Commits · 4ebf69ff1cbf666cc0a849f9e8ffb84f5fbead45 · Vineet Kumar / RAJA · GitLab

Aug 31, 2017
- Merge remote branch 'origin/develop' into feature/kunen1/atomic · 4ebf69ff
  Adam J. Kunen authored Aug 31, 2017
  
  4ebf69ff
- Updated to use acquire/release for builtin atomics · be4050ce
  Adam J. Kunen authored Aug 31, 2017
  
  be4050ce
- Merge pull request #317 from jeffhammond/feature/hammond/intel_mm · fd40ee61
  Tom Scogland authored Aug 31, 2017
  fd40ee61
- explicitly exit with success if no errors pop up · 36a1978b
  Tom Scogland authored Aug 31, 2017
  
  36a1978b
- tweak travis to avoid intel on external PRs · cb444c57
  Tom Scogland authored Aug 30, 2017
  
  cb444c57
Aug 30, 2017
- Added some documentation for atomic operations · 873baab2
  Adam J. Kunen authored Aug 30, 2017
  
  873baab2
- Switched _InterlockedCompareExchange to _InterlockedCompareExchange64 for 64-bit CAS · aa3a7989
  Adam J. Kunen authored Aug 30, 2017
  
  aa3a7989
- Fixed cast for MSVC atomic CAS · 7e734711
  Adam J. Kunen authored Aug 30, 2017
  
  7e734711
- Merge remote branch 'origin/develop' into feature/kunen1/atomic · 88e4ea84
  Adam J. Kunen authored Aug 30, 2017
  
  88e4ea84
- Refactored reinterp_A_to_B conversion, and (hopefully) fixed atomic oper for msvc · 24e3ac74
  Adam J. Kunen authored Aug 30, 2017
  
  24e3ac74
- Merge branch 'develop' into feature/hammond/intel_mm · fe101591
  David Beckingsale authored Aug 30, 2017
  
  fe101591
- Merge pull request #319 from LLNL/feature/kunen1/fix_icc_chaos5 · b4435c2b
  David Beckingsale authored Aug 30, 2017
  b4435c2b
- Merge branch 'develop' into feature/hammond/intel_mm · 14757c29
  Tom Scogland authored Aug 30, 2017
  
  14757c29
- Merge branch 'develop' into feature/kunen1/fix_icc_chaos5 · 9a22a6a8
  Tom Scogland authored Aug 30, 2017
  
  9a22a6a8
- Merge pull request #318 from LLNL/bugfix/trws/extra_nvcc_14_check · c3a72edb
  Tom Scogland authored Aug 30, 2017
  c3a72edb
- Trying out _InterlockedCompareExchange for MSVC instead of... · ec55ad24
  Adam J. Kunen authored Aug 29, 2017
  ec55ad24
- Guarded logical atomics to permit only integral types. · 6ad180f4
  Adam J. Kunen authored Aug 29, 2017
  6ad180f4
- Fixed configuration testing for "power of 2" with our broken intel compiler install on Chaos5 · a710a10e
  Adam J. Kunen authored Aug 29, 2017
  
  a710a10e
- Merge remote branch 'origin/develop' into feature/kunen1/atomic · e340aa5f
  Adam J. Kunen authored Aug 29, 2017
  e340aa5f
- ensure we are testing the correct compiler · da7d08ff
  Tom Scogland authored Aug 29, 2017
  
  da7d08ff
- add an extra check before activating 14 on nvcc, it is picky about host compilers · 99e423e7
  Tom Scogland authored Aug 29, 2017
  
  99e423e7
Aug 29, 2017
- malloc.h not required (and problematic) · 4badba3e
  Jeff Hammond authored Aug 29, 2017
  
  4badba3e
- add support for Intel compiler intrinsics _mm_{malloc,free} · e6cb8438
  Jeff Hammond authored Aug 29, 2017
  e6cb8438
- Got basic builtin atomic support, cleaned up CUDA support, got most operators... · 84782b2d
  Adam J. Kunen authored Aug 29, 2017
  84782b2d
- Merge pull request #316 from LLNL/bugfix/trws/aligned_alloc · c95fb3d1
  Tom Scogland authored Aug 29, 2017
  c95fb3d1
- fix typo, thanks @davidbeckingsale · 418c64e7
  Tom Scogland authored Aug 29, 2017
  
  418c64e7
- add comments about storing the original address · 995a25ed
  Tom Scogland authored Aug 29, 2017
  
  995a25ed
- cleanup: remove extraneous semicolons · 19caf6f5
  Tom Scogland authored Aug 29, 2017
  
  19caf6f5
- remove compile-time error from memutils, add portable alligned allocator · 93e88f9b
  Tom Scogland authored Aug 29, 2017
  
  93e88f9b
- Merge pull request #315 from LLNL/bugfix/trws/actually-use-flags · 6e574d3b
  Tom Scogland authored Aug 29, 2017
  6e574d3b
- Merge branch 'develop' into bugfix/trws/actually-use-flags · 60c94113
  Tom Scogland authored Aug 29, 2017
  
  60c94113
- Merge pull request #314 from LLNL/feature/trws/reduction-refactor · ad7f03e5
  Tom Scogland authored Aug 29, 2017
  ad7f03e5
- resolve annoying header cycle · 4a590a28
  Tom Scogland authored Aug 28, 2017
  
  4a590a28
- factor out common combinable implementation, add local method · 7782c4ad
  Tom Scogland authored Aug 28, 2017
  
  7782c4ad
- appease msvc and nvcc · 1ec50f7e
  Tom Scogland authored Aug 25, 2017
  
  1ec50f7e
- fix host-device issue for cuda 8 · 32fa567c
  Tom Scogland authored Aug 25, 2017
  
  32fa567c
- address cuda issues, combine test-cuda-reduce-{min,max}loc · d0073dba
  Tom Scogland authored Aug 25, 2017
  
  d0073dba
- clean up remaining spacing issues, factor out annoying repetetive declarations · 32f672ae
  Tom Scogland authored Aug 25, 2017
  
  32f672ae
- moving includes inside header guard · 97b37a38
  Tom Scogland authored Aug 25, 2017
  
  97b37a38
- cleanup spacing and comments · 7c02e956
  Tom Scogland authored Aug 25, 2017
  
  7c02e956