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 2.2.011Mar22Feb161413121142131Jan29281514826Nov25242322208Sep7319Aug828Jul19121126Jun25201813125328May16103124Apr2320151487431Mar3027262322201916131211643221Feb201912111020Jan421Oct78Aug1May30Apr2830Mar29212018Feb1413128726Jan238Dec211Nov31Oct126Sep227Aug25151210920Jun17133May28Apr2531Mar2126Feb2426Jan211813828Oct19930Jun1288May530Apr28278428Mar3Feb8Jan6Dec24Nov23Oct22131127Aug25159Jul4319Jun18176May52128Apr25241817161514Fix clang initialization order warnings in image wrappersIssue useful warnings in clang/gcc buildsMore random testing changesFix a couple of exception warningsSupport ImageOwner make sure arguments passing is by referenceUse ImageRef type-trait for image pointers owned by the script engineMake sure all arguments are passed through references to execute/processSupport for ImageOwner semanticsOwnership semantics (use public deleted constructors for clarity)Bunch of debugging and possible int/uint fixes.Simple python test-caseTesting code for metaprogramming helpersrebuilt agains cuda 9.1WIP: Portions of the new script interfaceTemplate metaprogramming helpers (and some C++14-style features).Function to pull script-engine type ids.Fix for implicit Vec<T> -> dim3 conversion in cudaSmall test script for visualizing filter outputSet python errors when kernel cannot be createdAssume row-major dimension order for 1-D vectors (this case is ambiguous)Use "row-major" (z,y,x) ordering for vector inputs (e.g. Gaussian sigmas)Added more type matches, and a compile error if numeric conversion unsupported in Python.Use int64_t/uint64_t for integer sums.Sum should now be workingMerge branch 'testing' into developPython snapshot capture codeUse smaller kernel to stop median filter from falling back (or crashing)Additional .git ignores for python and miscellaneous vs filesFixed and normalized python/matlab kernel image convertersFixed buffer overrun issue when creating image dimensions from diminfoSum needs to be able to return size_t and long long typesCapture and compare image processing snapshotsCode to generate test image setFix for sum memory allocation issueUse Vec<uint> for block/thread countsPull from Github/HIP. ScopedProcessMutex, Cuda 9.2,Avoid including windows.h in headers where possibleUse windows-specific process mutex when _WIN32 definedBinaries for Matlab HIP wrappers.Use a scoped process mutex at top-level of matlab commands