V4.1 - XMRIG throws SIGSEGV (Address boundary error) #1424

ajboni · 2021-03-24T05:20:37Z

Describe the bug
It was all wotking great before ROCm v4.1 now it gives me the following error:

~/crypto/xmrig-6.10.0  sudo ./xmrig                                                                                                                                             02:12:46
 * ABOUT        XMRig/6.10.0 gcc/9.3.0
 * LIBS         libuv/1.41.0 OpenSSL/1.1.1j hwloc/2.4.1
 * HUGE PAGES   supported
 * 1GB PAGES    supported
 * CPU          AMD Ryzen 7 2700 Eight-Core Processor (1) 64-bit AES
                L2:4.0 MB L3:16.0 MB 8C/16T NUMA:1
 * MEMORY       4.4/15.6 GB (28%)
                DIMM_A1: <empty>
                DIMM_A2: 8 GB DDR4 @ 2400 MHz 9905702-012.A00G    
                DIMM_B1: <empty>
                DIMM_B2: 8 GB DDR4 @ 2400 MHz 9905702-012.A00G    
 * MOTHERBOARD  ASUSTeK COMPUTER INC. - PRIME B450M-A
 * DONATE       1%
 * ASSEMBLY     ryzen
 * POOL #1      haven.herominers.com:10451 algo cn-heavy/xhv
 * COMMANDS     hashrate, pause, resume, results, connection
 * ADL          press e for health report
 * OPENCL       #0 AMD Accelerated Parallel Processing/OpenCL 2.0 AMD-APP (3241.0)
 * OPENCL GPU   #0 08:00.0 Ellesmere [Radeon RX 470/480/570/570X/580/580X/590] (gfx803) 1405 MHz cu:36 mem:6963/8192 MB
 * CUDA         disabled
[2021-03-24 02:13:23.679]  net      use pool haven.herominers.com:10451 TLSv1.2 168.119.11.231
[2021-03-24 02:13:23.679]  net      fingerprint (SHA-256): "fece0801e2afe588c90685d695abe4948126c1bde1a41b654fda89de59eca276"
[2021-03-24 02:13:23.679]  net      new job from haven.herominers.com:10451 diff 30000 algo cn-heavy/xhv height 817791
[2021-03-24 02:13:23.683]  msr      register values for "ryzen_17h" preset have been set successfully (4 ms)
[2021-03-24 02:13:23.683]  cpu      use profile  cn-heavy  (4 threads) scratchpad 4096 KB
[2021-03-24 02:13:23.684]  opencl   use profile  cn-heavy  (2 threads) scratchpad 4096 KB
|  # | GPU |  BUS ID | INTENSITY | WSIZE | MEMORY | NAME
|  0 |   0 | 08:00.0 |       864 |     8 |   3456 | Ellesmere [Radeon RX 470/480/570/570X/580/580X/590] (gfx803)
|  1 |   0 | 08:00.0 |       864 |     8 |   3456 | Ellesmere [Radeon RX 470/480/570/570X/580/580X/590] (gfx803)
[2021-03-24 02:13:23.834]  cpu      READY threads 4/4 (4) huge pages 100% 8/8 memory 16384 KB (151 ms)
fish: Job 1, 'sudo ./xmrig' terminated by signal SIGSEGV (Address boundary error)
 139  ~/crypto/xmrig-6.10.0                                                                                                                                            1598ms  02:13:24

 ~/crypto/xmrig-6.10.0  /opt/rocm/bin/rocminfo                                                                                                                                   02:16:26
ROCk module is loaded
=====================    
HSA System Attributes    
=====================    
Runtime Version:         1.1
System Timestamp Freq.:  1000.000000MHz
Sig. Max Wait Duration:  18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count)
Machine Model:           LARGE                              
System Endianness:       LITTLE                             

==========               
HSA Agents               
==========               
*******                  
Agent 1                  
*******                  
  Name:                    AMD Ryzen 7 2700 Eight-Core Processor
  Uuid:                    CPU-XX                             
  Marketing Name:          AMD Ryzen 7 2700 Eight-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)                             
  Cacheline Size:          64(0x40)                           
  Max Clock Freq. (MHz):   3200                               
  BDFID:                   0                                  
  Internal Node ID:        0                                  
  Compute Unit:            16                                 
  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: KERNARG, FINE GRAINED
      Size:                    16392024(0xfa1f58) KB              
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
    Pool 2                   
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED      
      Size:                    16392024(0xfa1f58) KB              
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
  ISA Info:                
    N/A                      
*******                  
Agent 2                  
*******                  
  Name:                    gfx803                             
  Uuid:                    GPU-XX                             
  Marketing Name:          Ellesmere [Radeon RX 470/480/570/570X/580/580X/590]
  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:                 26591(0x67df)                      
  Cacheline Size:          64(0x40)                           
  Max Clock Freq. (MHz):   1405                               
  BDFID:                   2048                               
  Internal Node ID:        1                                  
  Compute Unit:            36                                 
  SIMDs per CU:            4                                  
  Shader Engines:          4                                  
  Shader Arrs. per Eng.:   1                                  
  WatchPts on Addr. Ranges:4                                  
  Features:                KERNEL_DISPATCH 
  Fast F16 Operation:      FALSE                              
  Wavefront Size:          64(0x40)                           
  Workgroup Max Size:      1024(0x400)                        
  Workgroup Max Size per Dimension:
    x                        1024(0x400)                        
    y                        1024(0x400)                        
    z                        1024(0x400)                        
  Max Waves Per CU:        40(0x28)                           
  Max Work-item Per CU:    2560(0xa00)                        
  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:                    8388608(0x800000) 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--gfx803          
      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 ***             
 ~/crypto/xmrig-6.10.0 

I really don't know how to troubleshoot this.
Thanks

The text was updated successfully, but these errors were encountered:

ROCmSupport · 2021-03-24T13:01:26Z

Thanks @ajboni for reaching out.
I can not comment on gfx8 device as we are not supporting it officially.
But I will try to reproduce this on gfx9 device like Vega10 and share an update.
Before that, I need the exact steps to reproduce the problem.
Thank you.

ajboni · 2021-03-24T18:08:18Z

Thanks! here are the steps:

(uninstall old rocm version)
Install latest rocm
wget https://github.com/xmrig/xmrig/releases/download/v6.10.0/xmrig-6.10.0-linux-x64.tar.gz
tar -xf xmrig-6.10.0-linux-x64.tar.gz
cd xmrig-6.10.0/
edit config.json and set opencl to true
run ./xmrig

ROCmSupport · 2021-03-25T10:54:21Z

After changing opencl to "true" also, its no detecting in my case.
Please help me with resolving this issue.

taccuser@taccuser-X399-DESIGNARE-EX:~/xmrig-6.10.0$ ./xmrig

ABOUT XMRig/6.10.0 gcc/5.4.0
LIBS libuv/1.41.0 OpenSSL/1.1.1j hwloc/2.4.1
HUGE PAGES supported
1GB PAGES disabled
CPU AMD Ryzen Threadripper 2990WX 32-Core Processor (1) 64-bit AES
L2:16.0 MB L3:64.0 MB 32C/64T NUMA:4
MEMORY 1.7/31.3 GB (5%)
DONATE 1%
ASSEMBLY auto:ryzen
POOL README.md cleanup from release #1 donate.v2.xmrig.com:3333 algo auto
COMMANDS hashrate, pause, resume, results, connection
[2021-03-25 15:36:19.307] config configuration saved to: "/home/taccuser/xmrig-6.10.0/config.json"
OPENCL disabled (failed to load OpenCL runtime)
CUDA disabled
[2021-03-25 15:36:19.720] net use pool donate.v2.xmrig.com:3333 199.247.27.41
[2021-03-25 15:36:19.720] net new job from donate.v2.xmrig.com:3333 diff 1000K algo rx/0 height 2324610
[2021-03-25 15:36:19.720] cpu use argon2 implementation AVX2
[2021-03-25 15:36:19.799] msr msr kernel module is not available
[2021-03-25 15:36:19.799] msr FAILED TO APPLY MSR MOD, HASHRATE WILL BE LOW
[2021-03-25 15:36:19.799] randomx init dataset algo rx/0 (64 threads) seed fdedc07141ec5024...
[2021-03-25 15:36:19.800] randomx #0 allocated 2080 MB huge pages 0% (1 ms)
[2021-03-25 15:36:19.802] randomx #0 allocated 256 MB huge pages 0% +JIT (2 ms)
[2021-03-25 15:36:19.802] randomx -- allocated 2336 MB huge pages 0% 0/1168 (3 ms)
[2021-03-25 15:36:24.080] randomx #0 dataset ready (4278 ms)
[2021-03-25 15:36:24.081] cpu use profile rx (32 threads) scratchpad 2048 KB
[2021-03-25 15:36:24.082] CPU rocm 1.1.1 removed rocm-smi #16 warning: "can't bind memory"

ajboni · 2021-03-27T18:46:53Z

I tried blender and its showing no compatible GPU
also clinfo ends with ERROR: clBuildProgram(-11)
I've read RX580 is no longer supported on v4, is there any way to go back to previous version?

Thanks!

clinfo                                                                                                                                                                       15:45:43
Number of platforms:				 1
  Platform Profile:				 FULL_PROFILE
  Platform Version:				 OpenCL 2.0 AMD-APP (3241.0)
  Platform Name:				 AMD Accelerated Parallel Processing
  Platform Vendor:				 Advanced Micro Devices, Inc.
  Platform Extensions:				 cl_khr_icd cl_amd_event_callback 


  Platform Name:				 AMD Accelerated Parallel Processing
Number of devices:				 1
  Device Type:					 CL_DEVICE_TYPE_GPU
  Vendor ID:					 1002h
  Board name:					 Ellesmere [Radeon RX 470/480/570/570X/580/580X/590]
  Device Topology:				 PCI[ B#8, D#0, F#0 ]
  Max compute units:				 36
  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:				 1405Mhz
  Address bits:					 64
  Max memory allocation:			 7301444400
  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:			 26591
  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:					 No
    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:				 8589934592
  Constant buffer size:				 7301444400
  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:				 3006477104
  Max global variable size:			 7301444400
  Max global variable preferred total size:	 8589934592
  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
ERROR: clBuildProgram(-11)

briansp2020 · 2021-03-27T21:20:22Z

I think you can point to the previous version of repo directly (see #768 (comment))

So, instead of

echo 'deb [arch=amd64] https://repo.radeon.com/rocm/apt/debian/ xenial main' | sudo tee /etc/apt/sources.list.d/rocm.list

Do

echo 'deb [arch=amd64] https://repo.radeon.com/rocm/apt/3.9.1/ xenial main' | sudo tee /etc/apt/sources.list.d/rocm.list

ajboni · 2021-03-28T03:11:27Z

Thanks!
Tried to get back, but I face a lot of dependencies issues and couldnt even got clinfo to work.
I finally gave up and went with standard amdgpu-pro
./amdgpu-pro-install --opencl=legacy,pal --headless --no-dkms

ajboni closed this as completed Mar 28, 2021

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

V4.1 - XMRIG throws SIGSEGV (Address boundary error) #1424

V4.1 - XMRIG throws SIGSEGV (Address boundary error) #1424

ajboni commented Mar 24, 2021

ROCmSupport commented Mar 24, 2021

ajboni commented Mar 24, 2021

ROCmSupport commented Mar 25, 2021 •

edited

Loading

ajboni commented Mar 27, 2021 •

edited

Loading

briansp2020 commented Mar 27, 2021

ajboni commented Mar 28, 2021

V4.1 - XMRIG throws SIGSEGV (Address boundary error) #1424

V4.1 - XMRIG throws SIGSEGV (Address boundary error) #1424

Comments

ajboni commented Mar 24, 2021

ROCmSupport commented Mar 24, 2021

ajboni commented Mar 24, 2021

ROCmSupport commented Mar 25, 2021 • edited Loading

ajboni commented Mar 27, 2021 • edited Loading

briansp2020 commented Mar 27, 2021

ajboni commented Mar 28, 2021

ROCmSupport commented Mar 25, 2021 •

edited

Loading

ajboni commented Mar 27, 2021 •

edited

Loading