You are not logged in.
After some months I performed a full system update today, and Darktable doesn't start anymore. I don't know how to fix it, and neither how to debug it, whether this should be reported to the Darktable maintainers, or whether it's OpenCL fault, or whether I am missing something (most probably). Before upgrading Darktable was running fine with OpenCL support. Now I get the following output:
$ darktable -d opencl
0.067941 [opencl_init] opencl related configuration options:
0.067957 [opencl_init]
0.067962 [opencl_init] opencl: 1
0.067965 [opencl_init] opencl_scheduling_profile: 'default'
0.067972 [opencl_init] opencl_library: ''
0.067977 [opencl_init] opencl_memory_requirement: 768
0.067982 [opencl_init] opencl_memory_headroom: 400
0.068000 [opencl_init] opencl_device_priority: '*/!0,*/*/*/!0,*'
0.068005 [opencl_init] opencl_mandatory_timeout: 200
0.068011 [opencl_init] opencl_size_roundup: 16
0.068014 [opencl_init] opencl_async_pixelpipe: 0
0.068019 [opencl_init] opencl_synch_cache: active module
0.068024 [opencl_init] opencl_number_event_handles: 25
0.068029 [opencl_init] opencl_micro_nap: 1000
0.068034 [opencl_init] opencl_use_pinned_memory: 0
0.068039 [opencl_init] opencl_use_cpu_devices: 0
0.068044 [opencl_init] opencl_avoid_atomics: 0
0.068048 [opencl_init]
0.068268 [opencl_init] found opencl runtime library 'libOpenCL'
0.068296 [opencl_init] opencl library 'libOpenCL' found on your system and loaded
0.273922 [opencl_init] found 1 platform
0.273944 [opencl_init] found 1 device
0.273988 [opencl_init] device 0 `Intel(R) Gen9 HD Graphics NEO' supports image sizes of 16384 x 16384
0.273995 [opencl_init] device 0 `Intel(R) Gen9 HD Graphics NEO' allows GPU memory allocations of up to 2948MB
[opencl_init] device 0: Intel(R) Gen9 HD Graphics NEO
GLOBAL_MEM_SIZE: 5896MB
MAX_WORK_GROUP_SIZE: 256
MAX_WORK_ITEM_DIMENSIONS: 3
MAX_WORK_ITEM_SIZES: [ 256 256 256 ]
DRIVER_VERSION: 1.0.0
DEVICE_VERSION: OpenCL 2.1 NEO
0.274063 [opencl_init] options for OpenCL compiler: -w -DINTEL=1 -I"/usr/share/darktable/kernels"
0.274184 [opencl_init] compiling program `demosaic_ppg.cl' ..
0.274388 [opencl_load_program] loaded cached binary program from file '/home/leonixyz/.cache/darktable/cached_kernels_for_IntelRGen9HDGraphicsNEO_100/demosaic_ppg.cl.bin' MD5: '77b1bcd7d7d499e6a1569d0f188ee6b7'
0.274395 [opencl_load_program] successfully loaded program from '/usr/share/darktable/kernels/demosaic_ppg.cl' MD5: '77b1bcd7d7d499e6a1569d0f188ee6b7'
0.274788 [opencl_build_program] successfully built program
0.274794 [opencl_build_program] BUILD STATUS: 0
0.274797 BUILD LOG:
0.274799
0.274805 [opencl_init] compiling program `atrous.cl' ..
0.274847 [opencl_fopen_stat] could not open file `/home/leonixyz/.cache/darktable/cached_kernels_for_IntelRGen9HDGraphicsNEO_100/atrous.cl.bin'!
0.274854 [opencl_load_program] could not load cached binary program, trying to compile source
0.274874 [opencl_load_program] successfully loaded program from '/usr/share/darktable/kernels/atrous.cl' MD5: '877e4325f34824dd987075b3b81da75d'
an error occurred while trying to execute gdb. please check if gdb is installed on your system.
backtrace written to /tmp/darktable_bt_64L2R0.txt
[1] 12529 segmentation fault (core dumped) darktable -d openclThese are the OpenCL related packages that I have installed atm
$ pacman -Ss opencl | grep installed
extra/ocl-icd 2.2.12-4 [installed]
community/intel-compute-runtime 20.30.17454-1 [installed]
community/intel-graphics-compiler 1:1.0.4427-1 [installed]
community/intel-opencl-clang 10.0.0.1-1 [installed]My graphic card
00:02.0 VGA compatible controller: Intel Corporation Skylake GT2 [HD Graphics 520] (rev 07) (prog-if 00 [VGA controller])
Subsystem: Lenovo Device 2238
Flags: bus master, fast devsel, latency 0, IRQ 125
Memory at f0000000 (64-bit, non-prefetchable) [size=16M]
Memory at e0000000 (64-bit, prefetchable) [size=256M]
I/O ports at e000 [size=64]
Expansion ROM at 000c0000 [virtual] [disabled] [size=128K]
Capabilities: [40] Vendor Specific Information: Len=0c <?>
Capabilities: [70] Express Root Complex Integrated Endpoint, MSI 00
Capabilities: [ac] MSI: Enable+ Count=1/1 Maskable- 64bit-
Capabilities: [d0] Power Management version 2
Capabilities: [100] Process Address Space ID (PASID)
Capabilities: [200] Address Translation Service (ATS)
Capabilities: [300] Page Request Interface (PRI)
Kernel driver in use: i915
Kernel modules: i915If I run darktable --disable-opencl the program starts and works ok, and this can be my workaround atm, but It'd be great if I can get OpenCL back working.
I tried installing darktable-git but I run into the same problem.
What should I do? Report to the Darktable folks? Use the workaround waiting for an update of Darktable or OpenCL?
Thanks in advance
Offline
pacman -Qs opencl would have saved you a pipe / grep construction .
Please post the full output of clinfo (install clinfo if it's not present yet)
Disliking systemd intensely, but not satisfied with alternatives so focusing on taming systemd.
clean chroot building not flexible enough ?
Try clean chroot manager by graysky
Online
Please post the full output of clinfo
Hi Lone_Wolf, thanks for your support.
Number of platforms 1
Platform Name Intel(R) OpenCL HD Graphics
Platform Vendor Intel(R) Corporation
Platform Version OpenCL 2.1
Platform Profile FULL_PROFILE
Platform Extensions cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_icd cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_intel_subgroups cl_intel_required_subgroup_size cl_intel_subgroups_short cl_khr_spir cl_intel_accelerator cl_intel_driver_diagnostics cl_khr_priority_hints cl_khr_throttle_hints cl_khr_create_command_queue cl_intel_subgroups_char cl_intel_subgroups_long cl_khr_il_program cl_khr_fp64 cl_khr_subgroups cl_intel_spirv_device_side_avc_motion_estimation cl_intel_spirv_media_block_io cl_intel_spirv_subgroups cl_khr_spirv_no_integer_wrap_decoration cl_intel_unified_shared_memory_preview cl_khr_mipmap_image cl_khr_mipmap_image_writes cl_intel_planar_yuv cl_intel_packed_yuv cl_intel_motion_estimation cl_intel_device_side_avc_motion_estimation cl_intel_advanced_motion_estimation cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_image2d_from_buffer cl_khr_depth_images cl_intel_media_block_io cl_khr_3d_image_writes cl_intel_va_api_media_sharing
Platform Host timer resolution 1ns
Platform Extensions function suffix INTEL
Platform Name Intel(R) OpenCL HD Graphics
Number of devices 1
Device Name Intel(R) Gen9 HD Graphics NEO
Device Vendor Intel(R) Corporation
Device Vendor ID 0x8086
Device Version OpenCL 2.1 NEO
Driver Version 1.0.0
Device OpenCL C Version OpenCL C 2.0
Device Type GPU
Device Profile FULL_PROFILE
Device Available Yes
Compiler Available Yes
Linker Available Yes
Max compute units 24
Max clock frequency 1000MHz
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 256x256x256
Max work group size 256
Preferred work group size multiple 32
Max sub-groups per work group 32
Sub-group sizes (Intel) 8, 16, 32
Preferred / native vector sizes
char 16 / 16
short 8 / 8
int 4 / 4
long 1 / 1
half 8 / 8 (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 6182445056 (5.758GiB)
Error Correction support No
Max memory allocation 3091222528 (2.879GiB)
Unified memory for Host and Device Yes
Shared Virtual Memory (SVM) capabilities (core)
Coarse-grained buffer sharing Yes
Fine-grained buffer sharing No
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 64 bytes
Global 64 bytes
Local 64 bytes
Max size for global variable 65536 (64KiB)
Preferred total size of global vars 3091222528 (2.879GiB)
Global Memory cache type Read/Write
Global Memory cache size 524288 (512KiB)
Global Memory cache line size 64 bytes
Image support Yes
Max number of samplers per kernel 16
Max size for 1D images from buffer 193201408 pixels
Max 1D or 2D image array size 2048 images
Base address alignment for 2D image buffers 4 bytes
Pitch alignment for 2D image buffers 4 pixels
Max 2D image size 16384x16384 pixels
Max planar YUV image size 16384x16352 pixels
Max 3D image size 16384x16384x2048 pixels
Max number of read image args 128
Max number of write image args 128
Max number of read/write image args 128
Max number of pipe args 16
Max active pipe reservations 1
Max pipe packet size 1024
Local memory type Local
Local memory size 65536 (64KiB)
Max number of constant args 8
Max constant buffer size 3091222528 (2.879GiB)
Max size of kernel argument 2048 (2KiB)
Queue properties (on host)
Out-of-order execution Yes
Profiling Yes
Queue properties (on device)
Out-of-order execution Yes
Profiling Yes
Preferred size 131072 (128KiB)
Max size 67108864 (64MiB)
Max queues on device 1
Max events on device 1024
Prefer user sync for interop Yes
Profiling timer resolution 83ns
Execution capabilities
Run OpenCL kernels Yes
Run native kernels No
Sub-group independent forward progress Yes
IL version SPIR-V_1.2
SPIR versions 1.2
printf() buffer size 4194304 (4MiB)
Built-in kernels block_motion_estimate_intel;block_advanced_motion_estimate_check_intel;block_advanced_motion_estimate_bidirectional_check_intel;
Motion Estimation accelerator version (Intel) 2
Device-side AVC Motion Estimation version 1
Supports texture sampler use Yes
Supports preemption No
Device Extensions cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_icd cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_intel_subgroups cl_intel_required_subgroup_size cl_intel_subgroups_short cl_khr_spir cl_intel_accelerator cl_intel_driver_diagnostics cl_khr_priority_hints cl_khr_throttle_hints cl_khr_create_command_queue cl_intel_subgroups_char cl_intel_subgroups_long cl_khr_il_program cl_khr_fp64 cl_khr_subgroups cl_intel_spirv_device_side_avc_motion_estimation cl_intel_spirv_media_block_io cl_intel_spirv_subgroups cl_khr_spirv_no_integer_wrap_decoration cl_intel_unified_shared_memory_preview cl_khr_mipmap_image cl_khr_mipmap_image_writes cl_intel_planar_yuv cl_intel_packed_yuv cl_intel_motion_estimation cl_intel_device_side_avc_motion_estimation cl_intel_advanced_motion_estimation cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_image2d_from_buffer cl_khr_depth_images cl_intel_media_block_io cl_khr_3d_image_writes cl_intel_va_api_media_sharing
NULL platform behavior
clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...) Intel(R) OpenCL HD Graphics
clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...) Success [INTEL]
clCreateContext(NULL, ...) [default] Success [INTEL]
clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT) Success (1)
Platform Name Intel(R) OpenCL HD Graphics
Device Name Intel(R) Gen9 HD Graphics NEO
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) No devices found in platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU) Success (1)
Platform Name Intel(R) OpenCL HD Graphics
Device Name Intel(R) Gen9 HD Graphics NEO
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 Intel(R) OpenCL HD Graphics
Device Name Intel(R) Gen9 HD Graphics NEO
ICD loader properties
ICD loader Name OpenCL ICD Loader
ICD loader Vendor OCL Icd free software
ICD loader Version 2.2.12
ICD loader Profile OpenCL 2.2Offline
I can report that this is happening to me as well.
carlos echenique
ce.photography
Offline
clinfo output looks fine and does indicate there's "image support" .
leonixyz, run and post output of
$ darktable-cltest@etrigan63 : to verify you do have the same issue, please post the above and clinfo output from your system.
Disliking systemd intensely, but not satisfied with alternatives so focusing on taming systemd.
clean chroot building not flexible enough ?
Try clean chroot manager by graysky
Online
Same issue here, it's a few weeks now. I have an Optimus setup, working with optimus-manager.
I have tested both the default and the -lts kernel, and tried rebuilding darktable manually to no avail. Running without OpenCL support works around the issue, but it makes the program so slow it's really hard to be productive.
[bardo@ged 16:03 ~]$ clinfo
Number of platforms 2
Platform Name Intel(R) OpenCL HD Graphics
Platform Vendor Intel(R) Corporation
Platform Version OpenCL 2.1
Platform Profile FULL_PROFILE
Platform Extensions cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_icd cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_intel_subgroups cl_intel_required_subgroup_size cl_intel_subgroups_short cl_khr_spir cl_intel_accelerator cl_intel_driver_diagnostics cl_khr_priority_hints cl_khr_throttle_hints cl_khr_create_command_queue cl_intel_subgroups_char cl_intel_subgroups_long cl_khr_il_program cl_khr_fp64 cl_khr_subgroups cl_intel_spirv_device_side_avc_motion_estimation cl_intel_spirv_media_block_io cl_intel_spirv_subgroups cl_khr_spirv_no_integer_wrap_decoration cl_intel_unified_shared_memory_preview cl_khr_mipmap_image cl_khr_mipmap_image_writes cl_intel_planar_yuv cl_intel_packed_yuv cl_intel_motion_estimation cl_intel_device_side_avc_motion_estimation cl_intel_advanced_motion_estimation cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_image2d_from_buffer cl_khr_depth_images cl_intel_media_block_io cl_khr_3d_image_writes cl_intel_va_api_media_sharing
Platform Host timer resolution 1ns
Platform Extensions function suffix INTEL
Platform Name NVIDIA CUDA
Platform Vendor NVIDIA Corporation
Platform Version OpenCL 1.2 CUDA 11.1.70
Platform Profile FULL_PROFILE
Platform Extensions 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_fp64 cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_copy_opts cl_nv_create_buffer cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_device_uuid
Platform Extensions function suffix NV
Platform Name Intel(R) OpenCL HD Graphics
Number of devices 1
Device Name Intel(R) Gen9 HD Graphics NEO
Device Vendor Intel(R) Corporation
Device Vendor ID 0x8086
Device Version OpenCL 2.1 NEO
Driver Version 1.0.0
Device OpenCL C Version OpenCL C 2.0
Device Type GPU
Device Profile FULL_PROFILE
Device Available Yes
Compiler Available Yes
Linker Available Yes
Max compute units 24
Max clock frequency 1150MHz
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 256x256x256
Max work group size 256
Preferred work group size multiple 32
Max sub-groups per work group 32
Sub-group sizes (Intel) 8, 16, 32
Preferred / native vector sizes
char 16 / 16
short 8 / 8
int 4 / 4
long 1 / 1
half 8 / 8 (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 13128458240 (12.23GiB)
Error Correction support No
Max memory allocation 4294959104 (4GiB)
Unified memory for Host and Device Yes
Shared Virtual Memory (SVM) capabilities (core)
Coarse-grained buffer sharing Yes
Fine-grained buffer sharing No
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 64 bytes
Global 64 bytes
Local 64 bytes
Max size for global variable 65536 (64KiB)
Preferred total size of global vars 4294959104 (4GiB)
Global Memory cache type Read/Write
Global Memory cache size 524288 (512KiB)
Global Memory cache line size 64 bytes
Image support Yes
Max number of samplers per kernel 16
Max size for 1D images from buffer 268434944 pixels
Max 1D or 2D image array size 2048 images
Base address alignment for 2D image buffers 4 bytes
Pitch alignment for 2D image buffers 4 pixels
Max 2D image size 16384x16384 pixels
Max planar YUV image size 16384x16352 pixels
Max 3D image size 16384x16384x2048 pixels
Max number of read image args 128
Max number of write image args 128
Max number of read/write image args 128
Max number of pipe args 16
Max active pipe reservations 1
Max pipe packet size 1024
Local memory type Local
Local memory size 65536 (64KiB)
Max number of constant args 8
Max constant buffer size 4294959104 (4GiB)
Max size of kernel argument 2048 (2KiB)
Queue properties (on host)
Out-of-order execution Yes
Profiling Yes
Queue properties (on device)
Out-of-order execution Yes
Profiling Yes
Preferred size 131072 (128KiB)
Max size 67108864 (64MiB)
Max queues on device 1
Max events on device 1024
Prefer user sync for interop Yes
Profiling timer resolution 83ns
Execution capabilities
Run OpenCL kernels Yes
Run native kernels No
Sub-group independent forward progress Yes
IL version SPIR-V_1.2
SPIR versions 1.2
printf() buffer size 4194304 (4MiB)
Built-in kernels block_motion_estimate_intel;block_advanced_motion_estimate_check_intel;block_advanced_motion_estimate_bidirectional_check_intel;
Motion Estimation accelerator version (Intel) 2
Device-side AVC Motion Estimation version 1
Supports texture sampler use Yes
Supports preemption No
Device Extensions cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_icd cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_intel_subgroups cl_intel_required_subgroup_size cl_intel_subgroups_short cl_khr_spir cl_intel_accelerator cl_intel_driver_diagnostics cl_khr_priority_hints cl_khr_throttle_hints cl_khr_create_command_queue cl_intel_subgroups_char cl_intel_subgroups_long cl_khr_il_program cl_khr_fp64 cl_khr_subgroups cl_intel_spirv_device_side_avc_motion_estimation cl_intel_spirv_media_block_io cl_intel_spirv_subgroups cl_khr_spirv_no_integer_wrap_decoration cl_intel_unified_shared_memory_preview cl_khr_mipmap_image cl_khr_mipmap_image_writes cl_intel_planar_yuv cl_intel_packed_yuv cl_intel_motion_estimation cl_intel_device_side_avc_motion_estimation cl_intel_advanced_motion_estimation cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_image2d_from_buffer cl_khr_depth_images cl_intel_media_block_io cl_khr_3d_image_writes cl_intel_va_api_media_sharing
Platform Name NVIDIA CUDA
Number of devices 1
Device Name GeForce GTX 1650
Device Vendor NVIDIA Corporation
Device Vendor ID 0x10de
Device Version OpenCL 1.2 CUDA
Driver Version 455.23.04
Device OpenCL C Version OpenCL C 1.2
Device Type GPU
Device Topology (NV) PCI-E, 01:00.0
Device Profile FULL_PROFILE
Device Available Yes
Compiler Available Yes
Linker Available Yes
Max compute units 16
Max clock frequency 1560MHz
Compute Capability (NV) 7.5
Device Partition (core)
Max number of sub-devices 1
Supported partition types None
Supported affinity domains (n/a)
Max work item dimensions 3
Max work item sizes 1024x1024x64
Max work group size 1024
Preferred work group size multiple 32
Warp size (NV) 32
Preferred / native vector sizes
char 1 / 1
short 1 / 1
int 1 / 1
long 1 / 1
half 0 / 0 (n/a)
float 1 / 1
double 1 / 1 (cl_khr_fp64)
Half-precision Floating-point support (n/a)
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 4104323072 (3.822GiB)
Error Correction support No
Max memory allocation 1026080768 (978.5MiB)
Unified memory for Host and Device No
Integrated memory (NV) No
Minimum alignment for any data type 128 bytes
Alignment of base address 4096 bits (512 bytes)
Global Memory cache type Read/Write
Global Memory cache size 524288 (512KiB)
Global Memory cache line size 128 bytes
Image support Yes
Max number of samplers per kernel 32
Max size for 1D images from buffer 268435456 pixels
Max 1D or 2D image array size 2048 images
Max 2D image size 32768x32768 pixels
Max 3D image size 16384x16384x16384 pixels
Max number of read image args 256
Max number of write image args 32
Local memory type Local
Local memory size 49152 (48KiB)
Registers per block (NV) 65536
Max number of constant args 9
Max constant buffer size 65536 (64KiB)
Max size of kernel argument 4352 (4.25KiB)
Queue properties
Out-of-order execution Yes
Profiling Yes
Prefer user sync for interop No
Profiling timer resolution 1000ns
Execution capabilities
Run OpenCL kernels Yes
Run native kernels No
Kernel execution timeout (NV) Yes
Concurrent copy and kernel execution (NV) Yes
Number of async copy engines 3
printf() buffer size 1048576 (1024KiB)
Built-in kernels (n/a)
Device Extensions 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_fp64 cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_copy_opts cl_nv_create_buffer cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_device_uuid
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 [INTEL]
clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT) Success (1)
Platform Name Intel(R) OpenCL HD Graphics
Device Name Intel(R) Gen9 HD Graphics NEO
clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU) No devices found in platform
clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU) Success (1)
Platform Name Intel(R) OpenCL HD Graphics
Device Name Intel(R) Gen9 HD Graphics NEO
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 Intel(R) OpenCL HD Graphics
Device Name Intel(R) Gen9 HD Graphics NEO
NOTE: your OpenCL library only supports OpenCL 2.0,
but some installed platforms support OpenCL 2.1.
Programs using 2.1 features may crash
or behave unexpectedly
[bardo@ged 16:11 ~]$ [bardo@ged 16:11 ~]$ darktable-cltest
0.031334 [opencl_init] opencl related configuration options:
0.031342 [opencl_init]
0.031343 [opencl_init] opencl: 0
0.031367 [opencl_init] opencl_scheduling_profile: 'multiple GPUs'
0.031369 [opencl_init] opencl_library: ''
0.031371 [opencl_init] opencl_memory_requirement: 768
0.031374 [opencl_init] opencl_memory_headroom: 400
0.031377 [opencl_init] opencl_device_priority: '*/!0,*/*/*'
0.031403 [opencl_init] opencl_mandatory_timeout: 200
0.031406 [opencl_init] opencl_size_roundup: 16
0.031407 [opencl_init] opencl_async_pixelpipe: 0
0.031409 [opencl_init] opencl_synch_cache: active module
0.031412 [opencl_init] opencl_number_event_handles: 25
0.031414 [opencl_init] opencl_micro_nap: 1000
0.031415 [opencl_init] opencl_use_pinned_memory: 0
0.031417 [opencl_init] opencl_use_cpu_devices: 0
0.031420 [opencl_init] opencl_avoid_atomics: 0
0.031422 [opencl_init]
0.031591 [opencl_init] found opencl runtime library 'libOpenCL'
0.031627 [opencl_init] opencl library 'libOpenCL' found on your system and loaded
0.215333 [opencl_init] found 2 platforms
0.215349 [opencl_init] found 2 devices
0.215365 [opencl_init] device 0 `Intel(R) Gen9 HD Graphics NEO' supports image sizes of 16384 x 16384
0.215367 [opencl_init] device 0 `Intel(R) Gen9 HD Graphics NEO' allows GPU memory allocations of up to 4095MB
[opencl_init] device 0: Intel(R) Gen9 HD Graphics NEO
GLOBAL_MEM_SIZE: 12520MB
MAX_WORK_GROUP_SIZE: 256
MAX_WORK_ITEM_DIMENSIONS: 3
MAX_WORK_ITEM_SIZES: [ 256 256 256 ]
DRIVER_VERSION: 1.0.0
DEVICE_VERSION: OpenCL 2.1 NEO
0.215420 [opencl_init] options for OpenCL compiler: -w -DINTEL=1 -I"/usr/share/darktable/kernels"
0.215537 [opencl_init] compiling program `demosaic_ppg.cl' ..
0.215776 [opencl_load_program] loaded cached binary program from file '/home/bardo/.cache/darktable/cached_kernels_for_IntelRGen9HDGraphicsNEO_100/demosaic_ppg.cl.bin' MD5: '77b1bcd7d7d499e6a1569d0f188ee6b7'
0.215780 [opencl_load_program] successfully loaded program from '/usr/share/darktable/kernels/demosaic_ppg.cl' MD5: '77b1bcd7d7d499e6a1569d0f188ee6b7'
0.216077 [opencl_build_program] successfully built program
0.216080 [opencl_build_program] BUILD STATUS: 0
0.216083 BUILD LOG:
0.216085
0.216112 [opencl_init] compiling program `atrous.cl' ..
0.216130 [opencl_fopen_stat] could not open file `/home/bardo/.cache/darktable/cached_kernels_for_IntelRGen9HDGraphicsNEO_100/atrous.cl.bin'!
0.216152 [opencl_load_program] could not load cached binary program, trying to compile source
0.216158 [opencl_load_program] successfully loaded program from '/usr/share/darktable/kernels/atrous.cl' MD5: '877e4325f34824dd987075b3b81da75d'
[New LWP 6535]
[New LWP 6536]
[New LWP 6537]
[Thread debugging using libthread_db enabled]
Using host libthread_db library "/usr/lib/libthread_db.so.1".
0x00007fa2c7952eef in wait4 () from /usr/lib/libc.so.6
warning: Currently logging to /tmp/darktable_bt_J5X4R0.txt. Turn the logging off and on to make the new setting effective.
#0 0x00007fa2c7952eef in wait4 () at /usr/lib/libc.so.6
#1 0x00007fa2c7b7db32 in () at /usr/lib/libdarktable.so
#2 0x00007fa2c78c36a0 in <signal handler called> () at /usr/lib/libc.so.6
#3 0x00007fa2a6703217 in () at /usr/lib/libigc.so.1
#4 0x00007fa2a6704a2a in () at /usr/lib/libigc.so.1
#5 0x00007fa2a66a4c00 in () at /usr/lib/libigc.so.1
#6 0x00007fa2a66a4e5b in () at /usr/lib/libigc.so.1
#7 0x00007fa2a658fc10 in () at /usr/lib/libigc.so.1
#8 0x00007fa2a66253e8 in () at /usr/lib/libigc.so.1
#9 0x00007fa2a64b4934 in () at /usr/lib/libigc.so.1
#10 0x00007fa2a650814f in () at /usr/lib/libigc.so.1
#11 0x00007fa2ab7005d8 in llvm::FPPassManager::runOnFunction(llvm::Function&) () at /usr/lib/libLLVM-10.so
#12 0x00007fa2ab701bdd in llvm::FPPassManager::runOnModule(llvm::Module&) () at /usr/lib/libLLVM-10.so
#13 0x00007fa2ab701f70 in llvm::legacy::PassManagerImpl::run(llvm::Module&) () at /usr/lib/libLLVM-10.so
#14 0x00007fa2a6350dd4 in () at /usr/lib/libigc.so.1
#15 0x00007fa2a632a061 in () at /usr/lib/libigc.so.1
#16 0x00007fa2a620f994 in () at /usr/lib/libigc.so.1
#17 0x00007fa2a62c2bba in () at /usr/lib/libigc.so.1
#18 0x00007fa2bf2c52ea in () at /usr/lib/intel-opencl/libigdrcl.so
#19 0x00007fa2bf0c8d50 in () at /usr/lib/intel-opencl/libigdrcl.so
#20 0x00007fa2bf060a02 in () at /usr/lib/intel-opencl/libigdrcl.so
#21 0x00007fa2c7b62e58 in dt_opencl_build_program () at /usr/lib/libdarktable.so
#22 0x00007fa2c7b642c3 in () at /usr/lib/libdarktable.so
#23 0x00007fa2c7b680d0 in dt_opencl_init () at /usr/lib/libdarktable.so
#24 0x00007fa2c7ae41fd in dt_init () at /usr/lib/libdarktable.so
#25 0x000055a3804720e0 in ()
#26 0x00007fa2c78ae152 in __libc_start_main () at /usr/lib/libc.so.6
#27 0x000055a38047213e in ()
=========
Id Target Id Frame
* 1 Thread 0x7fa2c0d7d180 (LWP 6534) "darktable-cltes" 0x00007fa2c7952eef in wait4 () from /usr/lib/libc.so.6
2 Thread 0x7fa2c07c8640 (LWP 6535) "gmain" 0x00007fa2c797b46f in poll () from /usr/lib/libc.so.6
3 Thread 0x7fa2bffc7640 (LWP 6536) "gdbus" 0x00007fa2c797b46f in poll () from /usr/lib/libc.so.6
4 Thread 0x7fa2bef5c640 (LWP 6537) "darktable-cltes" 0x00007fa2c78736a2 in pthread_cond_wait@@GLIBC_2.3.2 () from /usr/lib/libpthread.so.0
=========
Thread 4 (Thread 0x7fa2bef5c640 (LWP 6537)):
#0 0x00007fa2c78736a2 in pthread_cond_wait@@GLIBC_2.3.2 () at /usr/lib/libpthread.so.0
#1 0x00007fa2c4f29c11 in __gthread_cond_wait (__mutex=<optimized out>, __cond=<optimized out>) at /build/gcc/src/gcc-build/x86_64-pc-linux-gnu/libstdc++-v3/include/x86_64-pc-linux-gnu/bits/gthr-default.h:865
__e = <optimized out>
#2 std::condition_variable::wait(std::unique_lock<std::mutex>&) (this=<optimized out>, __lock=...) at /build/gcc/src/gcc/libstdc++-v3/src/c++11/condition_variable.cc:53
__e = <optimized out>
#3 0x00007fa2bf37820e in () at /usr/lib/intel-opencl/libigdrcl.so
#4 0x00007fa2c786d3e9 in start_thread () at /usr/lib/libpthread.so.0
#5 0x00007fa2c7986293 in clone () at /usr/lib/libc.so.6
Thread 3 (Thread 0x7fa2bffc7640 (LWP 6536)):
#0 0x00007fa2c797b46f in poll () at /usr/lib/libc.so.6
#1 0x00007fa2c7651188 in () at /usr/lib/libglib-2.0.so.0
#2 0x00007fa2c75ff163 in g_main_loop_run () at /usr/lib/libglib-2.0.so.0
#3 0x00007fa2c6a7cfe8 in () at /usr/lib/libgio-2.0.so.0
#4 0x00007fa2c762ca91 in () at /usr/lib/libglib-2.0.so.0
#5 0x00007fa2c786d3e9 in start_thread () at /usr/lib/libpthread.so.0
#6 0x00007fa2c7986293 in clone () at /usr/lib/libc.so.6
Thread 2 (Thread 0x7fa2c07c8640 (LWP 6535)):
#0 0x00007fa2c797b46f in poll () at /usr/lib/libc.so.6
#1 0x00007fa2c7651188 in () at /usr/lib/libglib-2.0.so.0
#2 0x00007fa2c75fe421 in g_main_context_iteration () at /usr/lib/libglib-2.0.so.0
#3 0x00007fa2c75fe472 in () at /usr/lib/libglib-2.0.so.0
#4 0x00007fa2c762ca91 in () at /usr/lib/libglib-2.0.so.0
#5 0x00007fa2c786d3e9 in start_thread () at /usr/lib/libpthread.so.0
#6 0x00007fa2c7986293 in clone () at /usr/lib/libc.so.6
Thread 1 (Thread 0x7fa2c0d7d180 (LWP 6534)):
#0 0x00007fa2c7952eef in wait4 () at /usr/lib/libc.so.6
#1 0x00007fa2c7b7db32 in () at /usr/lib/libdarktable.so
#2 0x00007fa2c78c36a0 in <signal handler called> () at /usr/lib/libc.so.6
#3 0x00007fa2a6703217 in () at /usr/lib/libigc.so.1
#4 0x00007fa2a6704a2a in () at /usr/lib/libigc.so.1
#5 0x00007fa2a66a4c00 in () at /usr/lib/libigc.so.1
#6 0x00007fa2a66a4e5b in () at /usr/lib/libigc.so.1
#7 0x00007fa2a658fc10 in () at /usr/lib/libigc.so.1
#8 0x00007fa2a66253e8 in () at /usr/lib/libigc.so.1
#9 0x00007fa2a64b4934 in () at /usr/lib/libigc.so.1
#10 0x00007fa2a650814f in () at /usr/lib/libigc.so.1
#11 0x00007fa2ab7005d8 in llvm::FPPassManager::runOnFunction(llvm::Function&) () at /usr/lib/libLLVM-10.so
#12 0x00007fa2ab701bdd in llvm::FPPassManager::runOnModule(llvm::Module&) () at /usr/lib/libLLVM-10.so
#13 0x00007fa2ab701f70 in llvm::legacy::PassManagerImpl::run(llvm::Module&) () at /usr/lib/libLLVM-10.so
#14 0x00007fa2a6350dd4 in () at /usr/lib/libigc.so.1
#15 0x00007fa2a632a061 in () at /usr/lib/libigc.so.1
#16 0x00007fa2a620f994 in () at /usr/lib/libigc.so.1
#17 0x00007fa2a62c2bba in () at /usr/lib/libigc.so.1
#18 0x00007fa2bf2c52ea in () at /usr/lib/intel-opencl/libigdrcl.so
#19 0x00007fa2bf0c8d50 in () at /usr/lib/intel-opencl/libigdrcl.so
#20 0x00007fa2bf060a02 in () at /usr/lib/intel-opencl/libigdrcl.so
#21 0x00007fa2c7b62e58 in dt_opencl_build_program () at /usr/lib/libdarktable.so
#22 0x00007fa2c7b642c3 in () at /usr/lib/libdarktable.so
#23 0x00007fa2c7b680d0 in dt_opencl_init () at /usr/lib/libdarktable.so
#24 0x00007fa2c7ae41fd in dt_init () at /usr/lib/libdarktable.so
#25 0x000055a3804720e0 in ()
#26 0x00007fa2c78ae152 in __libc_start_main () at /usr/lib/libc.so.6
#27 0x000055a38047213e in ()
[Inferior 1 (process 6534) detached]
backtrace written to /tmp/darktable_bt_J5X4R0.txt
Segmentation fault (core dumped)
[bardo@ged 16:12 ~]$ dreaming in digital / living in realtime / thinking in binary / talking in ip / welcome to our world
Offline
Attaching output for darktable-cltest from an unstripped build. The issue seems to be with the Intel card only. I will try to set up my darktablerc to use only the nVidia and see what happens.
this is darktable 3.2.1 reporting a segfault:
warning: Currently logging to /tmp/darktable_bt_1RRZR0.txt. Turn the logging off and on to make the new setting effective.
#0 0x00007fac0f4e5eef in wait4 () at /usr/lib/libc.so.6
#1 0x00007fac0f7160b2 in _dt_sigsegv_handler(int) (param=11) at /home/bardo/code/darktable/repos/community-x86_64/src/darktable-3.2.1/src/common/system_signal_handling.c:114
#2 0x00007fac0f4566a0 in <signal handler called> () at /usr/lib/libc.so.6
#3 0x00007fabeddaf217 in () at /usr/lib/libigc.so.1
#4 0x00007fabeddb0a2a in () at /usr/lib/libigc.so.1
#5 0x00007fabedd50c00 in () at /usr/lib/libigc.so.1
#6 0x00007fabedd50e5b in () at /usr/lib/libigc.so.1
#7 0x00007fabedc3bc10 in () at /usr/lib/libigc.so.1
#8 0x00007fabedcd13e8 in () at /usr/lib/libigc.so.1
#9 0x00007fabedb60934 in () at /usr/lib/libigc.so.1
#10 0x00007fabedbb414f in () at /usr/lib/libigc.so.1
#11 0x00007fabf37005d8 in llvm::FPPassManager::runOnFunction(llvm::Function&) () at /usr/lib/libLLVM-10.so
#12 0x00007fabf3701bdd in llvm::FPPassManager::runOnModule(llvm::Module&) () at /usr/lib/libLLVM-10.so
#13 0x00007fabf3701f70 in llvm::legacy::PassManagerImpl::run(llvm::Module&) () at /usr/lib/libLLVM-10.so
#14 0x00007fabed9fcdd4 in () at /usr/lib/libigc.so.1
#15 0x00007fabed9d6061 in () at /usr/lib/libigc.so.1
#16 0x00007fabed8bb994 in () at /usr/lib/libigc.so.1
#17 0x00007fabed96ebba in () at /usr/lib/libigc.so.1
#18 0x00007fac06e582ea in () at /usr/lib/intel-opencl/libigdrcl.so
#19 0x00007fac06c5bd50 in () at /usr/lib/intel-opencl/libigdrcl.so
#20 0x00007fac06bf3a02 in () at /usr/lib/intel-opencl/libigdrcl.so
#21 0x00007fac0f6f8318 in dt_opencl_build_program(int, int, char const*, char const*, char*, int) (dev=dev@entry=0, prog=prog@entry=1, binname=binname@entry=0x5643d9f27330 "/home/bardo/.cache/darktable/cached_kernels_for_IntelRGen9HDGraphicsNEO_100/atrous.cl.bin", cachedir=cachedir@entry=0x5643da4ee030 "/home/bardo/.cache/darktable/cached_kernels_for_IntelRGen9HDGraphicsNEO_100", md5sum=md5sum@entry=0x7ffce1b82bb0 "877e4325f34824dd987075b3b81da75d", loaded_cached=0) at /home/bardo/code/darktable/repos/community-x86_64/src/darktable-3.2.1/src/common/opencl.c:1740
#22 0x00007fac0f6fd5b3 in dt_opencl_device_init(dt_opencl_t*, int, cl_device_id*, int, int) (cl=cl@entry=0x5643d9cee2a0, dev=dev@entry=0, devices=devices@entry=0x5643da4ef060, k=k@entry=0, opencl_memory_requirement=opencl_memory_requirement@entry=768) at /home/bardo/code/darktable/repos/community-x86_64/src/darktable-3.2.1/src/common/opencl.c:477
#23 0x00007fac0f6feec0 in dt_opencl_init(dt_opencl_t*, gboolean, gboolean) (cl=0x5643d9cee2a0, exclude_opencl=<optimized out>, print_statistics=<optimized out>) at /home/bardo/code/darktable/repos/community-x86_64/src/darktable-3.2.1/src/common/opencl.c:708
#24 0x00007fac0f678527 in dt_init(int, char**, gboolean, gboolean, lua_State*) (argc=<optimized out>, argv=<optimized out>, init_gui=0, load_data=0, L=0x0) at /home/bardo/code/darktable/repos/community-x86_64/src/darktable-3.2.1/src/common/darktable.c:933
#25 0x00005643d918c0e0 in main (argc=5, arg=0x7ffce1b88128) at /home/bardo/code/darktable/repos/community-x86_64/src/darktable-3.2.1/src/cltest/main.c:47
=========
Id Target Id Frame
* 1 Thread 0x7fac08910180 (LWP 27897) "darktable-cltes" 0x00007fac0f4e5eef in wait4 () from /usr/lib/libc.so.6
2 Thread 0x7fac0835b640 (LWP 27898) "gmain" 0x00007fac0f50e46f in poll () from /usr/lib/libc.so.6
3 Thread 0x7fac07b5a640 (LWP 27899) "gdbus" 0x00007fac0f50e46f in poll () from /usr/lib/libc.so.6
4 Thread 0x7fac06aef640 (LWP 27900) "darktable-cltes" 0x00007fac0f4066a2 in pthread_cond_wait@@GLIBC_2.3.2 () from /usr/lib/libpthread.so.0
=========
Thread 4 (Thread 0x7fac06aef640 (LWP 27900)):
#0 0x00007fac0f4066a2 in pthread_cond_wait@@GLIBC_2.3.2 () at /usr/lib/libpthread.so.0
#1 0x00007fac0cabcc11 in __gthread_cond_wait (__mutex=<optimized out>, __cond=<optimized out>) at /build/gcc/src/gcc-build/x86_64-pc-linux-gnu/libstdc++-v3/include/x86_64-pc-linux-gnu/bits/gthr-default.h:865
__e = <optimized out>
#2 std::condition_variable::wait(std::unique_lock<std::mutex>&) (this=<optimized out>, __lock=...) at /build/gcc/src/gcc/libstdc++-v3/src/c++11/condition_variable.cc:53
__e = <optimized out>
#3 0x00007fac06f0b20e in () at /usr/lib/intel-opencl/libigdrcl.so
#4 0x00007fac0f4003e9 in start_thread () at /usr/lib/libpthread.so.0
#5 0x00007fac0f519293 in clone () at /usr/lib/libc.so.6
Thread 3 (Thread 0x7fac07b5a640 (LWP 27899)):
#0 0x00007fac0f50e46f in poll () at /usr/lib/libc.so.6
#1 0x00007fac0f1e4188 in () at /usr/lib/libglib-2.0.so.0
#2 0x00007fac0f192163 in g_main_loop_run () at /usr/lib/libglib-2.0.so.0
#3 0x00007fac0e60ffe8 in () at /usr/lib/libgio-2.0.so.0
#4 0x00007fac0f1bfa91 in () at /usr/lib/libglib-2.0.so.0
#5 0x00007fac0f4003e9 in start_thread () at /usr/lib/libpthread.so.0
#6 0x00007fac0f519293 in clone () at /usr/lib/libc.so.6
Thread 2 (Thread 0x7fac0835b640 (LWP 27898)):
#0 0x00007fac0f50e46f in poll () at /usr/lib/libc.so.6
#1 0x00007fac0f1e4188 in () at /usr/lib/libglib-2.0.so.0
#2 0x00007fac0f191421 in g_main_context_iteration () at /usr/lib/libglib-2.0.so.0
#3 0x00007fac0f191472 in () at /usr/lib/libglib-2.0.so.0
#4 0x00007fac0f1bfa91 in () at /usr/lib/libglib-2.0.so.0
#5 0x00007fac0f4003e9 in start_thread () at /usr/lib/libpthread.so.0
#6 0x00007fac0f519293 in clone () at /usr/lib/libc.so.6
Thread 1 (Thread 0x7fac08910180 (LWP 27897)):
#0 0x00007fac0f4e5eef in wait4 () at /usr/lib/libc.so.6
#1 0x00007fac0f7160b2 in _dt_sigsegv_handler(int) (param=11) at /home/bardo/code/darktable/repos/community-x86_64/src/darktable-3.2.1/src/common/system_signal_handling.c:114
pid = 27904
name_used = 0x5643da42e680 "/tmp/darktable_bt_1RRZR0.txt"
fout = <optimized out>
delete_file = 0
datadir = "/usr/share/darktable", '\000' <repeats 4075 times>
pid_arg = 0x5643da5ddbe0 "27897"
comm_arg = 0x5643da5ee8d0 "/usr/share/darktable/gdb_commands"
log_arg = 0x5643dabcd8d0 "set logging on /tmp/darktable_bt_1RRZR0.txt"
#2 0x00007fac0f4566a0 in <signal handler called> () at /usr/lib/libc.so.6
#3 0x00007fabeddaf217 in () at /usr/lib/libigc.so.1
#4 0x00007fabeddb0a2a in () at /usr/lib/libigc.so.1
#5 0x00007fabedd50c00 in () at /usr/lib/libigc.so.1
#6 0x00007fabedd50e5b in () at /usr/lib/libigc.so.1
#7 0x00007fabedc3bc10 in () at /usr/lib/libigc.so.1
#8 0x00007fabedcd13e8 in () at /usr/lib/libigc.so.1
#9 0x00007fabedb60934 in () at /usr/lib/libigc.so.1
#10 0x00007fabedbb414f in () at /usr/lib/libigc.so.1
#11 0x00007fabf37005d8 in llvm::FPPassManager::runOnFunction(llvm::Function&) () at /usr/lib/libLLVM-10.so
#12 0x00007fabf3701bdd in llvm::FPPassManager::runOnModule(llvm::Module&) () at /usr/lib/libLLVM-10.so
#13 0x00007fabf3701f70 in llvm::legacy::PassManagerImpl::run(llvm::Module&) () at /usr/lib/libLLVM-10.so
#14 0x00007fabed9fcdd4 in () at /usr/lib/libigc.so.1
#15 0x00007fabed9d6061 in () at /usr/lib/libigc.so.1
#16 0x00007fabed8bb994 in () at /usr/lib/libigc.so.1
#17 0x00007fabed96ebba in () at /usr/lib/libigc.so.1
#18 0x00007fac06e582ea in () at /usr/lib/intel-opencl/libigdrcl.so
#19 0x00007fac06c5bd50 in () at /usr/lib/intel-opencl/libigdrcl.so
#20 0x00007fac06bf3a02 in () at /usr/lib/intel-opencl/libigdrcl.so
#21 0x00007fac0f6f8318 in dt_opencl_build_program(int, int, char const*, char const*, char*, int) (dev=dev@entry=0, prog=prog@entry=1, binname=binname@entry=0x5643d9f27330 "/home/bardo/.cache/darktable/cached_kernels_for_IntelRGen9HDGraphicsNEO_100/atrous.cl.bin", cachedir=cachedir@entry=0x5643da4ee030 "/home/bardo/.cache/darktable/cached_kernels_for_IntelRGen9HDGraphicsNEO_100", md5sum=md5sum@entry=0x7ffce1b82bb0 "877e4325f34824dd987075b3b81da75d", loaded_cached=0) at /home/bardo/code/darktable/repos/community-x86_64/src/darktable-3.2.1/src/common/opencl.c:1740
cl = 0x5643d9cee2a0
program = 0x5643d9ab2370
err = <optimized out>
build_status = 0
build_log = <optimized out>
ret_val_size = 1
#22 0x00007fac0f6fd5b3 in dt_opencl_device_init(dt_opencl_t*, int, cl_device_id*, int, int) (cl=cl@entry=0x5643d9cee2a0, dev=dev@entry=0, devices=devices@entry=0x5643da4ef060, k=k@entry=0, opencl_memory_requirement=opencl_memory_requirement@entry=768) at /home/bardo/code/darktable/repos/community-x86_64/src/darktable-3.2.1/src/common/opencl.c:477
prog = <optimized out>
rd = <optimized out>
end = <optimized out>
programname = <optimized out>
programnumber = <optimized out>
tokens = 0x5643d9f49240
confline_pattern = <optimized out>
loaded_cached = 0
md5sum = "877e4325f34824dd987075b3b81da75d"
res = <optimized out>
err = 0
devid = 0x5643d9e21260
infostr = 0x5643da6ffc20 "Intel(R) Gen9 HD Graphics NEO"
infostr_size = 30
cname = 0x5643d9b58e90 "intelrg"
cname_size = <optimized out>
options = 0x0
vendor = 0x5643da4eaf00 "Intel(R) Corporation"
vendor_size = 21
driverversion = 0x5643da7c4b60 "1.0.0"
driverversion_size = 6
deviceversion = 0x5643da7bc170 "OpenCL 2.1 NEO "
deviceversion_size = 16
infoint = 3
infointtab = 0x0
type = 4
image_support = 1
device_available = 1
vendor_id = 32902
little_endian = 1
dtcache = 0x5643d9ea2bc0 "/home/bardo/.cache/darktable"
cachedir = 0x5643da4ee030 "/home/bardo/.cache/darktable/cached_kernels_for_IntelRGen9HDGraphicsNEO_100"
devname = 0x5643d9aaadb0 "IntelRGen9HDGraphicsNEO"
drvversion = 0x5643da7adf20 "100"
dtpath = <optimized out>
filename = 0x5643da4f9310 "/usr/share/darktable/kernels/atrous.cl"
confentry = 0x5643d9f283f0 "atrous.cl", ' ' <repeats 16 times>, "1"
binname = 0x5643d9f27330 "/home/bardo/.cache/darktable/cached_kernels_for_IntelRGen9HDGraphicsNEO_100/atrous.cl.bin"
tstart = 311220973.94761002
tend = <optimized out>
tdiff = <optimized out>
len = <optimized out>
j = <optimized out>
kerneldir = "/usr/share/darktable/kernels", '\000' <repeats 4067 times>
escapedkerneldir = 0x0
clincludes = {0x7fac0f95d2bc "color_conversion.cl", 0x7fac0f95d2d0 "colorspaces.cl", 0x7fac0f95d2df "colorspace.cl", 0x7fac0f95d2ed "common.h", 0x0}
includemd5 = {0x5643da6c9560 "fdeb65b3cff190ad7a10c0f005eaba3d", 0x5643da7b4d40 "7a12c84140de8294af5ef8620704ea3d", 0x5643da7adcd0 "a1ed1a321182df502eee68785e9e74f9", 0x5643da7ade00 "baea09a91d62c44324ce02e1de400f17", 0x0}
f = 0x5643d9caf960
#23 0x00007fac0f6feec0 in dt_opencl_init(dt_opencl_t*, gboolean, gboolean) (cl=0x5643d9cee2a0, exclude_opencl=<optimized out>, print_statistics=<optimized out>) at /home/bardo/code/darktable/repos/community-x86_64/src/darktable-3.2.1/src/common/opencl.c:708
k = 0
str = <optimized out>
locale = 0x5643d9cedee0 "en_US.UTF-8"
handles = <optimized out>
all_platforms = 0x5643d9ce4500
all_num_devices = 0x5643d9a7b040
opencl_memory_requirement = <optimized out>
library = <optimized out>
err = <optimized out>
num_platforms = 2
num_devices = 2
devices = <optimized out>
devs = <optimized out>
dev = 0
#24 0x00007fac0f678527 in dt_init(int, char**, gboolean, gboolean, lua_State*) (argc=<optimized out>, argv=<optimized out>, init_gui=0, load_data=0, L=0x0) at /home/bardo/code/darktable/repos/community-x86_64/src/darktable-3.2.1/src/common/darktable.c:933
start_wtime = 311220973.76274502
sse2_supported = <optimized out>
recursive_locking = {__size = "\001\000\000", __align = 1}
dbfilename_from_command = <optimized out>
noiseprofiles_from_command = <optimized out>
datadir_from_command = <optimized out>
moduledir_from_command = <optimized out>
localedir_from_command = <optimized out>
tmpdir_from_command = <optimized out>
configdir_from_command = <optimized out>
cachedir_from_command = <optimized out>
exclude_opencl = <optimized out>
print_statistics = 0
lua_command = <optimized out>
config_override = <optimized out>
datadir = "/home/bardo/.config/darktable", '\000' <repeats 4066 times>
darktablerc = "/home/bardo/.config/darktable/darktablerc", '\000' <repeats 4054 times>
changed_xmp_files = <optimized out>
#25 0x00005643d918c0e0 in main (argc=5, arg=0x7ffce1b88128) at /home/bardo/code/darktable/repos/community-x86_64/src/darktable-3.2.1/src/cltest/main.c:47
result = <optimized out>
m_arg = {0x5643d918d004 "-d", 0x5643d918d007 "opencl", 0x5643d918d00e "--library", 0x5643d918d018 ":memory:"}
argv = 0x5643d9aa4770
[Inferior 1 (process 27897) detached]dreaming in digital / living in realtime / thinking in binary / talking in ip / welcome to our world
Offline
Tried to force various opencl_device_priority settings in darktablerc, to no avail. It looks like first OpenCL has to be correctly initialized for all devices, and then Darktable applies the device filter.
dreaming in digital / living in realtime / thinking in binary / talking in ip / welcome to our world
Offline
leonixyz, run and post output of
$ darktable-cltest
$ darktable-cltest
0.029298 [opencl_init] opencl related configuration options:
0.029311 [opencl_init]
0.029314 [opencl_init] opencl: 1
0.029317 [opencl_init] opencl_scheduling_profile: 'default'
0.029319 [opencl_init] opencl_library: ''
0.029322 [opencl_init] opencl_memory_requirement: 768
0.029325 [opencl_init] opencl_memory_headroom: 400
0.029345 [opencl_init] opencl_device_priority: '*/!0,*/*/*/!0,*'
0.029347 [opencl_init] opencl_mandatory_timeout: 200
0.029350 [opencl_init] opencl_size_roundup: 16
0.029355 [opencl_init] opencl_async_pixelpipe: 0
0.029357 [opencl_init] opencl_synch_cache: active module
0.029360 [opencl_init] opencl_number_event_handles: 25
0.029364 [opencl_init] opencl_micro_nap: 1000
0.029366 [opencl_init] opencl_use_pinned_memory: 0
0.029369 [opencl_init] opencl_use_cpu_devices: 0
0.029371 [opencl_init] opencl_avoid_atomics: 0
0.029373 [opencl_init]
0.033926 [opencl_init] found opencl runtime library 'libOpenCL'
0.034011 [opencl_init] opencl library 'libOpenCL' found on your system and loaded
0.597288 [opencl_init] found 1 platform
0.597319 [opencl_init] found 1 device
0.597358 [opencl_init] device 0 `Intel(R) Gen9 HD Graphics NEO' supports image sizes of 16384 x 16384
0.597372 [opencl_init] device 0 `Intel(R) Gen9 HD Graphics NEO' allows GPU memory allocations of up to 2948MB
[opencl_init] device 0: Intel(R) Gen9 HD Graphics NEO
GLOBAL_MEM_SIZE: 5896MB
MAX_WORK_GROUP_SIZE: 256
MAX_WORK_ITEM_DIMENSIONS: 3
MAX_WORK_ITEM_SIZES: [ 256 256 256 ]
DRIVER_VERSION: 1.0.0
DEVICE_VERSION: OpenCL 2.1 NEO
0.597606 [opencl_init] options for OpenCL compiler: -w -DINTEL=1 -I"/usr/share/darktable/kernels"
0.599805 [opencl_init] compiling program `demosaic_ppg.cl' ..
0.602321 [opencl_load_program] loaded cached binary program from file '/home/leonixyz/.cache/darktable/cached_kernels_for_IntelRGen9HDGraphicsNEO_100/demosaic_ppg.cl.bin' MD5: '77b1bcd7d7d499e6a1569d0f188ee6b7'
0.602349 [opencl_load_program] successfully loaded program from '/usr/share/darktable/kernels/demosaic_ppg.cl' MD5: '77b1bcd7d7d499e6a1569d0f188ee6b7'
0.603012 [opencl_build_program] successfully built program
0.603026 [opencl_build_program] BUILD STATUS: 0
0.603032 BUILD LOG:
0.603036
0.603054 [opencl_init] compiling program `atrous.cl' ..
0.603530 [opencl_fopen_stat] could not open file `/home/leonixyz/.cache/darktable/cached_kernels_for_IntelRGen9HDGraphicsNEO_100/atrous.cl.bin'!
0.603551 [opencl_load_program] could not load cached binary program, trying to compile source
0.603566 [opencl_load_program] successfully loaded program from '/usr/share/darktable/kernels/atrous.cl' MD5: '877e4325f34824dd987075b3b81da75d'
an error occurred while trying to execute gdb. please check if gdb is installed on your system.
backtrace written to /tmp/darktable_bt_9916R0.txt
[1] 12745 segmentation fault (core dumped) darktable-cltestOffline
leonixyz, I think we are seeing the same error, however your output does not contain the debug data. Can you install the gdb package and run the command again?
dreaming in digital / living in realtime / thinking in binary / talking in ip / welcome to our world
Offline
leonixyz, I think we are seeing the same error, however your output does not contain the debug data. Can you install the gdb package and run the command again?
darktable-cltest
0.051928 [opencl_init] opencl related configuration options:
0.051940 [opencl_init]
0.051942 [opencl_init] opencl: 1
0.051945 [opencl_init] opencl_scheduling_profile: 'default'
0.051948 [opencl_init] opencl_library: ''
0.051950 [opencl_init] opencl_memory_requirement: 768
0.051953 [opencl_init] opencl_memory_headroom: 400
0.051956 [opencl_init] opencl_device_priority: '*/!0,*/*/*/!0,*'
0.051976 [opencl_init] opencl_mandatory_timeout: 200
0.051979 [opencl_init] opencl_size_roundup: 16
0.051985 [opencl_init] opencl_async_pixelpipe: 0
0.051988 [opencl_init] opencl_synch_cache: active module
0.051992 [opencl_init] opencl_number_event_handles: 25
0.051996 [opencl_init] opencl_micro_nap: 1000
0.051998 [opencl_init] opencl_use_pinned_memory: 0
0.052002 [opencl_init] opencl_use_cpu_devices: 0
0.052005 [opencl_init] opencl_avoid_atomics: 0
0.052007 [opencl_init]
0.053370 [opencl_init] found opencl runtime library 'libOpenCL'
0.053393 [opencl_init] opencl library 'libOpenCL' found on your system and loaded
0.678741 [opencl_init] found 1 platform
0.678781 [opencl_init] found 1 device
0.678857 [opencl_init] device 0 `Intel(R) Gen9 HD Graphics NEO' supports image sizes of 16384 x 16384
0.678871 [opencl_init] device 0 `Intel(R) Gen9 HD Graphics NEO' allows GPU memory allocations of up to 2948MB
[opencl_init] device 0: Intel(R) Gen9 HD Graphics NEO
GLOBAL_MEM_SIZE: 5896MB
MAX_WORK_GROUP_SIZE: 256
MAX_WORK_ITEM_DIMENSIONS: 3
MAX_WORK_ITEM_SIZES: [ 256 256 256 ]
DRIVER_VERSION: 1.0.0
DEVICE_VERSION: OpenCL 2.1 NEO
0.679036 [opencl_init] options for OpenCL compiler: -w -DINTEL=1 -I"/usr/share/darktable/kernels"
0.680359 [opencl_init] compiling program `demosaic_ppg.cl' ..
0.682229 [opencl_load_program] loaded cached binary program from file '/home/leonixyz/.cache/darktable/cached_kernels_for_IntelRGen9HDGraphicsNEO_100/demosaic_ppg.cl.bin' MD5: '77b1bcd7d7d499e6a1569d0f188ee6b7'
0.682248 [opencl_load_program] successfully loaded program from '/usr/share/darktable/kernels/demosaic_ppg.cl' MD5: '77b1bcd7d7d499e6a1569d0f188ee6b7'
0.683053 [opencl_build_program] successfully built program
0.683070 [opencl_build_program] BUILD STATUS: 0
0.683078 BUILD LOG:
0.683082
0.683098 [opencl_init] compiling program `atrous.cl' ..
0.683379 [opencl_fopen_stat] could not open file `/home/leonixyz/.cache/darktable/cached_kernels_for_IntelRGen9HDGraphicsNEO_100/atrous.cl.bin'!
0.683400 [opencl_load_program] could not load cached binary program, trying to compile source
0.683415 [opencl_load_program] successfully loaded program from '/usr/share/darktable/kernels/atrous.cl' MD5: '877e4325f34824dd987075b3b81da75d'
[New LWP 51600]
[New LWP 51601]
[New LWP 51602]
[Thread debugging using libthread_db enabled]
Using host libthread_db library "/usr/lib/libthread_db.so.1".
0x00007f5950773eef in wait4 () from /usr/lib/libc.so.6
warning: Currently logging to /tmp/darktable_bt_AHNES0.txt. Turn the logging off and on to make the new setting effective.
#0 0x00007f5950773eef in wait4 () at /usr/lib/libc.so.6
#1 0x00007f595099eb22 in () at /usr/lib/libdarktable.so
#2 0x00007f59506e46a0 in <signal handler called> () at /usr/lib/libc.so.6
#3 0x00007f592e703217 in () at /usr/lib/libigc.so.1
#4 0x00007f592e704a2a in () at /usr/lib/libigc.so.1
#5 0x00007f592e6a4c00 in () at /usr/lib/libigc.so.1
#6 0x00007f592e6a4e5b in () at /usr/lib/libigc.so.1
#7 0x00007f592e58fc10 in () at /usr/lib/libigc.so.1
#8 0x00007f592e6253e8 in () at /usr/lib/libigc.so.1
#9 0x00007f592e4b4934 in () at /usr/lib/libigc.so.1
#10 0x00007f592e50814f in () at /usr/lib/libigc.so.1
#11 0x00007f59337005d8 in llvm::FPPassManager::runOnFunction(llvm::Function&) () at /usr/lib/libLLVM-10.so
#12 0x00007f5933701bdd in llvm::FPPassManager::runOnModule(llvm::Module&) () at /usr/lib/libLLVM-10.so
#13 0x00007f5933701f70 in llvm::legacy::PassManagerImpl::run(llvm::Module&) () at /usr/lib/libLLVM-10.so
#14 0x00007f592e350dd4 in () at /usr/lib/libigc.so.1
#15 0x00007f592e32a061 in () at /usr/lib/libigc.so.1
#16 0x00007f592e20f994 in () at /usr/lib/libigc.so.1
#17 0x00007f592e2c2bba in () at /usr/lib/libigc.so.1
#18 0x00007f59485342ea in () at /usr/lib/intel-opencl/libigdrcl.so
#19 0x00007f5948337d50 in () at /usr/lib/intel-opencl/libigdrcl.so
#20 0x00007f59482cfa02 in () at /usr/lib/intel-opencl/libigdrcl.so
#21 0x00007f59487fe10e in clBuildProgram () at /usr/lib/libOpenCL.so
#22 0x00007f5950983e48 in dt_opencl_build_program () at /usr/lib/libdarktable.so
#23 0x00007f59509852b3 in () at /usr/lib/libdarktable.so
#24 0x00007f59509890c0 in dt_opencl_init () at /usr/lib/libdarktable.so
#25 0x00007f59509051ed in dt_init () at /usr/lib/libdarktable.so
#26 0x000055f2005840e0 in ()
#27 0x00007f59506cf152 in __libc_start_main () at /usr/lib/libc.so.6
#28 0x000055f20058413e in ()
=========
Id Target Id Frame
* 1 Thread 0x7f5949bb0180 (LWP 51599) "darktable-cltes" 0x00007f5950773eef in wait4 () from /usr/lib/libc.so.6
2 Thread 0x7f5949844640 (LWP 51600) "gmain" 0x00007f595079c46f in poll () from /usr/lib/libc.so.6
3 Thread 0x7f5949043640 (LWP 51601) "gdbus" 0x00007f595079c46f in poll () from /usr/lib/libc.so.6
4 Thread 0x7f5943fff640 (LWP 51602) "darktable-cltes" 0x00007f59506946a2 in pthread_cond_wait@@GLIBC_2.3.2 () from /usr/lib/libpthread.so.0
=========
Thread 4 (Thread 0x7f5943fff640 (LWP 51602)):
#0 0x00007f59506946a2 in pthread_cond_wait@@GLIBC_2.3.2 () at /usr/lib/libpthread.so.0
#1 0x00007f594dd5cc11 in __gthread_cond_wait (__mutex=<optimized out>, __cond=<optimized out>) at /build/gcc/src/gcc-build/x86_64-pc-linux-gnu/libstdc++-v3/include/x86_64-pc-linux-gnu/bits/gthr-default.h:865
__e = <optimized out>
#2 std::condition_variable::wait(std::unique_lock<std::mutex>&) (this=<optimized out>, __lock=...) at /build/gcc/src/gcc/libstdc++-v3/src/c++11/condition_variable.cc:53
__e = <optimized out>
#3 0x00007f59485e720e in () at /usr/lib/intel-opencl/libigdrcl.so
#4 0x00007f595068e3e9 in start_thread () at /usr/lib/libpthread.so.0
#5 0x00007f59507a7293 in clone () at /usr/lib/libc.so.6
Thread 3 (Thread 0x7f5949043640 (LWP 51601)):
#0 0x00007f595079c46f in poll () at /usr/lib/libc.so.6
#1 0x00007f5950472188 in () at /usr/lib/libglib-2.0.so.0
#2 0x00007f5950420163 in g_main_loop_run () at /usr/lib/libglib-2.0.so.0
#3 0x00007f594f89dfe8 in () at /usr/lib/libgio-2.0.so.0
#4 0x00007f595044da91 in () at /usr/lib/libglib-2.0.so.0
#5 0x00007f595068e3e9 in start_thread () at /usr/lib/libpthread.so.0
#6 0x00007f59507a7293 in clone () at /usr/lib/libc.so.6
Thread 2 (Thread 0x7f5949844640 (LWP 51600)):
#0 0x00007f595079c46f in poll () at /usr/lib/libc.so.6
#1 0x00007f5950472188 in () at /usr/lib/libglib-2.0.so.0
#2 0x00007f595041f421 in g_main_context_iteration () at /usr/lib/libglib-2.0.so.0
#3 0x00007f595041f472 in () at /usr/lib/libglib-2.0.so.0
#4 0x00007f595044da91 in () at /usr/lib/libglib-2.0.so.0
#5 0x00007f595068e3e9 in start_thread () at /usr/lib/libpthread.so.0
#6 0x00007f59507a7293 in clone () at /usr/lib/libc.so.6
Thread 1 (Thread 0x7f5949bb0180 (LWP 51599)):
#0 0x00007f5950773eef in wait4 () at /usr/lib/libc.so.6
#1 0x00007f595099eb22 in () at /usr/lib/libdarktable.so
#2 0x00007f59506e46a0 in <signal handler called> () at /usr/lib/libc.so.6
#3 0x00007f592e703217 in () at /usr/lib/libigc.so.1
#4 0x00007f592e704a2a in () at /usr/lib/libigc.so.1
#5 0x00007f592e6a4c00 in () at /usr/lib/libigc.so.1
#6 0x00007f592e6a4e5b in () at /usr/lib/libigc.so.1
#7 0x00007f592e58fc10 in () at /usr/lib/libigc.so.1
#8 0x00007f592e6253e8 in () at /usr/lib/libigc.so.1
#9 0x00007f592e4b4934 in () at /usr/lib/libigc.so.1
#10 0x00007f592e50814f in () at /usr/lib/libigc.so.1
#11 0x00007f59337005d8 in llvm::FPPassManager::runOnFunction(llvm::Function&) () at /usr/lib/libLLVM-10.so
#12 0x00007f5933701bdd in llvm::FPPassManager::runOnModule(llvm::Module&) () at /usr/lib/libLLVM-10.so
#13 0x00007f5933701f70 in llvm::legacy::PassManagerImpl::run(llvm::Module&) () at /usr/lib/libLLVM-10.so
#14 0x00007f592e350dd4 in () at /usr/lib/libigc.so.1
#15 0x00007f592e32a061 in () at /usr/lib/libigc.so.1
#16 0x00007f592e20f994 in () at /usr/lib/libigc.so.1
#17 0x00007f592e2c2bba in () at /usr/lib/libigc.so.1
#18 0x00007f59485342ea in () at /usr/lib/intel-opencl/libigdrcl.so
#19 0x00007f5948337d50 in () at /usr/lib/intel-opencl/libigdrcl.so
#20 0x00007f59482cfa02 in () at /usr/lib/intel-opencl/libigdrcl.so
#21 0x00007f59487fe10e in clBuildProgram () at /usr/lib/libOpenCL.so
#22 0x00007f5950983e48 in dt_opencl_build_program () at /usr/lib/libdarktable.so
#23 0x00007f59509852b3 in () at /usr/lib/libdarktable.so
#24 0x00007f59509890c0 in dt_opencl_init () at /usr/lib/libdarktable.so
#25 0x00007f59509051ed in dt_init () at /usr/lib/libdarktable.so
#26 0x000055f2005840e0 in ()
#27 0x00007f59506cf152 in __libc_start_main () at /usr/lib/libc.so.6
#28 0x000055f20058413e in ()
[Inferior 1 (process 51599) detached]
backtrace written to /tmp/darktable_bt_AHNES0.txt
[1] 51599 segmentation fault (core dumped) darktable-cltestOffline
The issue has been reported at https://github.com/darktable-org/darktable/issues/5842 and it has been root-caused to a bug in the Intel OpenCL stack, which can be worked around by downgrading the intel-graphics-compiler package:
pacman -U https://archive.archlinux.org/packages/i/intel-graphics-compiler/intel-graphics-compiler-1%3A1.0.4361-2-x86_64.pkg.tar.zstdreaming in digital / living in realtime / thinking in binary / talking in ip / welcome to our world
Offline
The new release of
intel-graphics-compilersolves the issue. Please mark as resolved if you don't see the issue anymore.
dreaming in digital / living in realtime / thinking in binary / talking in ip / welcome to our world
Offline