github.com/marian-nmt/nccl.git - Unnamed repository; edit this file 'description' to name the repository.

Age	Commit message (Collapse)	Author
2016-06-17	Add a debug level to NCCL and CUDA versions at init	Sylvain Jeaugey

2016-06-07	Make NCCL collectives work on communicators with only one rank	Sylvain Jeaugey

2016-06-03	Removing unneeded includes	Sylvain Jeaugey

2016-04-19	Fix random deadlock during ncclCommInitRank.	Sylvain Jeaugey

2016-02-19	Fixed useRemoteRecv consistency issue.	Nathan Luehr
	Change-Id: Ib093a8dc3bb093eddc89dad81d3fffa53c03a6a2 Reviewed-on: http://git-master/r/1013543 Reviewed-by: Cliff Woolley <jwoolley@nvidia.com> Tested-by: Przemek Tredak <ptredak@nvidia.com>
2016-02-13	Fixed buffer overflow in ReduceOrCopy	Nathan Luehr
	Bug caused AllGathers and ReduceScatters of less than 8 bytes to fail in certain cases. Change-Id: I33e1beb50805bfdb457ae16a90e3f91c1b283b9b Reviewed-on: http://git-master/r/1011505 Reviewed-by: Przemek Tredak <ptredak@nvidia.com> Tested-by: Przemek Tredak <ptredak@nvidia.com>
2016-01-29	Libwrap checks for LIB.so.1 if LIB.so not found	Nathan Luehr
	Change-Id: I6f07f887f828cb2259dcfd496a2ad707db898cf5 Reviewed-on: http://git-master/r/1000162 Reviewed-by: Przemek Tredak <ptredak@nvidia.com> Tested-by: Przemek Tredak <ptredak@nvidia.com>
2016-01-29	Enabled support for char type to be unsigned.	Nathan Luehr
	GCC on POWER arch defines char type as unsigned. Change-Id: Ic143cb058fe42414b1f6f1f45b02132c837726ae Reviewed-on: http://git-master/r/999614 Reviewed-by: Przemek Tredak <ptredak@nvidia.com> Tested-by: Przemek Tredak <ptredak@nvidia.com>
2016-01-28	Moved tests to separate dir and improved MPI test	Sylvain Jeaugey
	test sources moved to test/ directory. MPI test displays PASS/FAIL and returns code accordingly. Change-Id: I058ebd1bd5202d8f38cc9787898b2480100c102b Reviewed-on: http://git-master/r/936086 Reviewed-by: Przemek Tredak <ptredak@nvidia.com> Tested-by: Przemek Tredak <ptredak@nvidia.com>
2016-01-22	Added support for more than 8 GPUs.	Nathan Luehr
	Change-Id: Iaa1841036a7bfdad6ebec99fed0adcd2bbe6ffad Reviewed-on: http://git-master/r/935459 Reviewed-by: Cliff Woolley <jwoolley@nvidia.com> Tested-by: Przemek Tredak <ptredak@nvidia.com>
2016-01-21	Fixed deadlock in back-to-back reduce_scatters.	Nathan Luehr
	Change-Id: I92d32b15e516a39710b676aee692ae9b70638937 Reviewed-on: http://git-master/r/935458 Reviewed-by: Przemek Tredak <ptredak@nvidia.com> Tested-by: Przemek Tredak <ptredak@nvidia.com>
2015-12-11	Fixed bug in MPI initialization.	Nathan Luehr

2015-12-04	Add int64 and uint64 types for all algorithms and tests	Simon Layton

2015-11-19	Fixed a race condition in reduce and braodcast.	Nathan Luehr

2015-11-17	Initial release.	Nathan Luehr