Directory | Changes | Lines of Code | Lines per Change |
---|---|---|---|
Totals | 392 (100.0%) | 11261 (100.0%) | 28.7 |
CCA/Components/Schedulers/ | 197 (50.3%) | 8981 (79.8%) | 45.5 |
CCA/Components/Models/Radiation/RMCRT/ | 29 (7.4%) | 1240 (11.0%) | 42.7 |
Core/Containers/ | 4 (1.0%) | 371 (3.3%) | 92.7 |
Core/Parallel/ | 19 (4.8%) | 135 (1.2%) | 7.1 |
/ | 18 (4.6%) | 134 (1.2%) | 7.4 |
CCA/Ports/ | 5 (1.3%) | 99 (0.9%) | 19.8 |
Core/Grid/Variables/ | 4 (1.0%) | 93 (0.8%) | 23.2 |
CCA/Components/LoadBalancers/ | 8 (2.0%) | 45 (0.4%) | 5.6 |
Core/Geometry/ | 2 (0.5%) | 39 (0.3%) | 19.5 |
Core/Malloc/ | 2 (0.5%) | 38 (0.3%) | 19.0 |
Core/Grid/ | 15 (3.8%) | 23 (0.2%) | 1.5 |
CCA/Components/SimulationController/ | 4 (1.0%) | 17 (0.2%) | 4.2 |
CCA/Components/Regridder/ | 3 (0.8%) | 16 (0.1%) | 5.3 |
build_scripts/ | 3 (0.8%) | 7 (0.1%) | 2.3 |
R_Tester/ | 1 (0.3%) | 7 (0.1%) | 7.0 |
Core/Thread/ | 5 (1.3%) | 4 (0.0%) | 0.8 |
CCA/Components/Examples/ | 1 (0.3%) | 4 (0.0%) | 4.0 |
StandAlone/ | 4 (1.0%) | 3 (0.0%) | 0.7 |
Core/Util/ | 6 (1.5%) | 2 (0.0%) | 0.3 |
CCA/Components/Arches/ | 7 (1.8%) | 2 (0.0%) | 0.2 |
CCA/Components/MPM/ConstitutiveModel/UnusedCM/ | 2 (0.5%) | 1 (0.0%) | 0.5 |
include/sci_defs/ | 2 (0.5%) | 0 (0.0%) | 0.0 |
include/ | 3 (0.8%) | 0 (0.0%) | 0.0 |
Core/Basis/ | 42 (10.7%) | 0 (0.0%) | 0.0 |
CCA/Components/Parent/ | 4 (1.0%) | 0 (0.0%) | 0.0 |
CCA/Components/MPM/ | 1 (0.3%) | 0 (0.0%) | 0.0 |
CCA/Components/DataArchiver/ | 1 (0.3%) | 0 (0.0%) | 0.0 |
Make sure and distinguish between ExecTimes, WaitTimes and MPIScheduler_TimingsOut SCI_DEBUG flags. This was missed when this code, common to all schedulers was extracted into a method (outputTimingStats) and put into MPIScheduler.
0 lines of code changed in 2 files:
Some cleanup and work toward refining and better understanding MPI timings and stats.
Pull ancient VAMPIR weeds.
134 lines of code changed in 18 files:
Unified scheduler can run multi-threaded on intial timestep. This speeds up the 0th timestep considerably, especially with large problems and particle creation, etc.
4 lines of code changed in 1 file:
Consolidate ExecTimes, WaitTimes, and MPI Timing code into parent (MPI) scheduler. This eliminates miles of redundnat and error-prone code. Now it only has to be correct in one place.
162 lines of code changed in 7 files:
Make the SCI_DEBUG flag "DynamicMPI_TimingsOut" actually output timings files. This is needed for the Sandia frameworks tech report.
Also do some various formatting, cleanup and add some comments.
51 lines of code changed in 3 files:
Pull some leftover MSC_VER weeds
0 lines of code changed in 10 files:
Remove antiquated TAU support.
124 lines of code changed in 57 files:
Cleanup in Switcher component - for merge with and usage in arl_dev branch.
0 lines of code changed in 4 files:
We can now use the static version of the CUDA runtime lib on Titan.
12 lines of code changed in 2 files:
Following r53735, varLabel name change boundFlux -> RMCRTboundFlux for GPU code.
9 lines of code changed in 1 file:
Eliminate linking with cudart_static with static builds. This is not working on Titan due to the current CUDA Toolkit version, 5.5. Once Titan is upgraded to CUDA 6.5, we can then use cudart_static in static builds.
* generated new configure script
24 lines of code changed in 2 files:
Accurately report specs on all available on-node GPUs.
5 lines of code changed in 1 file:
Comment out multi-GPU code that's not working on local SCI cluster. Will fix this soon.
7 lines of code changed in 1 file:
Remove ProblemSetupException thrown when trying to use > 1 available GPU per node. We correctly support multiple GPUs.
5 lines of code changed in 1 file:
Eliminate compiler warning about comparison between signed and unsigned integer expressions.
1 lines of code changed in 1 file:
* Don't pass c++11 flag to NVCC. NVCC from CUDA <=6.0 doesn't support it. We don't use C++11 features in any NVCC compiled code anyway (yet).
* this allows us to run using C++11 features in Uintah code and CUDA 5.5 on Titan
* generate new configure script
* Fix C++11 compiler error about inability to find string literal in Allocator.cc (SCIRun::PrintTag(void*))
46 lines of code changed in 5 files:
Do not throw exception when fine-level halo used in GPU::RMCRT_DO. This is all working properly now.
0 lines of code changed in 1 file:
Get rid of operator new calls on device. Use compile time constant to size arrays for now.
4 lines of code changed in 1 file:
Cleanup TaskDBG output in threaded schedulers, reporting in ThreadedMPI and Unified schedulers has not been consistent. Also restrict thread-specific debugstream output.
20 lines of code changed in 4 files:
Some minor refactoring and debug stream improvements while hunting down the multi-threaded Hypre bug.
13 lines of code changed in 6 files:
(65 more)