Skip to content

Releases: openucx/ucx

v1.9.0-rc7

17 Sep 02:24
@shamisp shamisp
v1.9.0-rc7
1785f82
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.9.0-rc7 Pre-release
Pre-release

1.9.0-rc7 (September 16, 2020)

Features:

UCX Core

  • Added a new class of communication APIs '*_nbx' that enable API extendability while
    preserving ABI backward compatibility
  • Added asynchronous event support to UCT/IB/DEVX
  • Added support for latest CUDA library version
  • Added NAK-based reliability protocol for UCT/IB/UD to optimize resends
  • Added new tests for ROCm
  • Added new configuration parameters for protocol selection
  • Added performance optimization for Fujitsu A64FX with InfiniBand
  • Added performance optimization for clear cache code aarch64
  • Added support for relaxed-order PCIe access in IB RDMA transports
  • Added new TCP connection manager
  • Added support for UCT/IB PKey with partial membership in IB transports
  • Added support for RoCE LAG
  • Added support for ROCm 3.7 and above
  • Added flow control for RDMA read operations
  • Improved endpoint flush implementation for UCT/IB
  • Improved UD timer to avoid interrupting the main thread when not in use
  • Improved latency estimation for network path with CUDA
  • Improved error reporting messages
  • Improved performance in active message flow (removed malloc call)
  • Improved performance in ptr_array flow
  • Improved performance in UCT/SM progress engine flow
  • Improved I/O demo code
  • Improved rendezvous protocol for CUDA
  • Updated examples code

UCX Java (API Preview)

  • Added support for UCX shared library loading from both classpath and LD_LIBRARY_PATH
  • Added configuration map to ucp_params to be able to set UCX properties programmatically

Bugfixes:

  • Fixes for most resent versions of GCC, CLANG, ARMCLANG, PGI
  • Fixes in UCT/IB for strict order keys
  • Fixes in memory barrier code for aarch64
  • Fixes in UCT/IB/DEVX for fork system call
  • Fixes in UCT/IB for rand() call in rdma-core
  • Fixed in group rescheduling for UCT/IB/DC
  • Fixes in UCT/CUDA bandwidth reporting
  • Fixes in rkey_ptr protocol
  • Fixes in lane selection for rendezvous protocol based on get-zero-copy flow
  • Fixes for ROCm build
  • Fixes for XPMEM transport
  • Fixes in closing endpoint code
  • Fixes in RDMACM code
  • Fixes in memcpy selection for AMD
  • Fixed in UCT/UD endpoint flush functionality
  • Fixes in XPMEM detection
  • Fixes in rendezvous staging protocol
  • Fixes in ROCEv1 mlx5 UDP source port configuration
  • Multiple fixes in RPM spec file
  • Multiple fixes in UCP documentation
  • Multiple fixes in socket connection manager
  • Multiple fixes in gtest
  • Multiple fixes in JAVA API implementation
Assets 12
Loading

v1.9.0-rc6

16 Sep 20:21
@shamisp shamisp
v1.9.0-rc6
495efb0
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.9.0-rc6 Pre-release
Pre-release

1.9.0-rc6 (September 15, 2020)

Features:

UCX Core

  • Added a new class of communication APIs '*_nbx' that enable API extendability while
    preserving ABI backward compatibility
  • Added asynchronous event support to UCT/IB/DEVX
  • Added support for latest CUDA library version
  • Added NAK-based reliability protocol for UCT/IB/UD to optimize resends
  • Added new tests for ROCm
  • Added new configuration parameters for protocol selection
  • Added performance optimization for Fujitsu A64FX with InfiniBand
  • Added performance optimization for clear cache code aarch64
  • Added support for relaxed-order PCIe access in IB RDMA transports
  • Added new TCP connection manager
  • Added support for UCT/IB PKey with partial membership in IB transports
  • Added support for RoCE LAG
  • Added support for ROCm 3.7 and above
  • Added flow control for RDMA read operations
  • Improved endpoint flush implementation for UCT/IB
  • Improved UD timer to avoid interrupting the main thread when not in use
  • Improved latency estimation for network path with CUDA
  • Improved error reporting messages
  • Improved performance in active message flow (removed malloc call)
  • Improved performance in ptr_array flow
  • Improved performance in UCT/SM progress engine flow
  • Improved I/O demo code
  • Improved rendezvous protocol for CUDA
  • Updated examples code

UCX Java (API Preview)

  • Added support for UCX shared library loading from both classpath and LD_LIBRARY_PATH
  • Added configuration map to ucp_params to be able to set UCX properties programmatically

Bugfixes:

  • Fixes for most resent versions of GCC, CLANG, ARMCLANG, PGI
  • Fixes in UCT/IB for strict order keys
  • Fixes in memory barrier code for aarch64
  • Fixes in UCT/IB/DEVX for fork system call
  • Fixes in UCT/IB for rand() call in rdma-core
  • Fixed in group rescheduling for UCT/IB/DC
  • Fixes in UCT/CUDA bandwidth reporting
  • Fixes in rkey_ptr protocol
  • Fixes in lane selection for rendezvous protocol based on get-zero-copy flow
  • Fixes for ROCm build
  • Fixes for XPMEM transport
  • Fixes in closing endpoint code
  • Fixes in RDMACM code
  • Fixes in memcpy selection for AMD
  • Fixed in UCT/UD endpoint flush functionality
  • Fixes in XPMEM detection
  • Fixes in rendezvous staging protocol
  • Fixes in ROCEv1 mlx5 UDP source port configuration
  • Multiple fixes in RPM spec file
  • Multiple fixes in UCP documentation
  • Multiple fixes in socket connection manager
  • Multiple fixes in gtest
  • Multiple fixes in JAVA API implementation
Assets 9
Loading

v1.9.0-rc5

10 Sep 19:14
@shamisp shamisp
v1.9.0-rc5
9294d2b
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.9.0-rc5 Pre-release
Pre-release

1.9.0-rc5 (September 10, 2020)

Features:

UCX Core

  • Added a new class of communication APIs '*_nbx' that enable API extendability while
    preserving ABI backward compatibility
  • Added asynchronous event support to UCT/IB/DEVX
  • Added support for latest CUDA library version
  • Added NAK-based reliability protocol for UCT/IB/UD to optimize resends
  • Added new tests for ROCm
  • Added new configuration parameters for protocol selection
  • Added performance optimization for Fujitsu A64FX with InfiniBand
  • Added performance optimization for clear cache code aarch64
  • Added support for relaxed-order PCIe access in IB RDMA transports
  • Added new TCP connection manager
  • Added support for UCT/IB PKey with partial membership in IB transports
  • Added support for RoCE LAG
  • Added flow control for RDMA read operations
  • Improved endpoint flush implementation for UCT/IB
  • Improved UD timer to avoid interrupting the main thread when not in use
  • Improved latency estimation for network path with CUDA
  • Improved error reporting messages
  • Improved performance in active message flow (removed malloc call)
  • Improved performance in ptr_array flow
  • Improved performance in UCT/SM progress engine flow
  • Improved I/O demo code
  • Improved rendezvous protocol for CUDA
  • Updated examples code

UCX Java (API Preview)

  • Added support for UCX shared library loading from both classpath and LD_LIBRARY_PATH
  • Added configuration map to ucp_params to be able to set UCX properties programmatically

Bugfixes:

  • Fixes for most resent versions of GCC, CLANG, ARMCLANG, PGI
  • Fixes in UCT/IB for strict order keys
  • Fixes in memory barrier code for aarch64
  • Fixes in UCT/IB/DEVX for fork system call
  • Fixes in UCT/IB for rand() call in rdma-core
  • Fixed in group rescheduling for UCT/IB/DC
  • Fixes in UCT/CUDA bandwidth reporting
  • Fixes in rkey_ptr protocol
  • Fixes in lane selection for rendezvous protocol based on get-zero-copy flow
  • Fixes for ROCm build
  • Fixes for XPMEM transport
  • Fixes in closing endpoint code
  • Fixes in RDMACM code
  • Fixes in memcpy selection for AMD
  • Fixed in UCT/UD endpoint flush functionality
  • Fixes in XPMEM detection
  • Multiple fixes in RPM spec file
  • Multiple fixes in UCP documentation
  • Multiple fixes in socket connection manager
  • Multiple fixes in gtest
  • Multiple fixes in JAVA API implementation
Assets 12
Loading

v1.9.0-rc4

10 Sep 16:33
@shamisp shamisp
v1.9.0-rc4
cf9e2fb
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.9.0-rc4 Pre-release
Pre-release

1.9.0-rc4 (September 2, 2020)

Features:

UCX Core

  • Added a new class of communication APIs '*_nbx' that enable API extendability while
    preserving ABI backward compatibility
  • Added asynchronous event support to UCT/IB/DEVX
  • Added support for latest CUDA library version
  • Added NAK-based reliability protocol for UCT/IB/UD to optimize resends
  • Added new tests for ROCm
  • Added new configuration parameters for protocol selection
  • Added performance optimization for Fujitsu A64FX with InfiniBand
  • Added performance optimization for clear cache code aarch64
  • Added support for relaxed-order PCIe access in IB RDMA transports
  • Added new TCP connection manager
  • Added support for UCT/IB PKey with partial membership in IB transports
  • Added support for RoCE LAG
  • Added flow control for RDMA read operations
  • Improved endpoint flush implementation for UCT/IB
  • Improved UD timer to avoid interrupting the main thread when not in use
  • Improved latency estimation for network path with CUDA
  • Improved error reporting messages
  • Improved performance in active message flow (removed malloc call)
  • Improved performance in ptr_array flow
  • Improved performance in UCT/SM progress engine flow
  • Improved I/O demo code
  • Updated examples code

UCX Java (API Preview)

  • Added support for UCX shared library loading from both classpath and LD_LIBRARY_PATH
  • Added configuration map to ucp_params to be able to set UCX properties programmatically

Bugfixes:

  • Fixes for most resent versions of GCC, CLANG, ARMCLANG, PGI
  • Fixes in UCT/IB for strict order keys
  • Fixes in memory barrier code for aarch64
  • Fixes in UCT/IB/DEVX for fork system call
  • Fixes in UCT/IB for rand() call in rdma-core
  • Fixed in group rescheduling for UCT/IB/DC
  • Fixes in UCT/CUDA bandwidth reporting
  • Fixes in rkey_ptr protocol
  • Fixes in lane selection for rendezvous protocol based on get-zero-copy flow
  • Fixes for ROCm build
  • Fixes for XPMEM transport
  • Fixes in closing endpoint code
  • Fixes in RDMACM code
  • Fixes in memcpy selection for AMD
  • Fixed in UCT/UD endpoint flush functionality
  • Fixes in XPMEM detection
  • Multiple fixes in RPM spec file
  • Multiple fixes in UCP documentation
  • Multiple fixes in socket connection manager
  • Multiple fixes in gtest
  • Multiple fixes in JAVA API implementation
Assets 12
Loading

v1.9.0-rc3

30 Aug 02:18
@shamisp shamisp
v1.9.0-rc3
cac4887
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.9.0-rc3 Pre-release
Pre-release

1.9.0-rc3 (August 29, 2020)

Features:

UCX Core

  • Added a new class of communication APIs '*_nbx' that enable API extendability while
    preserving ABI backward compatibility
  • Added asynchronous event support to UCT/IB/DEVX
  • Added support for latest CUDA library version
  • Added NAK-based reliability protocol for UCT/IB/UD to optimize resends
  • Added new tests for ROCm
  • Added new configuration parameters for protocol selection
  • Added performance optimization for Fujitsu A64FX with InfiniBand
  • Added performance optimization for clear cache code aarch64
  • Added support for relaxed-order PCIe access in IB RDMA transports
  • Added new TCP connection manager
  • Added support for UCT/IB PKey with partial membership in IB transports
  • Added support for RoCE LAG
  • Added flow control for RDMA read operations
  • Improved endpoint flush implementation for UCT/IB
  • Improved UD timer to avoid interrupting the main thread when not in use
  • Improved latency estimation for network path with CUDA
  • Improved error reporting messages
  • Improved performance in active message flow (removed malloc call)
  • Improved performance in ptr_array flow
  • Improved performance in UCT/SM progress engine flow
  • Improved I/O demo code
  • Updated examples code

UCX Java (API Preview)

  • Added support for UCX shared library loading from both classpath and LD_LIBRARY_PATH
  • Added configuration map to ucp_params to be able to set UCX properties programmatically

Bugfixes:

  • Fixes for most resent versions of GCC, CLANG, ARMCLANG, PGI
  • Fixes in UCT/IB for strict order keys
  • Fixes in memory barrier code for aarch64
  • Fixes in UCT/IB/DEVX for fork system call
  • Fixes in UCT/IB for rand() call in rdma-core
  • Fixed in group rescheduling for UCT/IB/DC
  • Fixes in UCT/CUDA bandwidth reporting
  • Fixes in rkey_ptr protocol
  • Fixes in lane selection for rendezvous protocol based on get-zero-copy flow
  • Fixes for ROCm build
  • Fixes for XPMEM transport
  • Fixes in closing endpoint code
  • Fixes in RDMACM code
  • Fixes in memcpy selection for AMD
  • Fixed in UCT/UD endpoint flush functionality
  • Fixes in XPMEM detection
  • Multiple fixes in RPM spec file
  • Multiple fixes in UCP documentation
  • Multiple fixes in socket connection manager
  • Multiple fixes in gtest
  • Multiple fixes in JAVA API implementation
Assets 2
Loading

v1.9.0-rc2

27 Aug 23:14
@shamisp shamisp
v1.9.0-rc2
8f9e291
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.9.0-rc2 Pre-release
Pre-release

1.9.0-rc2 (August 27, 2020)

Features:

UCX Core

  • Added a new class of communication APIs '*_nbx' that enable API extendability while
    preserving ABI backward compatibility
  • Added asynchronous event support to UCT/IB/DEVX
  • Added support for latest CUDA library version
  • Added NAK-based reliability protocol for UCT/IB/UD to optimize resends
  • Added new tests for ROCm
  • Added new configuration parameters for protocol selection
  • Added performance optimization for Fujitsu A64FX with InfiniBand
  • Added performance optimization for clear cache code aarch64
  • Added support for relaxed-order PCIe access in IB RDMA transports
  • Added new TCP connection manager
  • Added support for UCT/IB PKey with partial membership in IB transports
  • Added support for RoCE LAG
  • Added flow control for RDMA read operations
  • Improved endpoint flush implementation for UCT/IB
  • Improved UD timer to avoid interrupting the main thread when not in use
  • Improved latency estimation for network path with CUDA
  • Improved error reporting messages
  • Improved performance in active message flow (removed malloc call)
  • Improved performance in ptr_array flow
  • Improved performance in UCT/SM progress engine flow
  • Improved I/O demo code
  • Updated examples code

UCX Java (API Preview)

  • Added support for UCX shared library loading from both classpath and LD_LIBRARY_PATH
  • Added configuration map to ucp_params to be able to set UCX properties programmatically

Bugfixes:

  • Fixes for most resent versions of GCC, CLANG, ARMCLANG, PGI
  • Fixes in UCT/IB for strict order keys
  • Fixes in memory barrier code for aarch64
  • Fixes in UCT/IB/DEVX for fork system call
  • Fixes in UCT/IB for rand() call in rdma-core
  • Fixed in group rescheduling for UCT/IB/DC
  • Fixes in UCT/CUDA bandwidth reporting
  • Fixes in rkey_ptr protocol
  • Fixes in lane selection for rendezvous protocol based on get-zero-copy flow
  • Fixes for ROCm build
  • Fixes for XPMEM transport
  • Fixes in closing endpoint code
  • Fixes in RDMACM code
  • Fixes in memcpy selection for AMD
  • Fixed in UCT/UD endpoint flush functionality
  • Fixes in XPMEM detection
  • Multiple fixes in RPM spec file
  • Multiple fixes in UCP documentation
  • Multiple fixes in socket connection manager
  • Multiple fixes in gtest
  • Multiple fixes in JAVA API implementation
Assets 2
Loading

v1.9.0-rc1

08 Aug 00:00
@shamisp shamisp
v1.9.0-rc1
7b189c9
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.9.0-rc1 Pre-release
Pre-release

1.9.0-rc1 (August 7, 2020)

Assets 2
Loading

v1.8.1

11 Jul 05:35
@shamisp shamisp
v1.8.1
6b29558
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.8.1

1.8.1 (July 10, 2020)

Features:

  • Added binary release pipeline in Azure CI

Bugfixes:

  • Multiple fixes in testing environment
  • Fixes in InfiniBand DEVX transport
  • Fixes in memory management for CUDA IPC transport
  • Fixes for binutils 2.34+
  • Fixes in RPM SPEC file and package generation
  • Fixes for AMD ROCM build environment
Assets 10
Loading

v1.8.1-rc4

07 Jul 23:31
@yosefe yosefe
v1.8.1-rc4
7a25cf2
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.8.1-rc4 Pre-release
Pre-release

1.8.1-rc4 (July 7, 2020)

Features:

  • Added binary release pipeline in Azure CI

Bugfixes:

  • Multiple fixes in testing environment
  • Fixes in InfiniBand DEVX transport
  • Fixes in memory management for CUDA IPC transport
  • Fixes for binutils 2.34+
  • Fixes in RPM SPEC file and package generation
  • Fixes for AMD ROCM build environment
Assets 10
Loading

v1.8.1-rc2

06 Jul 06:28
@shamisp shamisp
v1.8.1-rc2
6ec60d3
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.8.1-rc2 Pre-release
Pre-release

1.8.1-RC2 (July 4, 2020)

Features:

  • Added binary release pipeline in Azure CI

Bugfixes:

  • Multiple fixes in testing environment
  • Fixes in InfiniBand DEVX transport
  • Fixes in memory management for CUDA IPC transport
  • Fixes for binutils 2.34+
  • Fixes in RPM SPEC file and package generation
  • Fixes for AMD ROCM build environment
Assets 8
Loading