Skip to content
  • Categories
  • Recent
  • Tags
  • Popular
  • Users
  • Groups
Collapse
Brand Logo

ModalAI Forum

Peter MilaniP

Peter Milani

@Peter Milani
Contributor
Unfollow Follow
About
Posts
12
Topics
6
Shares
0
Groups
1
Followers
0
Following
0

Posts

Recent Best Controversial

  • Voxl2 Docker (Ubuntu 22) with OpenCL/Adreno
    Peter MilaniP Peter Milani

    @Alex-Kushleyev I was able to get the following when running opencl within the docker instance:

     clinfo
    Number of platforms                               1
      Platform Name                                   Portable Computing Language
      Platform Vendor                                 The pocl project
      Platform Version                                OpenCL 1.2 pocl 1.4, None+Asserts, LLVM 9.0.1, RELOC, SLEEF, POCL_DEBUG
      Platform Profile                                FULL_PROFILE
      Platform Extensions                             cl_khr_icd
      Platform Extensions function suffix             POCL
    
      Platform Name                                   Portable Computing Language
    Number of devices                                 1
      Device Name                                     pthread-0x805
      Device Vendor                                   Qualcomm
      Device Vendor ID                                0x13b5
      Device Version                                  OpenCL 1.2 pocl HSTR: pthread-aarch64-unknown-linux-gnu-GENERIC
      Driver Version                                  1.4
      Device OpenCL C Version                         OpenCL C 1.2 pocl
      Device Type                                     CPU
      Device Profile                                  FULL_PROFILE
      Device Available                                Yes
      Compiler Available                              Yes
      Linker Available                                Yes
      Max compute units                               8
      Max clock frequency                             1804MHz
      Device Partition                                (core)
        Max number of sub-devices                     8
        Supported partition types                     equally, by counts
        Supported affinity domains                    (n/a)
      Max work item dimensions                        3
      Max work item sizes                             4096x4096x4096
      Max work group size                             4096
      Preferred work group size multiple              8
      Preferred / native vector sizes                 
        char                                                16 / 16      
        short                                                8 / 8       
        int                                                  4 / 4       
        long                                                 2 / 2       
        half                                                 0 / 0        (n/a)
        float                                                4 / 4       
        double                                               2 / 2        (cl_khr_fp64)
      Half-precision Floating-point support           (n/a)
      Single-precision Floating-point support         (core)
        Denormals                                     No
        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                              5896568832 (5.492GiB)
      Error Correction support                        No
      Max memory allocation                           2147483648 (2GiB)
      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                        None
      Image support                                   Yes
        Max number of samplers per kernel             16
        Max size for 1D images from buffer            134217728 pixels
        Max 1D or 2D image array size                 2048 images
        Max 2D image size                             8192x8192 pixels
        Max 3D image size                             2048x2048x2048 pixels
        Max number of read image args                 128
        Max number of write image args                128
      Local memory type                               Global
      Local memory size                               33554432 (32MiB)
      Max number of constant args                     8
      Max constant buffer size                        33554432 (32MiB)
      Max size of kernel argument                     1024
      Queue properties                                
        Out-of-order execution                        Yes
        Profiling                                     Yes
      Prefer user sync for interop                    Yes
      Profiling timer resolution                      1ns
      Execution capabilities                          
        Run OpenCL kernels                            Yes
        Run native kernels                            Yes
      printf() buffer size                            16777216 (16MiB)
      Built-in kernels                                (n/a)
      Device Extensions                               cl_khr_byte_addressable_store 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_3d_image_writes cl_khr_fp64
    
    NULL platform behavior
      clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...)  Portable Computing Language
      clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...)   Success [POCL]
      clCreateContext(NULL, ...) [default]            Success [POCL]
      clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT)  Success (1)
        Platform Name                                 Portable Computing Language
        Device Name                                   pthread-0x805
      clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU)  Success (1)
        Platform Name                                 Portable Computing Language
        Device Name                                   pthread-0x805
      clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU)  No devices found in 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)  Success (1)
        Platform Name                                 Portable Computing Language
        Device Name                                   pthread-0x805
    
    ICD loader properties
      ICD loader Name                                 OpenCL ICD Loader
      ICD loader Vendor                               OCL Icd free software
      ICD loader Version                              2.2.11
      ICD loader Profile                              OpenCL 2.1
    
    

    but after installing:

    apt install -y -qq pocl-opencl-icd;
    
    Ask your questions right here!

  • Voxl2 Docker (Ubuntu 22) with OpenCL/Adreno
    Peter MilaniP Peter Milani

    @Alex-Kushleyev @eric I've implemented your solution and get the same result.

    I did get a bit confused as running clinfo only returned a single device of type CPU and without the name "Adreno".

    However I added to your test script a query on the device_type and it returned GPU so I guess its only finding the GPU. I would have expected it to return a few more devices as the [Qualcomm OpenCL guide] (https://docs.qualcomm.com/bundle/publicresource/80-NB295-11_REV_C_Qualcomm_Snapdragon_Mobile_Platform_Opencl_General_Programming_and_Optimization.pdf) suggests that the dsp and CPU could have been returned as well, so I'm not sure what is happening there. I didn't have to link devices only shared the volumes to the relevant libraries. I would have expected the CPU to be returned a a matter of course as that is what happens with the intel implementation.

    My additional lines to the script (given for info is):

      cl_device_type device_type;
      clGetDeviceInfo(devices[j], CL_DEVICE_TYPE, sizeof(cl_device_type), &device_type, NULL);
      printf("Device type: ");
      if (device_type & CL_DEVICE_TYPE_CPU)
          printf("CPU ");
      if (device_type & CL_DEVICE_TYPE_GPU)
          printf("GPU ");
      if (device_type & CL_DEVICE_TYPE_ACCELERATOR)
          printf("ACCELERATOR ");
      if (device_type & CL_DEVICE_TYPE_DEFAULT)
          printf("DEFAULT ");
      printf("\n");
    
    

    Which returns

    OpenCL platform count: 1
    OpenCL device count: 1
    1. Device: QUALCOMM Adreno(TM)
     1.1 Hardware version: OpenCL 2.0 Adreno(TM) 650
    Device type: GPU 
     1.2 Software version: OpenCL 2.0 QUALCOMM build: commit # changeid # Date: 11/10/21 Wed Local Branch:  Remote Branch:  Compiler E031.37.12.01
     1.3 OpenCL C version: OpenCL C 2.0 Adreno(TM) 650
     1.4 Parallel compute units: 3
    
    
    Ask your questions right here!

  • Yocto build instructions
    Peter MilaniP Peter Milani

    @Moderator Hi I'm just trying to find a good way to deploy to multiple devices via a "golden image" type setup. Is there a way to do that. Should I just follow the rules for the custom kernel instructions and add a custom bitbake layer onto that?

    Software Development

  • Yocto build instructions
    Peter MilaniP Peter Milani

    Hi
    I have the Qualcomm HLOS and non HLOS meta repositories, is there some information regarding yocto build instructions? a meta-modalai-voxl2-bsp by any chance? I don't really need too much of the modalai stuff if it is closed source, just the bsp so that the board will run with all its interfaces.
    cheers
    Peter

    Software Development

  • Exposing /dev/ttyHS1 -> HS3 + USB2
    Peter MilaniP Peter Milani

    Hi
    I've spun up an expansion board to expose the linux uarts on the legacy and high speed headers for the Voxl2 as well as give a usb2 interface.
    Would you be willing to review it? I'd buy a board that exposed these ports if it existed, but I haven't found a board that exposes USB2 (or USB3) as well as the three linux UARTs.
    cheers
    Peter

    PCB Design Reviews

  • Mating connector for M0173
    Peter MilaniP Peter Milani

    Hi ModalAI

    what is the recommended mating connector for the M0173 micocoax connector? I assume both J6 and J7 need to be connected for full functionality.
    cheers
    Peter

    Image Sensors

  • NDAA Compliance for Cameras
    Peter MilaniP Peter Milani

    Hi ModalAI,

    There have been a couple of posts regarding NDAA compliance in this forum, all of which have been unanswered. Hopefully here that wont be the case with this quesiton.

    I am after confirmation that there are NDAA compliant camera options for voxl(2) sensing. As far as I can tell there are but there are a number of non-compliant cameras available too.

    I assume that any Omnivision camera is non-compliant as it is Chinese Owned. ie all OV partnumbers.

    On-semi part numbers (AR) are compliant.
    Sony part numbers IMX are compliant.

    Is that roughly correct?
    cheers
    Peter

    Ask your questions right here!

  • Update on operating system upgrades to 20.04, 22.04 and 24.04
    Peter MilaniP Peter Milani

    I found commit ddc52dec132c777dd950c7f519bdd19f1e51d2cd in your https://gitlab.com/voxl-public/system-image-build/meta-voxl2/-/tree/ubun2.0-dev/recipes-append/recipes-core/ubuntu-base?ref_type=heads
    that has a bitbake append for ubuntu 20.04, seems that its in active development, do you have any guides to image build?

    I don't need the closed source stuff at moment.

    VOXL 2

  • Update on operating system upgrades to 20.04, 22.04 and 24.04
    Peter MilaniP Peter Milani

    Hi
    this was asked earlier in the year, any movement on enabling 20.04 or 22.04 on the rb5165 based platforms. I know other vendors have 20.04 HLOS and non-HLOS images from Qualcomm, any possibility of using those with modalAI bsp and other meta to get a 20.04 operating system on voxl2?
    cheers
    Peter

    VOXL 2

  • Download speeds for sdk slow
    Peter MilaniP Peter Milani

    @tom yes that link worked fine, thanks

    VOXL SDK

  • Download speeds for sdk slow
    Peter MilaniP Peter Milani

    FYI downloading v1.3.3 is fine, downloads at 7MBps. the v1.3.5 is slow

    VOXL SDK

  • Download speeds for sdk slow
    Peter MilaniP Peter Milani

    Any reason why the download speeds for the SDK should be slow. My internet speed test is showing >50MBps but the SDK when I go to download rarely meets 20Kbps. As it is a large file I though I'd ask here just in case theres a faster link or identify something wrong, if you weren't aware.

    downloading from here:
    https://developer.modalai.com/asset/eula-download/168

    cheers
    Peter

    VOXL SDK
  • Login

  • Don't have an account? Register

  • Login or register to search.
  • First post
    Last post
0
  • Categories
  • Recent
  • Tags
  • Popular
  • Users
  • Groups