Skip to content
Snippets Groups Projects
Select Git revision
  • develop
  • feature/MatlabBackup
  • feature/MatlabWrapper
  • feature/deviceName
  • feature/linux
  • master default protected
  • timing
  • v2.02
  • v2.01
  • v2.0
  • Release_1.0
  • HIP_name_chnage
  • deletedOld
  • v1.0.2
  • PaperRelease
  • Release-0.0.6b
  • Release-0.0.5b
  • Release-0.0.4b
  • Release-0.0.3a
  • Release-0.0.2a
  • Release-0.0.1a
21 results
You can move around the graph by using the arrow keys.
Created with Raphaël 2.2.04Jan21Oct78Aug1May30Apr2830Mar29212018Feb1413128726Jan238Dec211Nov31Oct126Sep227Aug25151210920Jun17133May28Apr2531Mar2126Feb2426Jan211813828Oct19930Jun1288May530Apr28278428Mar3Feb8Jan6Dec24Nov23Oct22131127Aug25159Jul4319Jun18176May52128Apr25241817161514128743231Mar28272524212024Feb21201586111Jan11Nov6131Oct29282725242221191611109328Sep2726242321121075230Aug6521Binary commitAdded a neighborhood sum kernelFixed memory allocation error for Linear UnmixingThe median filter shouldn't move memory to the card if there is nothing to do.v1.0.2v1.0.2Added a longer delay to the registry hack to handle large datasetsBinary commit3D LoG and large neighborhood implemented2-D LoG is workingSeperable kernel?Start of LoGBinary commitChoose the device with the most memory available not biggest possibleCorrected the log error in the entropy filterImage chuncks were not utilizing the memory when one dimension did not match the max chunk sizeMoved MexResize into the correct subfolder and updated vc project.First attempt at linux compilefeature/linuxfeature/linuxFixed the entropy filterAdded the start to an entropy filterDon't use linear interpolation if it is not nessasaryBinary CommitAdded a scoped mutex to command runAdded a floor to Vec so that resize can call it explicitlyBinary commitFixed a bug in calculating the max number of threads to use in a block.Added a random wait for the file semaphore which is important for multi threaded operations.Suppressing the warning by fixing the Vec functions correctlyFound memory leak in resizeBinary commitSuppressed a compiler warning in VecAdded an early out message to tell the matlab caller that resize cannot enlarge yetFixed bug where the image was not reduced or enlarged.Binary commitMoved the linear interpolation to CudaImageContainer and changed coordinate access to () instead of []Added the device name to the mutex txt file.Added the occupancy calculator to each kernelAdded a function to better calculate the optimal block occupancyAdded compute and shader model 5.0 to the compile flagsRemoved the old ReduceImageAdded the device name to the mutex txt file.feature/deviceN…feature/deviceNameResize now works for mean reductions