- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
I am trying to install openVINO on centos7, but when I want to inference a model with GPU device, it gives me this error. I use base docker environment: nvidia/cuda:10.0-cudnn7-runtime-centos7, and install openVINO on it following this instruction: https://docs.openvinotoolkit.org/latest/_docs_install_guides_installing_openvino_linux.html , and run the Steps for Intel® Processor Graphics (GPU), installation works without error. Then I run the infer process with "-d CPU",, and I can get the results. Then if I run the process with "-d GPU", it gives me "[CLDNN ERROR]. clGetPlatformIDs error -1001". After googling, then I touched the /etc/OpenCL/vendors/nvidia.icd with content "/usr/lib64/libnvidia-opencl.so.1". Run the same process again, I got "[CLDNN ERROR]. No GPU device was found.".
I'm new to linux, and I don't know why this happen. So I follow https://github.com/bashbaug/OpenCLPapers/blob/master/OpenCLOnLinux.asciidoc to check. Now I get the trace file, seems like the opencl can find the gpu device, but with "Inappropriate ioctl for device".
trace file:
stat("/etc/sysconfig/64bit_strstr_via_64bit_strstr_sse2_unaligned", 0x7ffc8e52c270) = -1 ENOENT (No such file or directory) open("/dev/dri/renderD128", O_RDWR) = 18 ioctl(18, DRM_IOCTL_VERSION, 0x7ffc8e52b3f0) = 0 close(18) = 0 open("/dev/dri/renderD129", O_RDWR) = 18 ioctl(18, DRM_IOCTL_VERSION, 0x7ffc8e52b3f0) = 0 close(18) = 0 ... open("/dev/dri/renderD132", O_RDWR) = -1 ENOENT (No such file or directory) ... open("/dev/dri/card0", O_RDWR) = 18 ioctl(18, DRM_IOCTL_VERSION, 0x7ffc8e52b400) = 0 close(18) = 0 open("/dev/dri/card1", O_RDWR) = 18 ioctl(18, DRM_IOCTL_VERSION, 0x7ffc8e52b400) = 0 close(18) = 0 ... open("/dev/dri/card5", O_RDWR) = -1 ENOENT (No such file or directory) ... close(3) = 0 munmap(0x7f8ebfcfe000, 12286744) = 0 munmap(0x7f8ebfadf000, 2220416) = 0 open("classification_sample.py", O_RDONLY|O_CLOEXEC) = 3 fstat(3, {st_mode=S_IFREG|0644, st_size=6223, ...}) = 0 ioctl(3, TCGETS, 0x7ffc8e52e480) = -1 ENOTTY (Inappropriate ioctl for device) lseek(3, 0, SEEK_CUR) = 0 fcntl(3, F_DUPFD_CLOEXEC, 0) = 18 fcntl(18, F_GETFL) = 0x8000 (flags O_RDONLY|O_LARGEFILE) fstat(18, {st_mode=S_IFREG|0644, st_size=6223, ...}) = 0 mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f8f3b97c000 read(18, "#!/usr/bin/env python\n\"\"\"\n Copyr"..., 4096) = 4096 close(18) = 0 munmap(0x7f8f3b97c000, 4096) = 0 lseek(3, 0, SEEK_SET) = 0 lseek(3, 0, SEEK_CUR) = 0 read(3, "#!/usr/bin/env python\n\"\"\"\n Copyr"..., 8192) = 6223 close(3) = 0 open("classification_sample.py", O_RDONLY|O_CLOEXEC) = 3 fstat(3, {st_mode=S_IFREG|0644, st_size=6223, ...}) = 0 ioctl(3, TCGETS, 0x7ffc8e52e480) = -1 ENOTTY (Inappropriate ioctl for device) lseek(3, 0, SEEK_CUR) = 0 fcntl(3, F_DUPFD_CLOEXEC, 0) = 18 fcntl(18, F_GETFL) = 0x8000 (flags O_RDONLY|O_LARGEFILE) fstat(18, {st_mode=S_IFREG|0644, st_size=6223, ...}) = 0 mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f8f3b97c000 read(18, "#!/usr/bin/env python\n\"\"\"\n Copyr"..., 4096) = 4096 close(18) = 0 munmap(0x7f8f3b97c000, 4096) = 0 lseek(3, 0, SEEK_SET) = 0 lseek(3, 0, SEEK_CUR) = 0 read(3, "#!/usr/bin/env python\n\"\"\"\n Copyr"..., 8192) = 6223 close(3) = 0 open("ie_api.pyx", O_RDONLY|O_CLOEXEC) = -1 ENOENT (No such file or directory) ... write(2, "Traceback (most recent call last"..., 633Traceback (most recent call last): File "classification_sample.py", line 132, in <module> sys.exit(main() or 0) File "classification_sample.py", line 96, in main exec_net = ie.load_network(network=net, device_name=args.device) File "ie_api.pyx", line 134, in openvino.inference_engine.ie_api.IECore.load_network File "ie_api.pyx", line 141, in openvino.inference_engine.ie_api.IECore.load_network RuntimeError: Failed to create plugin /opt/intel/openvino_2020.1.023/deployment_tools/inference_engine/lib/intel64/libclDNNPlugin.so for device gpu Please, check your environment [CLDNN ERROR]. No GPU device was found. ) = 633 rt_sigaction(SIGINT, {SIG_DFL, [], SA_RESTORER, 0x7f8f3b01d5f0}, {0x7f8f3b415d40, [], SA_RESTORER, 0x7f8f3b01d5f0}, 8) = 0
OS system:
LSB Version: :core-4.1-amd64:core-4.1-noarch
Distributor ID: CentOS
Description: CentOS Linux release 7.7.1908 (Core)
Release: 7.7.1908
Codename: Core
lspci | grep VGA
06:00.0 VGA compatible controller: ASPEED Technology, Inc. ASPEED Graphics Family (rev 30)
I also run sys_analyzer_linux.py:
[ OK ] Processor name: Intel(R) Xeon(R) CPU E5-2640 v4 @ 2.40GHz
[ OK ] user in video group
[ OK ] libva.so.1 found
[ ERROR ] libva not loading Intel iHD
[ ERROR ] vainfo not reporting codec entry points
[ ERROR ] Intel video adapter not using i915
[ ERROR ] no libdrm include files. Are Intel components installed?
[ ERROR ] no Media SDK include files. Are Intel components installed?
[ ERROR ] no OpenCL include files. Are Intel components installed?
I don't konw what to do next, could you please provide help? Thanks a lot.
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Jane,
Can you try the steps mentioned in Use the Docker image for GPU and let us know if this helps.
Regards,
Ram prasad
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Ram,
Thanks a lot for your reply. Now I follow the instructions you have provided, and I also change the docker image to ubuntu:18.04, all steps are same, except the openvino toolkit is this one: l_openvino_toolkit_p_2020.1.023.tgz. But all other OpenCL related packages has the same version with the GPU part, all are **19.41.14441_amd64.deb packages. And I build the docker image without those two 'build-arg' options.Now the cpu device can give me inference result, but GPU still has error:
[ INFO ] Creating Inference Engine
[ INFO ] Loading network files:
incep/inception_v1.frozen.xml
incep/inception_v1.frozen.bin
[ INFO ] Preparing input blobs
[ INFO ] Batch size is 1
[ INFO ] Loading model to the plugin
Traceback (most recent call last):
File "classification_sample.py", line 129, in <module>
sys.exit(main() or 0)
File "classification_sample.py", line 93, in main
exec_net = ie.load_network(network=net, device_name=args.device)
File "ie_api.pyx", line 134, in openvino.inference_engine.ie_api.IECore.load_network
File "ie_api.pyx", line 141, in openvino.inference_engine.ie_api.IECore.load_network
RuntimeError: Failed to create plugin /opt/intel/openvino_2020.1.023/deployment_tools/inference_engine/lib/intel64/libclDNNPlugin.so fordevice GPU
Please, check your environment
[CLDNN ERROR]. clGetPlatformIDs error -1001
On host, the kernel driver versions:
yum list installed | grep kernel
abrt-addon-kerneloops.x86_64 2.1.11-48.el7.centos @anaconda
kernel.x86_64 3.10.0-693.el7 @anaconda
kernel.x86_64 3.10.0-693.5.2.el7 @updates
kernel-devel.x86_64 3.10.0-693.el7 @anaconda
kernel-devel.x86_64 3.10.0-693.5.2.el7 @updates
kernel-headers.x86_64 3.10.0-693.5.2.el7 @updates
kernel-tools.x86_64 3.10.0-693.el7 @anaconda
kernel-tools-libs.x86_64 3.10.0-693.el7 @anaconda
Host CPU:
Intel(R) Xeon(R) CPU E5-2640 v4 @ 2.40GHz
Do you have any advice? Thanks a lot
Best Regards! Jane
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello Jane,
I think there is no Intel GPU inside your CPU, based on
Are you using Intel(R) Xeon(R) CPU E5-2640 v4 @ 2.40GHz >
For clDNN and -d GPU to work you need a CPU with an Intel GPU.
What is the output of
clinfo
Cheers,
nikos
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi nikos,
Thanks a lot for your help. Yes, there is no GPU in the cpu. And the clinfo output for ubuntu base image is:
Number of platforms 0
I only have separate GPUs, don't know whether these GPUs can be supported. Below is the clinfo output for nvidia/cuda:10.0-cudnn7-runtime-centos7 base image:
Number of platforms 1
Platform Name NVIDIA CUDA
Platform Vendor NVIDIA Corporation
Platform Version OpenCL 1.2 CUDA 10.0.141
Platform Profile FULL_PROFILE
Platform 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_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
Platform Extensions function suffix NVPlatform Name NVIDIA CUDA
Number of devices 4
Device Name Tesla P40
Device Vendor NVIDIA Corporation
Device Vendor ID 0x10de
Device Version OpenCL 1.2 CUDA
Driver Version 410.48
Device OpenCL C Version OpenCL C 1.2
Device Type GPU
Device Available Yes
Device Profile FULL_PROFILE
Device Topology (NV) PCI-E, 02:00.0
Max compute units 30
Max clock frequency 1531MHz
Compute Capability (NV) 6.1
Device Partition (core)
Max number of sub-devices 1
Supported partition types None
Max work item dimensions 3
Max work item sizes 1024x1024x64
Max work group size 1024
Compiler Available Yes
Linker Available Yes
Preferred work group size multiple 32
Warp size (NV) 32
Preferred / 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 Yes
Infinity and NANs Yes
Round to nearest Yes
Round to zero Yes
Round to infinity Yes
IEEE754-2008 fused multiply-add Yes
Support is emulated in software No
Correctly-rounded divide and sqrt operations Yes
Double-precision Floating-point support (cl_khr_fp64)
Denormals Yes
Infinity and NANs Yes
Round to nearest Yes
Round to zero Yes
Round to infinity Yes
IEEE754-2008 fused multiply-add Yes
Support is emulated in software No
Correctly-rounded divide and sqrt operations No
Address bits 64, Little-Endian
Global memory size 24032378880 (22.38GiB)
Error Correction support Yes
Max memory allocation 6008094720 (5.595GiB)
Unified memory for Host and Device No
Integrated memory (NV) No
Minimum alignment for any data type 128 bytes
Alignment of base address 4096 bits (512 bytes)
Global Memory cache type Read/Write
Global Memory cache size 491520 (480KiB)
Global Memory cache line 128 bytes
Image support Yes
Max number of samplers per kernel 32
Max size for 1D images from buffer 134217728 pixels
Max 1D or 2D image array size 2048 images
Max 2D image size 16384x32768 pixels
Max 3D image size 16384x16384x16384 pixels
Max number of read image args 256
Max number of write image args 16
Local memory type Local
Local memory size 49152 (48KiB)
Registers per block (NV) 65536
Max constant buffer size 65536 (64KiB)
Max number of constant args 9
Max size of kernel argument 4352 (4.25KiB)
Queue properties
Out-of-order execution Yes
Profiling Yes
Prefer user sync for interop No
Profiling timer resolution 1000ns
Execution capabilities
Run OpenCL kernels Yes
Run native kernels No
Kernel execution timeout (NV) No
Concurrent copy and kernel execution (NV) Yes
Number of async copy engines 2
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_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_bufferDevice Name Tesla P40
Device Vendor NVIDIA Corporation
Device Vendor ID 0x10de
Device Version OpenCL 1.2 CUDA
Driver Version 410.48
Device OpenCL C Version OpenCL C 1.2
Device Type GPU
Device Available Yes
Device Profile FULL_PROFILE
Device Topology (NV) PCI-E, 03:00.0
Max compute units 30
Max clock frequency 1531MHz
Compute Capability (NV) 6.1
Device Partition (core)
Max number of sub-devices 1
Supported partition types None
Max work item dimensions 3
Max work item sizes 1024x1024x64
Max work group size 1024
Compiler Available Yes
Linker Available Yes
Preferred work group size multiple 32
Warp size (NV) 32
Preferred / 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 Yes
Infinity and NANs Yes
Round to nearest Yes
Round to zero Yes
Round to infinity Yes
IEEE754-2008 fused multiply-add Yes
Support is emulated in software No
Correctly-rounded divide and sqrt operations Yes
Double-precision Floating-point support (cl_khr_fp64)
Denormals Yes
Infinity and NANs Yes
Round to nearest Yes
Round to zero Yes
Round to infinity Yes
IEEE754-2008 fused multiply-add Yes
Support is emulated in software No
Correctly-rounded divide and sqrt operations No
Address bits 64, Little-Endian
Global memory size 24032378880 (22.38GiB)
Error Correction support Yes
Max memory allocation 6008094720 (5.595GiB)
Unified memory for Host and Device No
Integrated memory (NV) No
Minimum alignment for any data type 128 bytes
Alignment of base address 4096 bits (512 bytes)
Global Memory cache type Read/Write
Global Memory cache size 491520 (480KiB)
Global Memory cache line 128 bytes
Image support Yes
Max number of samplers per kernel 32
Max size for 1D images from buffer 134217728 pixels
Max 1D or 2D image array size 2048 images
Max 2D image size 16384x32768 pixels
Max 3D image size 16384x16384x16384 pixels
Max number of read image args 256
Max number of write image args 16
Local memory type Local
Local memory size 49152 (48KiB)
Registers per block (NV) 65536
Max constant buffer size 65536 (64KiB)
Max number of constant args 9
Max size of kernel argument 4352 (4.25KiB)
Queue properties
Out-of-order execution Yes
Profiling Yes
Prefer user sync for interop No
Profiling timer resolution 1000ns
Execution capabilities
Run OpenCL kernels Yes
Run native kernels No
Kernel execution timeout (NV) No
Concurrent copy and kernel execution (NV) Yes
Number of async copy engines 2
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_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_bufferDevice Name Tesla P40
Device Vendor NVIDIA Corporation
Device Vendor ID 0x10de
Device Version OpenCL 1.2 CUDA
Driver Version 410.48
Device OpenCL C Version OpenCL C 1.2
Device Type GPU
Device Available Yes
Device Profile FULL_PROFILE
Device Topology (NV) PCI-E, 83:00.0
Max compute units 30
Max clock frequency 1531MHz
Compute Capability (NV) 6.1
Device Partition (core)
Max number of sub-devices 1
Supported partition types None
Max work item dimensions 3
Max work item sizes 1024x1024x64
Max work group size 1024
Compiler Available Yes
Linker Available Yes
Preferred work group size multiple 32
Warp size (NV) 32
Preferred / 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 Yes
Infinity and NANs Yes
Round to nearest Yes
Round to zero Yes
Round to infinity Yes
IEEE754-2008 fused multiply-add Yes
Support is emulated in software No
Correctly-rounded divide and sqrt operations Yes
Double-precision Floating-point support (cl_khr_fp64)
Denormals Yes
Infinity and NANs Yes
Round to nearest Yes
Round to zero Yes
Round to infinity Yes
IEEE754-2008 fused multiply-add Yes
Support is emulated in software No
Correctly-rounded divide and sqrt operations No
Address bits 64, Little-Endian
Global memory size 24032378880 (22.38GiB)
Error Correction support Yes
Max memory allocation 6008094720 (5.595GiB)
Unified memory for Host and Device No
Integrated memory (NV) No
Minimum alignment for any data type 128 bytes
Alignment of base address 4096 bits (512 bytes)
Global Memory cache type Read/Write
Global Memory cache size 491520 (480KiB)
Global Memory cache line 128 bytes
Image support Yes
Max number of samplers per kernel 32
Max size for 1D images from buffer 134217728 pixels
Max 1D or 2D image array size 2048 images
Max 2D image size 16384x32768 pixels
Max 3D image size 16384x16384x16384 pixels
Max number of read image args 256
Max number of write image args 16
Local memory type Local
Local memory size 49152 (48KiB)
Registers per block (NV) 65536
Max constant buffer size 65536 (64KiB)
Max number of constant args 9
Max size of kernel argument 4352 (4.25KiB)
Queue properties
Out-of-order execution Yes
Profiling Yes
Prefer user sync for interop No
Profiling timer resolution 1000ns
Execution capabilities
Run OpenCL kernels Yes
Run native kernels No
Kernel execution timeout (NV) No
Concurrent copy and kernel execution (NV) Yes
Number of async copy engines 2
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_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_bufferDevice Name Tesla P40
Device Vendor NVIDIA Corporation
Device Vendor ID 0x10de
Device Version OpenCL 1.2 CUDA
Driver Version 410.48
Device OpenCL C Version OpenCL C 1.2
Device Type GPU
Device Available Yes
Device Profile FULL_PROFILE
Device Topology (NV) PCI-E, 84:00.0
Max compute units 30
Max clock frequency 1531MHz
Compute Capability (NV) 6.1
Device Partition (core)
Max number of sub-devices 1
Supported partition types None
Max work item dimensions 3
Max work item sizes 1024x1024x64
Max work group size 1024
Compiler Available Yes
Linker Available Yes
Preferred work group size multiple 32
Warp size (NV) 32
Preferred / 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 Yes
Infinity and NANs Yes
Round to nearest Yes
Round to zero Yes
Round to infinity Yes
IEEE754-2008 fused multiply-add Yes
Support is emulated in software No
Correctly-rounded divide and sqrt operations Yes
Double-precision Floating-point support (cl_khr_fp64)
Denormals Yes
Infinity and NANs Yes
Round to nearest Yes
Round to zero Yes
Round to infinity Yes
IEEE754-2008 fused multiply-add Yes
Support is emulated in software No
Correctly-rounded divide and sqrt operations No
Address bits 64, Little-Endian
Global memory size 24032378880 (22.38GiB)
Error Correction support Yes
Max memory allocation 6008094720 (5.595GiB)
Unified memory for Host and Device No
Integrated memory (NV) No
Minimum alignment for any data type 128 bytes
Alignment of base address 4096 bits (512 bytes)
Global Memory cache type Read/Write
Global Memory cache size 491520 (480KiB)
Global Memory cache line 128 bytes
Image support Yes
Max number of samplers per kernel 32
Max size for 1D images from buffer 134217728 pixels
Max 1D or 2D image array size 2048 images
Max 2D image size 16384x32768 pixels
Max 3D image size 16384x16384x16384 pixels
Max number of read image args 256
Max number of write image args 16
Local memory type Local
Local memory size 49152 (48KiB)
Registers per block (NV) 65536
Max constant buffer size 65536 (64KiB)
Max number of constant args 9
Max size of kernel argument 4352 (4.25KiB)
Queue properties
Out-of-order execution Yes
Profiling Yes
Prefer user sync for interop No
Profiling timer resolution 1000ns
Execution capabilities
Run OpenCL kernels Yes
Run native kernels No
Kernel execution timeout (NV) No
Concurrent copy and kernel execution (NV) Yes
Number of async copy engines 2
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_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_bufferNULL platform behavior
clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...) NVIDIA CUDA
clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...) Success [NV]
clCreateContext(NULL, ...) [default] Success [NV]
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) No devices found in platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU) No platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_ACCELERATOR) No devices found in platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM) No devices found in platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL) No platformICD loader properties
ICD loader Name OpenCL ICD Loader
ICD loader Vendor OCL Icd free software
ICD loader Version 2.2.12
ICD loader Profile OpenCL 2.2
NOTE: your OpenCL library declares to support OpenCL 2.2,
but it seems to support up to OpenCL 2.1 only.
Best regards! Ying
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Jane,
Thank you for your clinfo output. It indicates there is no Intel GPU OpenCL device present so please use the CPU device (-d CPU).
> I only have separate GPUs, don't know whether these GPUs can be supported.
Please note OpenVino clDNN cannot run its OpenCL kernels on non-Intel GPUs, so at this point OpenVino will not run on your non-Intel GPU.
Cheers,
nikos
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Got it, thanks a lot.
Best regards! Jane

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page