Skip to content
Snippets Groups Projects
Select Git revision
  • 66-absolute-access-is-probably-not-copied-correctly-after-_eval_subs
  • const_fix
  • fhennig/v2.0-deprecations
  • fma
  • gpu_bufferfield_fix
  • gpu_liveness_opts
  • holzer-master-patch-46757
  • hyteg
  • improved_comm
  • master default protected
  • rangersbach/reductions
  • target_dh_refactoring
  • v2.0-dev
  • vectorization_sqrt_fix
  • zikeliml/124-rework-tutorials
  • zikeliml/Task-96-dotExporterForAST
  • release/1.3.7 protected
  • release/1.3.6 protected
  • release/2.0.dev0 protected
  • release/1.3.5 protected
  • release/1.3.4 protected
  • release/1.3.3 protected
  • release/1.3.2 protected
  • release/1.3.1 protected
  • release/1.3 protected
  • release/1.2 protected
  • release/1.1.1 protected
  • release/1.1 protected
  • release/1.0.1 protected
  • release/1.0 protected
  • release/0.4.4 protected
  • last/Kerncraft
  • last/OpenCL
  • last/LLVM
  • release/0.4.3 protected
  • release/0.4.2 protected
36 results
You can move around the graph by using the arrow keys.
Created with Raphaël 2.2.019Feb1817141312111065431Jan302928272423222120171615141318Dec131018Nov13127628Oct21141110128Sep824Aug191227Jul24231917161598543111Jun105131May282218161329Apr262322218543228Mar27252019151413121110876528Feb27252019183231Jan30282625191817161514121110918Dec124128Nov1417Oct29Sep282019181513729Aug2824231825Jul20171312530Jun292824227431May3011Apr109331Mar282724221711823Feb22Dec10Nov974325Oct241029Sep282728Jul2123May201143228Apr2728Mar25211621Feb17161110Merge branch 'bauerd/type-annotation' into 'v2.0-dev'Relax type annotation in PsBlock __init__Catch CUDARuntimeError for mising CUDA capable device in reduction GPU testMerge branch 'v2.0-dev' into rangersbach/reductionsMerge branch 'fhennig/lambdas' into 'v2.0-dev'GPU Indexing Schemes and Launch ConfigurationsMerge branch 'bauerd/canonicalize' into 'v2.0-dev'Extend symbol canonicalization[ci skip] [draft] First version that allows to follow an entire AST but the output is not nice yet.[ci skip] [draft] continue the printing of the nodes.Avoid duplicate definition of atomicMin/Max for HIPMerge branch 'bauerd/fix-vector-set' into 'v2.0-dev'Fix order of arguments in x86 set intrinsicsUse import or skip mechanism for cupyFix ImportError for cupyFix typecheck[ci skip] [draft] Now I know how it works and I managed to do it for sympy, but also found out that for sympy there is already a dot printer implementation... So now let's do it for pystencils.[ci skip] [draft] Test most basic sympy printing.Fix lintSplit reduction test into separate CPU/GPU tests[ci skip] [draft] Test around with the nodal elements and how to best pattern match them.Add generator for SIMD horizontal operations and the emitted code.Fix bug with doubly inverted sign for subtraction reductions[ci skip] [draft] Test writing and reading `.dot` files.[ci skip] [draft] Add tests for graphviz dot printing.[ci skip] [draft] try to create a .dot representation for the AST and define a draft for a visit funtion.[draft] Create two drafts for the dot printer from which the actual printer can be created. One is a copy of `ir_printer.py` to keep the dot printer as close to the codebase as possible and one is a attempt from copilot that considered both printers already available within the `emmision` folder, the `dot_printer` from the old backend, and the calling interface `to_dot` from `display_utils.py`.[ci skip] Convert tutorial jupyter notebooks to jupytext files in percent format.zikeliml/124-re…zikeliml/124-rework-tutorialsRevert "[ci skip] Convert getting started tutorial to percent script for jupytext.", as this was done with copilot, but there is a tool within jupytext that does the same and which I trust more.[ci skip] Convert getting started tutorial to percent script for jupytext.Minor fixRefactor PsVecHorizontal as PsBinOpMinor refactor of reduction opsMinor fixMerge remote-tracking branch 'origin/rangersbach/reductions' into rangersbach/reductionsAdd initial implementation for horizontal reductions for vectorizationSupport atomic sub, min, max for fp reductions using custom implementations with CAS mechanismTemporarily change default CUDA block size for CUDA jitAdd guard for INFINITY numeric limit macro used by cuda backendMerge branch 'v2.0-dev' into rangersbach/reductions