diff --git a/VERSION b/VERSION index 63469f84fb1..7618cdc6130 100644 --- a/VERSION +++ b/VERSION @@ -41,7 +41,7 @@ flex_min_version=2.5.4 # requirement is that it must be entirely printable ASCII characters # and have no white space. -greek=a1 +greek=rc1 # If repo_rev is empty, then the repository version number will be # obtained during "make dist" via the "git describe --tags --always" @@ -94,14 +94,14 @@ date="Unreleased developer copy" # Version numbers are described in the Libtool current:revision:age # format. -libmpi_so_version=80:5:40 -libmpi_mpifh_so_version=80:0:40 -libmpi_usempi_tkr_so_version=80:0:40 -libmpi_usempi_ignore_tkr_so_version=80:0:40 -libmpi_usempif08_so_version=80:2:40 -libopen_pal_so_version=80:4:0 -libmpi_java_so_version=80:0:40 -liboshmem_so_version=80:3:40 +libmpi_so_version=80:6:40 +libmpi_mpifh_so_version=80:1:40 +libmpi_usempi_tkr_so_version=80:1:40 +libmpi_usempi_ignore_tkr_so_version=80:1:40 +libmpi_usempif08_so_version=80:3:40 +libopen_pal_so_version=80:5:0 +libmpi_java_so_version=80:1:40 +liboshmem_so_version=80:4:40 libompitrace_so_version=80:0:40 # "Common" components install standalone libraries that are run-time @@ -115,7 +115,7 @@ libmca_ompi_common_monitoring_so_version=80:0:0 # OPAL layer libmca_opal_common_cuda_so_version=80:0:0 -libmca_opal_common_ofi_so_version=80:3:0 +libmca_opal_common_ofi_so_version=80:4:0 libmca_opal_common_sm_so_version=80:1:0 libmca_opal_common_ucx_so_version=80:1:0 libmca_opal_common_ugni_so_version=80:0:0 diff --git a/docs/release-notes/changelog/v5.0.x.rst b/docs/release-notes/changelog/v5.0.x.rst index 701b2cb55f7..f3107b81ddd 100644 --- a/docs/release-notes/changelog/v5.0.x.rst +++ b/docs/release-notes/changelog/v5.0.x.rst @@ -4,6 +4,36 @@ Open MPI v5.0.x series This file contains all the NEWS updates for the Open MPI v5.0.x series, in reverse chronological order. +Open MPI Version v5.0.6.rc1 +------------------------------ +:Date: 7 November 2024 + +- Internal PMIx and PRRTe version: + + - PMIx (v5.0.4). Repo: ``https://github.com/openpmix/openpmix``. Commit hash: ``c6b895e261384016e154865dd236faaaa471d173``. + - PRRTE (v3.0.7). repo: ``https://github.com/openpmix/prrte``. Commit hash: ``1b6e6d7e3cb8c0837eba1730cb62b62186ab042c``. + + - Session Management Enhancements: + - Finalization Control: Ensures proper finalization of classes when references to the OPAL utility layer reach zero. A new smoke test has been added to validate this behavior. + - Test and CI Additions: A smoke test was introduced for session management, also integrated into macOS GitHub CI to ensure stability across platforms. + - Recognize requests from the same instance rather than same communicator, fixes Waitall/Waitany/Testall/Testany. + - Multiple Init/Finalize Handling: Improvements to handling session multiple initializations and finalizations, addressing issues with parameter management and session destruction. + + - CUDA and NVIDIA HPC Compiler Compatibility: + - Stream-ordered Allocations: Adjustments for handling CUDA stream-ordered allocations and assigning primary device context in `opal/cuda` (Akshay Venkatesh). + - nvfortran Compatibility: Configure script updated to handle NVIDIA's `nvfortran` compiler, enabling proper compilation with `-fPIC` flags for shared libraries (Gilles Gouaillardet). + - CUDA Memory Address Management: Improvements for handling virtual memory manager (VMM) pointers in CUDA applications to prevent runtime issues. + + - MPI Communication and Resource Management: + - Info Duplication: Enhanced `MPI_Info_dup` function to ensure consistent key management across duplicated info objects, supporting better memory and resource handling. + - OFI/Initialization Improvements: Refactored code for OFI common components to support session-based initialization models per MPI 4 standards. + - Resource Leak Fixes: Addressed memory leaks and reference count issues in several components to improve memory management and stability in high-demand environments. + + - Detailed Locking Protocol: Modified default file-locking protocols in UFS component to ensure data consistency, especially when using data-sieving operations, which require broader locking. + + - MPI_T Interface Enhancements: Modified MCA parameter settings to allow runtime tuning of collectives through the MPI_T interface, adding flexibility for dynamic rules in collective operations. + - Corrected various documentation typos and clarified parameter settings in several API references, improving readability and usability for end users. + Open MPI version v5.0.5 -------------------------- :Date: 23 July 2024