresponding platform (if any) is then detected by querying the device platform of the first device;

clCreateteContext()

by trying to create a context from a device from the previous list (if any), and a context from a device from a different platform;

clCreateteContextFromType()

by trying to create contexts for each device type (except DEFAULT).

EXPERIMENTAL FEATURES

LIMITATIONS

CL_DEVICE_GLOBAL_FREE_MEMORY_AMD

documented in v3 of the cl_amd_device_attribute_query extension specification as being the global free memory in KBytes, without any explanation given on why there are two values, although in the source code of the ROCm stack the second value is documented as being the largest free block;

CL_DEVICE_AVAILABLE_ASYNC_QUEUES_AMD

documented in v3 of the cl_amd_device_attribute_query extension specification, but not reported by drivers supporting other v3 properties. This has now been enabled for drivers assumed to support v4 of the same extension;

CL_DEVICE_TERMINATE_CAPABILITY_KHR

exposed by the cl_khr_terminate_context has changed value between OpenCL 1.x and 2.x, and it's allegedly a bitfield, whose values are however not defined anywhere.

BUGS

General

LLVM CommandLine errors

: CommandLine Error: Option '(some option name)' registered more than once!
LLVM ERROR: inconsistency in registered CommandLine options

Segmentation faults

Example

find /etc/OpenCL/vendors/ -name '*.icd' | while read OPENCL_VENDOR_PATH ; do clinfo -l > /dev/null ; echo "$? ${OPENCL_VENDOR_PATH}" ; done