Davinci resolve 18.6.6 , media does not work

Hello everyone , ive managed to get Davinci Resolve Studio 18.6.6 working on fedora 40. i have 2 amd gpus (7900 xtx and igpu from my ryzen 7950 cpu). ive already installed all neccesary packages for davinci resolve including rocm-opencl. while davinci resolve launches proeprly , once i try to import media (audio , video , pictures , patented or not) it wont show me the thumbnail/preview. nor am i able to play the media , or the timeline in the edit page.
i can play the timeline in the fairlight page (albeit with no audio from the imported media actually playing)

if you know anything about this issue or using davinci with the open source amd drivers/software , please do help me out. Thank you :smile:.

I have got Resolve working on a Fedora 40 system with an AMD GPU by ensuring the right packages were installed and plugging in either a legitimate monitor or a ‘HDMI dummy’ into my eGPU.

First let’s ensure you have all the right packages with:

sudo dnf list installed '*amd-gpu*' '*amdgpu*' '*rocm*' '*roct*' '*hsa*' '*mesa*' '*vulkan*' 'kernel' | grep -v 'procmail|setproctitle

My packages are as follows:

Installed Packages
amd-gpu-firmware.noarch           20240610-1.fc40                 @System   
hsa-rocr.x86_64                   1.13.0.60102-119.el9            @System   
hsa-rocr-devel.x86_64             1.13.0.60102-119.el9            @System   
hsa-rocr5.4.1.x86_64              1.7.0.50401-84.el9              @rocm-copy
hsakmt-roct-devel.x86_64          20240125.5.08.60102-119.el9     @System   
kernel.x86_64                     6.8.9-300.fc40                  @System   
kernel.x86_64                     6.8.10-300.fc40                 @System   
kernel.x86_64                     6.8.11-300.fc40                 @System   
kernel.x86_64                     6.9.4-200.fc40                  @updates  
kernel.x86_64                     6.9.5-200.fc40                  @System   
kernel.x86_64                     6.9.6-200.fc40                  @System   
mesa-dri-drivers.x86_64           24.1.2-2.fc40                   @System   
mesa-dri-drivers.i686             24.1.2-7.fc40                   @System   
mesa-dri-drivers.x86_64           24.1.2-7.fc40                   @System   
mesa-filesystem.i686              24.1.2-2.fc40                   @System   
mesa-filesystem.x86_64            24.1.2-2.fc40                   @System   
mesa-filesystem.i686              24.1.2-7.fc40                   @System   
mesa-filesystem.x86_64            24.1.2-7.fc40                   @System   
mesa-libEGL.x86_64                24.1.2-2.fc40                   @System   
mesa-libEGL.i686                  24.1.2-7.fc40                   @System   
mesa-libEGL.x86_64                24.1.2-7.fc40                   @System   
mesa-libEGL-devel.x86_64          24.1.2-7.fc40                   @System   
mesa-libGL.i686                   24.1.2-7.fc40                   @System   
mesa-libGL.x86_64                 24.1.2-7.fc40                   @System   
mesa-libGLU.x86_64                9.0.3-4.fc40                    @System   
mesa-libOSMesa.i686               24.1.2-7.fc40                   @System   
mesa-libOSMesa.x86_64             24.1.2-7.fc40                   @System   
mesa-libgbm.x86_64                24.1.2-2.fc40                   @System   
mesa-libgbm.i686                  24.1.2-7.fc40                   @System   
mesa-libgbm.x86_64                24.1.2-7.fc40                   @System   
mesa-libglapi.x86_64              24.1.2-2.fc40                   @System   
mesa-libglapi.i686                24.1.2-7.fc40                   @System   
mesa-libglapi.x86_64              24.1.2-7.fc40                   @System   
mesa-libxatracker.x86_64          24.1.2-7.fc40                   @System   
mesa-va-drivers.x86_64            24.1.2-2.fc40                   @System   
mesa-va-drivers.i686              24.1.2-7.fc40                   @System   
mesa-va-drivers.x86_64            24.1.2-7.fc40                   @System   
mesa-vulkan-drivers.i686          24.1.2-7.fc40                   @System   
mesa-vulkan-drivers.x86_64        24.1.2-7.fc40                   @System   
rocm-clang-ocl.x86_64             0.5.0.60102-119.el9             @System   
rocm-cmake.x86_64                 0.12.0.60102-119.el9            @System   
rocm-core.x86_64                  6.1.2.60102-119.el9             @System   
rocm-core5.4.1.x86_64             5.4.1.50401-84.el9              @rocm-copy
rocm-dbgapi.x86_64                0.71.0.60102-119.el9            @System   
rocm-debug-agent.x86_64           2.0.3.60102-119.el9             @System   
rocm-device-libs.x86_64           1.0.0.60102-119.el9             @System   
rocm-llvm.x86_64                  17.0.0.24193.60102-119.el9      @System   
rocm-opencl.x86_64                2.0.0.60102-119.el9             @System   
rocm-opencl-devel.x86_64          2.0.0.60102-119.el9             @System   
rocm-opencl-icd-loader.x86_64     1.2.60102-119.el9               @System   
rocm-smi.x86_64                   6.0.2-1.fc40                    @System   
rocm-smi-lib.x86_64               7.2.0.60102-119.el9             @System   
rocm-utils.x86_64                 6.1.2.60102-119.el9             @System   
rocminfo.x86_64                   1.0.0.60102-119.el9             @System   
roctracer.x86_64                  4.1.60102.60102-119.el9         @System   
roctracer-devel.x86_64            4.1.60102.60102-119.el9         @System   
vulkan-headers.noarch             1.3.283.0-1.fc40                @System   
vulkan-loader.i686                1.3.283.0-2.fc40                @System   
vulkan-loader.x86_64              1.3.283.0-2.fc40                @System   
vulkan-loader-devel.x86_64        1.3.283.0-2.fc40                @System   
vulkan-tools.x86_64               1.3.283.0-1.fc40                @System

Please also share which ROCm repo you’re using (adjust filename in command as necessary):

cat /etc/yum.repos.d/rocm_copy.repo

My ROCm repo baseurl is: https://repo.radeon.com/rocm/rhel9/latest/main/

1 Like

Seeing as i have missing packages , i tried installing rocm based on the website’s instructions (Red Hat Enterprise Linux native installation — ROCm installation (Linux)).

i got an error during the installation of amdgpu dkms. here is the log from /var/lib/dkms/amdgpu/6.7.0-1781449.el9/build/make.log (although i dont think this is relevant?) :

/tmp/amd.cGMjLvKe/amd/amdgpu/…/pm/swsmu/smu11/vangogh_ppt.c: In function ‘vangogh_init_smc_tables’:
/tmp/amd.cGMjLvKe/amd/amdgpu/…/pm/swsmu/smu11/vangogh_ppt.c:454:42: error: ‘struct cpuinfo_x86’ has no member named ‘x86_max_cores’
454 | smu->cpu_core_num = boot_cpu_data.x86_max_cores;
| ^
make[3]: *** [scripts/Makefile.build:244: /tmp/amd.cGMjLvKe/amd/amdgpu/…/pm/swsmu/smu11/vangogh_ppt.o] Error 1
make[3]: *** Waiting for unfinished jobs…
make[2]: *** [scripts/Makefile.build:485: /tmp/amd.cGMjLvKe/amd/amdgpu] Error 2
make[1]: *** [/usr/src/kernels/6.9.7-200.fc40.x86_64/Makefile:1930: /tmp/amd.cGMjLvKe] Error 2
make: *** [Makefile:252: __sub-make] Error 2
make: Leaving directory ‘/usr/src/kernels/6.9.7-200.fc40.x86_64’

i also got this error

ERROR: clBuildProgram(-11)

when trying to verify my rocm installation with

/opt/rocm-6.1.2/bin/rocminfo
/opt/rocm-6.1.2/bin/clinfo

next , i plugged a HDMI cable connected to my monitor to my dedicated gpu , and lho and behold !!! audio works !!! as in the waveform thumbnail gets diplayed in the media pool , but when i go to check my image/video files they still dont show a thumbail , and davinci resolve freezes. So i restarted the program , and the waveform thumbnail previously shown for audio files dissapear and im back at 0 :frowning:

was this behaviour also experienced by you (we have different gpus) ? if so , what was your next course of action ?

i also assumed you installed davinci resolve with SKIP_PACKAGE_CHECK=1 to skip the zlib issue yes ? since zlib is no longer available in fedora 40 an has been replaced with zlib-ng.

We also have different rocm versions , mine is 6.1.2 . could this be the culprit ? i have all the packages* that you shown earlier.

*well , you have 4 kernelx86-64 packages i only have 1 , you have -devel versions of a package. i dont think such things is relevant/is caused by different hardware software requirments no ?

1 Like

I wouldn’t recommend following AMD’s official instructions. They’ve never worked for me or others I’ve spoken to, especially the dkms stuff.

In my experience there does need to be an active HDMI connection to the GPU for it to work properly even with all the correct packages installed, so try and keep that monitor plugged in when intending to use the GPU.

I didn’t pass any flags to the Resolve installer, I simply executed it and used the GUI to confirm installation.

However, I did experience symbol lookup errors such as: /lib64/libpango-1.0.so.0: undefined symbol. To resolve this, I disabled deleted some libraries packaged with Resolve so the software used my system libraries instead:

  1. Backup Resolve libraries folder: sudo cp -r /opt/resolve/libs /opt/resolve/libs_backup

  2. Delete outdated Resolve libraries: sudo rm /opt/resolve/libs/{libglib-2.0.so,libgio-2.0.so,libgmodule-2.0.so,libgobject-2.0.so}*

I’ve got the same ROCm version installed too, you’ll find rocm-core.x86_64 6.1.2 in my package list.

I break my system a lot so keep lots of old kernels to rollback to, but you won’t need them to get Resolve working.

I have no idea what the state of your system is at the moment, so to help me help you I recommend you try:

  1. Fully uninstalling Resolve and all AMD/ROCm packages you have. A command such as dnf remove "rocm*" "*amd-*" "hsa-rocr*" "hip-*" should do the trick, but do review the packages it requests to remove and ask here if you are unsure about any of them. You can check for any leftovers from the ROCm repo with dnf list installed | grep -i rocm - uninstall any that show up.
  2. Ensure your ROCm repo base URL is https://repo.radeon.com/rocm/rhel9/latest/main/ (nano /etc/yum.repos.d/rocm.repo)
  3. Ensure there is an active HDMI cable plugged into your GPU
  4. Reboot your system to clear out any of the dkms stuff from the official AMD install
  5. Install all of the amd/hsa/rocm/roctracer packages which are installed on my system, as they do make Resolve work on my machine
  6. Reboot your system again so it uses the new packages from boot with your GPU
  7. Share the output from the following commands:
sudo dnf list installed '*amd-gpu*' '*amdgpu*' '*rocm*' '*roct*' '*hsa*' '*mesa*' '*vulkan*' 'kernel'
sudo lspci -vnn | grep VGA -A 12
inxi -G
glxinfo | grep 'OpenGL renderer'
DRI_PRIME=1 glxinfo | grep 'OpenGL renderer'
clinfo
rocm-smi
/opt/rocm/bin/rocminfo

And if you’re feeling lucky, install Resolve (not Studio, for testing purposes as I don’t own Studio), apply the library patch I shared above, and try out some audio/video in the timeline

3 Likes

ive managed to install almost all of the packages you listed* , with :

sudo dnf install amd-gpu-firmware hsa-rocr hsa-rocr-devel \
hsakmt-roct-devel mesa-dri-drivers mesa-filesystem mesa-libEGL \
mesa-libEGL-devel mesa-libGL mesa-libGLU mesa-libOSMesa \
mesa-libgbm mesa-libglapi mesa-libxatracker mesa-va-drivers \
mesa-vulkan-drivers rocm-clang-ocl rocm-cmake rocm-core \
rocm-dbgapi rocm-debug-agent rocm-device-libs rocm-llvm \
rocm-opencl rocm-opencl-devel rocm-opencl-icd-loader \
rocm-smi rocm-smi-lib rocm-utils rocminfo roctracer roctracer-devel \
vulkan-headers vulkan-loader vulkan-tools rocm-core5

however , dnf couldnt find the rocm-core5 package :thinking:
No match for argument: rocm-core5

here is the current contents of /etc/yum.repos.d/rocm.repo :

[ROCm-6.1.2]
name=ROCm6.1.2
baseurl=https://repo.radeon.com/rocm/rhel9/latest/main
enabled=1
priority=50
gpgcheck=1
gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key

do i need to have the display enabled in display configuraion , its enabled this whole time?

when booting , dkms.service failed to start
systemctl status dkms.service gives this output

× dkms.service - Builds and install new kernel modules through DKMS
     Loaded: loaded (/usr/lib/systemd/system/dkms.service; enabled; preset: enabled)
    Drop-In: /usr/lib/systemd/system/service.d
             └─10-timeout-abort.conf
     Active: failed (Result: exit-code) since Sun 2024-07-07 15:13:04 WIB; 5min ago
       Docs: man:dkms(8)
    Process: 1219 ExecStart=/usr/sbin/dkms autoinstall --verbose --kernelver 6.9.7-200.fc40.x86_64>
   Main PID: 1219 (code=exited, status=11)
        CPU: 6min 58.440s

Jul 07 15:13:04 fedora dkms[1449]: (bad exit status: 2)
Jul 07 15:13:04 fedora dkms[9780]: Error! Bad return status for module build on kernel: 6.9.7-200.>
Jul 07 15:13:04 fedora dkms[9780]: Consult /var/lib/dkms/amdgpu/6.7.0-1781449.el9/build/make.log f>
Jul 07 15:13:04 fedora dkms[1219]: dkms autoinstall on 6.9.7-200.fc40.x86_64/x86_64 failed for amd>
Jul 07 15:13:04 fedora dkms[9781]: Error! One or more modules failed to install during autoinstall.
Jul 07 15:13:04 fedora dkms[9781]: Refer to previous errors for more information.
Jul 07 15:13:04 fedora systemd[1]: dkms.service: Main process exited, code=exited, status=11/n/a
Jul 07 15:13:04 fedora systemd[1]: dkms.service: Failed with result 'exit-code'.
Jul 07 15:13:04 fedora systemd[1]: Failed to start dkms.service - Builds and install new kernel mo>
Jul 07 15:13:04 fedora systemd[1]: dkms.service: Consumed 6min 58.440s CPU time.

is this dkms thing from the system/amd ? if from amd , how can i remove it ?

sudo dnf list installed '*amd-gpu*' '*amdgpu*' '*rocm*' '*roct*' '*hsa*' '*mesa*' '*vulkan*' 'kernel'

gives :

Installed Packages
amd-gpu-firmware.noarch                20240610-1.fc40                      @updates               
amdgpu-core.noarch                     1:6.1.60102-1781449.el9              @amdgpu                
amdgpu-dkms.noarch                     1:6.7.0.60102-1781449.el9            @amdgpu                
amdgpu-dkms-firmware.noarch            1:6.7.0.60102-1781449.el9            @amdgpu                
hsa-rocr.x86_64                        1.13.0.60102-119.el9                 @ROCm-6.1.2            
hsa-rocr-devel.x86_64                  1.13.0.60102-119.el9                 @ROCm-6.1.2            
hsakmt-roct-devel.x86_64               20240125.5.08.60102-119.el9          @ROCm-6.1.2            
kernel.x86_64                          6.8.5-301.fc40                       @anaconda              
kernel.x86_64                          6.9.7-200.fc40                       @updates               
libdrm-amdgpu.x86_64                   1:2.4.120.60102-1781449.el9          @amdgpu                
libdrm-amdgpu-common.noarch            1.0.0.60102-1781449.el9              @amdgpu                
libdrm-amdgpu-devel.x86_64             1:2.4.120.60102-1781449.el9          @amdgpu                
mesa-dri-drivers.x86_64                24.1.2-7.fc40                        @updates               
mesa-filesystem.i686                   24.1.2-7.fc40                        @updates               
mesa-filesystem.x86_64                 24.1.2-7.fc40                        @updates               
mesa-libEGL.x86_64                     24.1.2-7.fc40                        @updates               
mesa-libEGL-devel.x86_64               24.1.2-7.fc40                        @updates               
mesa-libGL.x86_64                      24.1.2-7.fc40                        @updates               
mesa-libGLU.x86_64                     9.0.3-4.fc40                         @fedora                
mesa-libOSMesa.x86_64                  24.1.2-7.fc40                        @updates               
mesa-libOpenCL.x86_64                  24.1.2-7.fc40                        @updates               
mesa-libgbm.x86_64                     24.1.2-7.fc40                        @updates               
mesa-libglapi.x86_64                   24.1.2-7.fc40                        @updates               
mesa-libxatracker.x86_64               24.1.2-7.fc40                        @updates               
mesa-va-drivers.x86_64                 24.1.2-7.fc40                        @updates               
mesa-va-drivers-freeworld.i686         24.1.2-2.fc40                        @rpmfusion-free-updates
mesa-vulkan-drivers.x86_64             24.1.2-7.fc40                        @updates               
rocm-clang-ocl.x86_64                  0.5.0.60102-119.el9                  @ROCm-6.1.2            
rocm-cmake.x86_64                      0.12.0.60102-119.el9                 @ROCm-6.1.2            
rocm-core.x86_64                       6.1.2.60102-119.el9                  @ROCm-6.1.2            
rocm-dbgapi.x86_64                     0.71.0.60102-119.el9                 @ROCm-6.1.2            
rocm-debug-agent.x86_64                2.0.3.60102-119.el9                  @ROCm-6.1.2            
rocm-device-libs.x86_64                1.0.0.60102-119.el9                  @ROCm-6.1.2            
rocm-llvm.x86_64                       17.0.0.24193.60102-119.el9           @ROCm-6.1.2            
rocm-opencl.x86_64                     2.0.0.60102-119.el9                  @ROCm-6.1.2            
rocm-opencl-devel.x86_64               2.0.0.60102-119.el9                  @ROCm-6.1.2            
rocm-opencl-icd-loader.x86_64          1.2.60102-119.el9                    @ROCm-6.1.2            
rocm-smi.x86_64                        6.0.2-1.fc40                         @updates               
rocm-smi-lib.x86_64                    7.2.0.60102-119.el9                  @ROCm-6.1.2            
rocm-utils.x86_64                      6.1.2.60102-119.el9                  @ROCm-6.1.2            
rocminfo.x86_64                        1.0.0.60102-119.el9                  @ROCm-6.1.2            
roctracer.x86_64                       4.1.60102.60102-119.el9              @ROCm-6.1.2            
roctracer-devel.x86_64                 4.1.60102.60102-119.el9              @ROCm-6.1.2            
vulkan-headers.noarch                  1.3.283.0-1.fc40                     @updates               
vulkan-loader.x86_64                   1.3.283.0-2.fc40                     @updates               
vulkan-tools.x86_64                    1.3.283.0-1.fc40                     @updates

sudo lspci -vnn | grep VGA -A 12
gives :

03:00.0 VGA compatible controller [0300]: Advanced Micro Devices, Inc. [AMD/ATI] Navi 31 [Radeon RX 7900 XT/7900 XTX/7900M] [1002:744c] (rev c8) (prog-if 00 [VGA controller])
        Subsystem: Sapphire Technology Limited NITRO+ RX 7900 XTX Vapor-X [1da2:e471]
        Flags: bus master, fast devsel, latency 0, IRQ 131, IOMMU group 14
        Memory at f000000000 (64-bit, prefetchable) [size=32G]
        Memory at f800000000 (64-bit, prefetchable) [size=256M]
        I/O ports at f000 [size=256]
        Memory at f6b00000 (32-bit, non-prefetchable) [size=1M]
        Expansion ROM at f6c00000 [disabled] [size=128K]
        Capabilities: [48] Vendor Specific Information: Len=08 <?>
        Capabilities: [50] Power Management version 3
        Capabilities: [64] Express Legacy Endpoint, IntMsgNum 0
        Capabilities: [a0] MSI: Enable+ Count=1/1 Maskable- 64bit+
        Capabilities: [100] Vendor Specific Information: ID=0001 Rev=1 Len=010 <?>
--
18:00.0 VGA compatible controller [0300]: Advanced Micro Devices, Inc. [AMD/ATI] Raphael [1002:164e] (rev c1) (prog-if 00 [VGA controller])
        Subsystem: ASRock Incorporation Device [1849:364e]
        Flags: bus master, fast devsel, latency 0, IRQ 78, IOMMU group 26
        Memory at f820000000 (64-bit, prefetchable) [size=256M]
        Memory at f830000000 (64-bit, prefetchable) [size=2M]
        I/O ports at e000 [size=256]
        Memory at f6a00000 (32-bit, non-prefetchable) [size=512K]
        Capabilities: [48] Vendor Specific Information: Len=08 <?>
        Capabilities: [50] Power Management version 3
        Capabilities: [64] Express Legacy Endpoint, IntMsgNum 0
        Capabilities: [a0] MSI: Enable- Count=1/4 Maskable- 64bit+
        Capabilities: [c0] MSI-X: Enable+ Count=4 Masked-
        Capabilities: [100] Vendor Specific Information: ID=0001 Rev=1 Len=010 <?>
inxi -G
glxinfo | grep 'OpenGL renderer'
DRI_PRIME=1 glxinfo | grep 'OpenGL renderer'

gives :

Graphics:
  Device-1: AMD Navi 31 [Radeon RX 7900 XT/7900 XTX/7900M] driver: amdgpu
    v: kernel
  Device-2: AMD Raphael driver: amdgpu v: kernel
  Display: wayland server: Xwayland v: 24.1.0 compositor: kwin_wayland
    driver: N/A resolution: 1: 2560x1440 2: 2048x1152
  API: EGL v: 1.5 drivers: radeonsi,swrast
    platforms: wayland,x11,surfaceless,device
  API: OpenGL v: 4.6 compat-v: 4.5 vendor: amd mesa v: 24.1.2 renderer: AMD
    Radeon Graphics (radeonsi raphael_mendocino LLVM 18.1.6 DRM 3.57
    6.9.7-200.fc40.x86_64)
  API: Vulkan v: 1.3.283 drivers: N/A surfaces: xcb,xlib,wayland
OpenGL renderer string: AMD Radeon Graphics (radeonsi, raphael_mendocino, LLVM 18.1.6, DRM 3.57, 6.9.7-200.fc40.x86_64)
OpenGL renderer string: Radeon RX 7900 XTX (radeonsi, navi31, LLVM 18.1.6, DRM 3.57, 6.9.7-200.fc40.x86_64)

clinfo gives :


Number of platforms                               3
  Platform Name                                   rusticl
  Platform Vendor                                 Mesa/X.org
  Platform Version                                OpenCL 3.0 
  Platform Profile                                FULL_PROFILE
  Platform Extensions                             cl_khr_byte_addressable_store cl_khr_create_command_queue cl_khr_expect_assume cl_khr_extended_versioning cl_khr_icd cl_khr_il_program cl_khr_spirv_no_integer_wrap_decoration cl_khr_suggested_local_work_size
  Platform Extensions with Version                cl_khr_byte_addressable_store                                    0x400000 (1.0.0)
                                                  cl_khr_create_command_queue                                      0x400000 (1.0.0)
                                                  cl_khr_expect_assume                                             0x400000 (1.0.0)
                                                  cl_khr_extended_versioning                                       0x400000 (1.0.0)
                                                  cl_khr_icd                                                       0x400000 (1.0.0)
                                                  cl_khr_il_program                                                0x400000 (1.0.0)
                                                  cl_khr_spirv_no_integer_wrap_decoration                          0x400000 (1.0.0)
                                                  cl_khr_suggested_local_work_size                                 0x400000 (1.0.0)
  Platform Numeric Version                        0xc00000 (3.0.0)
  Platform Extensions function suffix             MESA
  Platform Host timer resolution                  1ns

  Platform Name                                   Clover
  Platform Vendor                                 Mesa
  Platform Version                                OpenCL 1.1 Mesa 24.1.2
  Platform Profile                                FULL_PROFILE
  Platform Extensions                             cl_khr_icd
  Platform Extensions function suffix             MESA

  Platform Name                                   AMD Accelerated Parallel Processing
  Platform Vendor                                 Advanced Micro Devices, Inc.
  Platform Version                                OpenCL 2.1 AMD-APP (3614.0)
  Platform Profile                                FULL_PROFILE
  Platform Extensions                             cl_khr_icd cl_amd_event_callback 
  Platform Extensions function suffix             AMD
  Platform Host timer resolution                  1ns

  Platform Name                                   rusticl
Number of devices                                 0

  Platform Name                                   Clover
Number of devices                                 2
  Device Name                                     Radeon RX 7900 XTX (radeonsi, navi31, LLVM 18.1.6, DRM 3.57, 6.9.7-200.fc40.x86_64)
  Device Vendor                                   AMD
  Device Vendor ID                                0x1002
  Device Version                                  OpenCL 1.1 Mesa 24.1.2
  Device Numeric Version                          0x401000 (1.1.0)
  Driver Version                                  24.1.2
  Device OpenCL C Version                         OpenCL C 1.1 
  Device OpenCL C Numeric Version                 0x401000 (1.1.0)
  Device Type                                     GPU
  Device Profile                                  FULL_PROFILE
  Device Available                                Yes
  Compiler Available                              Yes
  Max compute units                               96
  Max clock frequency                             2526MHz
  Max work item dimensions                        3
  Max work item sizes                             256x256x256
  Max work group size                             256
=== CL_PROGRAM_BUILD_LOG ===
<built-in>:1:10: fatal error: 'clc/clc.h' file not found
  Preferred work group size multiple (kernel)     <getWGsizes:1980: create kernel : error -46>
  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                              25769803776 (24GiB)
  Error Correction support                        No
  Max memory allocation                           6442450944 (6GiB)
  Unified memory for Host and Device              No
  Minimum alignment for any data type             128 bytes
  Alignment of base address                       32768 bits (4096 bytes)
  Global Memory cache type                        None
  Image support                                   No
  Local memory type                               Local
  Local memory size                               65536 (64KiB)
  Max number of constant args                     16
  Max constant buffer size                        67108864 (64MiB)
  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
    ILs with version                              SPIR-V                                                           0x400000 (1.0.0)
  Built-in kernels with version                   (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_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_fp64 cl_khr_extended_versioning
  Device Extensions with Version                  cl_khr_byte_addressable_store                                    0x400000 (1.0.0)
                                                  cl_khr_global_int32_base_atomics                                 0x400000 (1.0.0)
                                                  cl_khr_global_int32_extended_atomics                             0x400000 (1.0.0)
                                                  cl_khr_local_int32_base_atomics                                  0x400000 (1.0.0)
                                                  cl_khr_local_int32_extended_atomics                              0x400000 (1.0.0)
                                                  cl_khr_int64_base_atomics                                        0x400000 (1.0.0)
                                                  cl_khr_int64_extended_atomics                                    0x400000 (1.0.0)
                                                  cl_khr_fp64                                                      0x400000 (1.0.0)
                                                  cl_khr_extended_versioning                                       0x400000 (1.0.0)

  Device Name                                     AMD Radeon Graphics (radeonsi, raphael_mendocino, LLVM 18.1.6, DRM 3.57, 6.9.7-200.fc40.x86_64)
  Device Vendor                                   AMD
  Device Vendor ID                                0x1002
  Device Version                                  OpenCL 1.1 Mesa 24.1.2
  Device Numeric Version                          0x401000 (1.1.0)
  Driver Version                                  24.1.2
  Device OpenCL C Version                         OpenCL C 1.1 
  Device OpenCL C Numeric Version                 0x401000 (1.1.0)
  Device Type                                     GPU
  Device Profile                                  FULL_PROFILE
  Device Available                                Yes
  Compiler Available                              Yes
  Max compute units                               2
  Max clock frequency                             2200MHz
  Max work item dimensions                        3
  Max work item sizes                             256x256x256
  Max work group size                             256
=== CL_PROGRAM_BUILD_LOG ===
<built-in>:1:10: fatal error: 'clc/clc.h' file not found
  Preferred work group size multiple (kernel)     <getWGsizes:1980: create kernel : error -46>
  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                              33237602304 (30.95GiB)
  Error Correction support                        No
  Max memory allocation                           8309400576 (7.739GiB)
  Unified memory for Host and Device              No
  Minimum alignment for any data type             128 bytes
  Alignment of base address                       32768 bits (4096 bytes)
  Global Memory cache type                        None
  Image support                                   No
  Local memory type                               Local
  Local memory size                               65536 (64KiB)
  Max number of constant args                     16
  Max constant buffer size                        67108864 (64MiB)
  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
    ILs with version                              SPIR-V                                                           0x400000 (1.0.0)
  Built-in kernels with version                   (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_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_fp64 cl_khr_extended_versioning
  Device Extensions with Version                  cl_khr_byte_addressable_store                                    0x400000 (1.0.0)
                                                  cl_khr_global_int32_base_atomics                                 0x400000 (1.0.0)
                                                  cl_khr_global_int32_extended_atomics                             0x400000 (1.0.0)
                                                  cl_khr_local_int32_base_atomics                                  0x400000 (1.0.0)
                                                  cl_khr_local_int32_extended_atomics                              0x400000 (1.0.0)
                                                  cl_khr_int64_base_atomics                                        0x400000 (1.0.0)
                                                  cl_khr_int64_extended_atomics                                    0x400000 (1.0.0)
                                                  cl_khr_fp64                                                      0x400000 (1.0.0)
                                                   cl_khr_extended_versioning                                       0x400000 (1.0.0)

and


  Platform Name                                   AMD Accelerated Parallel Processing
Number of devices                                 2
  Device Name                                     gfx1100
  Device Vendor                                   Advanced Micro Devices, Inc.
  Device Vendor ID                                0x1002
  Device Version                                  OpenCL 2.0 
  Driver Version                                  3614.0 (HSA1.1,LC)
  Device OpenCL C Version                         OpenCL C 2.0 
  Device Type                                     GPU
  Device Board Name (AMD)                         Radeon RX 7900 XTX
  Device PCI-e ID (AMD)                           0x744c
  Device Topology (AMD)                           PCI-E, 0000:03:00.0
  Device Profile                                  FULL_PROFILE
  Device Available                                Yes
  Compiler Available                              Yes
  Linker Available                                Yes
  Max compute units                               48
  SIMD per compute unit (AMD)                     4
  SIMD width (AMD)                                32
  SIMD instruction width (AMD)                    1
  Max clock frequency                             2526MHz
  Graphics IP (AMD)                               11.0
  Device Partition                                (core)
    Max number of sub-devices                     48
    Supported partition types                     None
    Supported affinity domains                    (n/a)
  Max work item dimensions                        3
  Max work item sizes                             1024x1024x1024
  Max work group size                             256
  Preferred work group size (AMD)                 256
  Max work group size (AMD)                       1024
  Preferred work group size multiple (kernel)     32
  Wavefront width (AMD)                           32
  Preferred / native vector sizes                 
    char                                                 4 / 4       
    short                                                2 / 2       
    int                                                  1 / 1       
    long                                                 1 / 1       
    half                                                 1 / 1        (cl_khr_fp16)
    float                                                1 / 1       
    double                                               1 / 1        (cl_khr_fp64)
  Half-precision Floating-point support           (cl_khr_fp16)
    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
  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
  Address bits                                    64, Little-Endian
  Global memory size                              25753026560 (23.98GiB)
  Global free memory (AMD)                        24952832 (23.8GiB) 24952832 (23.8GiB)
  Global memory channels (AMD)                    12
  Global memory banks per channel (AMD)           4
  Global memory bank width (AMD)                  256 bytes
  Error Correction support                        No
  Max memory allocation                           21890072576 (20.39GiB)
  Unified memory for Host and Device              No
  Shared Virtual Memory (SVM) capabilities        (core)
    Coarse-grained buffer sharing                 Yes
    Fine-grained buffer sharing                   Yes
    Fine-grained system sharing                   No
    Atomics                                       No
  Minimum alignment for any data type             128 bytes
  Alignment of base address                       1024 bits (128 bytes)
  Preferred alignment for atomics                 
    SVM                                           0 bytes
    Global                                        0 bytes
    Local                                         0 bytes
  Max size for global variable                    21890072576 (20.39GiB)
  Preferred total size of global vars             25753026560 (23.98GiB)
  Global Memory cache type                        Read/Write
  Global Memory cache size                        32768 (32KiB)
  Global Memory cache line size                   64 bytes
  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                 8192 images
    Base address alignment for 2D image buffers   256 bytes
    Pitch alignment for 2D image buffers          256 pixels
    Max 2D image size                             16384x16384 pixels
    Max 3D image size                             16384x16384x8192 pixels
    Max number of read image args                 128
    Max number of write image args                8
    Max number of read/write image args           64
  Max number of pipe args                         16
  Max active pipe reservations                    16
  Max pipe packet size                            415236096 (396MiB)
  Local memory type                               Local
  Local memory size                               65536 (64KiB)
  Local memory size per CU (AMD)                  65536 (64KiB)
  Local memory banks (AMD)                        32
  Max number of constant args                     8
  Max constant buffer size                        21890072576 (20.39GiB)
  Preferred constant buffer size (AMD)            16384 (16KiB)
  Max size of kernel argument                     1024
  Queue properties (on host)                      
    Out-of-order execution                        No
    Profiling                                     Yes
  Queue properties (on device)                    
    Out-of-order execution                        Yes
    Profiling                                     Yes
    Preferred size                                262144 (256KiB)
    Max size                                      8388608 (8MiB)
  Max queues on device                            1
  Max events on device                            1024
  Prefer user sync for interop                    Yes
  Number of P2P devices (AMD)                     0
  Profiling timer resolution                      1ns
  Profiling timer offset since Epoch (AMD)        0ns (Thu Jan  1 07:00:00 1970)
  Execution capabilities                          
    Run OpenCL kernels                            Yes
    Run native kernels                            No
    Thread trace supported (AMD)                  No
    Number of async queues (AMD)                  8
    Max real-time compute queues (AMD)            8
    Max real-time compute units (AMD)             48
  printf() buffer size                            4194304 (4MiB)
  Built-in kernels                                (n/a)
  Device Extensions                               cl_khr_fp64 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_3d_image_writes cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_gl_sharing cl_amd_device_attribute_query cl_amd_media_ops cl_amd_media_ops2 cl_khr_image2d_from_buffer cl_khr_subgroups cl_khr_depth_images cl_amd_copy_buffer_p2p cl_amd_assembly_program 
  Device Name                                     gfx1036
  Device Vendor                                   Advanced Micro Devices, Inc.
  Device Vendor ID                                0x1002
  Device Version                                  OpenCL 2.0 
  Driver Version                                  3614.0 (HSA1.1,LC)
  Device OpenCL C Version                         OpenCL C 2.0 
  Device Type                                     GPU
  Device Board Name (AMD)                         AMD Radeon Graphics
  Device PCI-e ID (AMD)                           0x164e
  Device Topology (AMD)                           PCI-E, 0000:18:00.0
  Device Profile                                  FULL_PROFILE
  Device Available                                Yes
  Compiler Available                              Yes
  Linker Available                                Yes
  Max compute units                               1
  SIMD per compute unit (AMD)                     4
  SIMD width (AMD)                                32
  SIMD instruction width (AMD)                    1
  Max clock frequency                             2200MHz
  Graphics IP (AMD)                               10.3
  Device Partition                                (core)
    Max number of sub-devices                     1
    Supported partition types                     None
    Supported affinity domains                    (n/a)
  Max work item dimensions                        3
  Max work item sizes                             1024x1024x1024
  Max work group size                             256
  Preferred work group size (AMD)                 256
  Max work group size (AMD)                       1024
  Preferred work group size multiple (kernel)     32
  Wavefront width (AMD)                           32
  Preferred / native vector sizes                 
    char                                                 4 / 4       
    short                                                2 / 2       
    int                                                  1 / 1       
    long                                                 1 / 1       
    half                                                 1 / 1        (cl_khr_fp16)
    float                                                1 / 1       
    double                                               1 / 1        (cl_khr_fp64)
  Half-precision Floating-point support           (cl_khr_fp16)
    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
  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
  Address bits                                    64, Little-Endian
  Global memory size                              536870912 (512MiB)
  Global free memory (AMD)                        481280 (470MiB) 481280 (470MiB)
  Global memory channels (AMD)                    4
  Global memory banks per channel (AMD)           4
  Global memory bank width (AMD)                  256 bytes
  Error Correction support                        No
  Max memory allocation                           402653184 (384MiB)
  Unified memory for Host and Device              No
  Shared Virtual Memory (SVM) capabilities        (core)
    Coarse-grained buffer sharing                 Yes
    Fine-grained buffer sharing                   Yes
    Fine-grained system sharing                   No
    Atomics                                       No
  Minimum alignment for any data type             128 bytes
  Alignment of base address                       1024 bits (128 bytes)
  Preferred alignment for atomics                 
    SVM                                           0 bytes
    Global                                        0 bytes
    Local                                         0 bytes
  Max size for global variable                    402653184 (384MiB)
  Preferred total size of global vars             536870912 (512MiB)
  Global Memory cache type                        Read/Write
  Global Memory cache size                        16384 (16KiB)
  Global Memory cache line size                   128 bytes
  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                 8192 images
    Base address alignment for 2D image buffers   256 bytes
    Pitch alignment for 2D image buffers          256 pixels
    Max 2D image size                             16384x16384 pixels
    Max 3D image size                             16384x16384x8192 pixels
    Max number of read image args                 128
    Max number of write image args                8
    Max number of read/write image args           64
  Max number of pipe args                         16
  Max active pipe reservations                    16
  Max pipe packet size                            402653184 (384MiB)
  Local memory type                               Local
  Local memory size                               65536 (64KiB)
  Local memory size per CU (AMD)                  65536 (64KiB)
  Local memory banks (AMD)                        32
  Max number of constant args                     8
  Max constant buffer size                        402653184 (384MiB)
  Preferred constant buffer size (AMD)            16384 (16KiB)
  Max size of kernel argument                     1024
  Queue properties (on host)                      
    Out-of-order execution                        No
    Profiling                                     Yes
  Queue properties (on device)                    
    Out-of-order execution                        Yes
    Profiling                                     Yes
    Preferred size                                262144 (256KiB)
    Max size                                      8388608 (8MiB)
  Max queues on device                            1
  Max events on device                            1024
  Prefer user sync for interop                    Yes
  Number of P2P devices (AMD)                     0
  Profiling timer resolution                      1ns
  Profiling timer offset since Epoch (AMD)        0ns (Thu Jan  1 07:00:00 1970)
  Execution capabilities                          
    Run OpenCL kernels                            Yes
    Run native kernels                            No
    Thread trace supported (AMD)                  No
    Number of async queues (AMD)                  8
    Max real-time compute queues (AMD)            8
    Max real-time compute units (AMD)             1
  printf() buffer size                            4194304 (4MiB)
  Built-in kernels                                (n/a)
  Device Extensions                               cl_khr_fp64 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_3d_image_writes cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_gl_sharing cl_amd_device_attribute_query cl_amd_media_ops cl_amd_media_ops2 cl_khr_image2d_from_buffer cl_khr_subgroups cl_khr_depth_images cl_amd_copy_buffer_p2p cl_amd_assembly_program 

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 [MESA]
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT)  No devices found in platform
  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)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL)  No devices found in platform

ICD loader properties
  ICD loader Name                                 Khronos OpenCL ICD Loader
  ICD loader Vendor                               Khronos Group
  ICD loader Version                              3.0.6
  ICD loader Profile                              OpenCL 3.0

rocm-smi gives :

Number of platforms                               3
  Platform Name                                   rusticl
  Platform Vendor                                 Mesa/X.org
  Platform Version                                OpenCL 3.0 
  Platform Profile                                FULL_PROFILE
  Platform Extensions                             cl_khr_byte_addressable_store cl_khr_create_command_queue cl_khr_expect_assume cl_khr_extended_versioning cl_khr_icd cl_khr_il_program cl_khr_spirv_no_integer_wrap_decoration cl_khr_suggested_local_work_size
  Platform Extensions with Version                cl_khr_byte_addressable_store                                    0x400000 (1.0.0)
                                                  cl_khr_create_command_queue                                      0x400000 (1.0.0)
                                                  cl_khr_expect_assume                                             0x400000 (1.0.0)
                                                  cl_khr_extended_versioning                                       0x400000 (1.0.0)
                                                  cl_khr_icd                                                       0x400000 (1.0.0)
                                                  cl_khr_il_program                                                0x400000 (1.0.0)
                                                  cl_khr_spirv_no_integer_wrap_decoration                          0x400000 (1.0.0)
                                                  cl_khr_suggested_local_work_size                                 0x400000 (1.0.0)
  Platform Numeric Version                        0xc00000 (3.0.0)
  Platform Extensions function suffix             MESA
  Platform Host timer resolution                  1ns

  Platform Name                                   Clover
  Platform Vendor                                 Mesa
  Platform Version                                OpenCL 1.1 Mesa 24.1.2
  Platform Profile                                FULL_PROFILE
  Platform Extensions                             cl_khr_icd
  Platform Extensions function suffix             MESA

  Platform Name                                   AMD Accelerated Parallel Processing
  Platform Vendor                                 Advanced Micro Devices, Inc.
  Platform Version                                OpenCL 2.1 AMD-APP (3614.0)
  Platform Profile                                FULL_PROFILE
  Platform Extensions                             cl_khr_icd cl_amd_event_callback 
  Platform Extensions function suffix             AMD
  Platform Host timer resolution                  1ns

  Platform Name                                   rusticl
Number of devices                                 0

  Platform Name                                   Clover
Number of devices                                 2
  Device Name                                     Radeon RX 7900 XTX (radeonsi, navi31, LLVM 18.1.6, DRM 3.57, 6.9.7-200.fc40.x86_64)
  Device Vendor                                   AMD
  Device Vendor ID                                0x1002
  Device Version                                  OpenCL 1.1 Mesa 24.1.2
  Device Numeric Version                          0x401000 (1.1.0)
  Driver Version                                  24.1.2
  Device OpenCL C Version                         OpenCL C 1.1 
  Device OpenCL C Numeric Version                 0x401000 (1.1.0)
  Device Type                                     GPU
  Device Profile                                  FULL_PROFILE
  Device Available                                Yes
  Compiler Available                              Yes
  Max compute units                               96
  Max clock frequency                             2526MHz
  Max work item dimensions                        3
  Max work item sizes                             256x256x256
  Max work group size                             256
=== CL_PROGRAM_BUILD_LOG ===
<built-in>:1:10: fatal error: 'clc/clc.h' file not found
  Preferred work group size multiple (kernel)     <getWGsizes:1980: create kernel : error -46>
  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                              25769803776 (24GiB)
  Error Correction support                        No
  Max memory allocation                           6442450944 (6GiB)
  Unified memory for Host and Device              No
  Minimum alignment for any data type             128 bytes
  Alignment of base address                       32768 bits (4096 bytes)
  Global Memory cache type                        None
  Image support                                   No
  Local memory type                               Local
  Local memory size                               65536 (64KiB)
  Max number of constant args                     16
  Max constant buffer size                        67108864 (64MiB)
  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
    ILs with version                              SPIR-V                                                           0x400000 (1.0.0)
  Built-in kernels with version                   (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_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_fp64 cl_khr_extended_versioning
  Device Extensions with Version                  cl_khr_byte_addressable_store                                    0x400000 (1.0.0)
                                                  cl_khr_global_int32_base_atomics                                 0x400000 (1.0.0)
                                                  cl_khr_global_int32_extended_atomics                             0x400000 (1.0.0)
                                                  cl_khr_local_int32_base_atomics                                  0x400000 (1.0.0)
                                                  cl_khr_local_int32_extended_atomics                              0x400000 (1.0.0)
                                                  cl_khr_int64_base_atomics                                        0x400000 (1.0.0)
                                                  cl_khr_int64_extended_atomics                                    0x400000 (1.0.0)
                                                  cl_khr_fp64                                                      0x400000 (1.0.0)
                                                  cl_khr_extended_versioning                                       0x400000 (1.0.0)

  Device Name                                     AMD Radeon Graphics (radeonsi, raphael_mendocino, LLVM 18.1.6, DRM 3.57, 6.9.7-200.fc40.x86_64)
  Device Vendor                                   AMD
  Device Vendor ID                                0x1002
  Device Version                                  OpenCL 1.1 Mesa 24.1.2
  Device Numeric Version                          0x401000 (1.1.0)
  Driver Version                                  24.1.2
  Device OpenCL C Version                         OpenCL C 1.1 
  Device OpenCL C Numeric Version                 0x401000 (1.1.0)
  Device Type                                     GPU
  Device Profile                                  FULL_PROFILE
  Device Available                                Yes
  Compiler Available                              Yes
  Max compute units                               2
  Max clock frequency                             2200MHz
  Max work item dimensions                        3
  Max work item sizes                             256x256x256
  Max work group size                             256
=== CL_PROGRAM_BUILD_LOG ===
<built-in>:1:10: fatal error: 'clc/clc.h' file not found
  Preferred work group size multiple (kernel)     <getWGsizes:1980: create kernel : error -46>
  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                              33237602304 (30.95GiB)
  Error Correction support                        No
  Max memory allocation                           8309400576 (7.739GiB)
  Unified memory for Host and Device              No
  Minimum alignment for any data type             128 bytes
  Alignment of base address                       32768 bits (4096 bytes)
  Global Memory cache type                        None
  Image support                                   No
  Local memory type                               Local
  Local memory size                               65536 (64KiB)
  Max number of constant args                     16
  Max constant buffer size                        67108864 (64MiB)
  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
    ILs with version                              SPIR-V                                                           0x400000 (1.0.0)
  Built-in kernels with version                   (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_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_fp64 cl_khr_extended_versioning
  Device Extensions with Version                  cl_khr_byte_addressable_store                                    0x400000 (1.0.0)
                                                  cl_khr_global_int32_base_atomics                                 0x400000 (1.0.0)
                                                  cl_khr_global_int32_extended_atomics                             0x400000 (1.0.0)
                                                  cl_khr_local_int32_base_atomics                                  0x400000 (1.0.0)
                                                  cl_khr_local_int32_extended_atomics                              0x400000 (1.0.0)
                                                  cl_khr_int64_base_atomics                                        0x400000 (1.0.0)
                                                  cl_khr_int64_extended_atomics                                    0x400000 (1.0.0)
                                                  cl_khr_fp64                                                      0x400000 (1.0.0)
                                                  cl_khr_extended_versioning                                       0x400000 (1.0.0)

  Platform Name                                   AMD Accelerated Parallel Processing
Number of devices                                 2
  Device Name                                     gfx1100
  Device Vendor                                   Advanced Micro Devices, Inc.
  Device Vendor ID                                0x1002
  Device Version                                  OpenCL 2.0 
  Driver Version                                  3614.0 (HSA1.1,LC)
  Device OpenCL C Version                         OpenCL C 2.0 
  Device Type                                     GPU
  Device Board Name (AMD)                         Radeon RX 7900 XTX
  Device PCI-e ID (AMD)                           0x744c
  Device Topology (AMD)                           PCI-E, 0000:03:00.0
  Device Profile                                  FULL_PROFILE
  Device Available                                Yes
  Compiler Available                              Yes
  Linker Available                                Yes
  Max compute units                               48
  SIMD per compute unit (AMD)                     4
  SIMD width (AMD)                                32
  SIMD instruction width (AMD)                    1
  Max clock frequency                             2526MHz
  Graphics IP (AMD)                               11.0
  Device Partition                                (core)
    Max number of sub-devices                     48
    Supported partition types                     None
    Supported affinity domains                    (n/a)
  Max work item dimensions                        3
  Max work item sizes                             1024x1024x1024
  Max work group size                             256
  Preferred work group size (AMD)                 256
  Max work group size (AMD)                       1024
  Preferred work group size multiple (kernel)     32
  Wavefront width (AMD)                           32
  Preferred / native vector sizes                 
    char                                                 4 / 4       
    short                                                2 / 2       
    int                                                  1 / 1       
    long                                                 1 / 1       
    half                                                 1 / 1        (cl_khr_fp16)
    float                                                1 / 1       
    double                                               1 / 1        (cl_khr_fp64)
  Half-precision Floating-point support           (cl_khr_fp16)
    Denormals                                     Yes
    Infinity and NANs                             Yes
    Round to nearest                              Yes
    Round to zero                                 Yes
    Round to infinity                             Yes
    IEEE754-2008 fused multiply-add               Yes

and

    Support is emulated in software               No
  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
  Address bits                                    64, Little-Endian
  Global memory size                              25753026560 (23.98GiB)
  Global free memory (AMD)                        24952832 (23.8GiB) 24952832 (23.8GiB)
  Global memory channels (AMD)                    12
  Global memory banks per channel (AMD)           4
  Global memory bank width (AMD)                  256 bytes
  Error Correction support                        No
  Max memory allocation                           21890072576 (20.39GiB)
  Unified memory for Host and Device              No
  Shared Virtual Memory (SVM) capabilities        (core)
    Coarse-grained buffer sharing                 Yes
    Fine-grained buffer sharing                   Yes
    Fine-grained system sharing                   No
    Atomics                                       No
  Minimum alignment for any data type             128 bytes
  Alignment of base address                       1024 bits (128 bytes)
  Preferred alignment for atomics                 
    SVM                                           0 bytes
    Global                                        0 bytes
    Local                                         0 bytes
  Max size for global variable                    21890072576 (20.39GiB)
  Preferred total size of global vars             25753026560 (23.98GiB)
  Global Memory cache type                        Read/Write
  Global Memory cache size                        32768 (32KiB)
  Global Memory cache line size                   64 bytes
  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                 8192 images
    Base address alignment for 2D image buffers   256 bytes
    Pitch alignment for 2D image buffers          256 pixels
    Max 2D image size                             16384x16384 pixels
    Max 3D image size                             16384x16384x8192 pixels
    Max number of read image args                 128
    Max number of write image args                8
    Max number of read/write image args           64
  Max number of pipe args                         16
  Max active pipe reservations                    16
  Max pipe packet size                            415236096 (396MiB)
  Local memory type                               Local
  Local memory size                               65536 (64KiB)
  Local memory size per CU (AMD)                  65536 (64KiB)
  Local memory banks (AMD)                        32
  Max number of constant args                     8
  Max constant buffer size                        21890072576 (20.39GiB)
  Preferred constant buffer size (AMD)            16384 (16KiB)
  Max size of kernel argument                     1024
  Queue properties (on host)                      
    Out-of-order execution                        No
    Profiling                                     Yes
  Queue properties (on device)                    
    Out-of-order execution                        Yes
    Profiling                                     Yes
    Preferred size                                262144 (256KiB)
    Max size                                      8388608 (8MiB)
  Max queues on device                            1
  Max events on device                            1024
  Prefer user sync for interop                    Yes
  Number of P2P devices (AMD)                     0
  Profiling timer resolution                      1ns
  Profiling timer offset since Epoch (AMD)        0ns (Thu Jan  1 07:00:00 1970)
  Execution capabilities                          
    Run OpenCL kernels                            Yes
    Run native kernels                            No
    Thread trace supported (AMD)                  No
    Number of async queues (AMD)                  8
    Max real-time compute queues (AMD)            8
    Max real-time compute units (AMD)             48
  printf() buffer size                            4194304 (4MiB)
  Built-in kernels                                (n/a)
  Device Extensions                               cl_khr_fp64 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_3d_image_writes cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_gl_sharing cl_amd_device_attribute_query cl_amd_media_ops cl_amd_media_ops2 cl_khr_image2d_from_buffer cl_khr_subgroups cl_khr_depth_images cl_amd_copy_buffer_p2p cl_amd_assembly_program 
  Device Name                                     gfx1036
  Device Vendor                                   Advanced Micro Devices, Inc.
  Device Vendor ID                                0x1002
  Device Version                                  OpenCL 2.0 
  Driver Version                                  3614.0 (HSA1.1,LC)
  Device OpenCL C Version                         OpenCL C 2.0 
  Device Type                                     GPU
  Device Board Name (AMD)                         AMD Radeon Graphics
  Device PCI-e ID (AMD)                           0x164e
  Device Topology (AMD)                           PCI-E, 0000:18:00.0
  Device Profile                                  FULL_PROFILE
  Device Available                                Yes
  Compiler Available                              Yes
  Linker Available                                Yes
  Max compute units                               1
  SIMD per compute unit (AMD)                     4
  SIMD width (AMD)                                32
  SIMD instruction width (AMD)                    1
  Max clock frequency                             2200MHz
  Graphics IP (AMD)                               10.3
  Device Partition                                (core)
    Max number of sub-devices                     1
    Supported partition types                     None
    Supported affinity domains                    (n/a)
  Max work item dimensions                        3
  Max work item sizes                             1024x1024x1024
  Max work group size                             256
  Preferred work group size (AMD)                 256
  Max work group size (AMD)                       1024
  Preferred work group size multiple (kernel)     32
  Wavefront width (AMD)                           32
  Preferred / native vector sizes                 
    char                                                 4 / 4       
    short                                                2 / 2       
    int                                                  1 / 1       
    long                                                 1 / 1       
    half                                                 1 / 1        (cl_khr_fp16)
    float                                                1 / 1       
    double                                               1 / 1        (cl_khr_fp64)
  Half-precision Floating-point support           (cl_khr_fp16)
    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
  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
  Address bits                                    64, Little-Endian
  Global memory size                              536870912 (512MiB)
  Global free memory (AMD)                        481280 (470MiB) 481280 (470MiB)
  Global memory channels (AMD)                    4
  Global memory banks per channel (AMD)           4
  Global memory bank width (AMD)                  256 bytes
  Error Correction support                        No
  Max memory allocation                           402653184 (384MiB)
  Unified memory for Host and Device              No
  Shared Virtual Memory (SVM) capabilities        (core)
    Coarse-grained buffer sharing                 Yes
    Fine-grained buffer sharing                   Yes
    Fine-grained system sharing                   No
    Atomics                                       No
  Minimum alignment for any data type             128 bytes
  Alignment of base address                       1024 bits (128 bytes)
  Preferred alignment for atomics                 
    SVM                                           0 bytes
    Global                                        0 bytes
    Local                                         0 bytes
  Max size for global variable                    402653184 (384MiB)
  Preferred total size of global vars             536870912 (512MiB)
  Global Memory cache type                        Read/Write
  Global Memory cache size                        16384 (16KiB)
  Global Memory cache line size                   128 bytes
  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                 8192 images
    Base address alignment for 2D image buffers   256 bytes
    Pitch alignment for 2D image buffers          256 pixels
    Max 2D image size                             16384x16384 pixels
    Max 3D image size                             16384x16384x8192 pixels
    Max number of read image args                 128
    Max number of write image args                8
    Max number of read/write image args           64
  Max number of pipe args                         16
  Max active pipe reservations                    16
  Max pipe packet size                            402653184 (384MiB)
  Local memory type                               Local
  Local memory size                               65536 (64KiB)
  Local memory size per CU (AMD)                  65536 (64KiB)
  Local memory banks (AMD)                        32
  Max number of constant args                     8
  Max constant buffer size                        402653184 (384MiB)
  Preferred constant buffer size (AMD)            16384 (16KiB)
  Max size of kernel argument                     1024
  Queue properties (on host)                      
    Out-of-order execution                        No
    Profiling                                     Yes
  Queue properties (on device)                    
    Out-of-order execution                        Yes
    Profiling                                     Yes
    Preferred size                                262144 (256KiB)
    Max size                                      8388608 (8MiB)
  Max queues on device                            1
  Max events on device                            1024
  Prefer user sync for interop                    Yes
  Number of P2P devices (AMD)                     0
  Profiling timer resolution                      1ns
  Profiling timer offset since Epoch (AMD)        0ns (Thu Jan  1 07:00:00 1970)
  Execution capabilities                          
    Run OpenCL kernels                            Yes
    Run native kernels                            No
    Thread trace supported (AMD)                  No
    Number of async queues (AMD)                  8
    Max real-time compute queues (AMD)            8
    Max real-time compute units (AMD)             1
  printf() buffer size                            4194304 (4MiB)
  Built-in kernels                                (n/a)
  Device Extensions                               cl_khr_fp64 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_3d_image_writes cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_gl_sharing cl_amd_device_attribute_query cl_amd_media_ops cl_amd_media_ops2 cl_khr_image2d_from_buffer cl_khr_subgroups cl_khr_depth_images cl_amd_copy_buffer_p2p cl_amd_assembly_program 

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 [MESA]
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT)  No devices found in platform
  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)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL)  No devices found in platform

ICD loader properties
  ICD loader Name                                 Khronos OpenCL ICD Loader
  ICD loader Vendor                               Khronos Group
  ICD loader Version                              3.0.6
  ICD loader Profile                              OpenCL 3.0
peppermint@fedora:~$ rocm-smi


Exception caught: map::at
========================================= ROCm System Management Interface =========================================
=================================================== Concise Info ===================================================
Device  [Model : Revision]    Temp    Power    Partitions      SCLK  MCLK     Fan  Perf  PwrCap       VRAM%  GPU%  
        Name (20 chars)       (Edge)  (Avg)    (Mem, Compute)                                                      
====================================================================================================================
0       [NITRO+ RX 7900 XTX   33.0°C  14.0W    N/A, N/A        0Mhz  96Mhz    0%   auto  339.0W         0%   0%    
        Navi 31 [Radeon RX 7                                                                                       
1       [0x364e : 0xc1]       39.0°C  44.173W  N/A, N/A        None  3000Mhz  0%   auto  Unsupported   90%   0%    
        Raphael                                                                                                    
====================================================================================================================
=============================================== End of ROCm SMI Log ================================================

/opt/rocm/bin/rocminfo gives :


ROCk module is loaded
=====================    
HSA System Attributes    
=====================    
Runtime Version:         1.13
Runtime Ext Version:     1.4
System Timestamp Freq.:  1000.000000MHz
Sig. Max Wait Duration:  18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count)
Machine Model:           LARGE                              
System Endianness:       LITTLE                             
Mwaitx:                  DISABLED
DMAbuf Support:          YES

==========               
HSA Agents               
==========               
*******                  
Agent 1                  
*******                  
  Name:                    AMD Ryzen 9 7950X 16-Core Processor
  Uuid:                    CPU-XX                             
  Marketing Name:          AMD Ryzen 9 7950X 16-Core Processor
  Vendor Name:             CPU                                
  Feature:                 None specified                     
  Profile:                 FULL_PROFILE                       
  Float Round Mode:        NEAR                               
  Max Queue Number:        0(0x0)                             
  Queue Min Size:          0(0x0)                             
  Queue Max Size:          0(0x0)                             
  Queue Type:              MULTI                              
  Node:                    0                                  
  Device Type:             CPU                                
  Cache Info:              
    L1:                      32768(0x8000) KB                   
  Chip ID:                 0(0x0)                             
  ASIC Revision:           0(0x0)                             
  Cacheline Size:          64(0x40)                           
  Max Clock Freq. (MHz):   5881                               
  BDFID:                   0                                  
  Internal Node ID:        0                                  
  Compute Unit:            32                                 
  SIMDs per CU:            0                                  
  Shader Engines:          0                                  
  Shader Arrs. per Eng.:   0                                  
  WatchPts on Addr. Ranges:1                                  
  Features:                None
  Pool Info:               
    Pool 1                   
      Segment:                 GLOBAL; FLAGS: FINE GRAINED        
      Size:                    64917196(0x3de8ecc) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
    Pool 2                   
      Segment:                 GLOBAL; FLAGS: KERNARG, FINE GRAINED
      Size:                    64917196(0x3de8ecc) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
    Pool 3                   
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED      
      Size:                    64917196(0x3de8ecc) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
  ISA Info:                
*******                  
Agent 2                  
*******                  
  Name:                    gfx1100                            
  Uuid:                    GPU-93a17b67b3d347bc               
  Marketing Name:          Radeon RX 7900 XTX                 
  Vendor Name:             AMD                                
  Feature:                 KERNEL_DISPATCH                    
  Profile:                 BASE_PROFILE                       
  Float Round Mode:        NEAR                               
  Max Queue Number:        128(0x80)                          
  Queue Min Size:          64(0x40)                           
  Queue Max Size:          131072(0x20000)                    
  Queue Type:              MULTI                              
  Node:                    1                                  
  Device Type:             GPU                                
  Cache Info:              
    L1:                      32(0x20) KB                        
    L2:                      6144(0x1800) KB                    
    L3:                      98304(0x18000) KB                  
  Chip ID:                 29772(0x744c)                      
  ASIC Revision:           0(0x0)                             
  Cacheline Size:          64(0x40)                           
  Max Clock Freq. (MHz):   2526                               
  BDFID:                   768                                
  Internal Node ID:        1                                  
  Compute Unit:            96                                 
  SIMDs per CU:            2                                  
  Shader Engines:          6                                  
  Shader Arrs. per Eng.:   2                                  
  WatchPts on Addr. Ranges:4                                  
  Coherent Host Access:    FALSE                              
  Features:                KERNEL_DISPATCH 
  Fast F16 Operation:      TRUE                               
  Wavefront Size:          32(0x20)                           
  Workgroup Max Size:      1024(0x400)                        
  Workgroup Max Size per Dimension:
    x                        1024(0x400)                        
    y                        1024(0x400)                        
    z                        1024(0x400)                        
  Max Waves Per CU:        32(0x20)                           
  Max Work-item Per CU:    1024(0x400)                        
  Grid Max Size:           4294967295(0xffffffff)             
  Grid Max Size per Dimension:
    x                        4294967295(0xffffffff)             
    y                        4294967295(0xffffffff)             
    z                        4294967295(0xffffffff)             
  Max fbarriers/Workgrp:   32                                 
  Packet Processor uCode:: 202                                
  SDMA engine uCode::      21                                 
  IOMMU Support::          None                               
  Pool Info:               
    Pool 1                   
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED      
      Size:                    25149440(0x17fc000) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:2048KB                             
      Alloc Alignment:         4KB                                
      Accessible by all:       FALSE                              
    Pool 2                   
      Segment:                 GLOBAL; FLAGS: EXTENDED FINE GRAINED
      Size:                    25149440(0x17fc000) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:2048KB                             
      Alloc Alignment:         4KB                                
      Accessible by all:       FALSE                              
    Pool 3                   
      Segment:                 GROUP                              
      Size:                    64(0x40) KB                        
      Allocatable:             FALSE                              
      Alloc Granule:           0KB                                
      Alloc Recommended Granule:0KB                                
      Alloc Alignment:         0KB                                
      Accessible by all:       FALSE                              
  ISA Info:                
    ISA 1                    
      Name:                    amdgcn-amd-amdhsa--gfx1100         
      Machine Models:          HSA_MACHINE_MODEL_LARGE            
      Profiles:                HSA_PROFILE_BASE                   
      Default Rounding Mode:   NEAR                               
      Default Rounding Mode:   NEAR                               
      Fast f16:                TRUE                               
      Workgroup Max Size:      1024(0x400)                        
      Workgroup Max Size per Dimension:
        x                        1024(0x400)                        
        y                        1024(0x400)                        
        z                        1024(0x400)                        
      Grid Max Size:           4294967295(0xffffffff)             
      Grid Max Size per Dimension:
        x                        4294967295(0xffffffff)             
        y                        4294967295(0xffffffff)             
        z                        4294967295(0xffffffff)             
      FBarrier Max Size:       32                                 
*******                  
Agent 3                  
*******                  
  Name:                    gfx1036                            
  Uuid:                    GPU-XX                             
  Marketing Name:          AMD Radeon Graphics                
  Vendor Name:             AMD                                
  Feature:                 KERNEL_DISPATCH                    
  Profile:                 BASE_PROFILE                       
  Float Round Mode:        NEAR                               
  Max Queue Number:        128(0x80)                          
  Queue Min Size:          64(0x40)                           
  Queue Max Size:          131072(0x20000)                    
  Queue Type:              MULTI                              
  Node:                    2                                  
  Device Type:             GPU                                
  Cache Info:              
    L1:                      16(0x10) KB                        
    L2:                      256(0x100) KB                      
  Chip ID:                 5710(0x164e)                       
  ASIC Revision:           1(0x1)                             
  Cacheline Size:          128(0x80)                          
  Max Clock Freq. (MHz):   2200                               
  BDFID:                   6144                               
  Internal Node ID:        2                                  
  Compute Unit:            2                                  
  SIMDs per CU:            2                                  
  Shader Engines:          1                                  
  Shader Arrs. per Eng.:   1                                  
  WatchPts on Addr. Ranges:4                                  
  Coherent Host Access:    FALSE                              
  Features:                KERNEL_DISPATCH 
  Fast F16 Operation:      TRUE                               
  Wavefront Size:          32(0x20)                           
  Workgroup Max Size:      1024(0x400)                        
  Workgroup Max Size per Dimension:
    x                        1024(0x400)                        
    y                        1024(0x400)                        
    z                        1024(0x400)                        
  Max Waves Per CU:        32(0x20)                           
  Max Work-item Per CU:    1024(0x400)                        
  Grid Max Size:           4294967295(0xffffffff)             
  Grid Max Size per Dimension:
    x                        4294967295(0xffffffff)             
    y                        4294967295(0xffffffff)             
    z                        4294967295(0xffffffff)             
  Max fbarriers/Workgrp:   32                                 
  Packet Processor uCode:: 21                                 
  SDMA engine uCode::      9                                  
  IOMMU Support::          None                               
  Pool Info:               
    Pool 1                   
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED      
      Size:                    524288(0x80000) KB                 
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:2048KB                             
      Alloc Alignment:         4KB                                
      Accessible by all:       FALSE                              
    Pool 2                   
      Segment:                 GLOBAL; FLAGS: EXTENDED FINE GRAINED
      Size:                    524288(0x80000) KB                 
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Recommended Granule:2048KB                             
      Alloc Alignment:         4KB                                
      Accessible by all:       FALSE                              
    Pool 3                   
      Segment:                 GROUP                              
      Size:                    64(0x40) KB                        
      Allocatable:             FALSE                              
      Alloc Granule:           0KB                                
      Alloc Recommended Granule:0KB                                
      Alloc Alignment:         0KB                                
      Accessible by all:       FALSE                              
  ISA Info:                
    ISA 1                    
      Name:                    amdgcn-amd-amdhsa--gfx1036         
      Machine Models:          HSA_MACHINE_MODEL_LARGE            
      Profiles:                HSA_PROFILE_BASE                   
      Default Rounding Mode:   NEAR                               
      Default Rounding Mode:   NEAR                               
      Fast f16:                TRUE                               
      Workgroup Max Size:      1024(0x400)                        
      Workgroup Max Size per Dimension:
        x                        1024(0x400)                        
        y                        1024(0x400)                        
        z                        1024(0x400)                        
      Grid Max Size:           4294967295(0xffffffff)             
      Grid Max Size per Dimension:
        x                        4294967295(0xffffffff)             
        y                        4294967295(0xffffffff)             
        z                        4294967295(0xffffffff)             
      FBarrier Max Size:       32                                 
*** Done ***

jeez , sure is a mess , if you prefer it all being in one text file , let me know.
thanks for the help so far fancy hat man ;D
you sure are fancy with that heart

1 Like

I took the liberty to reformat your post, They could prove to be relevant and help others in the future.

2 Likes

It gets installed as part of the amdgpu-install command unless you explicitly pass in the flag --no-dkms. However, I don’t recommend using the amdgpu-install command at all.

I recall none of my ROCm packages working properly with AMD’s recommended DKMS setup. I needed to clean my environment from the mess the official AMD installer created before I was able to get things working.

I recommend you try removing all AMD/ROCm packages again. We should focus on properly clearing out your system of all residual mess including dkms leftovers before moving forward with installing the correct packages.

This looks good

The correct package name is rocm-core5.4.1, it’s a little strange. The command dnf install rocm-core5.4.1 should work, but I don’t recommend doing that just yet.

To be honest, I believe I may have some redundant packages on my system, but I know they work so my idea is to replicate my package environment on your system to get your drivers working properly. In the future, you could likely shave off some unnecessary packages if you wished.

In my Gnome settings I have my ‘dummy HDMI display’ in the off position. The important part for me is that my system detects a monitor is connected to the GPU, you may still configure your desktop environment’s user interface to ignore the display.

There are a few bad packages in your package list. If you do clear out your packages again as I suggested, could you please share the output of that dnf list command again so I can confirm the system is clean before moving forward with reinstalling any packages?

The outputs from all the other commands look promising. I believe we just need to get the right packages on your system for Resolve to use either of your AMD GPUs.

1 Like

It doesnt :smiling_face_with_tear: diff repo perhaps , my repo is just stock repo

if those are the only ones left , then its cleared out ;D

good to know ! davinci resolve is pretty weird.

already dealt with it btw ;D

and quick question , does some areas/features of davinci resolve just not work in linux with the open source amd stack ? just incase i have a blindspot in my knowledge

again , thanks for the help so far sweetie :kissing_heart:
ill try again with the broken packages you listed removed ;D

Your /etc/yum.repos.d/rocm.repo file would suggest we’re using the same rocm repo. Here’s more information about the package on my system:

$ dnf5 info --installed rocm-core5.4.1
Installed packages
Name            : rocm-core5.4.1
Epoch           : 0
Version         : 5.4.1.50401
Release         : 84.el9
Architecture    : x86_64
Installed size  : 23.5 KiB
Source          : rocm-core5.4.1-5.4.1.50401-84.el9.src.rpm
From repository : rocm-copy
Summary         : Radeon Open Compute (ROCm) Runtime software stack
URL             : 
License         : unknown
Description     : DESCRIPTION
                : ===========
                : 
                : This is an installer created using CPack (https://cmake.org). No additional instal
                : lation instructions provided.
Vendor          : Advanced Micro Devices, Inc.
$ dnf5 repo info rocm-copy
Updating and loading repositories:
Repositories loaded.
Repo ID              : rocm-copy
Name                 : ROCm rhel9 rpm (copy)
Status               : enabled
Priority             : 50
Cost                 : 1000
Type                 : available
Metadata expire      : 172800 seconds (last: 2024-07-22 20:18:33)
Skip if unavailable  : true
Config file          : /etc/yum.repos.d/rocm_copy.repo
URLs                 : 
  Base URL           : https://repo.radeon.com/rocm/rhel9/latest/main/
PGP                  : 
  Keys               : file:///etc/pki/rpm-gpg/RPM-GPG-KEY-rocm-copy
  Verify repodata    : false
  Verify packages    : true
Repodata info        : 
  Available packages : 403
  Total packages     : 403
  Size               : 13.7 GiB
  Revision           : 1717091247
  Updated            : 2024-05-30 17:47:27

I believe this particular quirk was actually with my GPU (anti crypto mining ‘feature’?) as rocminfo and clinfo would not detect my gpu at all and my eGPU enclosure would spin down its fans after a while.

Well done, I remember it being quite a headache to clear out on my system.

On my system the only limitation I’ve experienced is HEVC content won’t render, but I believe that is due to licensing issues and should not be an issue for you as you use Resolve Studio. I have previously transcoded content to DNxHD for editing in Resolve on Fedora as a work around for this.

No problem! Hope you come back with the good news :slight_smile:

Added davinci-resolve, rocm and removed amd, desktop, kde, workstation