Radeon ROCm 3.0 Released With LLVM "AOMP" For Radeon OpenMP, FFT Updates

[Naquatis]

You should never have to downgrade the kernel for AMD since there is no closed source kernel driver for AMD both the open and closed drivers use the same open in kernel driver on AMD hardware. Sometimes you might have to run an out of tree driver for recent stuff that hasn't made it into mainline yet.

Sounds easy but what magically works for OpenCL freezes the Kernel when using Blender with amdgpu-pro-libgl. No idea maybe I need to blacklist stuff or Mesa 19.3.1 will causing problems with amdgpu-pro-libgl 19.30_934563-1?

But hey no problem I will use amdgpu and radv for that!

[Marc Driftmeyer]

If I need to downgrade the kernel because the amdgpu-pro package does not work on latest kernel versions then I stay with NVidia.
What works nicely with RX 480 was installing the userspace opencl-amd package while using Mesa .. but that does not work for Navi.

AMDs professional card lineup .. pff .. look how this RX 5700 XT -> 7nm card is not even able to get close to an old NVidia GTX 1080 Ti when it comes to GPU calculations (.. and I did not add the openCL kernel compilation then it is 1 minute 45 seconds against 59 seconds).

mdriftmeyer@horus:~$ uname -a
Linux horus 5.4.0-trunk-amd64 #1 SMP Debian 5.4.2-1~exp1 (2019-12-05) x86_64 GNU/Linux
mdriftmeyer@horus:~$


mdriftmeyer@horus:~$ clinfo
Number of platforms 2
Platform Name Clover
Platform Vendor Mesa
Platform Version OpenCL 1.1 Mesa 19.2.6
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 (2906.7)
Platform Profile FULL_PROFILE
Platform Extensions cl_khr_icd cl_amd_event_callback cl_amd_offline_devices
Platform Host timer resolution 1ns
Platform Extensions function suffix AMD

Platform Name Clover
Number of devices 1
Device Name AMD Radeon (TM) RX 480 Graphics (POLARIS10, DRM 3.35.0, 5.4.0-trunk-amd64, LLVM 9.0.0)
Device Vendor AMD
Device Vendor ID 0x1002
Device Version OpenCL 1.1 Mesa 19.2.6
Driver Version 19.2.6
Device OpenCL C Version OpenCL C 1.1
Device Type GPU
Device Profile FULL_PROFILE
Device Available Yes
Compiler Available Yes
Max compute units 36
Max clock frequency 1338MHz
Max work item dimensions 3
Max work item sizes 256x256x256
Max work group size 256
Preferred work group size multiple 64
Preferred / native vector sizes
char 16 / 16
short 8 / 8
int 4 / 4
long 2 / 2
half 8 / 8 (cl_khr_fp16)
float 4 / 4
double 2 / 2 (cl_khr_fp64)
Half-precision Floating-point support (cl_khr_fp16)
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
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 8589934592 (8GiB)
Error Correction support No
Max memory allocation 6871947673 (6.4GiB)
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 32768 (32KiB)
Max number of constant args 16
Max constant buffer size 2147483647 (2GiB)
Max size of kernel argument 1024
Queue properties
Out-of-order execution No
Profiling Yes
Profiling timer resolution 0ns
Execution capabilities
Run OpenCL kernels Yes
Run native kernels No
Device 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_fp16

Platform Name AMD Accelerated Parallel Processing
Number of devices 1
Device Name Ellesmere
Device Vendor Advanced Micro Devices, Inc.
Device Vendor ID 0x1002
Device Version OpenCL 1.2 AMD-APP (2906.7)
Driver Version 2906.7
Device OpenCL C Version OpenCL C 1.2
Device Type GPU
Device Board Name (AMD) AMD Radeon (TM) RX 480 Graphics
Device Topology (AMD) PCI-E, 01:00.0
Device Profile FULL_PROFILE
Device Available Yes
Compiler Available Yes
Linker Available Yes
Max compute units 36
SIMD per compute unit (AMD) 4
SIMD width (AMD) 16
SIMD instruction width (AMD) 1
Max clock frequency 1338MHz
Graphics IP (AMD) 8.0
Device Partition (core)
Max number of sub-devices 36
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 64
Wavefront width (AMD) 64
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 No
Infinity and NANs No
Round to nearest No
Round to zero No
Round to infinity No
IEEE754-2008 fused multiply-add No
Support is emulated in software No
Single-precision Floating-point support (core)
Denormals No
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 7990919168 (7.442GiB)
Global free memory (AMD) 7771292 (7.411GiB)
Global memory channels (AMD) 8
Global memory banks per channel (AMD) 16
Global memory bank width (AMD) 256 bytes
Error Correction support No
Max memory allocation 4244635648 (3.953GiB)
Unified memory for Host and Device No
Minimum alignment for any data type 128 bytes
Alignment of base address 2048 bits (256 bytes)
Global Memory cache type Read/Write
Global Memory cache size 16384 (16KiB)
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 2048 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 2048x2048x2048 pixels
Max number of read image args 128
Max number of write image args 8
Local memory type Local
Local memory size 32768 (32KiB)
Local memory syze per CU (AMD) 65536 (64KiB)
Local memory banks (AMD) 32
Max number of constant args 8
Max constant buffer size 4244635648 (3.953GiB)
Preferred constant buffer size (AMD) 16384 (16KiB)
Max size of kernel argument 1024
Queue properties
Out-of-order execution No
Profiling Yes
Prefer user sync for interop Yes
Profiling timer resolution 1ns
Profiling timer offset since Epoch (AMD) 1577034120958670668ns (Sun Dec 22 09:02:00 2019)
Execution capabilities
Run OpenCL kernels Yes
Run native kernels No
Thread trace supported (AMD) Yes
Number of async queues (AMD) 2
Max real-time compute queues (AMD) 0
Max real-time compute units (AMD) 842221062
SPIR versions 1.2
printf() buffer size 4194304 (4MiB)
Built-in kernels (n/a)
Device Extensions cl_khr_fp64 cl_amd_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_vec3 cl_amd_printf cl_amd_media_ops cl_amd_media_ops2 cl_amd_popcnt cl_khr_image2d_from_buffer cl_amd_bus_addressable_memory cl_khr_spir cl_khr_gl_event


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) Success (1)
Platform Name Clover
Device Name AMD Radeon (TM) RX 480 Graphics (POLARIS10, DRM 3.35.0, 5.4.0-trunk-amd64, LLVM 9.0.0)
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) No devices found in platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU) Success (1)
Platform Name Clover
Device Name AMD Radeon (TM) RX 480 Graphics (POLARIS10, DRM 3.35.0, 5.4.0-trunk-amd64, LLVM 9.0.0)
clCreateContextFromType(NULL, CL_DEVICE_TYPE_ACCELERATOR) No devices found in platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM) No devices found in platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL) Success (1)
Platform Name Clover
Device Name AMD Radeon (TM) RX 480 Graphics (POLARIS10, DRM 3.35.0, 5.4.0-trunk-amd64, LLVM 9.0.0)
mdriftmeyer@horus:~$

AMDPRO-GPU debs installed by hand
Version: 19.30-934563

hip-amdgpu-pro, libopencl1-amdgpu-pro, opencl-amdgpu-pro-comgr, opencl-amdgpu-pro-dev, opencl-amdgpu-pro-icd, opencl-orca-amdgpu-pro-icd, amdgpu-pro-core, amdgpu-pro-pin, llvm-amdgpu, llvm-amdgpu-9.0, llvm-amdgpu-9.0-dev, llvm-amdgpu-9.0-runtime, llvm-amdgpu-dev, llvm-amdgpu-runtime, libllvm9.0-amdgpu, libdrm-amdgpu-amdgpu1, libdrm2-amdgpu

[ObiWan]

Afaik if your using amdgpu-pro-libgl mesa isn't in use, it will always force itself over mesa, maybe there's a problem with blender and the pro OpenGL stack.

$ glxinfo | grep OpenGL
OpenGL vendor string: X.Org
OpenGL renderer string: AMD Radeon RX 5700 XT (NAVI10, DRM 3.35.0, 5.4.6-1, LLVM 10.0.0)
OpenGL core profile version string: 4.6 (Core Profile) Mesa 20.0.0-devel (git-2d971cc1ca)
OpenGL core profile shading language version string: 4.60
OpenGL core profile context flags: (none)
OpenGL core profile profile mask: core profile
OpenGL core profile extensions:
OpenGL version string: 4.6 (Compatibility Profile) Mesa 20.0.0-devel (git-2d971cc1ca)
OpenGL shading language version string: 4.60
OpenGL context flags: (none)
OpenGL profile mask: compatibility profile
OpenGL extensions:
OpenGL ES profile version string: OpenGL ES 3.2 Mesa 20.0.0-devel (git-2d971cc1ca)
OpenGL ES profile shading language version string: OpenGL ES GLSL ES 3.20
OpenGL ES profile extensions:

That's everything I use from the pro driver:

$ pacman -Q | grep amdgpu-pro
amdgpu-pro-core-meta 19.30_934563-1
opencl-amdgpu-pro-comgr 19.30_934563-1
opencl-amdgpu-pro-dev 19.30_934563-1
opencl-amdgpu-pro-orca 19.30_934563-1
opencl-amdgpu-pro-pal 19.30_934563-1
vulkan-amdgpu-pro 19.30_934563-1

[bridgman]

Sounds easy but what magically works for OpenCL freezes the Kernel when using Blender with amdgpu-pro-libgl. No idea maybe I need to blacklist stuff or Mesa 19.3.1 will causing problems with amdgpu-pro-libgl 19.30_934563-1?

You should be able to install just the packaged OpenCL on top of an otherwise upstream stack.

[Naquatis]

You should be able to install just the packaged OpenCL on top of an otherwise upstream stack.

Yep, works fine on Archlinux if you use the packages ObiWan suggested! Now I have fully functional KMS back and can render with OpenCL on Red Devil RX 5700 XT! So this 7nm Ryzen/Navi Linux rig is ready for upcoming holidays! Thanks everybody and have a nice Xmas!