Skip to content
Snippets Groups Projects

Repository graph

You can move around the graph by using the arrow keys.
Select Git revision
  • 120-implementation-issue-with-alignment
  • 163-fix
  • adjust-ltemp-fix-scalars
  • admissible-inames-finder-avoid-pulling-in-extraneous-constraints
  • arguments-as-basestorage
  • barrier-insertion-use-self-dependencies
  • barrier-insertion-with-finer-dependency-tracking
  • better-offset-treatment
  • c99_native_complex_target
  • c_pragma
  • c_vec
  • c_vec_tag
  • cache-improvements
  • cache-invoker-and-type-inf
  • cl-function-descriptions
  • count-function-fix
  • count-granularity2
  • cpu-mutilevel-scan
  • divide-precedence-fix
  • do-not-uniquify-in-executor
  • v2017.2
  • v2017.1
  • v2016.2
  • v2016.1.1
  • v2016.1
25 results
Created with Raphaël 2.2.023Jan222119181514716Dec872130Nov2928272521426Oct22181716141398130Sep232221201714138128Aug272423212019171312111097228Jul262524222018151412976532130Jun292827262524232221201917161211105428May2524231413121173230Apr242319181613129625Mar2221141086428Feb242220191817161513121098653226Jan252019161428Nov2726729Jun25211817131230May2928111022Feb201918141396530Jan2827112130Dec24231918229Nov28278628Oct13Sep5Rename instruction attributes for more compatibility with pymbolic.imperativeDocument fuse_kernelsImplement access footprint gatheringFolds in statistics moduleImprove tag_inames interface: strings, like.INAME, unused.[gl]Add find_unused_axis_tagAdd sum_ops_to_dtypesget_op_poly doc fixImplement chunk_inameBump pymbolic depdency to fix dealing with Min/MaxOnly generate static workgroup size info if workgroup sizes are actually staticFix codegen from (immutable) tuples in Min/MaxFix up extras dependency declarationsv2016.1v2016.1Fix up declared depdendenciesBump versionFix up MANIFEST.in for releaseUpdate tutorial for better isl printing as of 0.16ISPC backend: Cast program indices to signedAdd OCCA codegen mode to ISPC targetIntroduce placeholders for hw axes, rather than using target-specific expressionsUse cgen from git in old PyOpenCL buildBump cache versionCUDA target: generate launch bounds, extern CPass kernel to get_{global,local}_axis_expr, use signed indices on CUDAImport cleanupExpressionInstruction -> AssignmentFix test failure: revert OpenCL barrier spacing styleFix CL image argumentsFix set_default_target initial setupSupport choosing target from the command lineFlatten target submodules, tweak CUDA backendUse cgen from gitFinish ISPC backendFirst steps towards an ISPC targetMinor loopy pyinstaller tweakAdd opt levels, make gNUMA test executableAdd initial version of gNUMA testAdd test for distributive law transformWorking version of the distributive law transformImprove error checking in ArrayChanger