1. 24 Apr, 2019 1 commit
    • Martin Bauer's avatar
      Improvements for GPU code generation · f504b40f
      Martin Bauer authored
      - turned on restrict keyword by default (makes large difference on GPUs)
      - smarter block indexing: changing block size depending on domain size
        Example: previously there where (1,1,1) blocks when requested
        block size was (64, 1, 1) and domain size (1, 512, 512), now the
        block size is changed automatically to (1, 64, 1) in this case
      - added __lauch_bounds__ to kernels to allow better optimizations from
        the CUDA compiler
  2. 21 Mar, 2019 1 commit
    • Martin Bauer's avatar
      Separated modules into subfolders with own setup.py · 1e02cdc7
      Martin Bauer authored
      This restructuring allows for easier separation of modules into
      separate repositories later. Also, now pip install with repo url can be
      The setup.py files have also been updated to correctly reference each
      other. Module versions are not extracted from git state
  3. 15 Mar, 2019 1 commit
  4. 12 Mar, 2019 1 commit
  5. 26 Feb, 2019 1 commit
    • Martin Bauer's avatar
      Random number generation support for pystencils · 6a01f3e2
      Martin Bauer authored
      - counter-based philox RNG: counter/key is filled with cell coordinate
        and optional external parameters like block position and time step
      - works on CPU and GPU - on CPU only for non-vectorized versions
      - introduced more flexible "CustomCodeNode" that can inject
        backend-specific hand-written code
  6. 14 Nov, 2018 3 commits
  7. 07 Jun, 2018 1 commit
    • Martin Bauer's avatar
      pystencils field · 8ca5e2fb
      Martin Bauer authored
      - better latex display for indirect accesses
      - new field type 'custom': only custom fields can be accessed indirectly
        no static bounds check possible for custom fields
  8. 30 Apr, 2018 1 commit
  9. 13 Apr, 2018 2 commits
  10. 10 Apr, 2018 3 commits
  11. 06 Feb, 2018 2 commits
    • Martin Bauer's avatar
      Changed parameter bind caching for CPU and GPU kernels · d30c5f73
      Martin Bauer authored
      - previously all objects where cached by id()
      - for waLBerla simulations in each time step a new np.array view
        is created from the waLBerla field. Each of these views has a
        different id -> caching did not work for waLBerla setups
      - changed hash for numpy arrays: instead of id, a tuple of
        (dataPtr, strides, shapes) is used as hash input
    • Martin Bauer's avatar
      New Boundary step system / fixes in lbmpy phasefield · b148d508
      Martin Bauer authored
      - scaling interface width eta instead of surface tensions tau to correct
        interface profile & surface tensions
  12. 31 Jan, 2018 1 commit
  13. 19 Jan, 2018 1 commit
    • João Victor Tozatti Risso's avatar
      Code generation for field serialization into buffers · 979ee93b
      João Victor Tozatti Risso authored and Martin Bauer's avatar Martin Bauer committed
      Concept: Generate code involving the (un)packing of fields (from)to linear
      (1D) arrays, i.e. (de)serialization of the field values for buffered
      A linear index is generated for the buffer, by inferring the strides and
      variables of the loops over fields in the AST. In the CPU, this information is
      obtained through the makeLoopOverDomain function, in
      pystencils/transformations/transformations.py. On CUDA, the strides of
      the fields (excluding buffers) are combined with the indexing variables to infer
      the indexing of the buffer.
      What is supported:
          - code generation for both CPU and GPU
          - (un)packing of fields with all the memory layouts supported by
          - (un)packing slices of fields (from)into the buffer
          - (un)packing subsets of cell values from the fields (from)into the buffer
      - assumes that only one buffer and one field are being operated within
      each kernel, however multiple equations involving the buffer and the
      field are supported.
      - (un)packing multiple cell values (from)into the buffer is supported,
      however it is limited to the fields with indexDimensions=1. The same
      applies to (un)packing subset of cell values of each cell.
      Changes in this commit:
      - add the FieldType enumeration to pystencils/field.py, to mark fields
      of various types. This is replaces and is a generalization of the
      isIndexedField boolean flag of the Field class. For now, the types
      supported are: generic, indexed and buffer fields.
      - add the fieldType property to the Field class, which indicates the
      type of the field. Modifications were also performed to the member
      functions of the Field class to add this property.
      - add resolveBufferAccesses function, which replaces the fields marked
      as buffers with the actual field access in the AST traversal.
      Miscelaneous changes:
      - add blockDim and gridDim variables as CUDA indexing variables.
  14. 11 Dec, 2017 1 commit
  15. 02 Dec, 2017 1 commit
  16. 10 Oct, 2017 1 commit
  17. 21 Jul, 2017 1 commit
  18. 11 Apr, 2017 2 commits
  19. 30 Mar, 2017 1 commit
  20. 24 Mar, 2017 4 commits
  21. 01 Mar, 2017 1 commit
    • Martin Bauer's avatar
      pystencils: cpujit · dd17cd30
      Martin Bauer authored
      - windows support
      - automatic caching and creation of shared library with all generated kernels
      - restrict keyword and function prefixes are preprocessor macros now -> easier to generate one code for linux, cuda, windows
  22. 21 Feb, 2017 1 commit
  23. 08 Dec, 2016 1 commit
  24. 06 Nov, 2016 2 commits
  25. 03 Nov, 2016 1 commit
    • Martin Bauer's avatar
      Documentation & Restructuring · aea202a7
      Martin Bauer authored
      - added sphinx files for documentation generation
      - collected kernel creation functions in new "cpu" and "cudagpu" modules
  26. 02 Nov, 2016 1 commit