Hello,
I'd like to do some benchmarks.
When I run with opencl enabled (checked "opencl" in the gui and restart)
I get the nearly the same two values (e.g. for equalizer):
[dev_process_preview] pixel pipeline processing took 1,005 secs (2,764 CPU)
It doesn't make any difference whether with or without opencl. The stay
always the same.
Why are there two values shown?
Here is the output with opencl enabled:
$ darktable -d opencl -d perf
[opencl_init] opencl related configuration options:
[opencl_init]
[opencl_init] opencl: 1
[opencl_init] opencl_library: ''
[opencl_init] opencl_memory_requirement: 768
[opencl_init] opencl_memory_headroom: 300
[opencl_init] opencl_device_priority: '*/!0,*/*/*'
[opencl_init] opencl_size_roundup: 16
[opencl_init] opencl_async_pixelpipe: 0
[opencl_init] opencl_synch_cache: 0
[opencl_init] opencl_number_event_handles: 25
[opencl_init] opencl_micro_nap: 1000
[opencl_init] opencl_use_pinned_memory: 0
[opencl_init] opencl_use_cpu_devices: 0
[opencl_init] opencl_avoid_atomics: 0
[opencl_init] opencl_omit_whitebalance: 0
[opencl_init]
[opencl_init] trying to load opencl library: '<system default>'
[opencl_init] opencl library 'libOpenCL' found on your system and loaded
[opencl_init] found 1 platform
[opencl_init] found 1 device
[opencl_init] device 0 `GeForce GTX 460' has sm_20 support.
[opencl_init] device 0 `GeForce GTX 460' supports image sizes of 32768 x
32768
[opencl_init] device 0 `GeForce GTX 460' allows GPU memory allocations
of up to 255MB
[opencl_init] device 0: GeForce GTX 460
GLOBAL_MEM_SIZE: 1023MB
MAX_WORK_GROUP_SIZE: 1024
MAX_WORK_ITEM_DIMENSIONS: 3
MAX_WORK_ITEM_SIZES: [ 1024 1024 64 ]
DRIVER_VERSION: 319.76
DEVICE_VERSION: OpenCL 1.1 CUDA
[...]
It exits well:
[opencl_summary_statistics] device 'GeForce GTX 460': 37 out of 37
events were successful and 0 events lost
The following OpenCL packages are installed. Perf Logging seems fine.
The following packages are installed:
nvidia-opencl-common
nvidia-opencl-icd
ocl-icd-libopencl1
I don't have a particular Cuda package installed. There are available
packages:
libcuda1
libcuda1-i386
libcudart5.5
nvidia-cuda-dev
nvidia-cuda-doc
nvidia-cuda-gdb
nvidia-cuda-mps
nvidia-cuda-toolkit
python-pycuda
python-pycuda-dbg
python-pycuda-doc
python3-pycuda
python3-pycuda-dbg
I'd love to get more into.
------------------------------------------------------------------------------
Managing the Performance of Cloud-Based Applications
Take advantage of what the Cloud has to offer - Avoid Common Pitfalls.
Read the Whitepaper.
http://pubads.g.doubleclick.net/gampad/clk?id=121051231&iu=/4140/ostg.clktrk
_______________________________________________
Darktable-users mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/darktable-users
