OpenCL 在命令行中clinfo 信息
在ubuntu 18.04上安装好opencl 以后在命令行中输入 clinfo显示信息如下：
Number of platforms 1Platform Name NVIDIA CUDAPlatform Vendor NVIDIA CorporationPlatform Version OpenCL 3.0 CUDA 12.0.151Platform Profile FULL_PROFILEPlatform Extensions cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_fp64 cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_copy_opts cl_nv_create_buffer cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_device_uuid cl_khr_pci_bus_info cl_khr_external_semaphore cl_khr_external_memory cl_khr_external_semaphore_opaque_fd cl_khr_external_memory_opaque_fdPlatform Host timer resolution 0nsPlatform Extensions function suffix NVPlatform Name NVIDIA CUDA
Number of devices 1Device Name NVIDIA GeForce GTX 1660Device Vendor NVIDIA CorporationDevice Vendor ID 0x10deDevice Version OpenCL 3.0 CUDADriver Version 525.105.17Device OpenCL C Version OpenCL C 1.2 Device Type GPUDevice Topology (NV) PCI-E, 01:00.0Device Profile FULL_PROFILEDevice Available YesCompiler Available YesLinker Available YesMax compute units 22Max clock frequency 1830MHzCompute Capability (NV) 7.5Device Partition (core)Max number of sub-devices 1Supported partition types NoneMax work item dimensions 3Max work item sizes 1024x1024x64Max work group size 1024Preferred work group size multiple 32Warp size (NV) 32Max sub-groups per work group 0Preferred / native vector sizes char 1 / 1 short 1 / 1 int 1 / 1 long 1 / 1 half 0 / 0 (n/a)float 1 / 1 double 1 / 1 (cl_khr_fp64)Half-precision Floating-point support (n/a)Single-precision Floating-point support (core)Denormals YesInfinity and NANs YesRound to nearest YesRound to zero YesRound to infinity YesIEEE754-2008 fused multiply-add YesSupport is emulated in software NoCorrectly-rounded divide and sqrt operations YesDouble-precision Floating-point support (cl_khr_fp64)Denormals YesInfinity and NANs YesRound to nearest YesRound to zero YesRound to infinity YesIEEE754-2008 fused multiply-add YesSupport is emulated in software NoAddress bits 64, Little-EndianGlobal memory size 6221987840 (5.795GiB)Error Correction support NoMax memory allocation 1555496960 (1.449GiB)Unified memory for Host and Device NoIntegrated memory (NV) NoShared Virtual Memory (SVM) capabilities (core)Coarse-grained buffer sharing YesFine-grained buffer sharing NoFine-grained system sharing NoAtomics NoMinimum alignment for any data type 128 bytesAlignment of base address 4096 bits (512 bytes)Preferred alignment for atomics SVM 0 bytesGlobal 0 bytesLocal 0 bytesMax size for global variable 0Preferred total size of global vars 0Global Memory cache type Read/WriteGlobal Memory cache size 720896 (704KiB)Global Memory cache line size 128 bytesImage support YesMax number of samplers per kernel 32Max size for 1D images from buffer 268435456 pixelsMax 1D or 2D image array size 2048 imagesMax 2D image size 32768x32768 pixelsMax 3D image size 16384x16384x16384 pixelsMax number of read image args 256Max number of write image args 32Max number of read/write image args 0Max number of pipe args 0Max active pipe reservations 0Max pipe packet size 0Local memory type LocalLocal memory size 49152 (48KiB)Registers per block (NV) 65536Max number of constant args 9Max constant buffer size 65536 (64KiB)Max size of kernel argument 4352 (4.25KiB)Queue properties (on host) Out-of-order execution YesProfiling YesQueue properties (on device) Out-of-order execution NoProfiling NoPreferred size 0Max size 0Max queues on device 0Max events on device 0Prefer user sync for interop NoProfiling timer resolution 1000nsExecution capabilities Run OpenCL kernels YesRun native kernels NoSub-group independent forward progress NoKernel execution timeout (NV) YesConcurrent copy and kernel execution (NV) YesNumber of async copy engines 3IL version printf() buffer size 1048576 (1024KiB)Built-in kernels Device Extensions cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_fp64 cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_copy_opts cl_nv_create_buffer cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_device_uuid cl_khr_pci_bus_info cl_khr_external_semaphore cl_khr_external_memory cl_khr_external_semaphore_opaque_fd cl_khr_external_memory_opaque_fdNULL platform behaviorclGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...) No platformclGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...) No platformclCreateContext(NULL, ...) [default] No platformclCreateContext(NULL, ...) [other] Success [NV]clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT) No platformclCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) No devices found in platformclCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU) No platformclCreateContextFromType(NULL, CL_DEVICE_TYPE_ACCELERATOR) No devices found in platformclCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM) Invalid device type for platformclCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL) No platformNOTE: your OpenCL library only supports OpenCL 2.2,but some installed platforms support OpenCL 3.0.Programs using 3.0 features may crashor behave unexepectedly