Accepting request 1298351 from science:HPC

OBS-URL: https://build.opensuse.org/request/show/1298351
OBS-URL: https://build.opensuse.org/package/show/openSUSE:Factory/openucx?expand=0&rev=37

UCS-TIME-Add-math.h-to-provide-INFINITY.patch

@@ -1,18 +0,0 @@
-commit c49bd7a5d183a57f41c801c7f5c9691bcd7d23da
-Author: Thomas Vegas <tvegas@nvidia.com>
-Date:   Mon Jun 24 16:52:04 2024 +0300
-
-    UCS/TIME: Add math.h to provide INFINITY
-
-diff --git src/ucs/time/time.h src/ucs/time/time.h
-index cff9810cdad8..c51362273f8d 100644
---- src/ucs/time/time.h
-+++ src/ucs/time/time.h
-@@ -11,6 +11,7 @@
- #include <ucs/time/time_def.h>
- #include <sys/time.h>
- #include <limits.h>
-+#include <math.h>
- 
- BEGIN_C_DECLS
- 

openucx-s390x-support.patch

@@ -1,6 +1,6 @@
-commit 70e243c8a6685a03d5faa65e706d318196ad712b
+commit ba1d7048df80ee535e01335992f70568e2f88c80
 Author: Nicolas Morey <nmorey@suse.com>
-Date:   Wed Jun 26 17:36:58 2024 +0200
+Date:   Wed Feb 19 16:46:33 2025 +0100
 
     openucx s390x support
     
@@ -33,10 +33,10 @@ index e5e66266d695..ef7e4ede93ce 100644
  AS_IF([test "x$bistro_hooks_happy" = "xyes"],
        [AC_DEFINE([UCM_BISTRO_HOOKS], [1], [Enable BISTRO hooks])],
 diff --git src/ucm/Makefile.am src/ucm/Makefile.am
-index fa7a722f2d31..e6df414a4ecb 100644
+index 7866aa0ac13b..2d44e20f124d 100644
 --- src/ucm/Makefile.am
 +++ src/ucm/Makefile.am
-@@ -34,6 +34,7 @@ noinst_HEADERS = \
+@@ -35,6 +35,7 @@ noinst_HEADERS = \
  	bistro/bistro_aarch64.h \
  	bistro/bistro_ppc64.h \
  	bistro/bistro_rv64.h
@@ -45,7 +45,7 @@ index fa7a722f2d31..e6df414a4ecb 100644
  libucm_la_SOURCES = \
  	event/event.c \
 diff --git src/ucm/bistro/bistro.h src/ucm/bistro/bistro.h
-index 8d0b90751676..a0b9d3f064c3 100644
+index fffbe738b116..31859a84b159 100644
 --- src/ucm/bistro/bistro.h
 +++ src/ucm/bistro/bistro.h
 @@ -23,6 +23,8 @@ typedef struct ucm_bistro_restore_point ucm_bistro_restore_point_t;
@@ -91,7 +91,7 @@ index 000000000000..2beb5de54fab
 +
 +#endif
 diff --git src/ucs/Makefile.am src/ucs/Makefile.am
-index 4a05f47b6369..c1cd2fb2cb57 100644
+index 86a469a60bcc..6751bad764b8 100644
 --- src/ucs/Makefile.am
 +++ src/ucs/Makefile.am
 @@ -24,6 +24,7 @@ nobase_dist_libucs_la_HEADERS = \
@@ -140,7 +140,7 @@ index 849647902fab..a328c37e2020 100644
  #  error "Unsupported architecture"
  #endif
 diff --git src/ucs/arch/bitops.h src/ucs/arch/bitops.h
-index 3e0e530f1336..f887e03ebac0 100644
+index f8e51c45888a..476631d95eb6 100644
 --- src/ucs/arch/bitops.h
 +++ src/ucs/arch/bitops.h
 @@ -23,6 +23,8 @@ BEGIN_C_DECLS
@@ -153,7 +153,7 @@ index 3e0e530f1336..f887e03ebac0 100644
  #  error "Unsupported architecture"
  #endif
 diff --git src/ucs/arch/cpu.c src/ucs/arch/cpu.c
-index 307fb61bfc4a..4356fff36f8b 100644
+index 6fe5e31dba31..f92c53f303cd 100644
 --- src/ucs/arch/cpu.c
 +++ src/ucs/arch/cpu.c
 @@ -64,6 +64,10 @@ const ucs_cpu_builtin_memcpy_t ucs_cpu_builtin_memcpy[UCS_CPU_VENDOR_LAST] = {
@@ -167,15 +167,15 @@ index 307fb61bfc4a..4356fff36f8b 100644
      [UCS_CPU_VENDOR_FUJITSU_ARM] = {
          .min = UCS_MEMUNITS_INF,
          .max = UCS_MEMUNITS_INF
-@@ -89,6 +93,7 @@ const size_t ucs_cpu_est_bcopy_bw[UCS_CPU_VENDOR_LAST] = {
+@@ -82,7 +86,6 @@ const ucs_cpu_builtin_memcpy_t ucs_cpu_builtin_memcpy[UCS_CPU_VENDOR_LAST] = {
-     [UCS_CPU_VENDOR_GENERIC_ARM]   = UCS_CPU_EST_BCOPY_BW_DEFAULT,
+     }
-     [UCS_CPU_VENDOR_GENERIC_PPC]   = UCS_CPU_EST_BCOPY_BW_DEFAULT,
+ };
-     [UCS_CPU_VENDOR_GENERIC_RV64G] = UCS_CPU_EST_BCOPY_BW_DEFAULT,
+ 
-+    [UCS_CPU_VENDOR_GENERIC_IBM] = UCS_CPU_EST_BCOPY_BW_DEFAULT,
+-
-     [UCS_CPU_VENDOR_FUJITSU_ARM]   = UCS_CPU_EST_BCOPY_BW_FUJITSU_ARM,
+ static void ucs_sysfs_get_cache_size()
-     [UCS_CPU_VENDOR_ZHAOXIN]       = UCS_CPU_EST_BCOPY_BW_DEFAULT,
+ {
-     [UCS_CPU_VENDOR_NVIDIA]        = UCS_CPU_EST_BCOPY_BW_DEFAULT
+     char type_str[32];  /* Data/Instruction/Unified */
-@@ -183,6 +188,7 @@ const char *ucs_cpu_vendor_name()
+@@ -167,6 +170,7 @@ const char *ucs_cpu_vendor_name()
          [UCS_CPU_VENDOR_GENERIC_ARM]   = "Generic ARM",
          [UCS_CPU_VENDOR_GENERIC_PPC]   = "Generic PPC",
          [UCS_CPU_VENDOR_GENERIC_RV64G] = "Generic RV64G",
@@ -183,7 +183,7 @@ index 307fb61bfc4a..4356fff36f8b 100644
          [UCS_CPU_VENDOR_FUJITSU_ARM]   = "Fujitsu ARM",
          [UCS_CPU_VENDOR_ZHAOXIN]       = "Zhaoxin",
          [UCS_CPU_VENDOR_NVIDIA]        = "Nvidia"
-@@ -212,6 +218,7 @@ const char *ucs_cpu_model_name()
+@@ -197,6 +201,7 @@ const char *ucs_cpu_model_name()
          [UCS_CPU_MODEL_ZHAOXIN_WUDAOKOU]   = "Wudaokou",
          [UCS_CPU_MODEL_ZHAOXIN_LUJIAZUI]   = "Lujiazui",
          [UCS_CPU_MODEL_RV64G]              = "RV64G",
@@ -192,10 +192,10 @@ index 307fb61bfc4a..4356fff36f8b 100644
      };
  
 diff --git src/ucs/arch/cpu.h src/ucs/arch/cpu.h
-index ca25e714d141..e97405c30d52 100644
+index 857b8b804cf7..89461d52d406 100644
 --- src/ucs/arch/cpu.h
 +++ src/ucs/arch/cpu.h
-@@ -39,6 +39,7 @@ typedef enum ucs_cpu_model {
+@@ -41,6 +41,7 @@ typedef enum ucs_cpu_model {
      UCS_CPU_MODEL_ZHAOXIN_WUDAOKOU,
      UCS_CPU_MODEL_ZHAOXIN_LUJIAZUI,
      UCS_CPU_MODEL_RV64G,
@@ -203,7 +203,7 @@ index ca25e714d141..e97405c30d52 100644
      UCS_CPU_MODEL_NVIDIA_GRACE,
      UCS_CPU_MODEL_LAST
  } ucs_cpu_model_t;
-@@ -68,6 +69,7 @@ typedef enum ucs_cpu_vendor {
+@@ -70,6 +71,7 @@ typedef enum ucs_cpu_vendor {
      UCS_CPU_VENDOR_AMD,
      UCS_CPU_VENDOR_GENERIC_ARM,
      UCS_CPU_VENDOR_GENERIC_PPC,
@@ -211,7 +211,7 @@ index ca25e714d141..e97405c30d52 100644
      UCS_CPU_VENDOR_FUJITSU_ARM,
      UCS_CPU_VENDOR_ZHAOXIN,
      UCS_CPU_VENDOR_GENERIC_RV64G,
-@@ -107,6 +109,8 @@ typedef struct ucs_cpu_builtin_memcpy {
+@@ -109,6 +111,8 @@ typedef struct ucs_cpu_builtin_memcpy {
  #  include "aarch64/cpu.h"
  #elif defined(__riscv)
  #  include "rv64/cpu.h"
@@ -278,10 +278,10 @@ index 000000000000..ce48ff1ff451
 +#endif
 diff --git src/ucs/arch/s390x/cpu.h src/ucs/arch/s390x/cpu.h
 new file mode 100644
-index 000000000000..0aee278010d2
+index 000000000000..e1d41a0ef8b8
 --- /dev/null
 +++ src/ucs/arch/s390x/cpu.h
-@@ -0,0 +1,84 @@
+@@ -0,0 +1,86 @@
 +/**
 +* Copyright (C) Mellanox Technologies Ltd. 2001-2013.  ALL RIGHTS RESERVED.
 +* Copyright (C) ARM Ltd. 2016-2017.  ALL RIGHTS RESERVED.
@@ -347,7 +347,9 @@ index 000000000000..0aee278010d2
 +{
 +}
 +
-+static inline void *ucs_memcpy_relaxed(void *dst, const void *src, size_t len)
++static inline void *ucs_memcpy_relaxed(void *dst, const void *src, size_t len,
++                                       ucs_arch_memcpy_hint_t hint,
++                                       size_t total_len)
 +{
 +    return memcpy(dst, src, len);
 +}
@@ -428,7 +430,7 @@ index 000000000000..225e4e5e896a
 +#endif
 +
 diff --git src/ucs/sys/sys.c src/ucs/sys/sys.c
-index 42ff75f64af5..b22418e3f4b0 100644
+index d0b5effe11a3..ce22a2097f18 100644
 --- src/ucs/sys/sys.c
 +++ src/ucs/sys/sys.c
 @@ -1258,8 +1258,19 @@ void *ucs_sys_realloc(void *old_ptr, size_t old_length, size_t new_length)

openucx.changes

@@ -1,3 +1,213 @@
+-------------------------------------------------------------------
+Wed Jun 25 15:49:50 UTC 2025 - Nicolas Morey <nicolas.morey@suse.com>
+
+- Update to ucx 1.19.0
+  - UCP
+    - Enabled multi-GPU support within a single process
+    - Added dynamic selection between strong and weak fences in RMA flush operations
+    - Improved endpoint reconfiguration capabilities
+    - Added All2All lane selection for multi-NIC-GPU systems
+    - Improved rkey debug info when config cache limit is reached
+    - Improved UCP protocol selection based on available memory types
+    - Removed dummy memory key from irrelevant transports (TCP, CMA and CUDA)
+    - Improved RNDV performance with device-local staging buffers
+    - Enabled error handling for RMA get_offload protocols
+    - Made UCX_TLS=^ib disable all transports including auxiliary
+    - Fixed send request status handling
+    - Fixed performance degradation in RNDV by optimizing md cache updates
+    - Fixed protocol selection when first lane is filtered out by fragment size
+    - Fixed rkey selection by using memory registration flag
+  - UCT
+    - Defined uct_rkey_unpack_v2 API to support passing sys-dev
+  - RDMA CORE (IB, ROCE, etc.)
+    - Added SRD transport support in EFA with reordering, AM, and control operations
+    - Removed XGVMI BF2 support (umem)
+    - Removed device memory indirect key
+    - Fixed VFS objects for DCIs and pools
+    - Added routing table cache to the reachability check
+    - Fixed strict order usage in IB auxiliary rkeys
+    - Improved various init logging messages
+    - Improved reliability of DC transport by adding DCI validation and separating connection logic
+    - Fixed segfault in DC fence operation
+  - UCS
+    - Removed compilation warnings
+    - Use UCS function for counting leading zeros on x86 architecture
+    - Fixed a compilation warning
+  - Shared Memory
+    - Fixed FIFO availability check for sm transport
+  - Tools
+    - Added name filter option (-F 'str') to ucx_info for config and feature dumps
+    - Improved ucx_info input validation
+  - Documentation
+    - Fixed open-mpi clone instruction
+  - Build
+    - Fixed enum-int-mismatch warnings with GCC 15
+- Drop patches merged upstream:
+  - UCT-IB-UD-Use-GRH-to-detect-address-family-on-non-Mellanox-hardware.patch
+  - openucx-extern-c.patch
+  - openucx-strict-headers-additional.patch
+  - openucx-strict-headers.patch
+
+-------------------------------------------------------------------
+Thu Jun 12 08:28:59 UTC 2025 - Nicolas Morey <nicolas.morey@suse.com>
+
+- Update to ucx 1.18.1
+  - CUDA
+    - Added config keys to update cuda_copy bandwidth for coherent platforms
+    - Improved cache invalidation of memory allocated using CUDA memory pool
+  - AZP
+    - Added Ubuntu 24.04 to build and release pipeline
+  - UCP
+    - Fixed assertion failure when maximum lane fragment is smaller than AM header
+    - Fixed potential active message user header use after free with protocol reconfiguration
+  - CUDA
+    - Fixed registration of CUDA Fabric memory allocated by UCT
+    - Fixed VA recycling check of memory allocated using VMM and CUDA memory pool
+  - RDMA CORE (IB, ROCE, etc.)
+    - Do not use ConnectX-8 SMI subdevices for communication
+    - Fixed remote access error by disabling ODP when the device supports DDP
+    - Fixed configuration logic by disabling DDP when AR is disabled
+  - UCM
+    - Fixed crash with bistro hooks for CUDA 12.9 on amd64
+
+-------------------------------------------------------------------
+Wed May  2 14:16:35 UTC 2025 - Friedrich Haubensak <hsk17@mail.de>
+
+- Add openucx-strict-headers.patch and openucx-extern-c.patch from
+  upstream and additional openucx-strict-headers-additional.patch
+  to build w/ gcc-15 (boo#1241939)
+
+-------------------------------------------------------------------
+Tue Apr  1 12:31:11 UTC 2025 - Nicolas Morey <nicolas.morey@suse.com>
+
+- Add UCT-IB-UD-Use-GRH-to-detect-address-family-on-non-Mellanox-hardware.patch
+  to fix an UD init issue on non-Mellanox RDMA HW (bsc#1240204).
+
+-------------------------------------------------------------------
+Wed Feb 19 15:47:23 UTC 2025 - Nicolas Morey <nicolas.morey@suse.com>
+
+- Update to ucx 1.18.0
+  - UCP
+    - Enabled using CUDA staging buffers for pipeline protocols by default
+    - Added endpoint reconfiguration support for non-reused p2p scenarios
+    - Enabled non-cacheable memory domains, activated for gdr_copy
+    - Added user_data parameter to ucp_ep_query
+    - Added support for host memory pipeline through CUDA buffers for rendezvous protocol
+    - Added global VA infrastructure and memory region in absence of error handling
+    - Made protocol performance node names more informative
+    - Enforced always running on the same thread in single thread mode
+    - Multiple improvements in protocols selection infrastructure
+    - Added UCP_MEM_MAP_LOCK API flag to enforce locked memory mapping
+    - Allowed up-to 64 endpoint lanes for systems with many transports or devices
+    - Added usage tracker to worker
+    - Improved various logging messages
+    - Fixed stack overflow in exported rkey unpack
+    - Removed extra remote-cpu overhead from protocol estimation for zcopy
+    - Fixed performance estimation for rndv pipeline protocols
+    - Fixed ATP sending by picking the correct lane
+    - Fixed missing reg_id on memh creation
+    - Fixed repeated invalidations by retaining existing access flags
+    - Fixed abort reason propagation for rendezvous RTR mtype
+    - Do not check transport availability if it is disabled by UCX_TLS environment variable
+    - Fixed wrong flag being used for checking BCOPY capability
+    - Fixed sending too many ATPs for small messages
+    - Enforced 16 bits size for Active Messages identifiers
+    - Fixed unnecessary status check for emulated AMO
+    - Fixed more than one fragment sending in rendezvous pipeline
+    - Fixed crash by using biggest max frag across all lanes
+    - Fixed missing memory handle flags by copying from parent to child
+    - Fixed worker interface activate count
+    - Fixed flush requests by replacing ATP/flush lane map with lane indexes
+    - Fixed lost uct_flags when merging memory regions
+  - UCT
+    - Fixed memory domain UCT flags description
+  - RDMA CORE (IB, ROCE, etc.)
+    - Added environment variable to manage DC initiator capacity
+    - Added DC dcs_hybrid policy
+    - Reduced MLX5/DV stack size consumption
+    - Added ODP support for verbs and mlx5dv
+    - Added support of CUDA managed memory on IB when ODP is available
+    - Added support of Adaptive Routing on RoCE
+    - Enabled use of implicit ODP with relaxed ordering
+    - Improved GPU-Direct detection in IB transport
+    - Increased DC initiator default count to 32 for performance optimization
+    - Added ConnectX-8 device support with DDP
+    - Added support for subnet filter list for RoCE interfaces
+    - Enhanced the error message to provide more details when a connection cannot be
+      established due to unreachable transports
+    - Added IB MLX5 as a separate UCX module with separate RPM sub-package
+    - Added initial support for GGA transport, for fast DPU memory access
+    - Set IB DevX atomic mode based on device capabilities
+    - Removed DC keepalive mechanism, since the keepalive is done on UCP layer
+    - Optimized cross-gVMI memory registration using indirect memory keys cache
+    - Improved various logging messages
+    - Fixed FETCH_ADD remote access error for ODP/KSM case
+    - Fixed missing conditional compilation checks for DM
+    - Fixed IB MD allocation naming typo
+    - Fixed invalid GIDs filter in IB
+    - Fixed flags usage in MLX5 zcopy_post
+    - Do not limit ODP registration retries
+    - Fixed JUCX failures by considering the number of supported completion vectors
+  - UCS
+    - Added support for wildcards in configuration parameter names
+    - Added ASAN protection to several internal data structures
+    - Reduced stack usage in topology detection code
+    - Improved bitmaps configuration parsing with wider bitfield
+    - Added options to set topology distance between devices
+    - Optimized VFS unix socket watch by using user private folder
+    - Added general IP subnet matching infrastructure
+    - Extend array data structure to support user-provided array copy routine
+    - Improved time units description
+    - Fixed a crash by using heap allocation to process expired timers in batch
+    - Fixed allocation issue on memtrack dump
+    - Fixed deletion of the monitored folder in VFS
+    - Fixed unsafe resize for DC initiator array
+    - Fixed function macro invocation to match C standard
+    - Fixed calling async handler on already released resource
+    - Fixed performance by setting higher bandwidth for different NUMA nodes on Grace
+    - Fixed undeclared value error in timer conversion routine
+    - Fixed uninitialized value access in registration cache
+  - UCM
+    - Extend CUDA memory hooks to include memory mapping APIs
+    - Fixed race condition in parsing proc maps
+    - Fixed mremap failure while parsing /proc/self/maps
+  - TCP
+    - Always bind endpoint to interface
+  - Tools
+    - Improved performance by increasing window size for put_bw and add get_bw in ucx_perftest
+    - Added multi-send flag for receive operations in bandwidth benchmarks in ucx_perftest
+    - Improved ucx_perftest uni-directional test with added fence
+    - Detailed ucx_perftest batch section of command-line documentation
+    - Fixed buffer size potential overflow in ucx_perftest
+    - Fixed missing address when packing memory keys on ucx_perftest
+    - Fixed memory leak for endpoint report in ucx_info
+    - Fixed build without openmp in ucx_perftest
+    - Fixed UCT device override on server side on ucx_perftest
+  - Documentation
+    - Added a section regarding adaptive routing on RoCE
+  - Architecture
+    - Added CPU Model for MI300A
+    - Added Fujitsu ARM specific values to ucx.conf
+    - Added AMD Turin support
+    - Added an optimized non-temporal memory copy implementation for AMD CPU
+  - Build
+    - Improved compiler error reporting with added flag
+    - Improved coverity script to allow faster turnaround time
+    - Improved Intel Compiler detection and support
+    - Fixed using correct ASAN version for running tests
+  - Configuration
+    - Used POSIX bourne syntax to check equality
+    - Fixed build failure by using proper flags in compiler.m4
+    - Fixed perftest MAD support default guessing
+  - GO
+    - Added multi-send flag and user memh support in request params
+    - Added serialized thread mode to avoid subtle races between threads
+    - Fixed make distcheck
+  - Packaging
+    - Improved dpkg-buildpackage sample command by explicitly adding mlx5 related arguments
+- Delete UCS-TIME-Add-math.h-to-provide-INFINITY.patch which was merged upstream
+- Refresh openucx-s390x-support.patch due to API changes
+
 -------------------------------------------------------------------
 Sat Sep  7 14:22:20 UTC 2024 - Nicolas Morey <nicolas.morey@suse.com>
 

openucx.spec

@@ -1,7 +1,7 @@
 #
 # spec file for package openucx
 #
-# Copyright (c) 2024 SUSE LLC
+# Copyright (c) 2025 SUSE LLC
 #
 # All modifications and additions to the file contributed by third parties
 # remain the property of their copyright owners, unless otherwise agreed
@@ -20,7 +20,7 @@
 %define version_suf %{nil}
 
 Name:           openucx
-Version:        1.17.0
+Version:        1.19.0
 Release:        0
 Summary:        Communication layer for Message Passing (MPI)
 License:        BSD-3-Clause
@@ -32,7 +32,6 @@ URL:            http://openucx.org/
 Source:         https://github.com/openucx/ucx/releases/download/v%version%{?version_suf}/ucx-%version.tar.gz
 Patch1:         openucx-s390x-support.patch
 Patch2:         ucm-fix-UCX_MEM_MALLOC_RELOC.patch
-Patch3:         UCS-TIME-Add-math.h-to-provide-INFINITY.patch
 BuildRequires:  autoconf >= 2.63
 BuildRequires:  automake >= 1.10
 BuildRequires:  binutils-devel
@@ -158,7 +157,8 @@ export UCX_CFLAGS="$UCX_CFLAGS -mno-sse -mno-sse2"
 		 --disable-debug --disable-assertions \
 		 --disable-params-check \
 		 --with-rc --with-ud --with-dc \
-		 --with-mlx5-dv --with-rdmacm
+                 --with-ib-hw-tm --with-dm --with-devx \
+		 --with-mlx5 --with-rdmacm
 
 # Override BASE_CFLAGS to disable Werror (boo#1121267)
 make %{?_smp_mflags} V=1 BASE_CFLAGS="-g -Wall"
@@ -230,6 +230,7 @@ mv %buildroot/%_bindir/io_demo  %buildroot/%_libexecdir/%{name}/
 %_libdir/libuct.so.*
 %dir %_libdir/ucx/
 %_libdir/ucx/libuct_*.so.*
+%_libdir/ucx/libucx_perftest_mad.so.*
 
 %files -n libuct-devel
 %defattr(-,root,root)
@@ -237,9 +238,12 @@ mv %buildroot/%_bindir/io_demo  %buildroot/%_libexecdir/%{name}/
 %_libdir/libuct.so
 %dir %_libdir/ucx/
 %_libdir/ucx/libuct_*.so
+%_libdir/ucx/libucx_perftest_mad.so
 %_libdir/pkgconfig/ucx-uct.pc
 %_libdir/pkgconfig/ucx-cma.pc
 %_libdir/pkgconfig/ucx-ib.pc
+%_libdir/pkgconfig/ucx-ib-efa.pc
+%_libdir/pkgconfig/ucx-ib-mlx5.pc
 %_libdir/pkgconfig/ucx-rdmacm.pc
 
 %changelog

ucx-1.19.0.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af07d55281059542f20c5b411db668643543174e51ac71f53f7ac839164f285
+size 3391294