Scheduled Maintenance: We are aware of an issue with Google, AOL, and Yahoo services as email providers which are blocking new registrations. We are trying to fix the issue and we have several internal and external support tickets in process to resolve the issue. Please see: viewtopic.php?t=158230

 

 

 

OpenCL v>=1.2 on amd radeon rx460/debian stretch (inst/cfg)

Linux Kernel, Network, and Services configuration.
Post Reply
Message
Author
khelair
Posts: 2
Joined: 2017-07-18 02:30

OpenCL v>=1.2 on amd radeon rx460/debian stretch (inst/cfg)

#1 Post by khelair »

I upgraded to stretch in order to locate more up-to-date libraries for an OpenCL version >= 1.2 that will work with my AMD Radeon RX460 for GPU computing. Although I have the correct x server installed, configured, and confirmed video acceleration working, I have yet to find (or configure correctly) an OpenCL other than 1.1.

System Info
uname: 4.9.0-3-amd64
dmesg|grep drm:

Code: Select all

[   26.624691] [drm] Initialized
[   26.880886] [drm] amdgpu kernel modesetting enabled.
[   26.946709] [drm] initializing kernel modesetting (POLARIS11 0x1002:0x67EF 0x174B:0xE344 0xCF).
[   26.946719] [drm] register mmio base: 0xF7E00000
[   26.946719] [drm] register mmio size: 262144
[   26.946723] [drm] doorbell mmio base: 0xF0000000
[   26.946723] [drm] doorbell mmio size: 2097152
[   26.946728] [drm] probing gen 2 caps for device 8086:c01 = 261ad03/e
[   26.946729] [drm] probing mlw for device 8086:c01 = 261ad03
[   26.946736] [drm] UVD is enabled in VM mode
[   26.946737] [drm] VCE enabled in VM mode
[   26.946832] [drm] GPU post is not needed
[   26.996681] [drm] Detected VRAM RAM=4096M, BAR=256M
[   26.996682] [drm] RAM width 128bits GDDR5
[   26.996691] [drm] amdgpu: 4096M of VRAM memory ready
[   26.996692] [drm] amdgpu: 16059M of GTT memory ready.
[   26.996702] [drm] GART: num cpu pages 4111165, num gpu pages 4111165
[   26.997869] [drm] PCIE GART of 16059M enabled (table at 0x0000000000040000).
[   26.997877] [drm] Supports vblank timestamp caching Rev 2 (21.10.2013).
[   26.997877] [drm] Driver supports precise vblank timestamp query.
[   26.997914] [drm] amdgpu: irq initialized.
[   26.998162] [drm] AMDGPU Display Connectors
[   26.998163] [drm] Connector 0:
[   26.998163] [drm]   DP-1
[   26.998163] [drm]   HPD5
[   26.998164] [drm]   DDC: 0x4868 0x4868 0x4869 0x4869 0x486a 0x486a 0x486b 0x486b
[   26.998164] [drm]   Encoders:
[   26.998165] [drm]     DFP1: INTERNAL_UNIPHY1
[   26.998165] [drm] Connector 1:
[   26.998166] [drm]   HDMI-A-1
[   26.998166] [drm]   HPD3
[   26.998167] [drm]   DDC: 0x4874 0x4874 0x4875 0x4875 0x4876 0x4876 0x4877 0x4877
[   26.998167] [drm]   Encoders:
[   26.998167] [drm]     DFP2: INTERNAL_UNIPHY1
[   26.998167] [drm] Connector 2:
[   26.998168] [drm]   DVI-D-1
[   26.998168] [drm]   HPD4
[   26.998169] [drm]   DDC: 0x4878 0x4878 0x4879 0x4879 0x487a 0x487a 0x487b 0x487b
[   26.998169] [drm]   Encoders:
[   26.998169] [drm]     DFP3: INTERNAL_UNIPHY
[   27.299073] [drm] Found UVD firmware Version: 1.79 Family ID: 16
[   27.315141] [drm] Found VCE firmware Version: 52.4 Binary ID: 3
[   27.454242] [drm] ring test on 0 succeeded in 12 usecs
...
[   27.480930] [drm] ring test on 11 succeeded in 1 usecs
[   27.480931] [drm] UVD initialized successfully.
[   27.580230] [drm] ring test on 12 succeeded in 15 usecs
[   27.580260] [drm] ring test on 13 succeeded in 11 usecs
[   27.580260] [drm] VCE initialized successfully.
[   27.659069] [drm] fb mappable at 0xE2204000
[   27.659069] [drm] vram apper at 0xE0000000
[   27.659070] [drm] size 5787648
[   27.659070] [drm] fb depth is 24
[   27.659070] [drm]    pitch is 6400
[   27.659119] fbcon: amdgpudrmfb (fb0) is primary device
[   27.783225] amdgpu 0000:01:00.0: fb0: amdgpudrmfb frame buffer device
[   27.796216] [drm] ib test on ring 0 succeeded
[   27.796394] [drm] ib test on ring 1 succeeded
...
[   27.799336] [drm] ib test on ring 12 succeeded
[   27.800303] [drm] Initialized amdgpu 3.8.0 20150101 for 0000:01:00.0 on minor 0
clinfo (prior to attempt to install AMD-APP-SDKInstaller-v3.0.130.136-GA-linux64.tar.bz2 breaking things):

Code: Select all

Number of platforms                               1
  Platform Name                                   Clover
  Platform Vendor                                 Mesa
  Platform Version                                OpenCL 1.1 Mesa 13.0.6
  Platform Profile                                FULL_PROFILE
  Platform Extensions                             cl_khr_icd
  Platform Extensions function suffix             MESA

  Platform Name                                   Clover
Number of devices                                 1
  Device Name                                     AMD POLARIS11 (DRM 3.8.0 / 4.9.0-3-amd64, LLVM 3.9.1)
  Device Vendor                                   AMD
  Device Vendor ID                                0x1002
  Device Version                                  OpenCL 1.1 Mesa 13.0.6
  Driver Version                                  13.0.6
  Device OpenCL C Version                         OpenCL C 1.1 
  Device Type                                     GPU
  Device Profile                                  FULL_PROFILE
  Max compute units                               14
  Max clock frequency                             1250MHz
  Max work item dimensions                        3
  Max work item sizes                             256x256x256
  Max work group size                             256
  Preferred work group size multiple              64
  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
    Correctly-rounded divide and sqrt operations  No
  Address bits                                    64, Little-Endian
  Global memory size                              15287869440 (14.24GiB)
  Error Correction support                        No
  Max memory allocation                           3821967360 (3.559GiB)
  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                                   No
  Local memory type                               Local
  Local memory size                               32768 (32KiB)
  Max constant buffer size                        2147483647 (2GiB)
  Max number of constant args                     16
  Max size of kernel argument                     1024
  Queue properties                                
    Out-of-order execution                        No
    Profiling                                     Yes
  Profiling timer resolution                      0ns
  Execution capabilities                          
    Run OpenCL kernels                            Yes
    Run native kernels                            No
  Device Available                                Yes
  Compiler Available                              Yes
  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_byte_addressable_store cl_khr_fp64

NULL platform behavior
  clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...)  Clover
  clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...)   Success [MESA]
  clCreateContext(NULL, ...) [default]            Success [MESA]
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU)  Success (1)
    Platform Name                                 Clover
    Device Name                                   AMD POLARIS11 (DRM 3.8.0 / 4.9.0-3-amd64, LLVM 3.9.1)
  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                                 Clover
    Device Name                                   AMD POLARIS11 (DRM 3.8.0 / 4.9.0-3-amd64, LLVM 3.9.1)

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
Current clinfo output reports 0 platforms, though I've tried reinstalling everything applicable via a search for 'opencl' from synaptic. I'm afraid I'm a bit of a neophyte when it comes to working with GPU computing/OpenCL applications. I don't really know what other sources of system information/package install logs or anything to include that might be useful here. Please let me know if I should be including anything else.

I desperately wish to be utilizing the GPU for things, though, and I really hate having to constantly reboot to Doze7 (dual boot, obviously) in order to keep the GPU utilized when I'm not actively doing anything requiring linux. Did I mention I hate 'doze? Regardless, this is a highly sub-optimal situation for me. I would be very grateful for any assistance that may be offered. Thanks in advance for help & pointers in the right direction!

-k

khelair
Posts: 2
Joined: 2017-07-18 02:30

Re: OpenCL v>=1.2 on amd radeon rx460/debian stretch (inst/c

#2 Post by khelair »

I don't mean to pointlessly bump, but is there seriously still no OpenCL v1.2+ available for the AMD Radeon rx460 and friends? :cry:

Post Reply