rocPRIM 3.1.0 for ROCm 6.1.5

rocPRIM code for ROCm 6.1.5 did not change. The library was rebuilt for the updated ROCm 6.1.5 stack.

rocPRIM 3.1.0 for ROCm 6.1.2

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

rocPRIM 3.1.0 for ROCm 6.1.1

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

rocPRIM 3.1.0 for ROCm 6.1.0

Additions

• New primitive: block_run_length_decode
• New primitive: batch_memcpy

Changes

• Renamed:
  • scan_config_v2 to scan_config
  • scan_by_key_config_v2 to scan_by_key_config
  • radix_sort_config_v2 to radix_sort_config
  • reduce_by_key_config_v2 to reduce_by_key_config
  • radix_sort_config_v2 to radix_sort_config
• Removed support for custom config types for device algorithms
• host_warp_size() was moved into rocprim/device/config_types.hpp; it now uses either device_id or
  a stream parameter to query the proper device and a device_id out parameter
  • The return type is hipError_t
• Added support for __int128_t in device_radix_sort and block_radix_sort
• Improved the performance of match_any, and block_histogram which uses it

Deprecations

• Removed reduce_by_key_config, MatchAny, scan_config, scan_by_key_config, and
  radix_sort_config

Fixes

• Build issues with rmake.py on Windows when using VS 2017 15.8 or later (due to a breaking fix with
  extended aligned storage)

rocPRIM 3.0.0 for ROCm 6.0.2

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

rocPRIM 3.0.0 for ROCm 6.0.0

Added

• block_sort::sort() overload for keys and values with a dynamic size, for all block sort algorithms. Additionally, all block_sort::sort() overloads with a dynamic size are now supported for block_sort_algorithm::merge_sort and block_sort_algorithm::bitonic_sort.
• New two-way partition primitive partition_two_way which can write to two separate iterators.

Optimizations

• Improved the performance of partition.

Fixed

• Fixed rocprim::MatchAny for devices with 64-bit warp size. The function rocprim::MatchAny is deprecated and rocprim::match_any is preferred instead.

rocPRIM 2.13.1 for ROCm 5.7.1

rocPRIM code for ROCm 5.7.1 did not change. The library was rebuilt for the updated ROCm 5.7.1 stack.

rocPRIM 2.13.1 for ROCm 5.7.0

Changed

• Deprecated configuration radix_sort_config for device-level radix sort as it no longer matches the algorithm's parameters. New configuration radix_sort_config_v2 is preferred instead.
• Removed erroneous implementation of device-level inclusive_scan and exclusive_scan. The prior default implementation using lookback-scan now is the only available implementation.
• The benchmark metric indicating the bytes processed for exclusive_scan_by_key and inclusive_scan_by_key has been changed to incorporate the key type. Furthermore, the benchmark log has been changed such that these algorithms are reported as scan and scan_by_key instead of scan_exclusive and scan_inclusive.
• Deprecated configurations scan_config and scan_by_key_config for device-level scans, as they no longer match the algorithm's parameters. New configurations scan_config_v2 and scan_by_key_config_v2 are preferred instead.

Fixed

• Fixed build issue caused by missing header in thread/thread_search.hpp.

rocPRIM 2.13.0 for ROCm 5.6.1

rocPRIM code for ROCm 5.6.1 did not change. The library was rebuilt for the updated ROCm 5.6.1 stack.

rocPRIM 2.13.0 for ROCm 5.6.0

rocPRIM code for ROCm 5.6.0 did not change. The library was rebuilt for the updated ROCm 5.6.0 stack.