• Files Changed
• Browse Source

Update to requested version and fix reference to fate in previous changelog (was references as a bsc)

- Update to v1.4.0 (bsc#1103494)
  * Features:
  * Improved support for installation with latest ROCm
  * Improved support for latest rdma-core
  * Added support for CUDA IPC for intra-node GPU, CUDA memory
    allocation cache for mem-type detection, latest Mellanox
    devices, Nvidia GPU managed memory, multiple connections
    between the same pair of workers, large worker address for
    client/server connection establishment and INADDR_ANY, and
    for bitwise atomics operations.
  * Bugfixes:
  * Performance fixes for rendezvous protocol
  * Memory hook fixes
  * Clang support fixes
  * Self tl multi-rail fix
  * Thread safety fixes in IB/RDMA transport
  * Compilation fixes with upstream rdma-core
  * Multiple minor bugfixes (full list on github)
  * Segfault fix for a code generated by armclang compiler
  * UCP memory-domain index fix for zero-copy active messages

- Update to v1.3.1 (fate#325996)

• Files Changed
• Browse Source

- Update to v1.3.1 (bsc#325996)
  - Prevent potential out-of-order sending in shared memory active messages
  - CUDA: Include cudamem.h in source tarball, pass cudaFree memory size
  - Registration cache: fix large range lookup, handle shmat(REMAP)/mmap(FIXED)
  - Limit IB CQE size for specific ARM boards

- Update to v1.3.0 (bsc#1104159)
  - Added stream-based communication API to UCP
  - Added support for GPU platforms: Nvidia CUDA and AMD ROCM software stacks
  - Added API for client/server based connection establishment
  - Added support for TCP transport
  - Support for InfiniBand tag-matching offload for DC and accelerated transports
  - Multi-rail support for eager and rendezvous protocols
  - Added support for tag-matching communications with CUDA buffers
  - Added ucp_rkey_ptr() to obtain pointer for shared memory region
  - Avoid progress overhead on unused transports
  - Improved scalability of software tag-matching by using a hash table
  - Added transparent huge-pages allocator
  - Added non-blocking flush and disconnect for UCP
  - Support fixed-address memory allocation via ucp_mem_map()
  - Added ucp_tag_send_nbr() API to avoid send request allocation
  - Support global addressing in all IB transports
  - Add support for external epoll fd and edge-triggered events
  - Added registration cache for knem
  - Initial support for Java bindings
  - Multiple bugfixes (full list on github)
- Drop UCT-UD-fixed-compilation-by-gcc8.patch as it was fixed upstream
- Refresh openucx-s390x-support.patch against latest sources

- Remove libnuma-devel on s390x for older releases

- Add UCT-UD-fixed-compilation-by-gcc8.patch to fix compilation
  with GCC8 (bsc#1084635)

• Files Changed
• Browse Source

initialize package as branch

• Browse Source