[ ERROR ] Device with "FPGA" name is not registered in the InferenceEngine

Anonymous · ‎07-29-2021

Hello I am submitting a job to OneAPI on DevCloud that is using one of Intel's Pre-Built models for Open Model Zoo (2021 version, installed ~2 months ago). I get the error

[ ERROR ] Device with "FPGA" name is not registered in the InferenceEngine

I am submitting the job with the command:

qsub -l nodes=1:fpga:ppn=2 -d . test.sh

The error occurs on any model that is running with the "-FPGA" device option. An example command is given below:

source /opt/intel/openvino/bin/setupvars.sh
~/.../interactive_face_detection_demo -i ~/.../input.mp4 -m ~/.../face-detection-adas-0001.xml -m_ag ~/.../age-gender-recognition-retail-0013.xml -m_hp ~/.../head-pose-estimation-adas-0001.xml -m_em ~/.../emotions-recognition-retail-0003.xml -m_lm ~/.../facial-landmarks-35-adas-0002.xml -d CPU -d_ag CPU -d_hp CPU -d_hp CPU -d_em FPGA -no_show &

Note: The three dots (...) represents the path to the files. The "-FPGA" does not work for any device specifier option. This command works properly when devices "-CPU" and "-GPU" are specified.

I have also tried these as alternates instead of "-FPGA" : "-FPGA.0", "-HETERO:FPGA", and "-FPGA,CPU" but all three yield the same error

Any help would be greatly appreciated, thank you

AbhijeetJ_Intel · ‎07-30-2021

Hi,

Thank you for reaching out. Could you please try out the following commands?

source /opt/intel/oneapi/setvars.sh --force

Could you please share with us the output of
```
clinfo
```

Regards

Abhijeet

Anonymous · ‎07-30-2021

Hi,

1).

The first command gives the same error as before after running.

2).

My output for "clinfo":

Number of platforms                               2
  Platform Name                                   Intel(R) FPGA Emulation Platform for OpenCL(TM)
  Platform Vendor                                 Intel(R) Corporation
  Platform Version                                OpenCL 1.2 Intel(R) FPGA SDK for OpenCL(TM), Version 20.3
  Platform Profile                                EMBEDDED_PROFILE
  Platform Extensions                             cl_khr_icd cl_khr_byte_addressable_store cl_intel_fpga_host_pipe cles_khr_int64 cl_khr_il_program cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics 
  Platform Extensions function suffix             IntelFPGA

  Platform Name                                   Intel(R) OpenCL
  Platform Vendor                                 Intel(R) Corporation
  Platform Version                                OpenCL 2.1 LINUX
  Platform Profile                                FULL_PROFILE
  Platform Extensions                             cl_khr_icd 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_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_byte_addressable_store cl_khr_depth_images cl_khr_3d_image_writes cl_khr_il_program cl_intel_unified_shared_memory_preview cl_intel_subgroups cl_intel_subgroups_char cl_intel_subgroups_short cl_intel_subgroups_long cl_intel_spirv_subgroups cl_intel_required_subgroup_size cl_intel_exec_by_local_thread cl_intel_vec_len_hint cl_intel_device_partition_by_names cl_khr_spir cl_khr_fp64 cl_khr_image2d_from_buffer 
  Platform Host timer resolution                  1ns
  Platform Extensions function suffix             INTEL

  Platform Name                                   Intel(R) FPGA Emulation Platform for OpenCL(TM)
Number of devices                                 1
  Device Name                                     Intel(R) FPGA Emulation Device
  Device Vendor                                   Intel(R) Corporation
  Device Vendor ID                                0x1172
  Device Version                                  OpenCL 1.2 
  Driver Version                                  2021.12.6.0.19_160000
  Device OpenCL C Version                         OpenCL C 1.2 
  Device Type                                     Accelerator
  Device Profile                                  EMBEDDED_PROFILE
  Device Available                                Yes
  Compiler Available                              Yes
  Linker Available                                Yes
  Max compute units                               24
  Max clock frequency                             3400MHz
  Device Partition                                (core)
    Max number of sub-devices                     24
    Supported partition types                     by counts, equally, by names (Intel)
    Supported affinity domains                    (n/a)
  Max work item dimensions                        3
  Max work item sizes                             67108864x67108864x67108864
  Max work group size                             67108864
  Preferred work group size multiple              128
  Preferred / native vector sizes                 
    char                                                 1 / 64      
    short                                                1 / 32      
    int                                                  1 / 16      
    long                                                 1 / 8       
    half                                                 0 / 0        (n/a)
    float                                                1 / 16      
    double                                               1 / 8        (n/a)
  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                                 No
    Round to infinity                             No
    IEEE754-2008 fused multiply-add               No
    Support is emulated in software               No
    Correctly-rounded divide and sqrt operations  No
  Double-precision Floating-point support         (n/a)
  Address bits                                    64, Little-Endian
  Global memory size                              202510090240 (188.6GiB)
  Error Correction support                        No
  Max memory allocation                           50627522560 (47.15GiB)
  Unified memory for Host and Device              Yes
  Minimum alignment for any data type             128 bytes
  Alignment of base address                       1024 bits (128 bytes)
  Global Memory cache type                        Read/Write
  Global Memory cache size                        262144 (256KiB)
  Global Memory cache line size                   64 bytes
  Image support                                   No
  Local memory type                               Global
  Local memory size                               262144 (256KiB)
  Max number of constant args                     480
  Max constant buffer size                        131072 (128KiB)
  Max size of kernel argument                     3840 (3.75KiB)
  Queue properties                                
    Out-of-order execution                        Yes
    Profiling                                     Yes
  Prefer user sync for interop                    No
  Profiling timer resolution                      1ns
  Execution capabilities                          
    Run OpenCL kernels                            Yes
    Run native kernels                            Yes
    IL version                                    SPIR-V_1.0
  printf() buffer size                            1048576 (1024KiB)
  Built-in kernels                                (n/a)
  Device Extensions                               cl_khr_icd cl_khr_byte_addressable_store cl_intel_fpga_host_pipe cles_khr_int64 cl_khr_il_program cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics 

  Platform Name                                   Intel(R) OpenCL
Number of devices                                 1
  Device Name                                     Intel(R) Xeon(R) Gold 6128 CPU @ 3.40GHz
  Device Vendor                                   Intel(R) Corporation
  Device Vendor ID                                0x8086
  Device Version                                  OpenCL 2.1 (Build 0)
  Driver Version                                  2021.12.6.0.19_160000
  Device OpenCL C Version                         OpenCL C 2.0 
  Device Type                                     CPU
  Device Profile                                  FULL_PROFILE
  Device Available                                Yes
  Compiler Available                              Yes
  Linker Available                                Yes
  Max compute units                               24
  Max clock frequency                             3400MHz
  Device Partition                                (core)
    Max number of sub-devices                     24
    Supported partition types                     by counts, equally, by names (Intel)
    Supported affinity domains                    (n/a)
  Max work item dimensions                        3
  Max work item sizes                             8192x8192x8192
  Max work group size                             8192
  Preferred work group size multiple              128
  Max sub-groups per work group                   2048
  Sub-group sizes (Intel)                         4, 8, 16
  Preferred / native vector sizes                 
    char                                                 1 / 64      
    short                                                1 / 32      
    int                                                  1 / 16      
    long                                                 1 / 8       
    half                                                 0 / 0        (n/a)
    float                                                1 / 16      
    double                                               1 / 8        (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                                 No
    Round to infinity                             No
    IEEE754-2008 fused multiply-add               No
    Support is emulated in software               No
    Correctly-rounded divide and sqrt operations  No
  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
  Address bits                                    64, Little-Endian
  Global memory size                              202510090240 (188.6GiB)
  Error Correction support                        No
  Max memory allocation                           50627522560 (47.15GiB)
  Unified memory for Host and Device              Yes
  Shared Virtual Memory (SVM) capabilities        (core)
    Coarse-grained buffer sharing                 Yes
    Fine-grained buffer sharing                   Yes
    Fine-grained system sharing                   Yes
    Atomics                                       Yes
  Minimum alignment for any data type             128 bytes
  Alignment of base address                       1024 bits (128 bytes)
  Preferred alignment for atomics                 
    SVM                                           64 bytes
    Global                                        64 bytes
    Local                                         0 bytes
  Max size for global variable                    65536 (64KiB)
  Preferred total size of global vars             65536 (64KiB)
  Global Memory cache type                        Read/Write
  Global Memory cache size                        262144 (256KiB)
  Global Memory cache line size                   64 bytes
  Image support                                   Yes
    Max number of samplers per kernel             480
    Max size for 1D images from buffer            3164220160 pixels
    Max 1D or 2D image array size                 2048 images
    Base address alignment for 2D image buffers   64 bytes
    Pitch alignment for 2D image buffers          64 pixels
    Max 2D image size                             16384x16384 pixels
    Max 3D image size                             2048x2048x2048 pixels
    Max number of read image args                 480
    Max number of write image args                480
    Max number of read/write image args           480
  Max number of pipe args                         16
  Max active pipe reservations                    10922
  Max pipe packet size                            1024
  Local memory type                               Global
  Local memory size                               32768 (32KiB)
  Max number of constant args                     480
  Max constant buffer size                        131072 (128KiB)
  Max size of kernel argument                     3840 (3.75KiB)
  Queue properties (on host)                      
    Out-of-order execution                        Yes
    Profiling                                     Yes
    Local thread execution (Intel)                Yes
  Queue properties (on device)                    
    Out-of-order execution                        Yes
    Profiling                                     Yes
    Preferred size                                4294967295 (4GiB)
    Max size                                      4294967295 (4GiB)
  Max queues on device                            4294967295
  Max events on device                            4294967295
  Prefer user sync for interop                    No
  Profiling timer resolution                      1ns
  Execution capabilities                          
    Run OpenCL kernels                            Yes
    Run native kernels                            Yes
    Sub-group independent forward progress        No
    IL version                                    SPIR-V_1.0
    SPIR versions                                 1.2
  printf() buffer size                            1048576 (1024KiB)
  Built-in kernels                                (n/a)
  Device Extensions                               cl_khr_icd 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_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_byte_addressable_store cl_khr_depth_images cl_khr_3d_image_writes cl_khr_il_program cl_intel_unified_shared_memory_preview cl_intel_subgroups cl_intel_subgroups_char cl_intel_subgroups_short cl_intel_subgroups_long cl_intel_spirv_subgroups cl_intel_required_subgroup_size cl_intel_exec_by_local_thread cl_intel_vec_len_hint cl_intel_device_partition_by_names cl_khr_spir cl_khr_fp64 cl_khr_image2d_from_buffer 


NULL platform behavior
  clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...)  No platform
  clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...)   No platform
  clCreateContext(NULL, ...) [default]            No platform
  clCreateContext(NULL, ...) [other]              Success [IntelFPGA]
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT)  Success (1)
    Platform Name                                 Intel(R) FPGA Emulation Platform for OpenCL(TM)
    Device Name                                   Intel(R) FPGA Emulation Device
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_ACCELERATOR)  Success (1)
    Platform Name                                 Intel(R) FPGA Emulation Platform for OpenCL(TM)
    Device Name                                   Intel(R) FPGA Emulation Device
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL)  Success (1)
    Platform Name                                 Intel(R) FPGA Emulation Platform for OpenCL(TM)
    Device Name                                   Intel(R) FPGA Emulation Device

Thank you for assisting

AbhijeetJ_Intel · ‎08-02-2021

Hi,

Thank you for providing the above information.

Could you please confirm which DevCloud you are using OneAPI DevCloud or DevCloud for edge.

OneAPI DevCloud: https://devcloud.intel.com/oneapi/

DevCloud for the Edge: https://software.intel.com/content/www/us/en/develop/tools/devcloud/edge/overview.html

Regards

Abhijeet

Anonymous · ‎08-03-2021

I am using oneAPI Devcloud

AbhijeetJ_Intel · ‎08-19-2021

Hi,

We are investigating your issue at our end.

We will get back to you soon.

Regards

Abhijeet

Munesh_Intel · ‎08-31-2021

Hi Ethan,

Our apologies to you for the delay in replying. We’ve just received your query in the proper queue.

FPGA devices have been deprecated on OpenVINO, there is only one version that supports FPGA devices (OpenVINO 2020.3.x LTS).

More information regarding this is available in Release Notes for Intel® Distribution of OpenVINO™ Toolkit 2021.4 LTS, in the ‘Support Change and Deprecation Notices’ section.

For your case, we recommend you try on Intel® DevCloud for the Edge, which provides an option to select OpenVINO 2020.3.1 LTS by selecting the right kernel, by following the steps given below:

Click Kernel from the menu bar
Select Change kernel
Select Python 3 (OpenVINO 2020.3.1 LTS)

For future DevCloud for Edge related questions, I would suggest you post in the Intel® DevCloud for Edge forum.

Link: https://community.intel.com/t5/Intel-DevCloud-for-Edge/bd-p/devcloud-edge

Regards,

Munesh

Munesh_Intel · ‎09-09-2021

Hi Ethan,

This thread will no longer be monitored since we have provided information and recommendation. If you need any additional information from Intel, please submit a new question.

Regards,

Munesh