1. 13 Jul, 2021 1 commit
  2. 17 Dec, 2020 1 commit
  3. 06 Mar, 2019 1 commit
  4. 23 Jan, 2019 1 commit
  5. 22 Jan, 2019 2 commits
    • Martin Bauer's avatar
      CUDA Parallel Streams & UniformGridGPU Benchmark · a0c86311
      Martin Bauer authored
      - LB on GPU, Uniform Grid Benchmark app
      - helper class to schedule tasks to multiple CUDA streams
      a0c86311
    • Martin Bauer's avatar
      New GPU communication scheme with GPU kernels for packing · 319909f0
      Martin Bauer authored
      Features:
         - uses generated pack infos for packing & unpacking directly on GPU
         - can directly send GPU buffers if cuda-enabled MPI is available,
           otherwise the packed buffers are transfered to CPU first
         - communication hiding with cuda streams: communication can be run
           asynchronously - especially useful when compute kernel is also
           split up into inner and outer part
      
      - added RAII classes for CUDA streams and events
      - equivalence test that checks if generated CPU and GPU (overlapped)
        versions are computing same result as normal waLBerla LBM kernel
      319909f0