- 09 Feb, 2019 1 commit
-
-
Christoph Rettinger authored
Remove boost::bind from tutorial See merge request walberla/walberla!161
-
- 07 Feb, 2019 1 commit
-
-
Dominik Thoennes authored
remove mscv 2015 from ci and use cuda 9.0 in ubuntu 16.04 Closes #79 See merge request walberla/walberla!162
-
- 04 Feb, 2019 2 commits
-
-
Dominik Thoennes authored
-
Michael Kuron authored
-
- 01 Feb, 2019 1 commit
-
-
Dominik Thoennes authored
remove clang 3 and intel 2016 Closes #79 See merge request walberla/walberla!160
-
- 30 Jan, 2019 1 commit
-
-
Dominik Thoennes authored
-
- 27 Jan, 2019 1 commit
-
-
Martin Bauer authored
Resolve "Replace deprecated CUDA APIs" Closes #71 See merge request walberla/walberla!157
-
- 26 Jan, 2019 1 commit
-
-
Michael Kuron authored
-
- 24 Jan, 2019 1 commit
-
-
Martin Bauer authored
- information from CMake to codegen: double/float, OpenMP, ...
-
- 23 Jan, 2019 2 commits
-
-
Martin Bauer authored
-
Martin Bauer authored
-
- 22 Jan, 2019 19 commits
-
-
Martin Bauer authored
-
Martin Bauer authored
- More flexibility for the user to implement custom checkpointing
-
Martin Bauer authored
MPICH2 apparently expects a non-const pointer for blocklenghts whereas other MPIs expect const pointer -> removed const to work with all
-
Martin Bauer authored
-
Martin Bauer authored
-
Martin Bauer authored
-
Martin Bauer authored
- intel 19 internal bug when using auto, and implicit capture in lambdas
-
Martin Bauer authored
-
Martin Bauer authored
-
Martin Bauer authored
-
Martin Bauer authored
- LB on GPU, Uniform Grid Benchmark app - helper class to schedule tasks to multiple CUDA streams
-
Martin Bauer authored
-
Martin Bauer authored
- comparison to old CPU transfer communication included
-
Martin Bauer authored
- CUDA compiler has problems to compile external json library - timing pool is included by BlockForest, and previously timing pool included JSON library
-
Martin Bauer authored
previously the ghost layer was aligned
-
Martin Bauer authored
-
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
-
Martin Bauer authored
- templated buffer classes allow the buffer systems to work with custom buffers, e.g. buffers of GPU memory
-
Sebastian Eibl authored
Fix for numerical issue in EPA See merge request !154
-
- 12 Jan, 2019 1 commit
-
-
Christoph Schwarzmeier authored
Add waLBerla-conforming .editorconfig See merge request !156
-
- 11 Jan, 2019 1 commit
-
-
Christoph Schwarzmeier authored
-
- 10 Jan, 2019 2 commits
-
-
Christoph Rettinger authored
Change stringstream name in macros to hopefully avoid name clashes See merge request !155
-
Christoph Rettinger authored
-
- 09 Jan, 2019 1 commit
-
-
Sebastian Eibl authored
-
- 08 Jan, 2019 3 commits
-
-
Martin Bauer authored
Resolve "add sent and received bytes to BufferSystem" Closes #75 See merge request !153
-
Tobias Leemann authored
-
Sebastian Eibl authored
-
- 07 Jan, 2019 2 commits
-
-
Christoph Schwarzmeier authored
-
Christoph Schwarzmeier authored
-