Script 'mail_helper' called by obssrc Hello community, here is the log from the commit of package openucx for openSUSE:Factory checked in at 2026-07-08 17:35:18 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Comparing /work/SRC/openSUSE:Factory/openucx (Old) and /work/SRC/openSUSE:Factory/.openucx.new.1982 (New) ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "openucx" Wed Jul 8 17:35:18 2026 rev:40 rq:1364050 version:1.21.0 Changes: -------- --- /work/SRC/openSUSE:Factory/openucx/openucx.changes 2026-01-06 17:42:08.727639685 +0100 +++ /work/SRC/openSUSE:Factory/.openucx.new.1982/openucx.changes 2026-07-08 17:37:05.862641098 +0200 @@ -1,0 +2,195 @@ +Mon Jul 06 10:46:59 UTC 2026 - Nicolas Morey <[email protected]> + +- Update to v1.21.0 + - RDMA CORE (IB, ROCE, etc.) + - Added UCX_IB_GDA_RETAIN_INACTIVE_CTX option to control inactive CUDA context retention in GDAKI + - Added configure option to enable or disable GGA transport + - Fixed GDA DMA-BUF offset handling + - Fixed GDA WQE ordering by using CAS-based readiness marking + - Fixed GDAKI CUDA context handling during endpoint creation + - Fixed GDAKI NIC/GPU mapping when CUDA_VISIBLE_DEVICES hides physical GPUs + - ROCM + - Fixed hangs in HIP MPI and OMB tests + - Fixed endpoint flush for in-flight ROCm operations + - TCP + - Fixed interface selection by skipping IPv4 link-local addresses + - UCP + - Added UCX_PROTO_EMULATION_ENABLE option to force zero-copy RMA protocol selection + - Added UCX_MAX_HCA_PER_GPU policy to limit GPU memory registrations to nearest HCAs + - Added device lanes that can access host memory for GPU transfer fallback + - Enabled gdr_copy for memtype endpoint transport + - Fixed progress counter to return the actual operation status + - Fixed multi protocol minimum size handling for 1-byte operations + - Fixed endpoint finalization when no P2P or connection-manager lane is available + - UCS + - Reverted dynamically loaded external module/plugin support + - UCT + - Added device channel pool support + - Added CPU memory usage as AMO local buffer for device operations + - Fixed notify callback handling by adding a NULL check +- Refresh openucx-s390x-support.patch against latest release +- Add UCS-add-missing-include-for-UCS_INFINITY.patch to fix build issue on ARM/S390 + +------------------------------------------------------------------- +Tue Jun 23 13:20:49 UTC 2026 - Nicolas Morey <[email protected]> + +- Update to v1.20.1 + - AWS EFA + - Added RMA WRITE operations support + - Added flush and fence operations for SRD + - Enabled EFA SRD support in tests + - Build + - Added ability to build CUDA device code for supported architectures + - Added ucx.spec into tarball for Universal Build System support + - Added CUDA 13 support + - Added GDA build failure when gpunetio not found + - Fixed NVCC search with explicit --with-cuda + - Fixed ZE transport build failures + - Fixed ucs_arch_get_cpu_flag compilation + - Fixed CUDA device code build for supported architectures + - Fixed IB configuration const correctness for strchr() to allow compilation with GCC 15.2.1 + - CI/Testing + - Added Rocky OS support to release pipeline + - Added RHEL 10 containers to build matrices + - Added Debian 13 to CI build stage + - Added ARM build testing + - Switched to MOFED 25.07 + - Switched GPU tests to Ubuntu 24.04 DOCA 3.1 (GPUNetIO) image + - Added support for nvidia_peermem module in testing + - Disabled Valgrind in CI Tests stage + - Disabled tag matching offload tests + - CUDA + - Added wrappers for NVML functions + - Added hook for cuLibraryGetGlobal + - Improved CUDA call logging + - Improved source/destination memory type detection for lane performance estimation + - Removed unsafe usage of cuCtxGetId + - Added support for cuCtxCreate_v4 for newer CUDA versions + - Improved context management for CUDA_IPC operations + - Fixed stack overflow bug when calling cuPointerGetAttribute + - Fixed mapping of DMA_BUF handle for Direct NIC + - Returned object to mpool in case of failure in CUDA_COPY + - Reduced log level of rkey unpacking failures + - Handled cuMemRelease error status properly + - Fixed context setting for local buffer in CUDA_IPC + - Fixed host unregister error message (changed to diagnostic) + - Fixed CUDA_IPC header installation + - Fixed CUDA context handling for system device during rkey unpack + - Documentation + - Added note about reachability check mode in README + - Mentioned nvlink as supported transport + - Documented return status for device APIs + - Clarified that user buffer can be modified after calling ucp_atomic_op_nbx + - GO Bindings + - Made go bindings thread safe + - Fixed go bindings compilation with CUDA + - IB/EFA + - Fixed error message when FLID is not available + - Packaging + - Moved driver level dependencies under Recommends section in Debian packages + - Added Provides field for upstream packages in Debian + - Migrated JUCX publish from OSSRH to Central Portal + - Added ib-mlx5-gda separate package + - Fixed RPM SPEC debug_package macro execution on SLES16 + - Fix libnvidia-compute removal from ucx-cuda debian package dependencies, breaking existing installation + - Obsoleted KNEM sub-package + - Fix maintainer field in debian packaging + - RDMA CORE (IB, ROCE, etc.) + - Added ConnectX-9 device support + - Split dp_ordering flag for DV/Devx transports + - Added VRF tables support for RoCe reachability check + - Added EFA-specific GPUDirect support detection + - Added 'auto' option for UCX_IB_MLX5_DEVX_OBJECTS which disables DevX when ODP is available (for Grace) + - Prioritize routes with longer subnet masks for improved reachability check accuracy + - Fixed RoCe network device name reading + - Fixed Direct NIC related issues + - Reverted RC EP address size adaptation without flush_rkey + - Fixed DevX objects flag handling + - Fixed device memory allocation alignment in MLX5 DevX + - Fixed IB memory handle flags enum order + - Disabled indirect atomic registration for Direct NIC + - Fixed stale destination endpoint ID and acks from before connection reset in UD transport + - Fix RoCe reachable route check when node_guuid is not unique among HCAs + - ROCM + - Fixed HSA memory type check for newer ROCm releases + - TCP + - Added routing table check during reachability verification + - Testing + - Fixed test_jenkins CI issues + - Decreased rwlock test duration + - Fixed error counting in gtest + - Enabled retries for test_arch.memcpy + - Fixed test_cuda_nvml condition relaxation + - Skipped build when generating packages + - Fixed CUDA device restoration in tests + - Improved error detection in UCP device tests + - Fixed global topo state cleanup during gtest + - Tools + - Added GDAKI kernel option to perftest + - Added UCP cuda device tests to perftest + - Added MPI+CUDA example + - Differentiated wakeup feature and extra info options in perftest + - Fixed perftest CUDA kernel issues + - UCM + - Changed module info print to debug level by default + - UCP + - Added new GPU device API for direct GPU-to-GPU communication + - Added host API for GPU device management + - Added device signaling API with cooperation levels and flags + - Added API for working with offsets and channel id in device operations + - Added method to write to local counter in device operations + - Added local and remote address fields to memory list element in device API + - Added device lane selection and allocated handle population + - Added support for Direct NIC (DPU) data path with CUDA + - Added rkey packing support for Direct NIC + - Added sender flush mechanism when memory sys_dev differs from remote lane sys_dev + - Added option to use single network device per protocol + - Added MIN_RMA_CHUNK_SIZE configuration parameter + - Decreased default value for MIN_RMA_CHUNK_SIZE from 16k to 8k + - Improved protocol lane selection with find_lanes callback to minimize overhead + - Improved send-zcopy latency factor for fast-completion cases + - Improved multi-ppn performance estimation + - Removed deprecated ucp_mem functions + - Deprecated ucp_request_alloc API + - Fixed fallback to blocking registration for network device only + - Fixed flush_state validity check before using it + - Fixed single net dev filtering for single proto + - Fixed rkey size estimation for rendezvous + - Fixed memory invalidation without RNDV + - Fixed gather_pending_requests to execute only when reconfig occurs + - Increased TLS info buffer size in transport selection to prevent potential truncation + - Fixed incorrect warning about valid environment variable names + - Fixed ucp_config_modify not reporting an error when no matching modifiable configuration exists. + - UCS + - Introduced lightweight rwlock data structure + - Added built-in atomics for rcache rwlock + - Improved VFS symlink paths and duplicate object handling + - Disabled error signal interception by default + - Fixed ARCH header inclusion when building with nvcc (arm_neon.h) + - Fixed VFS symlink path handling + - Fixed netlink message receiving to continue until 'done' flag is set + - Fixed rcache locking for GDR copy + - UCT + - Added new device API for GPU communication (rc_gda transport) + - Added GDAKI transport with endpoint export to GPU + - Added DEVX QP/CQ support on foreign memory + - Added device API implementation for CUDA_IPC transport + - Added device put multi, put partial, and atomic operations for CUDA_IPC + - Added peer failure error handling capability for GDAKI + - Added check for nvidia_peermem driver when using GDA transport + - Enabled Direct NIC by default for IB transport + - Added XDR performance recognition + - Added support for mapping DMA_BUF handle via PCIe for Direct NIC + - Improved GDR_COPY performance with fast-path cache lookup + - Fixed CUDA_IPC protocol selection for cuda_ipc + - Fixed GDA compilation issues + - Fixed GDAKI wqe_idx overflow + - Fixed MM FIFO room calculation for tail > head case + - Fixed CUDA_IPC indices handling in put partial + - Removed DOCA runtime dependency from GDAKI + - Fixed GDA log spam by reducing DOCA log level + - Fixed UAR support check when querying resources for GDA/MLX5 + - Fixed crash in GGA transport when EXPORTED_MKEY flag is missing +- Refresh openucx-s390x-support.patch against latest release + +------------------------------------------------------------------- Old: ---- ucx-1.19.1.tar.gz New: ---- UCS-add-missing-include-for-UCS_INFINITY.patch ucx-1.21.0.tar.gz ----------(New B)---------- New:- Refresh openucx-s390x-support.patch against latest release - Add UCS-add-missing-include-for-UCS_INFINITY.patch to fix build issue on ARM/S390 ----------(New E)---------- ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Other differences: ------------------ ++++++ openucx.spec ++++++ --- /var/tmp/diff_new_pack.kFATTs/_old 2026-07-08 17:37:07.650704184 +0200 +++ /var/tmp/diff_new_pack.kFATTs/_new 2026-07-08 17:37:07.650704184 +0200 @@ -20,7 +20,7 @@ %define version_suf %{nil} Name: openucx -Version: 1.19.1 +Version: 1.21.0 Release: 0 Summary: Communication layer for Message Passing (MPI) License: BSD-3-Clause @@ -35,6 +35,7 @@ Patch2: ucm-fix-UCX_MEM_MALLOC_RELOC.patch Patch3: UCP-CORE-Fix-config-type-for-dynamic_tl_progress_factor.patch Patch4: UCT-SELF-Fix-config-type-for-num_devices.patch +Patch5: UCS-add-missing-include-for-UCS_INFINITY.patch BuildRequires: autoconf >= 2.63 BuildRequires: automake >= 1.10 BuildRequires: binutils-devel ++++++ UCS-add-missing-include-for-UCS_INFINITY.patch ++++++ commit c0995f475cb75f9b071e8cafe5151d8496fbd83d Author: Nicolas Morey <[email protected]> Date: Mon Jul 6 11:12:51 2026 +0200 UCS: add missing include for UCS_INFINITY Signed-off-by: Nicolas Morey <[email protected]> diff --git a/src/ucs/time/time.h b/src/ucs/time/time.h index 2ec162f31a30..dedb8f543466 100644 --- src/ucs/time/time.h +++ src/ucs/time/time.h @@ -8,6 +8,7 @@ #define UCS_TIME_H #include <ucs/arch/cpu.h> +#include <ucs/sys/math.h> #include <ucs/time/time_def.h> #include <sys/time.h> #include <limits.h> ++++++ _scmsync.obsinfo ++++++ --- /var/tmp/diff_new_pack.kFATTs/_old 2026-07-08 17:37:07.730707006 +0200 +++ /var/tmp/diff_new_pack.kFATTs/_new 2026-07-08 17:37:07.734707147 +0200 @@ -1,6 +1,6 @@ -mtime: 1767360858 -commit: 3ed220414918e4999b606dd86751c590b8ae858c2aa40d3036ef437c3dc928fc -url: https://src.opensuse.org/HPC/openucx.git -revision: 3ed220414918e4999b606dd86751c590b8ae858c2aa40d3036ef437c3dc928fc +mtime: 1783329375 +commit: c9995295b363fb1d7ad4d67f6b2e6ec09adcb63a10df5df20b1c84fe81a740d0 +url: https://src.opensuse.org/HPC/openucx +revision: c9995295b363fb1d7ad4d67f6b2e6ec09adcb63a10df5df20b1c84fe81a740d0 projectscmsync: https://src.opensuse.org/HPC/_ObsPrj ++++++ build.specials.obscpio ++++++ ++++++ build.specials.obscpio ++++++ diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/.gitignore new/.gitignore --- old/.gitignore 1970-01-01 01:00:00.000000000 +0100 +++ new/.gitignore 2026-07-06 11:16:15.000000000 +0200 @@ -0,0 +1 @@ +.osc ++++++ openucx-s390x-support.patch ++++++ --- /var/tmp/diff_new_pack.kFATTs/_old 2026-07-08 17:37:07.922713780 +0200 +++ /var/tmp/diff_new_pack.kFATTs/_new 2026-07-08 17:37:07.930714063 +0200 @@ -1,16 +1,16 @@ -commit e5fd9ff24191cfd99b5759bdaf291cc36aaa6346 +commit 36da838548dd999bcf8c4dee15f60de71b63b833 Author: Nicolas Morey <[email protected]> -Date: Wed Feb 19 16:46:33 2025 +0100 +Date: Mon Jul 6 10:55:49 2026 +0200 openucx s390x support Signed-off-by: Nicolas Morey-Chaisemartin <[email protected]> -diff --git config/m4/ucm.m4 config/m4/ucm.m4 -index e5e66266d695..ef7e4ede93ce 100644 +diff --git a/config/m4/ucm.m4 b/config/m4/ucm.m4 +index c58909ac06df..cee56c8c257a 100644 --- config/m4/ucm.m4 +++ config/m4/ucm.m4 -@@ -80,9 +80,20 @@ AC_CHECK_DECLS([SYS_ipc], +@@ -87,9 +87,20 @@ AC_CHECK_DECLS([SYS_ipc], [ipc_hooks_happy=no], [#include <sys/syscall.h>]) @@ -32,7 +32,7 @@ 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 +diff --git a/src/ucm/Makefile.am b/src/ucm/Makefile.am index 7866aa0ac13b..2d44e20f124d 100644 --- src/ucm/Makefile.am +++ src/ucm/Makefile.am @@ -44,7 +44,7 @@ libucm_la_SOURCES = \ event/event.c \ -diff --git src/ucm/bistro/bistro.h src/ucm/bistro/bistro.h +diff --git a/src/ucm/bistro/bistro.h b/src/ucm/bistro/bistro.h index fffbe738b116..31859a84b159 100644 --- src/ucm/bistro/bistro.h +++ src/ucm/bistro/bistro.h @@ -57,7 +57,7 @@ #else # error "Unsupported architecture" #endif -diff --git src/ucm/bistro/bistro_s390x.h src/ucm/bistro/bistro_s390x.h +diff --git a/src/ucm/bistro/bistro_s390x.h b/src/ucm/bistro/bistro_s390x.h new file mode 100644 index 000000000000..2beb5de54fab --- /dev/null @@ -90,8 +90,8 @@ +} + +#endif -diff --git src/ucs/Makefile.am src/ucs/Makefile.am -index 699a4addcd29..2f20f9945411 100644 +diff --git a/src/ucs/Makefile.am b/src/ucs/Makefile.am +index 964606957431..64dd76c0b148 100644 --- src/ucs/Makefile.am +++ src/ucs/Makefile.am @@ -24,6 +24,7 @@ nobase_dist_libucs_la_HEADERS = \ @@ -102,7 +102,7 @@ arch/x86_64/bitops.h \ arch/bitops.h \ algorithm/crc.h \ -@@ -87,6 +88,7 @@ nobase_dist_libucs_la_HEADERS = \ +@@ -88,6 +89,7 @@ nobase_dist_libucs_la_HEADERS = \ arch/generic/atomic.h \ arch/ppc64/global_opts.h \ arch/rv64/global_opts.h \ @@ -110,7 +110,7 @@ arch/global_opts.h noinst_HEADERS = \ -@@ -94,6 +96,7 @@ noinst_HEADERS = \ +@@ -95,6 +97,7 @@ noinst_HEADERS = \ arch/generic/cpu.h \ arch/ppc64/cpu.h \ arch/rv64/cpu.h \ @@ -118,7 +118,7 @@ arch/x86_64/cpu.h \ arch/cpu.h \ config/ucm_opts.h \ -@@ -150,6 +153,7 @@ libucs_la_SOURCES = \ +@@ -154,6 +157,7 @@ libucs_la_SOURCES = \ algorithm/string_distance.c \ arch/aarch64/cpu.c \ arch/aarch64/global_opts.c \ @@ -126,7 +126,7 @@ arch/ppc64/timebase.c \ arch/ppc64/global_opts.c \ arch/rv64/cpu.c \ -diff --git src/ucs/arch/atomic.h src/ucs/arch/atomic.h +diff --git a/src/ucs/arch/atomic.h b/src/ucs/arch/atomic.h index 849647902fab..a328c37e2020 100644 --- src/ucs/arch/atomic.h +++ src/ucs/arch/atomic.h @@ -139,7 +139,7 @@ #else # error "Unsupported architecture" #endif -diff --git src/ucs/arch/bitops.h src/ucs/arch/bitops.h +diff --git a/src/ucs/arch/bitops.h b/src/ucs/arch/bitops.h index ae531834451e..d4228b135641 100644 --- src/ucs/arch/bitops.h +++ src/ucs/arch/bitops.h @@ -152,11 +152,11 @@ #else # error "Unsupported architecture" #endif -diff --git src/ucs/arch/cpu.c src/ucs/arch/cpu.c -index 6fe5e31dba31..f92c53f303cd 100644 +diff --git a/src/ucs/arch/cpu.c b/src/ucs/arch/cpu.c +index 7829062f6e66..1a0c5d84eb11 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] = { +@@ -65,6 +65,10 @@ const ucs_cpu_builtin_memcpy_t ucs_cpu_builtin_memcpy[UCS_CPU_VENDOR_LAST] = { .min = UCS_MEMUNITS_INF, .max = UCS_MEMUNITS_INF }, @@ -167,7 +167,7 @@ [UCS_CPU_VENDOR_FUJITSU_ARM] = { .min = UCS_MEMUNITS_INF, .max = UCS_MEMUNITS_INF -@@ -82,7 +86,6 @@ const ucs_cpu_builtin_memcpy_t ucs_cpu_builtin_memcpy[UCS_CPU_VENDOR_LAST] = { +@@ -83,7 +87,6 @@ const ucs_cpu_builtin_memcpy_t ucs_cpu_builtin_memcpy[UCS_CPU_VENDOR_LAST] = { } }; @@ -175,7 +175,7 @@ static void ucs_sysfs_get_cache_size() { char type_str[32]; /* Data/Instruction/Unified */ -@@ -167,6 +170,7 @@ const char *ucs_cpu_vendor_name() +@@ -168,6 +171,7 @@ 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", @@ -183,27 +183,27 @@ [UCS_CPU_VENDOR_FUJITSU_ARM] = "Fujitsu ARM", [UCS_CPU_VENDOR_ZHAOXIN] = "Zhaoxin", [UCS_CPU_VENDOR_NVIDIA] = "Nvidia" -@@ -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", +@@ -199,6 +203,7 @@ const char *ucs_cpu_model_name() + [UCS_CPU_MODEL_ZHAOXIN_WUDAOKOU] = "Wudaokou", + [UCS_CPU_MODEL_ZHAOXIN_LUJIAZUI] = "Lujiazui", + [UCS_CPU_MODEL_RV64G] = "RV64G", + [UCS_CPU_MODEL_S390X] = "S390x", - [UCS_CPU_MODEL_NVIDIA_GRACE] = "Grace" - }; - -diff --git src/ucs/arch/cpu.h src/ucs/arch/cpu.h -index 857b8b804cf7..89461d52d406 100644 + [UCS_CPU_MODEL_NVIDIA_GRACE] = "Grace", + [UCS_CPU_MODEL_FUJITSU_A64FX] = "FUJITSU-A64FX", + [UCS_CPU_MODEL_FUJITSU_MONAKA] = "FUJITSU-MONAKA" +diff --git a/src/ucs/arch/cpu.h b/src/ucs/arch/cpu.h +index db9b88934866..eebb28d74fd5 100644 --- src/ucs/arch/cpu.h +++ src/ucs/arch/cpu.h -@@ -41,6 +41,7 @@ typedef enum ucs_cpu_model { +@@ -44,6 +44,7 @@ typedef enum ucs_cpu_model { UCS_CPU_MODEL_ZHAOXIN_WUDAOKOU, UCS_CPU_MODEL_ZHAOXIN_LUJIAZUI, UCS_CPU_MODEL_RV64G, + UCS_CPU_MODEL_S390X, UCS_CPU_MODEL_NVIDIA_GRACE, - UCS_CPU_MODEL_LAST - } ucs_cpu_model_t; -@@ -70,6 +71,7 @@ typedef enum ucs_cpu_vendor { + UCS_CPU_MODEL_FUJITSU_A64FX, + UCS_CPU_MODEL_FUJITSU_MONAKA, +@@ -75,6 +76,7 @@ typedef enum ucs_cpu_vendor { UCS_CPU_VENDOR_AMD, UCS_CPU_VENDOR_GENERIC_ARM, UCS_CPU_VENDOR_GENERIC_PPC, @@ -211,7 +211,7 @@ UCS_CPU_VENDOR_FUJITSU_ARM, UCS_CPU_VENDOR_ZHAOXIN, UCS_CPU_VENDOR_GENERIC_RV64G, -@@ -109,6 +111,8 @@ typedef struct ucs_cpu_builtin_memcpy { +@@ -114,6 +116,8 @@ typedef struct ucs_cpu_builtin_memcpy { # include "aarch64/cpu.h" #elif defined(__riscv) # include "rv64/cpu.h" @@ -220,7 +220,7 @@ #else # error "Unsupported architecture" #endif -diff --git src/ucs/arch/global_opts.h src/ucs/arch/global_opts.h +diff --git a/src/ucs/arch/global_opts.h b/src/ucs/arch/global_opts.h index 550d22b8b751..d8e4a7cca694 100644 --- src/ucs/arch/global_opts.h +++ src/ucs/arch/global_opts.h @@ -233,7 +233,7 @@ #else # error "Unsupported architecture" #endif -diff --git src/ucs/arch/s390x/bitops.h src/ucs/arch/s390x/bitops.h +diff --git a/src/ucs/arch/s390x/bitops.h b/src/ucs/arch/s390x/bitops.h new file mode 100644 index 000000000000..88b74558f333 --- /dev/null @@ -276,12 +276,12 @@ +} + +#endif -diff --git src/ucs/arch/s390x/cpu.h src/ucs/arch/s390x/cpu.h +diff --git a/src/ucs/arch/s390x/cpu.h b/src/ucs/arch/s390x/cpu.h new file mode 100644 -index 000000000000..e1d41a0ef8b8 +index 000000000000..d3c5de4455eb --- /dev/null +++ src/ucs/arch/s390x/cpu.h -@@ -0,0 +1,86 @@ +@@ -0,0 +1,91 @@ +/** +* Copyright (C) Mellanox Technologies Ltd. 2001-2013. ALL RIGHTS RESERVED. +* Copyright (C) ARM Ltd. 2016-2017. ALL RIGHTS RESERVED. @@ -365,10 +365,15 @@ + return UCS_ERR_UNSUPPORTED; +} + ++static UCS_F_ALWAYS_INLINE void ucs_cpu_relax() ++{ ++ asm volatile ("" ::: "memory"); ++} ++ +END_C_DECLS + +#endif -diff --git src/ucs/arch/s390x/global_opts.c src/ucs/arch/s390x/global_opts.c +diff --git a/src/ucs/arch/s390x/global_opts.c b/src/ucs/arch/s390x/global_opts.c new file mode 100644 index 000000000000..4fa0c74034a7 --- /dev/null @@ -398,7 +403,7 @@ +} + +#endif -diff --git src/ucs/arch/s390x/global_opts.h src/ucs/arch/s390x/global_opts.h +diff --git a/src/ucs/arch/s390x/global_opts.h b/src/ucs/arch/s390x/global_opts.h new file mode 100644 index 000000000000..b7c5693266d9 --- /dev/null @@ -429,11 +434,11 @@ + +#endif + -diff --git src/ucs/sys/sys.c src/ucs/sys/sys.c -index 7cd875e8f7b2..b8b2d3c026be 100644 +diff --git a/src/ucs/sys/sys.c b/src/ucs/sys/sys.c +index 66fbdc2d6526..10d520a1ad0b 100644 --- src/ucs/sys/sys.c +++ src/ucs/sys/sys.c -@@ -1265,8 +1265,19 @@ void *ucs_sys_realloc(void *old_ptr, size_t old_length, size_t new_length) +@@ -1319,8 +1319,19 @@ void *ucs_sys_realloc(void *old_ptr, size_t old_length, size_t new_length) if (old_ptr == NULL) { /* Note: Must pass the 0 offset as "long", otherwise it will be * partially undefined when converted to syscall arguments */ ++++++ ucx-1.19.1.tar.gz -> ucx-1.21.0.tar.gz ++++++ ++++ 95472 lines of diff (skipped)
