UCT: Merge with latest master branch

Author: iyastreb

AUTHORS

@@ -1,14 +1,18 @@
+Aboorva Devarajan <[email protected]>
 Akshay Venkatesh <[email protected]>
+Alastair McKinstry <[email protected]>
 Aleksey Senin <[email protected]>
 Alex Margolin <[email protected]>
 Alex Mikheev <[email protected]>
 Alexey Rivkin <[email protected]>
 Alina Sklarevich <[email protected]>
+Alma Mastbaum <[email protected]>
 Anatoly Vildemanov <[email protected]>
 Andrey Maslennikov <[email protected]>
 Artem Polyakov <[email protected]>
 Artem Ryabov <[email protected]>
 Artemy Kovalyov <[email protected]>
+Arun Chandran <[email protected]>
 Aurelien Bouteiller <[email protected]>
 Bin Lei <[email protected]>
 Boris Karasev <[email protected]>
@@ -70,6 +74,7 @@ Pavan Balaji <[email protected]>
 Pavel Shamis (Pasha) <[email protected]>
 Peter Andreas Entschev <[email protected]>
 Peter Rudenko <[email protected]>
+Peter-Jan Gootzen <[email protected]>
 Qiang Yu <[email protected]>
 Raul Akhmetshin <[email protected]>
 Robert Dietrich <[email protected]>
@@ -96,9 +101,11 @@ Valentin Petrov <[email protected]>
 Wenbin Lu <[email protected]>
 Xin Zhao <[email protected]>
 Xu Yifeng <[email protected]>
+Yiltan Hassan Temucin <[email protected]>
 Yossi Itigin <[email protected]>
 Yuriy Shestakov <[email protected]>
 Zhu Yanjun <[email protected]>
+Zihao Zhao <[email protected]>
 
 In addition we would like to acknowledge the following members of UCX community
 for their participation in annual face-to-face meeting, design discussions, and

NEWS

@@ -11,6 +11,157 @@
 ### Features:
 ### Bugfixes:
 
+## 1.18.0 (January 17, 2025)
+### Features:
+#### 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
+#### 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
+#### CUDA
+ * Added multi-node NVlink support
+ * Added CUDA Fabric memory support with detection and allocation
+ * Improved gdr_copy latency estimations on AMD Milan systems
+ * Added check for gdr_copy runtime/build version mismatch
+ * Added handling missing IPC capability when unpacking keys
+ * Added caching for CUDA IPC memory pool import operation
+ * Added gdr_copy variables to optimize performance on Grace Hopper systems
+ * Improved CUDA IPC concurrency for a larger count of reachable peers
+#### 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
+#### UCM
+ * Extend CUDA memory hooks to include memory mapping APIs
+#### 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
+#### 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
+#### GO
+ * Added multi-send flag and user memh support in request params
+#### Packaging
+ * Improved dpkg-buildpackage sample command by explicitly adding mlx5 related arguments
+### Bugfixes:
+#### UCP
+ * 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.)
+ * 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
+#### CUDA
+ * Fixed async memory handling using CUDA memory type on Grace
+ * Added rcache overhead in performance estimation
+ * Fixed gdr_copy performance regression by providing maximum estimation between get and put
+ * Fixed CUDA IPC reachability check
+ * Fixed crash in MPI_Finalize when CUDA context is destroyed
+ * Always require rcache by default for gdr_copy
+ * Fixed crash in gdr_copy cleanup when registration cache is disabled
+ * Fixed CUDA copy memory domain allocations
+ * Fixed multiple tests for gdr_copy transport
+ * Fixed race condition in CUDA IPC peer accessible cache
+#### UCS
+ * 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
+ * Fixed race condition in parsing proc maps
+ * Fixed mremap failure while parsing /proc/self/maps
+#### ROCM
+ * Fixed ROCM interface reachability test
+ * Fixed memory domain fork test
+#### TCP
+ * Always bind endpoint to interface
+#### Tools
+ * 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
+#### Build
+ * 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 serialized thread mode to avoid subtle races between threads
+ * Fixed make distcheck
+
 ## 1.17.0 (June 13, 2024)
 ### Features:
 #### UCP

buildlib/azure-pipelines-perf.yml

@@ -89,6 +89,8 @@ stages:
       - job: Perf
         displayName: Performance testing
         timeoutInMinutes: 180
+        workspace:
+          clean: outputs
         pool:
           name: MLNX
           demands:

buildlib/jucx/jucx-build.yml

@@ -53,8 +53,8 @@ jobs:
           set -eE
           {
             echo -e "<settings><servers><server>"
-            echo -e "<id>ossrh</id><username>\${env.SONATYPE_USERNAME}</username>"
-            echo -e "<password>\${env.SONATYPE_PASSWORD}</password>"
+            echo -e "<id>ossrh</id><username>$(SONATYPE_USERNAME)</username>"
+            echo -e "<password>$(SONATYPE_PASSWORD)</password>"
             echo -e "</server></servers></settings>"
           } > $(temp_cfg)
         displayName: Generate temporary config

buildlib/pr/main.yml

@@ -18,24 +18,15 @@ resources:
     - container: fedora
       image: rdmz-harbor.rdmz.labs.mlnx/ucx/fedora33:2
       options: $(DOCKER_OPT_ARGS)
-    - container: fedora34
-      image: rdmz-harbor.rdmz.labs.mlnx/ucx/fedora34:2
+    - container: fedora41
+      image: rdmz-harbor.rdmz.labs.mlnx/hpcx/x86_64/fedora41/builder:inbox
       options: $(DOCKER_OPT_ARGS) $(DOCKER_OPT_VOLUMES)
     - container: coverity_rh7
       image: rdmz-harbor.rdmz.labs.mlnx/ucx/coverity:mofed-5.1-2.3.8.0
       options: $(DOCKER_OPT_ARGS) $(DOCKER_OPT_VOLUMES)
     - container: rhel76
       image: rdmz-harbor.rdmz.labs.mlnx/ucx/x86_64/rhel7.6/builder:mofed-5.0-1.0.0.0
       options: $(DOCKER_OPT_ARGS) $(DOCKER_OPT_VOLUMES)
-    - container: rhel76_mofed47
-      image: rdmz-harbor.rdmz.labs.mlnx/ucx/x86_64/rhel7.6/builder:mofed-4.7-1.0.0.1
-      options: $(DOCKER_OPT_ARGS) $(DOCKER_OPT_VOLUMES)
-    - container: rhel74
-      image: rdmz-harbor.rdmz.labs.mlnx/ucx/x86_64/rhel7.4/builder:mofed-5.0-1.0.0.0
-      options: $(DOCKER_OPT_ARGS) $(DOCKER_OPT_VOLUMES)
-    - container: rhel72
-      image: rdmz-harbor.rdmz.labs.mlnx/ucx/x86_64/rhel7.2/builder:mofed-5.0-1.0.0.0
-      options: $(DOCKER_OPT_ARGS) $(DOCKER_OPT_VOLUMES)
     - container: rhel82
       image: rdmz-harbor.rdmz.labs.mlnx/ucx/x86_64/rhel8.2/builder:mofed-5.0-1.0.0.0
       options: $(DOCKER_OPT_ARGS) $(DOCKER_OPT_VOLUMES)
@@ -63,11 +54,11 @@ resources:
     - container: debian109
       image: rdmz-harbor.rdmz.labs.mlnx/hpcx/x86_64/debian10.9/builder:mofed-5.8-3.0.7.0
       options: $(DOCKER_OPT_ARGS) $(DOCKER_OPT_VOLUMES)
-    - container: sles15sp2
-      image: rdmz-harbor.rdmz.labs.mlnx/ucx/x86_64/sles15sp2/builder:mofed-5.0-1.0.0.0
+    - container: debian125
+      image: rdmz-harbor.rdmz.labs.mlnx/hpcx/x86_64/debian12.5/builder:doca-2.9.0
       options: $(DOCKER_OPT_ARGS) $(DOCKER_OPT_VOLUMES)
-    - container: sles12sp5
-      image: rdmz-harbor.rdmz.labs.mlnx/ucx/x86_64/sles12sp5/builder:mofed-5.0-1.0.0.0
+    - container: sles15sp6
+      image: rdmz-harbor.rdmz.labs.mlnx/hpcx/x86_64/sles15sp6/builder:doca-2.9.0
       options: $(DOCKER_OPT_ARGS) $(DOCKER_OPT_VOLUMES)
     - container: centos7_cuda_11_0
       image: nvidia/cuda:11.0.3-devel-centos7
@@ -180,6 +171,15 @@ resources:
     - container: ubuntu2204_rocm_6_0_0
       image: rdmz-harbor.rdmz.labs.mlnx/ucx/x86_64/ubuntu2204:rocm-6.0.0
       options: $(DOCKER_OPT_ARGS) $(DOCKER_OPT_VOLUMES)
+    - container: kylin10sp3
+      image: rdmz-harbor.rdmz.labs.mlnx/hpcx/x86_64/kylin10sp3/builder:doca-2.9.0
+      options: $(DOCKER_OPT_ARGS) $(DOCKER_OPT_VOLUMES)
+    - container: euleros2sp12
+      image: rdmz-harbor.rdmz.labs.mlnx/hpcx/x86_64/euleros2.0sp12/builder:doca-2.9.0
+      options: $(DOCKER_OPT_ARGS) $(DOCKER_OPT_VOLUMES)
+    - container: centos10stream
+      image: rdmz-harbor.rdmz.labs.mlnx/hpcx/x86_64/centos10stream/builder:inbox
+      options: $(DOCKER_OPT_ARGS) $(DOCKER_OPT_VOLUMES)
 
 stages:
   - stage: Codestyle
@@ -201,16 +201,9 @@ stages:
             - ucx_docker -equals yes
         strategy:
           matrix:
-            rhel72:
-              CONTAINER: rhel72
-            rhel74:
-              CONTAINER: rhel74
             rhel76:
               CONTAINER: rhel76
               long_test: yes
-            rhel76_mofed47:
-              CONTAINER: rhel76_mofed47
-              long_test: yes
             ubuntu2004:
               CONTAINER: ubuntu2004
               long_test: yes
@@ -226,21 +219,28 @@ stages:
               CONTAINER: debian113
             debian109:
               CONTAINER: debian109
-            sles15sp2:
-              CONTAINER: sles15sp2
+            debian125:
+              CONTAINER: debian125
+            sles15sp6:
+              CONTAINER: sles15sp6
             rhel82:
               CONTAINER: rhel82
             rhel90:
               CONTAINER: rhel90
-            fedora34:
-              CONTAINER: fedora34
-              long_test: yes
+            fedora41:
+              CONTAINER: fedora41
             centos7:
               CONTAINER: centos7_ib
+            centos10stream:
+              CONTAINER: centos10stream
             ubuntu2004_rocm:
               CONTAINER: ubuntu2004_rocm_5_4_0
             ubuntu2204_rocm:
               CONTAINER: ubuntu2204_rocm_6_0_0
+            kylin10sp3:
+              CONTAINER: kylin10sp3
+            euleros2sp12:
+              CONTAINER: euleros2sp12
         container: $[ variables['CONTAINER'] ]
         timeoutInMinutes: 340
 

buildlib/tools/build_static.sh

@@ -64,7 +64,6 @@ az_init_modules
 prepare_build
 
 # Don't cross-connect RoCE devices
-export UCX_IB_ROCE_LOCAL_SUBNET=y
 export UCX_IB_ROCE_SUBNET_PREFIX_LEN=inf
 build_static
 

buildlib/tools/builds.sh

@@ -320,6 +320,10 @@ build_gcc_debug_opt() {
 	build_gcc CFLAGS=-Og CXXFLAGS=-Og
 }
 
+build_gcc_with_dndebug() {
+	build_gcc CFLAGS=-DNDEBUG CXXFLAGS=-DNDEBUG
+}
+
 #
 # Build with armclang compiler
 #
@@ -444,6 +448,7 @@ then
 			'build_no_devx' \
 			'build_no_openmp' \
 			'build_gcc_debug_opt' \
+			'build_gcc_with_dndebug' \
 			'build_clang' \
 			'build_armclang')
 fi

buildlib/tools/test_wire_compat.sh

@@ -11,7 +11,6 @@ common_opt=$3
 port=$((10000 + 1000 * ${AZP_AGENT_ID} + 100 * ${WIRE_COMPAT_STAGE_ID}))
 
 export UCX_CM_REUSEADDR=y UCX_LOG_LEVEL=info UCX_WARN_UNUSED_ENV_VARS=n
-export UCX_IB_ROCE_LOCAL_SUBNET=y
 
 exe_cmd="stdbuf -oL ${exe_name} -p ${port}"