[radeonsi] RUSTICL and AMD_DEBUG=useaco SIGFAULT / SIGABRT

Timur Kristóf timur.kristof at gmail.com
Wed Jul 12 09:29:41 UTC 2023


Hello Dieter,

Please note that RadeonSI + ACO combination is very experimental at the
moment, so it is expected that some things will break. For this
concrete issue, take a look at this MR to see if it helps:
https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24112

It is of course very possible that there will be other issues after
this which will need to be investigated further.

In the future, I recommend opening an issue on Mesa GitLab:
https://gitlab.freedesktop.org/mesa/mesa/-/issues

Best regards,
Timur

On Tue, 2023-07-11 at 15:09 +0200, Dieter Nützel wrote:
> Hello List,
> 
> running clinfo under RUSTICL on my Polaris 20, RX580 explode with ACO
> compiler.
> 
> AMD_DEBUG=useaco
> 
> RUSTICL_ENABLE=radeonsi
> RUSTICL_FEATURES=fp64
> 
> 
> Greetings,
> Dieter
> 
> 
> (gdb) r
> Starting program: /usr/bin/clinfo
> Downloading separate debug info for system-supplied DSO at 
> 0x7ffff7fc7000
> [Thread debugging using libthread_db enabled]
> Using host libthread_db library "/lib64/libthread_db.so.1".
> Downloading separate debug info for 
> /usr/local/lib64/libRusticlOpenCL.so.1
> [New Thread 0x7fffebfff6c0 (LWP 2435)]
> [New Thread 0x7fffeb6bd6c0 (LWP 2436)]
> [New Thread 0x7fffeaebc6c0 (LWP 2437)]
> [New Thread 0x7fffea6bb6c0 (LWP 2438)]
> Number of platforms                               1
>    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_extended_versioning cl_khr_icd cl_khr_il_program 
> cl_khr_spirv_no_integer_wrap_decoration
>    Platform Extensions with Version                
> cl_khr_byte_addressable_store                                    
> 0x400000 (1.0.0)
>                                                    
> cl_khr_create_command_queue                                      
> 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)
>    Platform Numeric Version                        0xc00000 (3.0.0)
>    Platform Extensions function suffix             MESA
>    Platform Host timer resolution                  1ns
> 
>    Platform Name                                   rusticl
> Number of devices                                 1
>    Device Name                                     AMD Radeon RX 580 
> Series (polaris10, LLVM 17.0.0git, DRM 3.52, 6.4.2-1.ge2dafc9-
> default)
>    Device Vendor                                   AMD
>    Device Vendor ID                                0x1002
>    Device Version                                  OpenCL 3.0
>    Device UUID                                     
> 00000000-0100-0000-0000-000000000000
>    Driver UUID                                     
> 414d442d-4d45-5341-2d44-525600000000
>    Valid Device LUID                               No
>    Device LUID                                     0000-000000000000
>    Device Node Mask                                0
>    Device Numeric Version                          0xc00000 (3.0.0)
>    Driver Version                                  23.2.0-devel 
> (git-0695ead057)
>    Device OpenCL C Version                         OpenCL C 1.2
>    Device OpenCL C Numeric Version                 0x402000 (1.2.0)
>    Device OpenCL C all versions                    OpenCL
> C               
>                                            0xc00000 (3.0.0)
>                                                    OpenCL
> C               
>                                            0x402000 (1.2.0)
>                                                    OpenCL
> C               
>                                            0x401000 (1.1.0)
>                                                    OpenCL
> C               
>                                            0x400000 (1.0.0)
>    Device OpenCL C features                        
> __opencl_c_integer_dot_product_input_4x8bit_packed               
> 0x800000 (2.0.0)
>                                                    
> __opencl_c_integer_dot_product_input_4x8bit                      
> 0x800000 (2.0.0)
>                                                   
> __opencl_c_fp64        
>                                            0x400000 (1.0.0)
>                                                   
> __opencl_c_int64       
>                                            0x400000 (1.0.0)
>                                                   
> __opencl_c_images      
>                                            0x400000 (1.0.0)
>                                                    
> __opencl_c_3d_image_writes                                       
> 0x400000 (1.0.0)
>                                                   
> __opencl_c_subgroups   
>                                            0x400000 (1.0.0)
>    Latest conformance test passed                  v0000-01-01-00
>    Device Type                                     GPU
>    Device PCI bus info (KHR)                       PCI-E,
> 0000:01:00.0
>    Device Profile                                  EMBEDDED_PROFILE
>    Device Available                                Yes
>    Compiler Available                              Yes
>    Linker Available                                Yes
>    Max compute units                               36
>    Max clock frequency                             1411MHz
>    Device Partition                                (core)
>      Max number of sub-devices                     0
>      Supported partition types                     None
>      Supported affinity domains                    (n/a)
>    Max work item dimensions                        3
>    Max work item sizes                             1024x1024x1024
>    Max work group size                             1024
>    Preferred work group size multiple (device)     64
> [New Thread 0x7fffe99796c0 (LWP 2439)]
> clinfo: ../src/amd/compiler/aco_instruction_selection_setup.cpp:673: 
> aco::isel_context aco::setup_isel_context(Program*, unsigned int, 
> nir_shader* const*, ac_shader_config*, const aco_compiler_options*, 
> const aco_shader_info*, const ac_shader_args*, bool): Assertion `!"" 
> "Shader stage not implemented"' failed.
> 
> Thread 4 "clinfo:sh0" received signal SIGABRT, Aborted.
> [Switching to Thread 0x7fffeaebc6c0 (LWP 2437)]
> __pthread_kill_implementation (threadid=<optimized out>, 
> signo=signo at entry=6,
>      no_tid=no_tid at entry=0) at pthread_kill.c:44
> Downloading source file /usr/src/debug/glibc-2.37/nptl/pthread_kill.c
> 44            return INTERNAL_SYSCALL_ERROR_P (ret) ? 
> INTERNAL_SYSCALL_ERRNO (ret) : 0;
> (gdb) bt
> #0  __pthread_kill_implementation (threadid=<optimized out>, 
> signo=signo at entry=6,
>      no_tid=no_tid at entry=0) at pthread_kill.c:44
> #1  0x00007ffff7dfab03 in __pthread_kill_internal (signo=6, 
> threadid=<optimized out>)
>      at pthread_kill.c:78
> #2  0x00007ffff7da9226 in __GI_raise (sig=sig at entry=6) at 
> ../sysdeps/posix/raise.c:26
> #3  0x00007ffff7d91897 in __GI_abort () at abort.c:79
> #4  0x00007ffff7d917ab in __assert_fail_base (
>      fmt=0x7ffff7f19b98 "%s%s%s:%u: %s%sAssertion `%s' failed.\n%n",
>      assertion=assertion at entry=0x7ffff695b080 "!\"\" \"Shader stage
> not 
> implemented\"",
>      file=file at entry=0x7ffff695ad30 
> "../src/amd/compiler/aco_instruction_selection_setup.cpp",
>      line=line at entry=673,
>      function=function at entry=0x7ffff695afc0 "aco::isel_context 
> aco::setup_isel_context(Program*, unsigned int, nir_shader* const*, 
> ac_shader_config*, const aco_compiler_options*, const
> aco_shader_info*, 
> const ac_shader_args*, bool)") at assert.c:92
> #5  0x00007ffff7da14b6 in __assert_fail (
>      assertion=0x7ffff695b080 "!\"\" \"Shader stage not
> implemented\"",
>      file=0x7ffff695ad30 
> "../src/amd/compiler/aco_instruction_selection_setup.cpp", line=673,
>      function=0x7ffff695afc0 "aco::isel_context 
> aco::setup_isel_context(Program*, unsigned int, nir_shader* const*, 
> ac_shader_config*, const aco_compiler_options*, const
> aco_shader_info*, 
> const ac_shader_args*, bool)") at assert.c:101
> #6  0x00007ffff73c8343 in ?? () from 
> /usr/local/lib64/libRusticlOpenCL.so.1
> #7  0x00007ffff73b3324 in ?? () from 
> /usr/local/lib64/libRusticlOpenCL.so.1
> #8  0x00007ffff73cb4ac in ?? () from 
> /usr/local/lib64/libRusticlOpenCL.so.1
> #9  0x00007ffff77431d1 in ?? () from 
> /usr/local/lib64/libRusticlOpenCL.so.1
> #10 0x00007ffff774056c in ?? () from 
> /usr/local/lib64/libRusticlOpenCL.so.1
> #11 0x00007ffff7741f06 in ?? () from 
> /usr/local/lib64/libRusticlOpenCL.so.1
> #12 0x00007ffff76ea021 in ?? () from 
> /usr/local/lib64/libRusticlOpenCL.so.1
> #13 0x00007ffff6ed284b in ?? () from 
> /usr/local/lib64/libRusticlOpenCL.so.1
> #14 0x00007ffff6f3bb5d in ?? () from 
> /usr/local/lib64/libRusticlOpenCL.so.1
> --Type <RET> for more, q to quit, c to continue without paging--
> #15 0x00007ffff7df8c24 in start_thread (arg=<optimized out>) at 
> pthread_create.c:444
> #16 0x00007ffff7e80510 in clone3 () at 
> ../sysdeps/unix/sysv/linux/x86_64/clone3.S:81
> (gdb) info registers
> rax            0x0                 0
> rbx            0x985               2437
> rcx            0x7ffff7dfaa7c      140737352018556
> rdx            0x6                 6
> rsi            0x985               2437
> rdi            0x97e               2430
> rbp            0x7fffeaebc6c0      0x7fffeaebc6c0
> rsp            0x7fffeaeb8b10      0x7fffeaeb8b10
> r8             0x7fffe0022700      140736951625472
> r9             0x0                 0
> r10            0x8                 8
> r11            0x246               582
> r12            0x7ffff695ad30      140737330392368
> r13            0x6                 6
> r14            0x7ffff695b080      140737330393216
> r15            0x7fffea6bc000      140737126318080
> rip            0x7ffff7dfaa7c      0x7ffff7dfaa7c 
> <__pthread_kill_implementation+270>
> eflags         0x246               [ PF ZF IF ]
> cs             0x33                51
> ss             0x2b                43
> ds             0x0                 0
> es             0x0                 0
> fs             0x0                 0
> gs             0x0                 0
> (gdb)



More information about the mesa-dev mailing list