PC Drivers & Software

Terrence8888 · ‎01-16-2021

Hello. I'm trying to get OpenCL working on Linux Ubuntu 20.04.1 LTS on my 6900XT. I've tried these combinations:

1)

ubuntu kernel 5.4.0-54

amdgpu driver 20.45-1188099 with included rocr dkms

result: GPU is detected but clinfo hangs part way through displaying the info. My opencl code hangs trying to create a context

2)

ubuntu kernel 5.4.0-54

amdgpu driver 20.45-1188099 with --no-dkms and rocm 4.0.0.40000-23 (rocm-opencl 3.6Beta-17-g875c1f8-rocm-rel-4.0-23)

result: GPU is not detected. clinfo shows the platform AMD Accelerated Parallel Processing but has 0 devices

3)

upstream kernel 5.10.0-051000

rocm 4.0.0.40000-23 (rocm-opencl 3.6Beta-17-g875c1f8-rocm-rel-4.0-23)

result: rocminfo sees the GPU fine, clinfo hangs after displaying some of the data for the GPU just like in 1)

Here's the GPU data for rocminfo:

*******                  
Agent 2                  
*******                  
  Name:                    gfx1030                            
  Uuid:                    GPU-XX                             
  Marketing Name:          Device 73bf                        
  Vendor Name:             AMD                                
  Feature:                 KERNEL_DISPATCH                    
  Profile:                 BASE_PROFILE                       
  Float Round Mode:        NEAR                               
  Max Queue Number:        128(0x80)                          
  Queue Min Size:          4096(0x1000)                       
  Queue Max Size:          131072(0x20000)                    
  Queue Type:              MULTI                              
  Node:                    1                                  
  Device Type:             GPU                                
  Cache Info:              
    L1:                      16(0x10) KB                        
  Chip ID:                 29631(0x73bf)                      
  Cacheline Size:          64(0x40)                           
  Max Clock Freq. (MHz):   2660                               
  BDFID:                   768                                
  Internal Node ID:        1                                  
  Compute Unit:            80                                 
  SIMDs per CU:            4                                  
  Shader Engines:          8                                  
  Shader Arrs. per Eng.:   2                                  
  WatchPts on Addr. Ranges:4                                  
  Features:                KERNEL_DISPATCH 
  Fast F16 Operation:      FALSE                              
  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:        64(0x40)                           
  Max Work-item Per CU:    2048(0x800)                        
  Grid Max Size:           4294967295(0xffffffff)             
  Grid Max Size per Dimension:
    x                        4294967295(0xffffffff)             
    y                        4294967295(0xffffffff)             
    z                        4294967295(0xffffffff)             
  Max fbarriers/Workgrp:   32                                 
  Pool Info:               
    Pool 1                   
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED      
      Size:                    16760832(0xffc000) KB              
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       FALSE                              
    Pool 2                   
      Segment:                 GROUP                              
      Size:                    64(0x40) KB                        
      Allocatable:             FALSE                              
      Alloc Granule:           0KB                                
      Alloc Alignment:         0KB                                
      Accessible by all:       FALSE                              
  ISA Info:                
    ISA 1                    
      Name:                    amdgcn-amd-amdhsa--gfx1030         
      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

Here's the clinfo for the GPU:

  Platform Name:				 AMD Accelerated Parallel Processing
Number of devices:				 1
  Device Type:					 CL_DEVICE_TYPE_GPU
  Vendor ID:					 1002h
  Board name:					 Device 73bf
  Device Topology:				 PCI[ B#3, D#0, F#0 ]
  Max compute units:				 40
  Max work items dimensions:			 3
    Max work items[0]:				 1024
    Max work items[1]:				 1024
    Max work items[2]:				 1024
  Max work group size:				 256
  Preferred vector width char:			 4
  Preferred vector width short:			 2
  Preferred vector width int:			 1
  Preferred vector width long:			 1
  Preferred vector width float:			 1
  Preferred vector width double:		 1
  Native vector width char:			 4
  Native vector width short:			 2
  Native vector width int:			 1
  Native vector width long:			 1
  Native vector width float:			 1
  Native vector width double:			 1
  Max clock frequency:				 2660Mhz
  Address bits:					 64
  Max memory allocation:			 14588628168
  Image support:				 Yes
  Max number of images read arguments:		 128
  Max number of images write arguments:		 8
  Max image 2D width:				 16384
  Max image 2D height:				 16384
  Max image 3D width:				 16384
  Max image 3D height:				 16384
  Max image 3D depth:				 8192
  Max samplers within kernel:			 29631
  Max size of kernel argument:			 1024
  Alignment (bits) of base address:		 1024
  Minimum alignment (bytes) for any datatype:	 128
  Single precision floating point capability
    Denorms:					 Yes
    Quiet NaNs:					 Yes
    Round to nearest even:			 Yes
    Round to zero:				 Yes
    Round to +ve and infinity:			 Yes
    IEEE754-2008 fused multiply-add:		 Yes
  Cache type:					 Read/Write
  Cache line size:				 64
  Cache size:					 16384
  Global memory size:				 17163091968
  Constant buffer size:				 14588628168
  Max number of constant args:			 8
  Local memory type:				 Scratchpad
  Local memory size:				 65536
  Max pipe arguments:				 16
  Max pipe active reservations:			 16
  Max pipe packet size:				 1703726280
  Max global variable size:			 14588628168
  Max global variable preferred total size:	 17163091968
  Max read/write image args:			 64
  Max on device events:				 1024
  Queue on device max size:			 8388608
  Max on device queues:				 1
  Queue on device preferred size:		 262144
  SVM capabilities:				 
    Coarse grain buffer:			 Yes
    Fine grain buffer:				 Yes
    Fine grain system:				 No
    Atomics:					 No
  Preferred platform atomic alignment:		 0
  Preferred global atomic alignment:		 0
  Preferred local atomic alignment:		 0

<clinfo hangs here>

Has anyone gotten OpenCL working? Am I doing something wrong? I got this card specifically for a compute research project I'm doing so any help I can get on this is appreciated. I'm happy to provide any other info I can. Thanks!

Terrence8888 · ‎01-17-2021

A couple of edits to my above post. My pyopencl code doesn't hang creating the context, it hangs after that when creating the command queue.

Also, I'm running the GPU with an FX-8350. From reading the rocm documentation older GPUs require PCIe 3.0 atomics which this CPU doesn't support but I also am guessing the 6900XT is new enough to not require it.

I'm open to other OS/software combinations to get this working so if anyone has this working under a different configuration I'd be happy to try it too! I've seen opencl benchmarks for this card so it has to work somehow right?

Thanks again

pete910 · ‎02-15-2021

Having the same issue with a 6800xt + VII

Clinfo + rocminfo hangs

Foldiong@home fails use either too.

Did you ever find the issue . Seems like the 6000 series is not yet supported maybe.

I'm using Manjaro (Arch based)

5950x

Kernel 5.11

ROCM 4.0.0.1

Terrence8888 · ‎02-15-2021

Unfortunately I never solved this. I confirmed that the same problem exists on CentOS. I've been running my code on Windows which isn't efficient for my workflow and also periodically produces bizarre results so I've been waiting for AMD to release an update for the Linux driver. It has been 2 months so hopefully it will happen soon.

Terrence8888 · ‎03-21-2021

Update: I downloaded the new 20.50 linux drivers and installed them in a fresh install of Ubuntu and it still hangs on clinfo. I was hoping that this basic functionality would work after 3 months but no luck yet

pete910 · ‎03-24-2021

Good news, The update to rocm-opencl/HSA-rocr 4.1 today seems to have fixed it for me .

Working well now

If memory serves the 6xxx series requires rocm to use openCL so might be an idea to try that Terrence !

Unbutu should have the update I would have thought.

Terrence8888 · ‎03-24-2021

Thanks for the info! I tried installing rocm-dkms from the ROCm repo but then my card wasn't detected at all. I also tried installing rocm-opencl4.1.0 and hsa-rocr-dev4.1.0 among others but that didn't help either. Did I miss a step?

colesdav · ‎03-24-2021

@dipak might be able to help with this?
Thanks.

colesdav · ‎03-24-2021

Have you tried reporting it to ROCm on GitHub?

pete910 · ‎03-25-2021

You need to remove the previous version as upgrading causes issues. Best off purging all related romc/hsa packages and then trying.

I don't have have hsa-rocr-dev installed so but have the following on mine

hsa-rocr 4.1.0-1
hsakmt-roct 4.1.0-1

rocclr 4.1.0-1
rock-dkms-bin 4.0.1-1
rock-dkms-firmware-bin 4.0.1-2
rocm-cmake 4.1.0-1
rocm-device-libs 4.1.0-1
rocm-opencl-runtime 4.1.0-1
rocminfo 4.1.0-1

Terrence8888 · ‎03-27-2021

Thanks for all the info. I'll give it a shot then file a bug report if I can't get it working

erickgruis · ‎04-21-2021

For anyone else struggling to get some Radeon RX6000 GPU's working to mine Eth on Linux, here is what I did to get it working:

Latest kernel 5.12rc7
Manjaro KDE

Install amdgpu-pro 20.40 using this PKGBUILD file. This will download the pro driver version 20.40 and extract the openCL driver to work alongside the open source driver.

Drivers 20.45, 20.50 and 21.10 do not work with the big Navi cards. AMD, this is utterly ridiculous! I was so excited to see 21.10 in the repositories only to find it still doesn't work (clinfo hangs half way through the second card and mining delivers 0.00H/s)

Drivers 20.45 and onward worked fine for me when using only 1 GPU in the first PCIE slot. When I added a second GPU things simply failed.

PC Drivers & Software

6900XT and OpenCL on Linux