Release Notes#

This section lists significant changes, new features, performance improvements, and various issues. Unless noted, listed issues should not impact functionality. When functionality is impacted, we offer a work-around to avoid the issue (if available).

0.2.5#

The cuRANDDx 0.2.5 brings support for Rubin architecture and MSVC compiler.

New Features#

  • Support for Rubin architecture sm_107 (SM<1070>).

  • Added support for MSVC 19.44+ (Visual Studio 2022 version 17.14 and above) as the host compiler on Windows.

Deprecations#

  • Support for GCC 7 as the host compiler is deprecated and will be removed in a future release. A warning is emitted when compiling with GCC 7. We recommend GCC 10 or newer.

Breaking Changes#

  • When generate4() produces four double values, it now returns 32-byte-aligned double4_32a instead of double4. double4 is deprecated in CUDA 13.

0.2.4#

The cuRANDDx 0.2.4 is an update from the previous release with a few minor updates.

New Features#

  • Example and builds use improved CUDA architecture filtering and compiler option propagation.

  • Added CURANDDX_SKIP_IF_NOT_APPLICABLE_SM() macro to skip kernel compilation for unintended device architectures, reducing compilation time and the final binary size. See SM for details.

0.2.3#

The cuRANDDx 0.2.3 is an update for MathDx 26.03 release with a few minor updates.

New Features#

  • Support for CUDA 12.0 is removed.

  • Support for SM70 and SM72 architectures is removed.

0.2.2#

The cuRANDDx 0.2.2 is an update for MathDx 25.12 release with a few minor documentation and example updates.

New Features#

  • Support for CUDA 13.0 Update 1.

0.2.1#

Update for MathDx 25.06.1 release.

New Features#

  • Support for CUDA 13.0

  • Deprecation of CUDA 11.X

  • Support for Thor SM renaming from sm_101 to sm_110 starting from CUDA 13.0 * Note: For CUDA 12.9 and older releases, Thor stays labeled as sm_101

0.2.0#

The cuRANDDx 0.2.0 release adds support for Blackwell architectures, including SM100, SM101, SM103, SM120, and SM121.

New Features#

  • Support for Blackwell architectures SM100, SM101, SM120; experimental support for SM101, SM121.

  • Support for NVIDIA Xavier Tegra SoC (SM<720> or sm_72) is deprecated.

0.1.1#

A patch release with a few minor documentation updates.

0.1.0#

The first early access (EA) release of cuRANDDx library.

New Features#

  • Thread-level API of random number generation using XORWOW, MRG32k3a, Philox_4x32, and quasirandom SOBOL generators.

  • Thread-level API of random number generation with uniform, normal, log normal, or Poisson distribution.

  • Support for SM70 - SM90 CUDA architectures.

  • Multiple examples included.