Merge pull request openucx#7 from avildema/int4_ci_call

Int4 ci call

.clang-format

@@ -0,0 +1,135 @@
+# C
+BasedOnStyle: LLVM
+AlignEscapedNewlines: Indent
+AlignConsecutiveAssignments: true
+AlignConsecutiveDeclarations: false
+AlignConsecutiveStructMembers: true
+AlignConsecutiveMacros: true
+AlignDeclarationByPointer: true
+AlignAfterOpenBracket: true
+AlignOperands: true
+PointerAlignment: Right
+DerivePointerAlignment: false
+AlignTrailingComments: false
+AllowAllArgumentsOnNextLine: false
+AllowAllParametersOfDeclarationOnNextLine: false
+AllowShortBlocksOnASingleLine: false
+AllowShortCaseLabelsOnASingleLine: false
+AllowShortFunctionsOnASingleLine: false
+AllowShortIfStatementsOnASingleLine: false
+AllowShortLoopsOnASingleLine: false
+AllowShortEnumsOnASingleLine: false
+AllowDesignatedInitializersOnASingleLine: false
+AlwaysBreakAfterReturnType: None
+PenaltyReturnTypeOnItsOwnLine: 20
+PenaltyBreakAssignment: 100
+PenaltyExcessCharacter: 100
+PenaltyBreakBeforeFirstCallParameter: 100
+PenaltyBreakMemberAccess: 250
+PenaltyBreakLastMemberAccess: 300
+PenaltyIndentedWhitespace: 0
+ColumnLimit: 80
+AlwaysBreakBeforeMultilineStrings: false
+BinPackArguments: true
+BinPackParameters: true
+BreakBeforeBraces: Custom
+BraceWrapping:
+  AfterClass: false
+  AfterControlStatement: false
+  AfterEnum: false
+  AfterFunction: true
+  AfterNamespace: false
+  AfterObjCDeclaration: false
+  AfterStruct: false
+  AfterUnion: false
+  AfterExternBlock: false
+  BeforeCatch: false
+  BeforeElse: false
+  IndentBraces: false
+  SplitEmptyFunction: true
+  SplitEmptyRecord: true
+  SplitEmptyNamespace: true
+BreakBeforeBinaryOperators: false
+BreakBeforeTernaryOperators: false
+BreakStringLiterals: true
+ContinuationIndentWidth: 8
+IncludeBlocks: Regroup
+IndentCaseLabels: false
+IndentWidth: 4
+KeepEmptyLinesAtTheStartOfBlocks: false
+IndentPPDirectives: None
+MaxEmptyLinesToKeep: 2
+SpacesInCStyleCastParentheses: false
+SpacesInParentheses: false
+SpacesInSquareBrackets: false
+SpaceInEmptyParentheses: false
+SpaceBeforeParens: ControlStatementsExceptForEachMacros
+SpaceBeforeAssignmentOperators: true
+SpaceAfterCStyleCast: false
+SortIncludes: false
+ForEachMacros: ['_UCS_BITMAP_FOR_EACH_WORD',
+                'FOR_EACH_ENTITY',
+                'kh_foreach',
+                'kh_foreach_key',
+                'kh_foreach_value',
+                'ucp_unpacked_address_for_each',
+                'ucs_array_for_each',
+                'UCS_BITMAP_FOR_EACH_BIT',
+                'ucs_for_each_bit',
+                'ucs_for_each_submask',
+                'ucs_hlist_for_each',
+                'ucs_hlist_for_each_extract',
+                'ucs_hlist_for_each_extract_if',
+                'ucs_list_for_each',
+                'ucs_list_for_each_safe',
+                'ucs_memory_type_for_each',
+                'UCS_PP_FOREACH',
+                'UCS_PP_FOREACH_SEP',
+                'ucs_profile_for_each_location',
+                'ucs_ptr_array_for_each',
+                'ucs_ptr_array_locked_for_each',
+                'ucs_queue_for_each',
+                'ucs_queue_for_each_extract',
+                'ucs_queue_for_each_safe',
+                'ucs_timerq_for_each_expired',
+                'UCT_IB_IFACE_VERBS_FOREACH_RXWQE',
+                'UCT_RC_VERBS_IFACE_FOREACH_TXWQE',
+                'UCS_INIT_ONCE',
+                'UCS_TEST_F',
+                'UCX_PERF_TEST_FOREACH']
+StatementMacros : []
+TypenameMacros: ['khash_t', 'ucs_array_t']
+WhitespaceSensitiveMacros: []
+
+# CPP
+Standard: Cpp11
+AccessModifierOffset: -4
+AlwaysBreakTemplateDeclarations: false
+BreakBeforeInheritanceComma: false
+BreakInheritanceList: AfterColon
+BreakConstructorInitializers: AfterColon
+CompactNamespaces: false
+ConstructorInitializerAllOnOneLineOrOnePerLine: true
+ConstructorInitializerIndentWidth: 4
+Cpp11BracedListStyle: true
+Cpp11BracedListLineBreak: true
+FixNamespaceComments: true
+NamespaceIndentation: None
+UseTab: Never
+ReflowComments: false
+SortIncludes: false
+IncludeCategories:
+ - Regex: '^"'
+   Priority: 1
+ - Regex: '^<'
+   Priority: 2
+SortUsingDeclarations: true
+TabWidth: 4
+SpacesInAngles: false
+SpacesBeforeTrailingComments: 1
+SpaceAfterTemplateKeyword: false
+SpacesInContainerLiterals: false
+---
+# Java
+Language: Java
+DisableFormat: true

.github/ISSUE_TEMPLATE/bug_report.md

@@ -18,6 +18,7 @@ A clear and concise description of what the bug is.
 ### Setup and versions
 - OS version (e.g Linux distro) + CPU architecture (x86_64/aarch64/ppc64le/...)
    - `cat /etc/issue` or `cat /etc/redhat-release` + `uname -a`
+   - For Nvidia Bluefield SmartNIC include `cat /etc/mlnx-release` (the string identifies software and firmware setup)
 - For RDMA/IB/RoCE related issues:
     - Driver version:
         - `rpm -q rdma-core` or `rpm -q libibverbs`

.gitignore

@@ -88,3 +88,8 @@ GTAGS
 *.swp
 compile_commands.json
 .idea/
+.externalToolBuilders
+.classpath
+.vscode
+src/tools/vfs/ucx_vfs
+test/apps/test_init_mt

Makefile.am

@@ -13,7 +13,12 @@
 EXTRA_DIST =
 ACLOCAL_AMFLAGS = -I config/m4
 
-noinst_HEADERS = src/uct/api/uct.h src/uct/api/uct_def.h src/uct/api/tl.h
+noinst_HEADERS = \
+	src/uct/api/uct.h \
+	src/uct/api/v2/uct_v2.h \
+	src/uct/api/uct_def.h \
+	src/uct/api/tl.h
+
 doxygen_doc_files = $(noinst_HEADERS)
 
 doc_dir = $(pkgdatadir)/doc
@@ -37,6 +42,7 @@ SUBDIRS += $(UCG_SUBDIR)
 endif
 
 SUBDIRS += \
+	src/tools/vfs \
 	src/tools/info \
 	src/tools/perf \
 	src/tools/profile \

NEWS

@@ -1,17 +1,186 @@
 #
-## Copyright (C) Mellanox Technologies Ltd. 2001-2020.  ALL RIGHTS RESERVED.
+## Copyright (C) Mellanox Technologies Ltd. 2001-2021.  ALL RIGHTS RESERVED.
 ## Copyright (C) UT-Battelle, LLC. 2014-2019. ALL RIGHTS RESERVED.
-## Copyright (C) ARM Ltd. 2017-2020.  ALL RIGHTS RESERVED.
+## Copyright (C) ARM Ltd. 2017-2021.  ALL RIGHTS RESERVED.
 ##
 ## See file LICENSE for terms.
 ##
 #
 
 ## Current
-### Features: TBD
-#### UCX Core TBD
-#### UCX Java (API Preview) TBD
-### Bugfixes: TBD
+### Features:
+#### UCP
+* Added API for querying UCP library attributes
+### Bugfixes:
+
+## 1.10.0 (March 9, 2021)
+### Features:
+#### Core
+* Added support for Nvidia HPC SDK
+* Added support for latest PGI and Clang
+* Added support for ROCM-3.7+ (warning generated if older version detected)
+* Added support for GCC11
+#### Architecture
+* Added Arm SVE memcpy()
+* Redesigned Arm WFE support
+* Improved clear_cache performance for Arm
+* Added architecture detection for Zhaoxin CPU
+#### CI
+* Added release builds on CUDA 11
+* Enabled performance validation in gtest
+* Added new OS for release CI
+#### UCP
+* Added locality awareness to the transport selection logic for GPU devices
+* Added put/offload/short and put/offload/zcopy protocols
+* Added receive message nbx routine
+* Reworked AM implementation and API, which adds support for RNDV semantics
+* Added support for multi-lane connection manager over TCP
+* Added support for printing AM tls with info log level
+* Implement flush and destroy for UCT EPs on UCP worker
+* Reduced UCP request size
+* Added support for keepalive protocol
+* Added support for multi-fragment protocol
+* Added implementation for protocol progress for eager, bcopy, and multicopy
+* Improved selection logic for protocol selection
+* Added new protocols for UCP get operation
+* Added bcopy protocols with support for GPU memory
+* Added RNDV protocol implementation for GPU devices (CUDA, ROCm)
+* Set SOCKADDR_CM_ENABLE=y by default
+* Added support for fast-path short with new tag protocols
+* Added a new parameter to control the CM listener's backlog
+* Added support sending AM RTS over short message protocol
+* Added support for shared memory multi-lane when CM is used
+* Added missing async locks
+#### UCT
+* Added API for keepalive_timeout value
+* Added add uct_completion.status
+* Allowed transports to access multiple mem_types
+* Removed status arg from uct_completion_callback_t
+* Restructured  uct_mem_alloc/uct_md_mem_alloc to use mem_type
+* Updated documentation for uct_listener_params
+* Lowered the log level for certain network errors
+* Added cuda_copy wakeup feature
+* Added wakeup support for shared memory
+#### UCS
+* Added "inf" and "auto" values to time units
+* Added on-stack constructors for array and string buffer
+* Added ucs_ptr_map_t data structure
+* Added bool CSWAP
+* Improved logging
+* Added optimization for namespace processing
+* Fixes for connection matching functionality
+#### CUDA
+* Added support for global IPC cache
+#### RDMA CORE (IB, ROCE, etc.)
+* Added support for auto detection of adapative routing settings
+* Added an option to poll TX CQ every progress iteration
+* Added local and remote addresses to the reject error message
+* Added support for UAR allocation with non-cacheable memory type
+* Added support for multiple flush cancel without completion
+* Added async events callback support
+* Added detection for  ConnectX-6, ConnectX-7 and BlueField-1/2 devices
+* Added support for connection matching for UD
+* Added a check for AM ordering
+* Added better support for non-4K MTU values
+#### Java (preview)
+* Added support for a different javadoc executable path for different java versions
+* Added UCS memory type constants
+* Added support build on Java10+
+* Added support for io-vector datatype.
+* Removed libjucx from packages.
+#### Tests
+* Added CI for CUDA 11
+* Added test_ucp_sockaddr_protocols.stream_short
+* Reimplemented tests using NBX API
+* Added flush(cancel) test
+* Added memory_wait mode to perftest
+* Added support for clang 10
+* Refactored RMA and atomic tests, add memtype support
+* Added test for uct_md_mem_query()
+* Added request interrupt support
+* Added support for connection manager fallbacks
+* Added new ucp request test checking for leaks from the ptr_map
+#### Documentation
+* Added glossaries
+
+### Bugfixes:
+#### Portability
+* Fixes in print functions to use format string like PRIx64, etc.
+* Fixes for Arm v8 cross compilation support
+#### Continues Integration:
+* Fixes in Github release flow
+* Fixes in docker image
+#### Packaging
+* Removed deb package dependencies
+* Fixes in SPEC to make the RPM relocatable
+#### Documentation
+* Fixes in documentation for ucp_am_recv_data_nbx
+* Fixes in quick start example
+* Fixes in installation instruction
+* Fixes in updates in author list
+#### Tests
+* Fixes for failures under valgrind runtime
+* Fixes in mmap tests for 0-length RMA
+* Fixes in definition of LAST_WQE wait timeout
+* Fixes in ROCm for mem_buffer test
+* Fixes in test name printing format
+* Fixes in tcp_sockcm test
+#### UCP
+* Fixes in worker cleanup flow
+* Fixes in RNDV RTS flow
+* Fix in length check condition for RMA PUT short
+* Fixes in handling failures from AM Bcopy
+* Fix in a release flow of deferred data
+* Fixes for invalid ID and handling of status in RNDV
+* Fixes in short active message reply protocol
+#### CUDA
+* Fixes in managed memory support
+* Fixes in topology detection
+#### RDMA CORE (IB, ROCE, etc.)
+* Fixes in assert definitions
+* Fixes in printing an error about invalid AM Bcopy length for UD
+* Fixes for thread safety support
+* Fixes to get ROCE device name according to GID
+* Fixes for SL selection
+* Fixes in create STRICT_ORDER key
+* Fixes addressing performance degradation in UD transport due to excess async events
+* Fixes in QP destroy
+* Fixes for CQ creation failure using old Verbs API
+#### UGNI
+* Fixing disable logic in config
+* Fixing clang 11 warnings
+#### Java
+* Fixes in build dependencies
+* Fixes in constructing UcpRequest object on error
+* Fixes in exception handling on endpoint closure request
+* Fixes for segfault in UcpErrorHandler
+#### UCP
+* Fixes in datatype support for get_zcopy RNDV
+* Fixes in connection manager disconnect
+* Fixes in assert definitions
+* Fixes in completion flow for failed EP
+* Fixes in flush error handling flow
+* Fixes in latency calculations for wireup protocol
+* Fixes in offload completion with inlined data
+* Fixes in unpacking flow
+* Fixes in error handling for various protocols
+#### UCT
+* Fixes in flush TX
+* Fixes in checks for enabling GPU Direct RDMA
+#### UCS
+* Fixes for crashes on incorrect value set in config
+* Fixes in ptr_array
+* Fixes in maximal size for ucs_snprintf_safe()
+* Fixes in compilation warning
+* Fixes in ucs_aarch64_dsb(_op) definition
+#### TCP
+* Fixes in default route interface confirmation flow
+* Fixes in PUT protocol
+* Fixes in max connection limit and improved error reporting
+#### UCM
+* Fixing crash on prevent unload
+* Fixes in libucm_rocm
+* Fixes for few racing conditions
 
 ## 1.9.0 (September 19, 2020)
 ### Features: