4/2/2023 0 Comments Nvidia cuda toolkit 6.5![]() ![]() | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. Skip this step if you have the following output: Yes, I've read about that too and have tried with cubic & lanczos resampling many times.Solve python environment related issues to utilize CUDA enabled GPUs NVIDIA GPU Driver And there is no menion of openCL in the debug output. GDAL: GDALClose(/home/ruggedroutes/testout.tiff, this=0x1255390)īut it's still running on the CPU. GTiff: Adjusted bytes to write from 6272 to 3136. OPENJPEG: info: Tile 3/3 has been decoded. ![]() OPENJPEG: info: Header of tile 3 / 3 has been read. OPENJPEG: info: Image data has been updated with tile 2. OPENJPEG: info: Tile 2/3 has been decoded. OPENJPEG: info: Header of tile 2 / 3 has been read. OPENJPEG: info: Image data has been updated with tile 1. OPENJPEG: info: Tile 1/3 has been decoded. OPENJPEG: info: Header of tile 1 / 3 has been read. OPENJPEG: info: Image data has been updated with tile 0. OPENJPEG: info: Tile 0/3 has been decoded. OPENJPEG: info: Header of tile 0 / 3 has been read. Warning 1: Empty SOT marker detected: Psot=12. Using band 4 of destination image as alpha. WARP: Copying metadata from first source to destination dataset GDAL: GDALDriver::Create(GTiff,/home/ruggedroutes/testout.tiff,784,943,4,Byte,(nil)) OGRCT: Target: +proj=utm +zone=12 +datum=NAD83 +units=m +no_defsĬreating output file that is 784P x 943L. OGRCT: Source: +proj=utm +zone=12 +datum=NAD83 +units=m +no_defs GDALJP2Metadata: Got projection from GeoJP2 (geotiff) box (0): PROJCS],AUTHORITY],PRIMEM,UNIT,AUTHORITY],PROJECTION Transverse_Mercator,PARAMETER,PARAMETER,PARAMETER,PARAMETER,PARAMETER,UNIT],AUTHORITY] OPENJPEG: info: Main header has been correctly decoded. ![]() OPENJPEG: info: Start to read j2k main header (246455). so it's good to know that OpenCL itself is working. I have the opencl sample code from nvidia running now and everything compiled fine. ![]() Here is the gdalwarp command that I've been using to test: configure -with-png=internal -with-libtiff=internal -with-geotiff=internal -with-jpeg=internal -with-gif=internal -with-openjpeg=/home/steven/SourceBuilds/openjpeg-2.1.0-Darwin-i386 -with-opencl=yes -with-opencl-include=/usr/local/cuda-6.5/include Here is the config command I've been using: Using options like -multi -wo USE_ALL_CPUS -wo ENABLE_OPENCL=TRUE all have no effect on time to run the proccess. However, when running gdalwarp, the processes is handled only on the CPU and the GPU remains untouched by gdal according to nvidia-smi and the gui system monitor. the samples run fine and activity shows in nvidia-smi I was able to run and compile the CUDA samples that were included in the toolkit. I've built gdal from source enabling opencl and pointing the configure options to the header files included in the Nvidia Cuda Toolkit v6.5. I'm on a new machine with linux mint 17.1 and a K420 Quadro card. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |