You are not logged in.
When I want to select my gpu (rx 6750 xt) on blender this message appears:
No compatible GPU's found for Cycles
I have try some stuff like:
- adding my user to render and video group
- adding /opt/rocm/bin to the PATH
- Downloaded blender from the official site
But nothing seems to work. These are the packages that i have installed:
hip-runtime-amd 5.7.1-1
rocm-hip-runtime 5.7.1-2
rocm-hip-sdk 5.7.1-2
rocm-opencl-sdk 5.7.1-2
Offline
Offically rocm 5.7.1 only supports the AMD Radeon RX 7900 XTX and AMD Radeon PRO W7900 when using the amd proprietary drivers.
There have however been people that succesfully used rocm + mesa drivers + blender with radeon 5x, 6x and 7x gpus.
Please post the output of
$ /opt/rocm/bin/hipconfig --full
Welcome to archlinux forums.
Last edited by Lone_Wolf (2023-11-19 11:53:49)
Disliking systemd intensely, but not satisfied with alternatives so focusing on taming systemd.
(A works at time B) && (time C > time B ) ≠ (A works at time C)
Offline
Offically rocm 5.7.1 only supports the AMD Radeon RX 7900 XTX and AMD Radeon PRO W7900 when using the amd proprietary drivers.
Oh I didn't know that
There have however been people that succesfully used rocm + mesa drivers + blender with radeon 5x, 6x and 7x gpus.
Yeah I was able to use hip like a month ago
HIP version : 5.7.31921-
== hipconfig
HIP_PATH : /opt/rocm
ROCM_PATH : /opt/rocm
HIP_COMPILER : clang
HIP_PLATFORM : amd
HIP_RUNTIME : rocclr
CPP_CONFIG : -D__HIP_PLATFORM_HCC__= -D__HIP_PLATFORM_AMD__= -I/opt/rocm/include -I/opt/rocm/llvm/lib/clang/17.0.0
== hip-clang
HIP_CLANG_PATH : /opt/rocm/llvm/bin
clang version 17.0.0
Target: x86_64-pc-linux-gnu
Thread model: posix
InstalledDir: /opt/rocm/llvm/bin
AOMP-16.0-45 (http://github.com/ROCm-Developer-Tools/aomp):
Source ID:16.0-45-6b875fb548b9ded0f07df02bc2af6e12568504a9
LLVM version 17.0.0git
Optimized build with assertions.
Default target: x86_64-pc-linux-gnu
Host CPU: alderlake
Registered Targets:
amdgcn - AMD GCN GPUs
nvptx - NVIDIA PTX 32-bit
nvptx64 - NVIDIA PTX 64-bit
r600 - AMD GPUs HD2XXX-HD6XXX
x86 - 32-bit X86: Pentium-Pro and above
x86-64 - 64-bit X86: EM64T and AMD64
hip-clang-cxxflags : -isystem "/opt/rocm/include" -O3
hip-clang-ldflags : -O3 --hip-link --rtlib=compiler-rt -unwindlib=libgcc
=== Environment Variables
PATH=/opt/rocm/bin:/usr/local/sbin:/usr/local/bin:/usr/bin:/home/izaird/.dotnet/tools:/var/lib/flatpak/exports/bin:/opt/flutter/bin:/usr/lib/jvm/default/bin:/usr/bin/site_perl:/usr/bin/vendor_perl:/usr/bin/core_perl:/usr/lib/rustup/bin:/home/izaird/.local/bin
egrep: warning: egrep is obsolescent; using grep -E
== Linux Kernel
Hostname : Can't exec "hostname": No such file or directory at /opt/rocm/bin//hipconfig.pl line 211.
Linux Alpha 6.1.62-1-lts #1 SMP PREEMPT_DYNAMIC Thu, 09 Nov 2023 17:21:17 +0000 x86_64 GNU/Linux
LSB Version: n/a
Distributor ID: Arch
Description: Arch Linux
Release: rolling
Codename: n/a
Welcome to archlinux forums.
Thank you and also thank you for your time
Offline
Output of hip config doesn't show weird things. Blender docs appear to have a separate section for grpahics troubleshooting, but I get timeouts & connection errors for the site.
Have you tried blender 17:4.0.1-2 that entered extra repo yesterday ?
Last edited by Lone_Wolf (2023-11-21 12:11:36)
Disliking systemd intensely, but not satisfied with alternatives so focusing on taming systemd.
(A works at time B) && (time C > time B ) ≠ (A works at time C)
Offline
Right now blender 4.0.1 is not working
https://bbs.archlinux.org/viewtopic.php?id=290466
So was testing with the steam version, with the linux-lts kernel is the same problem
No compatible GPU's found for Cycles
But i also tried with the linux kernel and now when I tried to select hip to then select my graphics card the window freezes, and when I tried to kill it, it doesn't work the process stays there until I reboot the system
Offline
Blender docs appear to have a separate section for grpahics troubleshooting, but I get timeouts & connection errors for the site.
Ryzen 5900X 12 core/24 thread - RTX 3090 FE 24 Gb, Asus Prime B450 Plus, 32Gb Corsair DDR4, Cooler Master N300 chassis, 5 HD (1 NvME PCI, 4SSD) + 1 x optical.
Linux user #545703
Offline
I have a RX 7600.
I've got the same thing happening with blender too. Segfaults on startup.
# Blender 4.0.1, Commit date: 2023-11-16 16:40, Hash d0dd92834a08
# backtrace
blender(+0xfd0683) [0x559599632683]
blender(+0x8ba21e) [0x559598f1c21e]
/usr/lib/libc.so.6(+0x3e710) [0x7f67b116f710]
/usr/lib/libLLVM-15.so(+0x17a7a0f) [0x7f67a5da7a0f]
/usr/lib/libLLVM-15.so(+0x17a7b98) [0x7f67a5da7b98]
/usr/lib/libLLVM-16.so(_ZN4llvm14FoldingSetBase19FindNodeOrInsertPosERKNS_16FoldingSetNodeIDERPvRKNS0_14FoldingSetInfoE+0xb6) [0x7f67bf7278e6]
/usr/lib/libLLVM-16.so(_ZN4llvm12SelectionDAG11getRegisterEjNS_3EVTE+0xbe) [0x7f67c02cbd3e]
/usr/lib/libLLVM-16.so(+0x3a0e7ce) [0x7f67c240e7ce]
/usr/lib/libLLVM-16.so(_ZN4llvm16SelectionDAGISel14LowerArgumentsERKNS_8FunctionE+0xef3) [0x7f67c028f453]
/usr/lib/libLLVM-16.so(_ZN4llvm16SelectionDAGISel20SelectAllBasicBlocksERKNS_8FunctionE+0x22dc) [0x7f67c030632c]
/usr/lib/libLLVM-16.so(+0x19079b6) [0x7f67c03079b6]
/usr/lib/libLLVM-16.so(+0x12ea945) [0x7f67bfcea945]
/usr/lib/libLLVM-16.so(_ZN4llvm13FPPassManager13runOnFunctionERNS_8FunctionE+0x459) [0x7f67bf9ab989]
/usr/lib/libLLVM-16.so(+0x282aefa) [0x7f67c122aefa]
/usr/lib/libLLVM-16.so(_ZN4llvm6legacy15PassManagerImpl3runERNS_6ModuleE+0x3ec) [0x7f67bf9ac6ac]
/usr/lib/dri/radeonsi_dri.so(+0x82f380) [0x7f676162f380]
/usr/lib/dri/radeonsi_dri.so(+0x830009) [0x7f6761630009]
/usr/lib/dri/radeonsi_dri.so(+0x84fffc) [0x7f676164fffc]
/usr/lib/dri/radeonsi_dri.so(+0x85c2cf) [0x7f676165c2cf]
/usr/lib/dri/radeonsi_dri.so(+0x867c4d) [0x7f6761667c4d]
/usr/lib/dri/radeonsi_dri.so(+0xd334b3) [0x7f6761b334b3]
/usr/lib/dri/radeonsi_dri.so(+0xd070f1) [0x7f6761b070f1]
/usr/lib/dri/radeonsi_dri.so(+0xbad593) [0x7f67619ad593]
/usr/lib/dri/radeonsi_dri.so(+0x1351b8e) [0x7f6762151b8e]
/usr/lib/dri/radeonsi_dri.so(+0x8bbed3) [0x7f67616bbed3]
/usr/lib/dri/radeonsi_dri.so(+0x607263) [0x7f6761407263]
/usr/lib/dri/radeonsi_dri.so(+0x5e8219) [0x7f67613e8219]
/usr/lib/dri/radeonsi_dri.so(+0x147f72a) [0x7f676227f72a]
/usr/lib/dri/radeonsi_dri.so(+0x60b018) [0x7f676140b018]
/usr/lib/dri/radeonsi_dri.so(+0x18753f) [0x7f6760f8753f]
/usr/lib/dri/radeonsi_dri.so(+0xbe454) [0x7f6760ebe454]
/usr/lib/libGLX_mesa.so.0(+0x5397f) [0x7f679306e97f]
/usr/lib/libGLX_mesa.so.0(+0x3f58b) [0x7f679305a58b]
blender(+0x294a356) [0x55959afac356]
blender(+0x2949928) [0x55959afab928]
blender(+0x293f759) [0x55959afa1759]
blender(+0x294968b) [0x55959afab68b]
blender(+0x2946028) [0x55959afa8028]
blender(+0x293bca4) [0x55959af9dca4]
blender(+0x10167d2) [0x5595996787d2]
blender(+0x1016a1d) [0x559599678a1d]
blender(+0xfe0454) [0x559599642454]
blender(+0xff62de) [0x5595996582de]
blender(+0xffb9f4) [0x55959965d9f4]
blender(+0x88d681) [0x559598eef681]
/usr/lib/libc.so.6(+0x27cd0) [0x7f67b1158cd0]
/usr/lib/libc.so.6(__libc_start_main+0x8a) [0x7f67b1158d8a]
blender(+0x8b5e05) [0x559598f17e05]
# Python backtrace
I'll see if I can figure out how to edit the config files to remove the GPU.
Here's hipconfig:
HIP version : 5.7.31921-
== hipconfig
HIP_PATH : /opt/rocm
ROCM_PATH : /opt/rocm
HIP_COMPILER : clang
HIP_PLATFORM : amd
HIP_RUNTIME : rocclr
CPP_CONFIG : -D__HIP_PLATFORM_HCC__= -D__HIP_PLATFORM_AMD__= -I/opt/rocm/include -I/opt/rocm/llvm/lib/clang/17.0.0
== hip-clang
HIP_CLANG_PATH : /opt/rocm/llvm/bin
clang version 17.0.0
Target: x86_64-pc-linux-gnu
Thread model: posix
InstalledDir: /opt/rocm/llvm/bin
AOMP-16.0-45 (http://github.com/ROCm-Developer-Tools/aomp):
Source ID:16.0-45-6b875fb548b9ded0f07df02bc2af6e12568504a9
LLVM version 17.0.0git
Optimized build with assertions.
Default target: x86_64-pc-linux-gnu
Host CPU: znver3
Registered Targets:
amdgcn - AMD GCN GPUs
nvptx - NVIDIA PTX 32-bit
nvptx64 - NVIDIA PTX 64-bit
r600 - AMD GPUs HD2XXX-HD6XXX
x86 - 32-bit X86: Pentium-Pro and above
x86-64 - 64-bit X86: EM64T and AMD64
hip-clang-cxxflags : -isystem "/opt/rocm/include" -O3
hip-clang-ldflags : -O3 --hip-link --rtlib=compiler-rt -unwindlib=libgcc
=== Environment Variables
PATH=/usr/local/sbin:/usr/local/bin:/usr/bin:/opt/brlcad/bin:/root/.dotnet/tools:/usr/lib/jvm/default/bin:/usr/bin/site_perl:/usr/bin/vendor_perl:/usr/bin/core_perl
egrep: warning: egrep is obsolescent; using grep -E
== Linux Kernel
Hostname : honcho
Linux honcho 6.6.2-arch1-1 #1 SMP PREEMPT_DYNAMIC Mon, 20 Nov 2023 23:18:21 +0000 x86_64 GNU/Linux
LSB Version: n/a
Distributor ID: Arch
Description: Arch Linux
Release: rolling
Codename: n/a
Plus I had clinfo segfaulting until I removed opencl-clover-mesa and opencl-rusticl-mesa. And I have to run darktable with opencl turned off or it segfaults too.
Here's clinfo after the opencl mesa packages were removed:
Number of platforms 2
Platform Name Portable Computing Language
Platform Vendor The pocl project
Platform Version OpenCL 3.0 PoCL 4.0 Linux, Release, RELOC, SPIR, LLVM 16.0.6, SLEEF, DISTRO, POCL_DEBUG
Platform Profile FULL_PROFILE
Platform Extensions cl_khr_icd cl_pocl_content_size
Platform Extensions with Version cl_khr_icd 0x400000 (1.0.0)
cl_pocl_content_size 0x400000 (1.0.0)
Platform Numeric Version 0xc00000 (3.0.0)
Platform Extensions function suffix POCL
Platform Host timer resolution 0ns
Platform Name AMD Accelerated Parallel Processing
Platform Vendor Advanced Micro Devices, Inc.
Platform Version OpenCL 2.1 AMD-APP.dbg (3590.0)
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 Portable Computing Language
Number of devices 1
Device Name cpu-AMD Ryzen 9 5900X 12-Core Processor
Device Vendor AuthenticAMD
Device Vendor ID 0x1022
Device Version OpenCL 3.0 PoCL HSTR: cpu-x86_64-pc-linux-gnu-znver3
Device Numeric Version 0xc00000 (3.0.0)
Driver Version 4.0
Device OpenCL C Version OpenCL C 1.2 PoCL
Device OpenCL C all versions OpenCL C 0x400000 (1.0.0)
OpenCL C 0x401000 (1.1.0)
OpenCL C 0x402000 (1.2.0)
OpenCL C 0xc00000 (3.0.0)
Device OpenCL C features __opencl_c_3d_image_writes 0xc00000 (3.0.0)
__opencl_c_images 0xc00000 (3.0.0)
__opencl_c_atomic_order_acq_rel 0xc00000 (3.0.0)
__opencl_c_atomic_order_seq_cst 0xc00000 (3.0.0)
__opencl_c_atomic_scope_device 0xc00000 (3.0.0)
__opencl_c_program_scope_global_variables 0xc00000 (3.0.0)
__opencl_c_generic_address_space 0xc00000 (3.0.0)
__opencl_c_subgroups 0xc00000 (3.0.0)
__opencl_c_atomic_scope_all_devices 0xc00000 (3.0.0)
__opencl_c_read_write_images 0xc00000 (3.0.0)
__opencl_c_fp16 0xc00000 (3.0.0)
__opencl_c_fp64 0xc00000 (3.0.0)
__opencl_c_int64 0xc00000 (3.0.0)
Latest comfornace test passed v2022-04-19-01
Device Type CPU
Device Profile FULL_PROFILE
Device Available Yes
Compiler Available Yes
Linker Available Yes
Max compute units 24
Max clock frequency 4951MHz
Device Partition (core)
Max number of sub-devices 24
Supported partition types equally, by counts
Supported affinity domains (n/a)
Max work item dimensions 3
Max work item sizes 4096x4096x4096
Max work group size 4096
Preferred work group size multiple (device) 8
Preferred work group size multiple (kernel) 8
Max sub-groups per work group 128
Sub-group sizes (Intel) 1, 2, 4, 8, 16, 32, 64, 128, 256, 512
Preferred / native vector sizes
char 16 / 16
short 16 / 16
int 8 / 8
long 4 / 4
half 16 / 16 (cl_khr_fp16)
float 8 / 8
double 4 / 4 (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 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 31407841280 (29.25GiB)
Error Correction support No
Max memory allocation 8589934592 (8GiB)
Unified memory for Host and Device Yes
Shared Virtual Memory (SVM) capabilities (core)
Coarse-grained buffer sharing Yes
Fine-grained buffer sharing Yes
Fine-grained system sharing No
Atomics Yes
Minimum alignment for any data type 128 bytes
Alignment of base address 1024 bits (128 bytes)
Preferred alignment for atomics
SVM 64 bytes
Global 64 bytes
Local 64 bytes
Atomic memory capabilities relaxed, acquire/release, sequentially-consistent, work-group scope, device scope, all-devices scope
Atomic fence capabilities relaxed, acquire/release, sequentially-consistent, work-item scope, work-group scope, device scope
Max size for global variable 64000 (62.5KiB)
Preferred total size of global vars 524288 (512KiB)
Global Memory cache type Read/Write
Global Memory cache size 33554432 (32MiB)
Global Memory cache line size 64 bytes
Image support Yes
Max number of samplers per kernel 16
Max size for 1D images from buffer 536870912 pixels
Max 1D or 2D image array size 2048 images
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 128
Max number of read/write image args 128
Pipe support No
Max number of pipe args 0
Max active pipe reservations 0
Max pipe packet size 0
Local memory type Global
Local memory size 524288 (512KiB)
Max number of constant args 8
Max constant buffer size 524288 (512KiB)
Generic address space support Yes
Max size of kernel argument 1024
Queue properties (on host)
Out-of-order execution Yes
Profiling Yes
Device enqueue capabilities (n/a)
Queue properties (on device)
Out-of-order execution No
Profiling No
Preferred size 0
Max size 0
Max queues on device 0
Max events on device 0
Prefer user sync for interop Yes
Profiling timer resolution 1ns
Execution capabilities
Run OpenCL kernels Yes
Run native kernels Yes
Non-uniform work-groups No
Work-group collective functions No
Sub-group independent forward progress Yes
IL version (n/a)
ILs with version (n/a)
SPIR versions (n/a)
printf() buffer size 16777216 (16MiB)
Built-in kernels pocl.add.i8;org.khronos.openvx.scale_image.nn.u8;org.khronos.openvx.scale_image.bl.u8;org.khronos.openvx.tensor_convert_depth.wrap.u8.f32
Built-in kernels with version pocl.add.i8 0x402000 (1.2.0)
org.khronos.openvx.scale_image.nn.u8 0x402000 (1.2.0)
org.khronos.openvx.scale_image.bl.u8 0x402000 (1.2.0)
org.khronos.openvx.tensor_convert_depth.wrap.u8.f32 0x402000 (1.2.0)
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_3d_image_writes cl_khr_command_buffer cl_khr_subgroups cl_intel_unified_shared_memory cl_khr_subgroup_ballot cl_khr_subgroup_shuffle cl_intel_subgroups cl_intel_required_subgroup_size cl_khr_spir cl_khr_fp16 cl_khr_fp64 cl_khr_int64_base_atomics cl_khr_int64_extended_atomics
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_3d_image_writes 0x400000 (1.0.0)
cl_khr_command_buffer 0x9000 (0.9.0)
cl_khr_subgroups 0x400000 (1.0.0)
cl_intel_unified_shared_memory 0x400000 (1.0.0)
cl_khr_subgroup_ballot 0x400000 (1.0.0)
cl_khr_subgroup_shuffle 0x400000 (1.0.0)
cl_intel_subgroups 0x400000 (1.0.0)
cl_intel_required_subgroup_size 0x400000 (1.0.0)
cl_khr_spir 0x801000 (2.1.0)
cl_khr_fp16 0x400000 (1.0.0)
cl_khr_fp64 0x400000 (1.0.0)
cl_khr_int64_base_atomics 0x400000 (1.0.0)
cl_khr_int64_extended_atomics 0x400000 (1.0.0)
Platform Name AMD Accelerated Parallel Processing
Number of devices 1
Device Name gfx1102
Device Vendor Advanced Micro Devices, Inc.
Device Vendor ID 0x1002
Device Version OpenCL 2.0
Driver Version 3590.0 (HSA1.1,LC)
Device OpenCL C Version OpenCL C 2.0
Device Type GPU
Device Board Name (AMD) AMD Radeon RX 7600
Device PCI-e ID (AMD) 0x7480
Device Topology (AMD) PCI-E, 0000:0d:00.0
Device Profile FULL_PROFILE
Device Available Yes
Compiler Available Yes
Linker Available Yes
Max compute units 16
SIMD per compute unit (AMD) 4
SIMD width (AMD) 32
SIMD instruction width (AMD) 1
Max clock frequency 2250MHz
Graphics IP (AMD) 11.0
Device Partition (core)
Max number of sub-devices 16
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) <getWGsizes:1504: create kernel : error -6>
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 8573157376 (7.984GiB)
Global free memory (AMD) 8321024 (7.936GiB) 8321024 (7.936GiB)
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 7287183768 (6.787GiB)
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 7287183768 (6.787GiB)
Preferred total size of global vars 8573157376 (7.984GiB)
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 2992216472 (2.787GiB)
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 7287183768 (6.787GiB)
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 (Wed Dec 31 16:00:00 1969)
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) 16
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 [POCL]
clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT) Success (1)
Platform Name Portable Computing Language
Device Name cpu-AMD Ryzen 9 5900X 12-Core Processor
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) Success (1)
Platform Name Portable Computing Language
Device Name cpu-AMD Ryzen 9 5900X 12-Core Processor
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) Success (1)
Platform Name Portable Computing Language
Device Name cpu-AMD Ryzen 9 5900X 12-Core Processor
NOTE: your OpenCL library only supports OpenCL 2.2,
but some installed platforms support OpenCL 3.0.
Programs using 3.0 features may crash
or behave unexpectedly
And running clinfo sends the GPU workload to 100%, and makes the OS hang on a re-boot. So the reset button has been getting a workout today.
Both hip and opencl were running fine until just recently, but I'm not sure if it was the recent rocm updates that did this yet. Or maybe a 6.6 regression? Or mesa?
Rolling releases! This is actually why I sorta like them.
Last edited by glenjo (2023-11-23 05:41:15)
Offline
There appear to be severe issues between blender , rocm , llvm and mesa on archlinux , see https://gitlab.archlinux.org/archlinux/ … -/issues/2
Disliking systemd intensely, but not satisfied with alternatives so focusing on taming systemd.
(A works at time B) && (time C > time B ) ≠ (A works at time C)
Offline
I have the same problem. Everything was working a couple days ago, made pacman -Syu, and now the gpu in Blender is broken. And also Stable Diffusion is dead too.... (rx 6500 xt)
Last edited by Cha14ka (2023-12-08 08:49:50)
Offline
Blender 17:4.0.1-7 has fixed the segfault, but the issues with using the GPU with blender (and OpenCL issues) remain (even with latest stable kernel).
I'm waiting for the mesa update and will report again.
Offline
Same here (AMD 5700XT)
I am tired of using rocm until it gives problems, then switching to opencl-amd until it gives problems, and so on...
Offline
Same here on 6600xt
Offline
Just a quick update. Mesa 23.3.1 is out, but installing opencl-rusticl-mesa and opencl-clover-mesa cause clinfo to segfault.
Further update. Switched to ROCm 6.0.0 from the AUR, upgraded to opencl-amd, and opencl-amd-dev with the same results as above.
Last edited by glenjo (2023-12-21 20:49:29)
Offline
Maybe this info is useful for someone, work configuration for me:
-> Open AMDGPU driver is used, all packages except following are up to date on current date.
Downdraded packages:
-> Following ROCm packages downgraded to package version 5.6.1-1:
comgr, hip-runtime-amd, hipblas, hipcub, hipfft, hipsolver, hipsparse, hsa-amd-aqlprofile-bin, hsa-rocr, hsakmt-roct, miopen-hip, rccl, rocalution, rocblas,
rocfft, rocm-clang-ocl, rocm-cmake, rocm-core, rocm-device-libs, rocm-hip-libraries, rocm-hip-runtime, rocm-hip-sdk, rocm-language-runtime, rocm-llvm,
rocm-opencl-runtime, rocm-smi-lib, rocminfo, rocprim, rocrand, rocsolver, rocsparse, rocthrust, roctracer
I'm not sure that all of these ROCm packages are required for blender
-> Following blender related packages are downgraded:
blender: 17:4.0.2-4
opencolorio: 2.2.1-13
openimageio: 2.4.17.0-1
openshadinglanguage: 1.12.14.0-1
usd: 23.11-3
The latest blender package(17:4.0.2-6) is broken to use of any ROCm backend for a rendering in my case
Last edited by Nickola (2024-01-07 18:34:25)
Offline
Thanks Nickola, I'm waiting for ROCm 6.0 to drop and I'll see how that works and report.
Offline
Blender + ROCm 6.0 totally crashed my computer (RESUIB didn't help) when I was trying to find HIP devices on Blender config. Later I tried mesa 24.0 rc2 with no success.
To avoid hardcore hangs, this kernel patch is needed: https://lore.kernel.org/amd-gfx/2024010 … gmail.com/
After that patch I can find my AMD-HIP device on Blender but GPU render fails: HIP hipInit: Invalid device.
At least my PC didn't crash anymore.
Excuse my poor English.
Offline
For me the patch works fully (blender render, clpeak) since kernel 6.7 - 6.6.x didn't work
As commented for the patch somewhere else, it only works for some...
Last edited by jl2 (2024-01-23 15:01:25)
Why I run Arch? To "BTW I run Arch" the guy one grade younger.
And to let my siblings and cousins laugh at Arsch Linux...
Offline
This problem is fixed since 6.7.2 , the commit which agapito's patch reverts has been reverted upstream.
Why I run Arch? To "BTW I run Arch" the guy one grade younger.
And to let my siblings and cousins laugh at Arsch Linux...
Offline
I'm now running kernel 6.7.3, mesa 23.3.5, and ROCm 5.7.1 (pretty much "stock" Arch) and can run blender 4.0.2 without locking up. but using the GPU for rendering is locked out. OpenCl is working for darktable 4.6.0 except that as soon as the GPU is used, it started running at 100% and does not stop until darktable is killed. Still waiting for ROCm 6.0.x to come out of testing.
Offline
So the ROCm updates are out today, and after installing these, I did some more testing.
Blender 4.0.2 - I can select the GPU for rendering with Cycles, but blender crashes while rendering with the following error: Memory access fault by GPU node-1 (Agent handle: 0x7d415472f600) on address (nil). Reason: Page not present or supervisor privilege.
Darktable 4.6.0 - Runs fine except it ramps the GPU to 100% when going to "darkroom" to edit photos.
DaVinci Resolve 18.6.4 - Runs fine except it ramps the GPU to 100%
Here is clinfo:
clinfo
Number of platforms 1
Platform Name AMD Accelerated Parallel Processing
Platform Vendor Advanced Micro Devices, Inc.
Platform Version OpenCL 2.1 AMD-APP.dbg (3602.0)
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 AMD Accelerated Parallel Processing
Number of devices 1
Device Name gfx1102
Device Vendor Advanced Micro Devices, Inc.
Device Vendor ID 0x1002
Device Version OpenCL 2.0
Driver Version 3602.0 (HSA1.1,LC)
Device OpenCL C Version OpenCL C 2.0
Device Type GPU
Device Board Name (AMD) AMD Radeon RX 7600
Device PCI-e ID (AMD) 0x7480
Device Topology (AMD) PCI-E, 0000:0d:00.0
Device Profile FULL_PROFILE
Device Available Yes
Compiler Available Yes
Linker Available Yes
Max compute units 16
SIMD per compute unit (AMD) 4
SIMD width (AMD) 32
SIMD instruction width (AMD) 1
Max clock frequency 2250MHz
Graphics IP (AMD) 11.0
Device Partition (core)
Max number of sub-devices 16
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 8573157376 (7.984GiB)
Global free memory (AMD) 8175616 (7.797GiB) 8175616 (7.797GiB)
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 7287183768 (6.787GiB)
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 7287183768 (6.787GiB)
Preferred total size of global vars 8573157376 (7.984GiB)
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 2992216472 (2.787GiB)
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 7287183768 (6.787GiB)
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 (Wed Dec 31 16:00:00 1969)
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) 16
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 [AMD]
clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT) Success (1)
Platform Name AMD Accelerated Parallel Processing
Device Name gfx1102
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) No devices found in platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU) Success (1)
Platform Name AMD Accelerated Parallel Processing
Device Name gfx1102
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 AMD Accelerated Parallel Processing
Device Name gfx1102
Here is hipconfig:
/opt/rocm/bin/hipconfig --full
HIP version : 6.0.32830-
== hipconfig
HIP_PATH : /opt/rocm
ROCM_PATH : /opt/rocm
HIP_COMPILER : clang
HIP_PLATFORM : amd
HIP_RUNTIME : rocclr
CPP_CONFIG : -D__HIP_PLATFORM_HCC__= -D__HIP_PLATFORM_AMD__= -I/opt/rocm/include -I/opt/rocm/lib/llvm/lib/clang/17.0.0
== hip-clang
HIP_CLANG_PATH : /opt/rocm/llvm/bin
clang version 17.0.0
Target: x86_64-pc-linux-gnu
Thread model: posix
InstalledDir: /opt/rocm/llvm/bin
AOMP-16.0-45 (http://github.com/ROCm-Developer-Tools/aomp):
Source ID:16.0-45-6b875fb548b9ded0f07df02bc2af6e12568504a9
LLVM version 17.0.0git
Optimized build with assertions.
Default target: x86_64-pc-linux-gnu
Host CPU: znver3
Registered Targets:
amdgcn - AMD GCN GPUs
nvptx - NVIDIA PTX 32-bit
nvptx64 - NVIDIA PTX 64-bit
r600 - AMD GPUs HD2XXX-HD6XXX
x86 - 32-bit X86: Pentium-Pro and above
x86-64 - 64-bit X86: EM64T and AMD64
hip-clang-cxxflags : -isystem "/opt/rocm/include" -O3
hip-clang-ldflags : --driver-mode=g++ -O3 --hip-link --rtlib=compiler-rt -unwindlib=libgcc
=== Environment Variables
PATH=/usr/local/sbin:/usr/local/bin:/usr/bin:/opt/brlcad/bin:/usr/lib/jvm/default/bin:/usr/bin/site_perl:/usr/bin/vendor_perl:/usr/bin/core_perl
egrep: warning: egrep is obsolescent; using grep -E
== Linux Kernel
Hostname : honcho
Linux honcho 6.7.3-arch1-2 #1 SMP PREEMPT_DYNAMIC Fri, 02 Feb 2024 17:03:55 +0000 x86_64 GNU/Linux
LSB Version: n/a
Distributor ID: Arch
Description: Arch Linux
Release: rolling
Codename: n/a
So I realize that ROCm does not support this GPU in Linux, but it does in Windows so I'm sorta hoping AMD gets to Linux support sooner since it was working fine before in earlier versions of ROCm. Plus, I don't have Clover or Rusticl installed so I will install those (separately) and do more opencl testing.
Offline
Same here (RX5700XT).
Offline
Well it broke here with rocm 6, so I downgraded again, dunno if it's the x86_64-v3 repo I have, I'll test that later.
Why I run Arch? To "BTW I run Arch" the guy one grade younger.
And to let my siblings and cousins laugh at Arsch Linux...
Offline
rocm has been broken for long time in Arch repos,
the last version that works (on both rx6800 and rx480 -- the latest not in blender, but sure in pytorch) is 5.6.1
I have tested 5.7.1 and rolled back -- I am not upgrading to rocm 6.0 in Arch repos until somebody confirms that it actually works
I am on 5.6.1, latest kernel (6.7.4-zen1-1-zen) and blender 4.0.2-10
See bug report closed but issue never addressed:
https://bugs.archlinux.org/task/80326#comment223998
Same bug on the new portal:
https://gitlab.archlinux.org/archlinux/ … -/issues/2
Offline
rocm has been broken for long time in Arch repos,
the last version that works (on both rx6800 and rx480 -- the latest not in blender, but sure in pytorch) is 5.6.1
I have tested 5.7.1 and rolled back -- I am not upgrading to rocm 6.0 in Arch repos until somebody confirms that it actually worksI am on 5.6.1, latest kernel (6.7.4-zen1-1-zen) and blender 4.0.2-10
See bug report closed but issue never addressed:
https://bugs.archlinux.org/task/80326#comment223998Same bug on the new portal:
https://gitlab.archlinux.org/archlinux/ … -/issues/2
I have to correct the above,
Actually blender 4.0.2-10 crashes with Cycles and HIP (rocm 5.6.1) with the following error:
Memory access fault by GPU node-1 (Agent handle: 0x7abc10097e00) on address 0x7ab9ee79f000. Reason: Page not present or supervisor privilege.
zsh: IOT instruction (core dumped) blender
Blender 4.0.2-9 works fine
Offline
Cellstije seeems to be right about ROCm. I ended up getting darkable and DaVinci Resolve running well by removing the rocm-opencl-runtime (and every other rocm package that required it) and installing opencl-rusticl-mesa. This doesn't fix blender since it uses HIP.
Offline