Changelog for libfabric1-1.16.0-2.1.x86_64.rpm :

* Thu Oct 06 2022 Nicolas Morey-Chaisemartin - Add prov-rxm-Disable-128-bit-atomics.patch to fix a potential segfault on misaligned buffers.
* Fri Sep 30 2022 Nicolas Morey-Chaisemartin - Update to 1.16.0 (jsc#PED-351, jsc#PED-190) - Core - Added HMEM IPC cache - Use exact string comparison checks for network interfaces - Restructuring of poll/epoll abstraction - Add ability to disable locks completely in debug builds - Serialize access to modifying the logging calls - Minor fixes to fi_tostr text formatting - Add hmem interface checks to memory registration - EFA - Added support of Synapse AI memory. - Improved error message - Net - Temporarily forked, optimized version of tcp provider - Focused on improved performance and scalability over tcp sockets - Fork ensures tcp provider stability while net provider is developed - Shares the tcp provider protocol and base implementation for msg endpoints - Integrates direct support for rdm endpoints, using a derivative from rxm - Implements own protocol for rdm endpoints, separate from rxm;tcp - OPX - Added initial support for SDMA - General performance enhancements - Performance improvements to reliability protocol - Improved deferred work pending complete - Added support for OPX_AV=runtime - Support iov memory registration ops - Added DAOS RPC support - Atomic ops enhancements - Improved documentation - Debug build enhancements - Fixed compiler warnings - Reduced time to compile prov/opx code - General bug fixes - Fixed PSN wrapping scaling - Added intranode fence - Addressed bugs discovered by coverity scan - PSM2 - Fix sending CQ data in some instances of fi_tsendmsg - PSM3 - Updated to match Intel Ethernet Fabric Suite (IEFS) 11.3 release - RxM - Update to read multiple completions at once from msg provider - Move RxM AV implementation to util code to share with net provider - Minor code cleanups - SHM - Implement and use ipc_cache - Add log messages for debugging and error tracking - Fix check for FI_MR_HMEM mr_mode - Move shm signal handlers initialization to EP - Added log messages for errors detected - TCP - Fix incorrect signaling of the CQ - Increase max number of poll events to retrieve - Acquire ep lock prior to flushing socket in shutdown - Verify ep state prior to progressing socket data - Read cm error data when receiving connreq response - Log error on connect failure - Fix assertion failure in CQ progress function - Util - Fix text in log of UFFD ioctl failure - Introduce cuda ipc monitor - Fix CQ memory leak handling overflow - Fix MR mode bit check for ver 1.5 and greater - Add max_array_size to track/check array overflow - Always progress transfers when reading from a CQ - Handle NULL address insertion - Try IPv4 before IPv6 addresses when starting name server - Fix IP util av default address length - Fix util IP getinfo path to read hints->addr_format - Fix debug print mismatch - Fix return code when memory allocation fails. - Fix build sign warning in ofi_bufpool_region_alloc - Minor code cleanups - Print warning if an addr is inserted into an AV again - Verbs - Fix support of FI_SOCKADDR_IB when requested by the application - Ensure all posted receives are flushed to the application - Update ofi_mr_cache_search API for hmem IPC support - Reduce logging verbosity for \"no active ports\" - Fix incorrect length used in memory registration - Various minor bug fixes for test failures - Fix a memory leak getting IB address - Implement verbs provider on Windows over NetworkDirect API - Set and check address format correctly - Only close qp if it was initialized - Portable detection of loopback device - Fabtests - multi_ep: Separate EP resources and fix MR registration - multi_recv: Fix possible crash and check for valid buffer - unexpected_msg: Fix printf compiler warning - dgram_pingpong.c: Use out-of-band sync - multinode: Make multinode tests platform agnostic, fix formatting - ubertest: Fix string comparison to include length, fix writedata completion check - av_test: add support for -e - New tests: - dmabuf-rdma: Component level test for dma-buf RDMA - sock_test: Component level performance test of poll, epoll, and select - rdm_stress: Multi-threaded, multi-process stress test for RDM endpoints - sighandler_test: Regression test for signal handler restoration- Drop patches fixed upstream: - prov-opx-Correctly-disable-OPX-if-unsupported.patch - disable-flatten-attr.patch
* Mon Aug 01 2022 Martin Liška - Add disable-flatten-attr.patch that drops flatten attribute. Note the flatten attribute results in huge compile time hog in inliner (same the binary size would be huge).- Use %make_build and enable LTO (boo#1133235).- Synchronize used Patches.
* Thu Jun 23 2022 Nicolas Morey-Chaisemartin - Update to 1.15.1 - Core - Fix fi_info indentation error in fi_tostr - hmem_ze: Add runtime option to choose specific copy engine - Cleanup of configure HMEM checks - Fixed stringop-truncation in ofi_ifaddr_get_speed - Add utility provider log suffix to make logs easier to read - Fix truncation of ipv6 addressing - hmem: add support for AWS Trainium devices - Fix potential sscanf overflows - hmem: pass through device and flags when querying memory interface - Rework locking in several areas to convert spinlocks to mutexes - Add new locking abstractions to select lock types at runtime - Add new FI_PROTO_RXM_TCP for optimized rxm over tcp path - Fix windows implementation to remove fd from poll set - EFA - Added windows support through efawin (https://github.com/aws/efawin) - Added support of AWS neuron. - Added support of using gdrcopy to copy data from host to device. - Fixed a bug that cause 0 byte read to fail. - Fixed a memory corruption issue that can caused forked process to crash. - Extended testing coverage through new pytest based testing framework. - HOOKS - Add new hooking provider dmabuf_peer_mem - Enable DL build of hooking providers - Add HMEM memory registration hook - OPX - New provider supporting Cornelis Networks Omni-path hardware - PSM3 - Updated psm3 to match IEFS 11.2.0.0 release - Added support for sockets (TCP/UDP) via a runtime selectable Hardware Abstraction Layer (HAL) - Added support for IPv6 addressing in RoCE and sockets - Added various NIC selection filtering options (wildcarded NIC name, address format, wildcarded IP subnet, link speed) - Performance tuning in conjunction with OneAPI and OneCCL - Improved PSM3_IDENTIFY output - Rename most internal symbols to psm3_ - Corrected vulnerabilities found during Coverity scans - configure options refined and help text improved - PSM3_MULTI_EP has been deprecated (recommend always enabled, default is enabled [same default as previous releases]) - Various bug fixes - RxM - Add check that atomic size is valid - Add support to passthru calls to tcp provider in specific - TCP - Add assert to verify RMA source/target msg sizes match - Wake-up threads blocked on CQ to update their poll events - Fix use of incorrect events in progress handler - Fixes for various compile warnings, mostly on Windows - Add support for FI_RMA_EVENT capability - Add support for completion counters - Fix check for CQ data in tagged messages - Add cancel support to shared rx context - Add src_addr receive buffer matching - Add provider control to assign a src_addr with an ep - Handle trecv with FI_PEEK flag - Allow binding a CQ with an SRX - Restructuring of code in source files - Handle EWOULDBLOCK returned by send call - Add hot (active) pollfd - SHM - Properly chain the original signal handlers - Avoid uninitialized variable with invalid atomic parameters - Fix 0 byte SAR read - Initialize len parameter to accept - Refactor and simplify protocol code - Remove broken support for 128-bit atomics - Fix FI_INJECT flag support - Add assert to verify RMA source/target msg sizes match - Set domain threading to thread safe - Fix possible use of uninitiated var in av_insert - Util - Fix sign warning in ofi_bufpool_region_alloc - Remove unused variable from ofi_bufpool_destroy - Fix check for valid datatype in ofi_atomic_valid - Return with error if util_coll_sched_copy fails - Fix use of uninitialized variable in ofi_ep_allreduce - Fix memory access in ip_av_insertsym - Track ep per collective operation not with multicast - Restructure collective av set creation/destruction - Change most locks from spin locks to mutexes - Allow selection of spinlocks for CQ and domain objects - Fix AV default addrlen - Update fi_getinfo checks to include hints->addr_ - Handle NULL address insertion to fi_av_insert - Verbs - Initial changes for compiling on Windows (via NetworkDirect) - Add a failover path to dma-buf based memory registration - Replace use of spin locks with mutexes - Check for valid qp prior to cleanup - Set and check for address format correct in fi_getinfo - Fabtests - hmem_cuda: used device allocated host buff to fill device buf - Add python scripts to control test execution - test_configs: include util provider in core config file - Add option \"--pin-core\" - Only call nrt_init once - Fix a bug in ft_neuron_cleanup - Correct help for unit test programs - Remove duplicate help prints from fi_mcast - configure.ac: fix --enable-debug=no not properly detected - msg_inject: handle the case ft_tsendmsg return -FI_EAGAIN - Add AWS Trainium device support - fi_inj_complete: Add FI_INJECT to fabtests - inj_complete.c: Make arguments align with the other tests - dgram_pingpong: handle the error return of fi_recv - recv_cancel: Remove requirement for unexpected msg handling - poll: Fix crash if unable to allocate pollset - ubertest: Add GPU testing and validation support - Add HMEM options parsing support - Update and re-enable fi_multi_ep test- Add prov-opx-Correctly-disable-OPX-if-unsupported.patch to disable OPX compilation on non x86_64 systems
* Tue Apr 19 2022 Nicolas Morey-Chaisemartin - Update to 1.14.1 - Core - Use non-shared memory allocations to use MADV_DONTFORK safely - Fix incorrect use of gdr_copy_from_mapping - Ensure proper timeout time for pollfds to avoid early exit - EFA - Handle read completion properly for multi_recv - Use shm\'s inject write when possible - Support 0 byte read - RxM - Ensure signaling the CQ fd after writing completion - Fix inject path for sending tagged messages with cq data - Negotiate credit based flow control support over CM - Add PID to CM messages to detect stale vs duplicate connections - Fix race handling unexpected messages from unknown peers - Fix possible leak of stack data in cm_accept - Restrict reported caps based on core provider - Delay starting listen until endpoint fully initialized - Verify valid atomic size - Sockets - Fix coverity reports on uninitialized data - Check for NULL pointers passed to memcpy - Add missing error return code from sock_ep_enable - TCP - Fix performance regression resulting from sparse pollfd sets - Fix assertion failure in CQ progress function - Do not generate error completions for inject msgs - Fix use of incorrect event names in progress handler - Fix check for CQ data in tagged messages - Make start_op array a static to reduce memory - Wake-up threads blocked on CQ to update their poll events - Verbs - Generate error completions for all failed transmits - Set all fields in the fi_fabric_attr for FI_CONNREQ events - Set proper completion flags for all failed transfer - Ensure that all attributes are provided when opening an endpoint - Fix error handling in vrb_eq_read - Fix memory leak in error case in vrb_get_sib - Work-around bug in verbs HW not reported correct send opcodes - Only call ibv_reg_dmabuf_mr when kernel support exists - Add a failover path to dma-buf based memory registration - Negotiate credit based flow control support over CM
* Mon Nov 22 2021 Nicolas Morey-Chaisemartin - Update to 1.14.0 - Add time stamps to log messages - Fix gdrcopy calculation of memory region size when aligned - Allow user to disable use of p2p transfers - Update fi_tostr print FI_SHARED_CONTEXT text instead of value - Update fi_tostr to output field names matching header file names - Fix narrow race condition in ofi_init - Add new fi_log_sparse API to rate limit repeated log output - Define memory registration for buffers used for collective operations - EFA, SHM, TCP, RXM, and verbs fixes
* Wed Nov 03 2021 Nicolas Morey-Chaisemartin - Enable PSM3 provider (jsc#SLE-18754)
* Fri Oct 29 2021 Nicolas Morey-Chaisemartin - Update to 1.13.2 - Sort DL providers to ensure consistent load ordering - Update hooking providers to handle fi_open_ops calls to avoid crashes - Replace cassert with assert.h to avoid C++ headers in C code - Enhance serialization for memory monitors to handle external monitors - EFA, SHM, TCP, RxM and vers fixes
* Wed Aug 25 2021 Nicolas Morey-Chaisemartin - Update to 1.13.1 - Enable loading ZE library with dlopen() - Add IPv6 support to fi_pingpong - EFA, PSM3 and SHM fixes
* Wed Jul 07 2021 Nicolas Morey-Chaisemartin - Update to 1.13.0 - Fix behavior of fi_param_get parsing an invalid boolean value - Add new APIs to open, export, and import specialized fid\'s - Define ability to import a monitor into the registration cache - Add API support for INT128/UINT128 atomics - Fix incorrect check for provider name in getinfo filtering path - Allow core providers to return default attributes which are lower then maximum supported attributes in getinfo call - Add option prefer external providers (in order discovered) over internal providers, regardless of provider version - Separate Ze (level-0) and DRM dependencies - Always maintain a list of all discovered providers - Fix incorrect CUDA warnings - Fix bug in cuda init/cleanup checking for gdrcopy support - Shift order providers are called from in fi_getinfo, move psm2 ahead of psm3 and efa ahead of psmX - See NEWS.md for changelog
* Fri Apr 02 2021 Nicolas Morey-Chaisemartin - Update to 1.12.1 - Fix initialization checks for CUDA HMEM support - Fail if a memory monitor is requested but not available - Adjust priority of psm3 provider to prefer HW specific providers, such as efa and psm2 - EFA and PSM3 fixes - See NEWS.md for changelog
* Tue Mar 09 2021 Nicolas Morey-Chaisemartin - Update to 1.12.0 - See NEWS.md for changelog
* Wed Dec 16 2020 Nicolas Morey-Chaisemartin - Update to 1.11.2 (bsc#1181983) - See NEWS.md for changelog
* Mon Oct 12 2020 Nicolas Morey-Chaisemartin - Update to 1.11.1 (jsc#SLE-13312) - See NEWS.md for changelog
* Tue Aug 18 2020 Nicolas Morey-Chaisemartin - Update to 1.11.0 - See NEWS.md for changelog
* Thu May 14 2020 Nicolas Morey-Chaisemartin - Update to 1.10.1 - See NEWS.md for changelog
* Mon Apr 27 2020 Nicolas Morey-Chaisemartin - Update to 1.10.0 - See NEWS.md for changelog
* Thu Mar 19 2020 Nicolas Morey-Chaisemartin - Update to 1.9.1 (bsc#1160275) - See NEWS.md for changelog
* Mon Nov 25 2019 Nicolas Morey-Chaisemartin - Update to 1.9.0 (jsc#SLE-8257) - See NEWS.md for changelog
* Tue Oct 01 2019 Nicolas Morey-Chaisemartin - Update to 1.8.1 (jsc#SLE-8257) - See NEWS.md for changelog
* Fri Sep 06 2019 Nicolas Morey-Chaisemartin - Update to 1.8.0 - See NEWS.md for changelog
* Wed Apr 24 2019 Martin Liška - Disable LTO (boo#1133235).
* Tue Apr 09 2019 Nicolas Morey-Chaisemartin - Update to 1.7.1 - See NEWS.md for changelog
* Mon Feb 11 2019 Jan Engelhardt - Remove silly Prefix: value, we do not support that in SUSE anyway.- Update summaries, make use of %make_install.
* Thu Feb 07 2019 nmoreychaisemartinAATTsuse.com- Update to v1.7.0 - fabtests and libfabric repos have been merged upstream - Core - Add ability to report NIC details with fi_info data - Improve MR cache notification mechanisms - Set sockaddr address format correctly - Avoid possible null dereference in eq_read - Handle FI_PEEK in CQ/EQ readerr - Add debug messages to name server - Feature and performance enhancements added to internal buffer pool - Add support for huge pages - Decrease memory use for idle buffer pools - Refactor utility AV functionality - Generic counter support enhancements - Optimize EP and CQ locking based on application threading level - Enhance common support for EQ error handling - Add free/alloc memory notification hooks for MR cache support - Fix memory monitor unsubscribe handling - Add CQ fd wait support - Add CQ overflow protection - Enhance IPv6 addressing support for AVs - Enhancements to support for AV address lookup - Fixes for emulated epoll support - Allow layering of multiple utility providers - Minor bug fixes and optimization - Hook - Improved hooking infrastructure - Add support for installing multiple hooks - Support hooks provided by external libraries. - GNI - Fix CQ readfrom overwriting src_addr in case of multiple events - Signal wait set if error entry is added to CQ - Fix state data issue with SMSG buffers - Enhance and fix possible misuse of default authorization key - Add cancel support for SEP - Rework SEP setup - Suppress huge page counting for ARM - Fix incorrect check of FI_SYNC_ERR flag - PSM2 - Requires PSM2 library version 10.2.260 or later - Clean up connection state in fi_av_remove - Use psm2_info_query to read HFI device info - Clean up CQ/counter poll list when endpoint is closed - Support shared address vector - Optimize CQ event conversion with psm2_mq_ipeek_dequeue_multi - Lock optimization for FI_THREAD_DOMAIN - Use new PSM2 fast path isend/irecv functions for large size RMA - Support building with latest PSM2 source code (version 11.2.68) - Support fabric direct - RxD - Initial release of RxD provider - Provides reliable datagram semantics over unreliable datagram EPs - Target is to improve scalability for very large clusters relative to RxM - RxM - Decrease memory use needed to maintain large number of connections - Set correct op_context and flags on CQ error completions - Fix file descriptor memory leaks - Introduce new protocol optimized for medium message transfers - Improve Rx software performance path - Use shared receive contexts if required by underlying provider - Handle addresses inserted multiple times into AV (for AV map) - Performance optimizations for single-thread applications - Rework deferred transmit processing - Separate and optimize eager and rendezvous protocol processing. - Fix passing incorrect addresses for AV insert/remove - Fix CM address handling - Fix race condition accessing connection handles - Simplify small RMA code path - Increment correct counter when processing FI_READ events - Dynamically grow the number of connections that can be supported - Fix padding in wire protocol structures - Report correct fi_addr when FI_SOURCE is requested - Fix truncating rendezvous messages - Fix use after free error in Rx buffer processing - Add support for manual progress - Make Tx/Rx queue sizes independent of MSG EP sizes - Decrease time needed to repost buffers to the MSG EP Rx queue. - Miscellaneous bug fixes - Sockets - Enable MSG EPs when user calls fi_accept - Fix fabric names to be underlying IP address - Add connection timeout environment variable. - Use size of addresses, not structures - Add debug messages to display selected addresses - Use loopback address in place of localhost - Simplify listen paths - Add support for IPv6 - Code restructuring - Avoid unneeded address to string to address translations - Check length of iovec entries prior to access buffers - Fix segfault - Avoid acquiring nested spinlocks resulting in hangs - Fix use after free error in triggered op handling - New connection manager for MSG EPs to reduce number of threads - Avoid retrying recv operations if connection has been broken - Fixes for Windows socket support - TCP - Initial release of optimized socket based tcp provider - Supports MSG EPs, to be used in conjunction with RxM provider - Targets eventual replacement of sockets provider - Verbs - Remove RDM EP support. Use RxM and RxD for RDM EPs. - Improve address handling and report in fi_getinfo - Handle FI_PEER when calling CQ/EQ readerr functions - Add support for XRC QPs. - Ignore destination address when allocating a PEP - Add workaround for i40iw incorrect return values when posting sends - Fix completion handling for FI_SELECTIVE_COMPLETION EP setting - Change format of fabric name to use hex instead of decimal values - Fix handling of err_data with EQ readerr - Report correct size of max_err_data - Fast path performance improvements - Improve progress under high system load - Optimize completion processing when handling hidden completions - Optimize RMA and MSG transfers by pre-formatting work requests - Remove locks based on application threading model - Add overflow support for CQ error events - Minor cleanups and bug fixes
* Thu Oct 25 2018 nmoreychaisemartinAATTsuse.com- Update to v1.6.2 (fate#325852) - Core - Cleanup of debug messages - Fix compile issues with older compilers - Check that all debug compiler flags are supported by compiler - GNI - Fix problems with Scalable Endpoint creation - Fix interoperability problem with HPC toolkit - Improve configuration check for kdreg - PSM - Enforce FI_RMA_EVENT checking when updating counters - Fix race condition in fi_cq_readerr() - Always try to make progress when fi_cntr_read is called - PSM2 - Revert \"Avoid long delay in psm2_ep_close\" - Fix memory corruption related to sendv - Performance tweak for bi-directional send/recv on KNL - Fix CPU detection - Enforce FI_RMA_EVENT checking when updating counters - Remove stale info from address vector when disconnecting - Fix race condition in fi_cq_readerr() - Adjust reported context numbers for special cases - Always try to make progress when fi_cntr_read is called - Support control functions related to MR mode - Unblock fi_cntr_wait on errors - Properly update error counters - Fix irregular performance drop for aggregated RMA operations - Reset Tx/Rx context counter when fabric is initialized - Fix incorrect completion event for iov send - Fix occasional assertion failure in psm2_ep_close - Avoid long delay in psm2_ep_close - Fix potential duplication of iov send completion - Replace some parameter checking with assertions - Check iov limit in sendmsg - Avoid adding FI_TRIGGER caps automatically - Avoid unnecessary calls to psmx2_am_progress() - RXM - Fix incorrect increments of error counters for small messages - Increment write completion counter for small transfers - Use FI_UNIVERSE_SIZE when defining MSG provider CQ size - Make TX, RX queue sizes independent of MSG provider - Make deferred requests opt-in - Fill missing rxm_conn in rx_buf when shared context is not used - Fix an issue where MSG endpoint recv queue got empty resulting in a hang - Set FI_ORDER_NONE for tx and rx completion ordering - Serialize access to repost_ready_list - Reprocess unexpected messages on av update - Fix a bug in matching directed receives - Fix desc field when postponing RMA ops - Fix incorrect reporting of mem_tag format - Don\'t include FI_DIRECTED_RECV, FI_SOURCE caps if they\'re not needed - Fix matching for RMA I/O vectors - Fix reading pointer after freeing it. - Avoid reading invalid AV entry - Handle deleting the same address multiple times - Fix crash in fi_av_remove if FI_SOURCE wasn\'t enabled - Sockets - Increase maximum messages size as MPICH bug work-around - Fix use after free error handling triggered ops. - Verbs - Detect string format of wildcard address in node argument - Don\'t report unusable fi_info (no source IP address) - Don\'t assert when a verbs device exposes unsupported MTU types - Report correct rma_iov_limit - Add new variable - FI_VERBS_MR_CACHE_MERGE_REGIONS - eq->err.err must return a positive error code
* Thu Mar 15 2018 nmoreychaisemartinAATTsuse.com- Update to v1.6.0 - Fixes stack smashing when using the verbs provider (bsc#1089190) - Core - Introduces support for performing RMA operations to persistent memory See FI_RMA_PMEM capability in fi_getinfo.3 - Define additional errno values - General code cleanups and restructuring - Force provider ordering when using dynamically loaded providers - Add const to fi_getinfo() hints parameter - Improve use of epoll for better scalability - Fixes to generic name service - PSM - Move environment variable reading out from fi_getinfo() - Shortcut obviously unsuccessful fi_getinfo() calls - Remove excessive name sever implementation - Enable ordering of RMA operations - PSM2 - Skip inactive units in round-robin context allocation - Allow contexts be shared by Tx-only and Rx-only endpoints - Use utility functions to check provider attributes - Turn on FI_THREAD_SAFE support - Make address vector operations thread-safe - Move environment variable reading out from fi_getinfo() - Reduce noise when optimizing tagged message functions - Shortcut obviously unsuccessful fi_getinfo() calls - Improve how Tx/Rx context limits are handled - Support auto selection from two different tag layout schemes - Add provider build options to debug output - Support remote CQ data for tagged messages, add specialization. - Support opening multiple domains - Put trigger implementation into a separate file - Update makefile and configure script - Replace allocated context with reserved space in psm2_mq_req - Limit exported symbols for DSO provider - Reduce HW context usage for certain TX only endpoints - Remove unnecessary dependencies from the configure script - Refactor the handling of op context type - Optimize the conversion between 96-bit and 64-bit tags - Code refactoring for completion generation - Remove obsolete feature checking code - Report correct source address for scalable endpoints - Allow binding any number of endpoints to a CQ/counter - Add shared Tx context support - Add alternative implementation for completion polling - Change the default value of FI_PSM2_DELAY to 0 - Add an environment variable for automatic connection cleanup - Abstract the completion polling mechanism - Use the new psm2_am_register_handlers_2 function when available - Allow specialization when FI_COMPLETION op_flag is set. - Put Tx/Rx context related functions into a separate file - Enable PSM2 multi-ep feature by default - Add option to build with PSM2 source included - Simplify the code for checking endpoint capabilities - Simplify the handling of self-targeted RMA operations - Allow all free contexts be used for scalable endpoints - Enable ordering of RMA operations - Enable multiple endpoints over PSM2 multi-ep support - Support multiple Tx/Rx contexts in address vector - Remove the virtual lane mechanism - Less code duplication in tagged, add more specialization. - Allow PSM2 epid be reused within the same session - Turn on user adjustable inject size for all operations - Use pre-allocated memory pool for RMA requests - Add support for lazy connection - Various bug fixes - SHM - Initial release of shared memory provider - See the fi_shm.7 man page for details on available features and limitations - Sockets - Scalability enhancements - Fix issue associating a connection with an AV entry that could result in application hangs - Add support for new persistent memory capabilities - Fix fi_cq_signal to unblock threads waiting on cq sread calls - Fix epoll_wait loop handling to avoid out of memory errors - Add support for TCP keepalives, controllable via environment variables - Reduce the number of threads allocated for handling connections - Several code cleanups in response to static code analysis reports - Fix reporting multiple completion events for the same request in error cases - usNIC - Minor adjustments to match new core MR mode bits functionality - Several code cleanups in response to static code analysis reports - Verbs - Code cleanups and simplifications - General code optimizations to improve performance - Fix handling of wildcard addresses - Check for fatal errors during connection establishment - Support larger inject sizes - Fix double locking issue - Add support for memory registration caching (disabled by default) - Enable setting thread affinity for CM threads - Fix hangs in MPI closing RDM endpoints - Add support for different CQ formats - Fix RMA read operations over iWarp devices - Optimize CM progress handling - Several bug fixes