rocThrust 3.2.0 for ROCm 6.3.0

Added

• Merged changes from upstream CCCL/thrust 2.3.2
  • Only the NVIDIA backend uses tuple and pair types from libcu++, other backends continue to
    use the original Thrust implementations and hence do not require libcu++ (CCCL) as a dependency.
• Added the thrust::hip::par_det execution policy to enable bitwise reproducibility on algorithms that are not bitwise reproducible by default.

Changed

• Updated the default value for the -a argument from rmake.py to gfx906:xnack-,gfx1030,gfx1100,gfx1101,gfx1102,gfx1151,gfx1200,gfx1201.
• Enabled the upstream (thrust) test suite for execution by default. It can still be disabled by CMake option -DENABLE_UPSTREAM_TESTS=OFF.

Resolved issues

• Fixed an issue in rmake.py where the list storing cmake options would contain individual characters instead of a full string of options.
• Fixed the HIP backend not passing TestCopyIfNonTrivial from the upstream (thrust) test suite.
• Fixed tests failing when compiled with -D_GLIBCXX_ASSERTIONS=ON.

rocThrust 3.1.1 for ROCm 6.2.4

Added

• gfx1151 Support

rocThrust 3.1.0 for ROCm 6.2.2

rocThrust code for ROCm 6.2.2 did not change. The library was rebuilt for the updated ROCm 6.2.2 stack.

rocThrust 3.1.0 for ROCm 6.2.1

rocThrust code for ROCm 6.2.1 did not change. The library was rebuilt for the updated ROCm 6.2.1 stack.

rocThrust 3.1.0 for ROCm 6.2.0

Additions

• Merged changes from upstream CCCL/thrust 2.2.0
  • Updated the contents of system/hip and test with the upstream changes to system/cuda and testing

Changes

• Updated internal calls to rocprim::detail::invoke_result to use the public API rocprim::invoke_result.
• Use rocprim::device_adjacent_difference for adjacent_difference API call.
• Updated internal use of custom iterator in thrust::detail::unique_by_key to use rocPRIM's rocprim::unique_by_key.
• Updated adjecent_difference to make use of rocprim:adjecent_difference when iterators are comparable and not equal otherwise use rocprim:adjacent_difference_inplace.

Known issues

• thrust::reduce_by_key outputs are not bit-wise reproducible, as run-to-run results for pseudo-associative reduction operators (e.g. floating-point arithmetic operators) are not deterministic on the same device.
• Note that currently, rocThrust memory allocation is performed in such a way that most algorithmic API functions cannot be called from within hipGraphs.

rocThrust 3.0.1 for ROCm 6.1.2

rocThrust code for ROCm 6.1.2 did not change. The library was rebuilt for the updated ROCm 6.1.2 stack.

rocThrust 3.0.1 for ROCm 6.1.1

rocThrust code for ROCm 6.1.1 did not change. The library was rebuilt for the updated ROCm 6.1.1 stack.

rocThrust 3.0.1 for ROCm 6.1.0

Fixes

• Ported a fix from thrust 2.2 that ensures thrust::optional is trivially copyable.

rocThrust 3.0.0 for ROCm 6.0.2

rocThrust code for ROCm 6.0.2 did not change. The library was rebuilt for the updated ROCm 6.0.2 stack.

rocThrust 3.0.0 for ROCm 6.0.0

Added

• Updated to match upstream Thrust 2.0.1
• NV_IF_TARGET macro from libcu++ for NVIDIA backend and HIP implementation for HIP backend.

Changed

• The cmake build system now additionally accepts GPU_TARGETS in addition to AMDGPU_TARGETS for
  setting the targeted gpu architectures. GPU_TARGETS=all will compile for all supported architectures.
  AMDGPU_TARGETS is only provided for backwards compatibility, GPU_TARGETS should be preferred.

Removed

• Removed cub symlink from the root of the repository.
• Removed support for deprecated macros (THRUST_DEVICE_BACKEND and THRUST_HOST_BACKEND).

Fixed

• Fixed a segmentation fault when binary search / upper bound / lower bound / equal range was invoked with hip_rocprim::execute_on_stream_base policy.

Known issues

• For NVIDIA backend, NV_IF_TARGET and THRUST_RDC_ENABLED intend to substitute the THRUST_HAS_CUDART macro, which is now no longer used in Thrust (provided for legacy support only). However, there is no THRUST_RDC_ENABLED macro available for the HIP backend, so some branches in Thrust's code may be unreachable in the HIP backend.