cuda-cccl 0.3.2__cp313-cp313-manylinux_2_24_aarch64.whl → 0.3.4__cp313-cp313-manylinux_2_24_aarch64.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of cuda-cccl might be problematic. Click here for more details.

Files changed (911) hide show
  1. cuda/cccl/headers/include/cub/agent/agent_adjacent_difference.cuh +12 -38
  2. cuda/cccl/headers/include/cub/agent/agent_batch_memcpy.cuh +16 -40
  3. cuda/cccl/headers/include/cub/agent/agent_for.cuh +2 -28
  4. cuda/cccl/headers/include/cub/agent/agent_histogram.cuh +24 -56
  5. cuda/cccl/headers/include/cub/agent/agent_merge_sort.cuh +12 -38
  6. cuda/cccl/headers/include/cub/agent/agent_radix_sort_downsweep.cuh +31 -56
  7. cuda/cccl/headers/include/cub/agent/agent_radix_sort_histogram.cuh +31 -35
  8. cuda/cccl/headers/include/cub/agent/agent_radix_sort_onesweep.cuh +47 -48
  9. cuda/cccl/headers/include/cub/agent/agent_radix_sort_upsweep.cuh +39 -42
  10. cuda/cccl/headers/include/cub/agent/agent_reduce.cuh +33 -60
  11. cuda/cccl/headers/include/cub/agent/agent_reduce_by_key.cuh +18 -44
  12. cuda/cccl/headers/include/cub/agent/agent_rle.cuh +26 -55
  13. cuda/cccl/headers/include/cub/agent/agent_scan.cuh +22 -49
  14. cuda/cccl/headers/include/cub/agent/agent_scan_by_key.cuh +15 -41
  15. cuda/cccl/headers/include/cub/agent/agent_segmented_radix_sort.cuh +9 -35
  16. cuda/cccl/headers/include/cub/agent/agent_select_if.cuh +20 -49
  17. cuda/cccl/headers/include/cub/agent/agent_sub_warp_merge_sort.cuh +14 -40
  18. cuda/cccl/headers/include/cub/agent/agent_three_way_partition.cuh +18 -40
  19. cuda/cccl/headers/include/cub/agent/agent_topk.cuh +0 -2
  20. cuda/cccl/headers/include/cub/agent/agent_unique_by_key.cuh +20 -46
  21. cuda/cccl/headers/include/cub/agent/single_pass_scan_operators.cuh +3 -28
  22. cuda/cccl/headers/include/cub/block/block_adjacent_difference.cuh +7 -31
  23. cuda/cccl/headers/include/cub/block/block_discontinuity.cuh +10 -34
  24. cuda/cccl/headers/include/cub/block/block_exchange.cuh +120 -154
  25. cuda/cccl/headers/include/cub/block/block_histogram.cuh +28 -52
  26. cuda/cccl/headers/include/cub/block/block_load.cuh +124 -146
  27. cuda/cccl/headers/include/cub/block/block_load_to_shared.cuh +0 -16
  28. cuda/cccl/headers/include/cub/block/block_merge_sort.cuh +58 -87
  29. cuda/cccl/headers/include/cub/block/block_radix_rank.cuh +81 -100
  30. cuda/cccl/headers/include/cub/block/block_radix_sort.cuh +92 -156
  31. cuda/cccl/headers/include/cub/block/block_raking_layout.cuh +8 -32
  32. cuda/cccl/headers/include/cub/block/block_reduce.cuh +21 -46
  33. cuda/cccl/headers/include/cub/block/block_run_length_decode.cuh +51 -79
  34. cuda/cccl/headers/include/cub/block/block_scan.cuh +94 -401
  35. cuda/cccl/headers/include/cub/block/block_shuffle.cuh +10 -34
  36. cuda/cccl/headers/include/cub/block/block_store.cuh +73 -97
  37. cuda/cccl/headers/include/cub/block/radix_rank_sort_operations.cuh +2 -29
  38. cuda/cccl/headers/include/cub/block/specializations/block_histogram_atomic.cuh +5 -29
  39. cuda/cccl/headers/include/cub/block/specializations/block_histogram_sort.cuh +25 -49
  40. cuda/cccl/headers/include/cub/block/specializations/block_reduce_raking.cuh +12 -34
  41. cuda/cccl/headers/include/cub/block/specializations/block_reduce_raking_commutative_only.cuh +10 -34
  42. cuda/cccl/headers/include/cub/block/specializations/block_reduce_warp_reductions.cuh +3 -27
  43. cuda/cccl/headers/include/cub/block/specializations/block_scan_raking.cuh +12 -36
  44. cuda/cccl/headers/include/cub/block/specializations/block_scan_warp_scans.cuh +9 -33
  45. cuda/cccl/headers/include/cub/config.cuh +2 -26
  46. cuda/cccl/headers/include/cub/cub.cuh +3 -27
  47. cuda/cccl/headers/include/cub/detail/array_utils.cuh +2 -26
  48. cuda/cccl/headers/include/cub/detail/choose_offset.cuh +2 -28
  49. cuda/cccl/headers/include/cub/detail/detect_cuda_runtime.cuh +3 -27
  50. cuda/cccl/headers/include/cub/detail/device_double_buffer.cuh +0 -2
  51. cuda/cccl/headers/include/cub/detail/device_memory_resource.cuh +1 -3
  52. cuda/cccl/headers/include/cub/detail/fast_modulo_division.cuh +2 -28
  53. cuda/cccl/headers/include/cub/detail/integer_utils.cuh +0 -2
  54. cuda/cccl/headers/include/cub/detail/launcher/cuda_driver.cuh +0 -2
  55. cuda/cccl/headers/include/cub/detail/launcher/cuda_runtime.cuh +0 -2
  56. cuda/cccl/headers/include/cub/detail/mdspan_utils.cuh +0 -2
  57. cuda/cccl/headers/include/cub/detail/ptx-json/README.md +7 -12
  58. cuda/cccl/headers/include/cub/detail/ptx-json/array.h +6 -33
  59. cuda/cccl/headers/include/cub/detail/ptx-json/json.h +13 -36
  60. cuda/cccl/headers/include/cub/detail/ptx-json/object.h +9 -38
  61. cuda/cccl/headers/include/cub/detail/ptx-json/string.h +58 -32
  62. cuda/cccl/headers/include/cub/detail/ptx-json/value.h +51 -51
  63. cuda/cccl/headers/include/cub/detail/ptx-json-parser.h +7 -31
  64. cuda/cccl/headers/include/cub/detail/rfa.cuh +2 -27
  65. cuda/cccl/headers/include/cub/detail/strong_load.cuh +3 -29
  66. cuda/cccl/headers/include/cub/detail/strong_store.cuh +3 -29
  67. cuda/cccl/headers/include/cub/detail/temporary_storage.cuh +2 -9
  68. cuda/cccl/headers/include/cub/detail/type_traits.cuh +0 -2
  69. cuda/cccl/headers/include/cub/detail/uninitialized_copy.cuh +6 -31
  70. cuda/cccl/headers/include/cub/detail/unsafe_bitcast.cuh +2 -25
  71. cuda/cccl/headers/include/cub/device/device_adjacent_difference.cuh +2 -26
  72. cuda/cccl/headers/include/cub/device/device_for.cuh +3 -5
  73. cuda/cccl/headers/include/cub/device/device_histogram.cuh +3 -27
  74. cuda/cccl/headers/include/cub/device/device_memcpy.cuh +2 -26
  75. cuda/cccl/headers/include/cub/device/device_merge_sort.cuh +2 -26
  76. cuda/cccl/headers/include/cub/device/device_partition.cuh +3 -27
  77. cuda/cccl/headers/include/cub/device/device_radix_sort.cuh +3 -27
  78. cuda/cccl/headers/include/cub/device/device_reduce.cuh +10 -31
  79. cuda/cccl/headers/include/cub/device/device_run_length_encode.cuh +3 -27
  80. cuda/cccl/headers/include/cub/device/device_scan.cuh +16 -34
  81. cuda/cccl/headers/include/cub/device/device_segmented_radix_sort.cuh +3 -27
  82. cuda/cccl/headers/include/cub/device/device_segmented_reduce.cuh +3 -27
  83. cuda/cccl/headers/include/cub/device/device_segmented_sort.cuh +2 -26
  84. cuda/cccl/headers/include/cub/device/device_select.cuh +3 -27
  85. cuda/cccl/headers/include/cub/device/dispatch/dispatch_adjacent_difference.cuh +2 -28
  86. cuda/cccl/headers/include/cub/device/dispatch/dispatch_batch_memcpy.cuh +2 -27
  87. cuda/cccl/headers/include/cub/device/dispatch/dispatch_copy_mdspan.cuh +0 -2
  88. cuda/cccl/headers/include/cub/device/dispatch/dispatch_for.cuh +3 -29
  89. cuda/cccl/headers/include/cub/device/dispatch/dispatch_histogram.cuh +14 -34
  90. cuda/cccl/headers/include/cub/device/dispatch/dispatch_merge_sort.cuh +5 -30
  91. cuda/cccl/headers/include/cub/device/dispatch/dispatch_radix_sort.cuh +4 -29
  92. cuda/cccl/headers/include/cub/device/dispatch/dispatch_reduce.cuh +5 -32
  93. cuda/cccl/headers/include/cub/device/dispatch/dispatch_reduce_by_key.cuh +3 -29
  94. cuda/cccl/headers/include/cub/device/dispatch/dispatch_reduce_deterministic.cuh +2 -29
  95. cuda/cccl/headers/include/cub/device/dispatch/dispatch_reduce_nondeterministic.cuh +1 -2
  96. cuda/cccl/headers/include/cub/device/dispatch/dispatch_rle.cuh +47 -59
  97. cuda/cccl/headers/include/cub/device/dispatch/dispatch_scan.cuh +21 -30
  98. cuda/cccl/headers/include/cub/device/dispatch/dispatch_scan_by_key.cuh +2 -27
  99. cuda/cccl/headers/include/cub/device/dispatch/dispatch_segmented_sort.cuh +3 -27
  100. cuda/cccl/headers/include/cub/device/dispatch/dispatch_select_if.cuh +3 -27
  101. cuda/cccl/headers/include/cub/device/dispatch/dispatch_streaming_reduce.cuh +0 -2
  102. cuda/cccl/headers/include/cub/device/dispatch/dispatch_streaming_reduce_by_key.cuh +51 -36
  103. cuda/cccl/headers/include/cub/device/dispatch/dispatch_three_way_partition.cuh +3 -28
  104. cuda/cccl/headers/include/cub/device/dispatch/dispatch_topk.cuh +0 -1
  105. cuda/cccl/headers/include/cub/device/dispatch/dispatch_transform.cuh +27 -55
  106. cuda/cccl/headers/include/cub/device/dispatch/dispatch_unique_by_key.cuh +4 -28
  107. cuda/cccl/headers/include/cub/device/dispatch/kernels/{for_each.cuh → kernel_for_each.cuh} +0 -2
  108. cuda/cccl/headers/include/cub/device/dispatch/kernels/{histogram.cuh → kernel_histogram.cuh} +149 -157
  109. cuda/cccl/headers/include/cub/device/dispatch/kernels/{merge_sort.cuh → kernel_merge_sort.cuh} +0 -2
  110. cuda/cccl/headers/include/cub/device/dispatch/kernels/{radix_sort.cuh → kernel_radix_sort.cuh} +0 -2
  111. cuda/cccl/headers/include/cub/device/dispatch/kernels/{reduce.cuh → kernel_reduce.cuh} +2 -28
  112. cuda/cccl/headers/include/cub/device/dispatch/kernels/{scan.cuh → kernel_scan.cuh} +2 -28
  113. cuda/cccl/headers/include/cub/device/dispatch/kernels/{segmented_reduce.cuh → kernel_segmented_reduce.cuh} +3 -29
  114. cuda/cccl/headers/include/cub/device/dispatch/kernels/{segmented_sort.cuh → kernel_segmented_sort.cuh} +0 -1
  115. cuda/cccl/headers/include/cub/device/dispatch/kernels/{three_way_partition.cuh → kernel_three_way_partition.cuh} +0 -1
  116. cuda/cccl/headers/include/cub/device/dispatch/kernels/{transform.cuh → kernel_transform.cuh} +11 -11
  117. cuda/cccl/headers/include/cub/device/dispatch/kernels/{unique_by_key.cuh → kernel_unique_by_key.cuh} +0 -1
  118. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_adjacent_difference.cuh +2 -26
  119. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_batch_memcpy.cuh +2 -26
  120. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_for.cuh +2 -28
  121. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_histogram.cuh +6 -26
  122. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_merge.cuh +2 -26
  123. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_merge_sort.cuh +5 -31
  124. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_radix_sort.cuh +31 -33
  125. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_reduce.cuh +15 -40
  126. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_reduce_by_key.cuh +2 -26
  127. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_run_length_encode.cuh +2 -28
  128. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_scan.cuh +20 -44
  129. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_scan_by_key.cuh +2 -26
  130. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_segmented_sort.cuh +20 -45
  131. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_select_if.cuh +2 -27
  132. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_three_way_partition.cuh +11 -36
  133. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_topk.cuh +0 -1
  134. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_transform.cuh +2 -27
  135. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_unique_by_key.cuh +14 -40
  136. cuda/cccl/headers/include/cub/grid/grid_even_share.cuh +3 -27
  137. cuda/cccl/headers/include/cub/grid/grid_mapping.cuh +3 -27
  138. cuda/cccl/headers/include/cub/grid/grid_queue.cuh +3 -27
  139. cuda/cccl/headers/include/cub/iterator/arg_index_input_iterator.cuh +3 -27
  140. cuda/cccl/headers/include/cub/iterator/cache_modified_input_iterator.cuh +3 -27
  141. cuda/cccl/headers/include/cub/iterator/cache_modified_output_iterator.cuh +3 -27
  142. cuda/cccl/headers/include/cub/iterator/tex_obj_input_iterator.cuh +3 -27
  143. cuda/cccl/headers/include/cub/thread/thread_load.cuh +3 -28
  144. cuda/cccl/headers/include/cub/thread/thread_operators.cuh +3 -27
  145. cuda/cccl/headers/include/cub/thread/thread_reduce.cuh +3 -26
  146. cuda/cccl/headers/include/cub/thread/thread_scan.cuh +3 -29
  147. cuda/cccl/headers/include/cub/thread/thread_search.cuh +3 -27
  148. cuda/cccl/headers/include/cub/thread/thread_simd.cuh +0 -2
  149. cuda/cccl/headers/include/cub/thread/thread_sort.cuh +2 -26
  150. cuda/cccl/headers/include/cub/thread/thread_store.cuh +3 -27
  151. cuda/cccl/headers/include/cub/util_allocator.cuh +3 -27
  152. cuda/cccl/headers/include/cub/util_arch.cuh +3 -29
  153. cuda/cccl/headers/include/cub/util_cpp_dialect.cuh +2 -26
  154. cuda/cccl/headers/include/cub/util_debug.cuh +3 -27
  155. cuda/cccl/headers/include/cub/util_device.cuh +18 -59
  156. cuda/cccl/headers/include/cub/util_macro.cuh +4 -28
  157. cuda/cccl/headers/include/cub/util_math.cuh +2 -28
  158. cuda/cccl/headers/include/cub/util_namespace.cuh +3 -28
  159. cuda/cccl/headers/include/cub/util_policy_wrapper_t.cuh +3 -27
  160. cuda/cccl/headers/include/cub/util_ptx.cuh +6 -30
  161. cuda/cccl/headers/include/cub/util_temporary_storage.cuh +3 -29
  162. cuda/cccl/headers/include/cub/util_type.cuh +5 -32
  163. cuda/cccl/headers/include/cub/util_vsmem.cuh +2 -28
  164. cuda/cccl/headers/include/cub/version.cuh +2 -26
  165. cuda/cccl/headers/include/cub/warp/specializations/warp_exchange_shfl.cuh +10 -35
  166. cuda/cccl/headers/include/cub/warp/specializations/warp_exchange_smem.cuh +5 -30
  167. cuda/cccl/headers/include/cub/warp/specializations/warp_reduce_shfl.cuh +15 -39
  168. cuda/cccl/headers/include/cub/warp/specializations/warp_reduce_smem.cuh +5 -35
  169. cuda/cccl/headers/include/cub/warp/specializations/warp_scan_shfl.cuh +22 -46
  170. cuda/cccl/headers/include/cub/warp/specializations/warp_scan_smem.cuh +3 -27
  171. cuda/cccl/headers/include/cub/warp/warp_exchange.cuh +2 -26
  172. cuda/cccl/headers/include/cub/warp/warp_load.cuh +4 -27
  173. cuda/cccl/headers/include/cub/warp/warp_merge_sort.cuh +2 -26
  174. cuda/cccl/headers/include/cub/warp/warp_reduce.cuh +3 -22
  175. cuda/cccl/headers/include/cub/warp/warp_scan.cuh +3 -27
  176. cuda/cccl/headers/include/cub/warp/warp_store.cuh +4 -27
  177. cuda/cccl/headers/include/cub/warp/warp_utils.cuh +0 -2
  178. cuda/cccl/headers/include/cuda/__barrier/barrier.h +1 -1
  179. cuda/cccl/headers/include/cuda/__barrier/barrier_arrive_tx.h +0 -1
  180. cuda/cccl/headers/include/cuda/__barrier/barrier_block_scope.h +277 -235
  181. cuda/cccl/headers/include/cuda/__barrier/barrier_expect_tx.h +0 -1
  182. cuda/cccl/headers/include/cuda/__driver/driver_api.h +13 -0
  183. cuda/cccl/headers/include/cuda/__execution/determinism.h +0 -2
  184. cuda/cccl/headers/include/cuda/__execution/output_ordering.h +0 -2
  185. cuda/cccl/headers/include/cuda/__functional/maximum.h +25 -7
  186. cuda/cccl/headers/include/cuda/__functional/minimum.h +25 -7
  187. cuda/cccl/headers/include/cuda/__functional/minimum_maximum_common.h +52 -0
  188. cuda/cccl/headers/include/cuda/__functional/proclaim_return_type.h +0 -2
  189. cuda/cccl/headers/include/cuda/__iterator/counting_iterator.h +13 -4
  190. cuda/cccl/headers/include/cuda/__iterator/zip_function.h +4 -2
  191. cuda/cccl/headers/include/cuda/__mdspan/host_device_accessor.h +0 -1
  192. cuda/cccl/headers/include/cuda/__memcpy_async/cp_async_bulk_shared_global.h +28 -7
  193. cuda/cccl/headers/include/cuda/__memcpy_async/dispatch_memcpy_async.h +1 -1
  194. cuda/cccl/headers/include/cuda/__memcpy_async/elect_one.h +52 -0
  195. cuda/cccl/headers/include/cuda/__memcpy_async/memcpy_async_tx.h +2 -3
  196. cuda/cccl/headers/include/cuda/__memcpy_async/memcpy_completion.h +1 -7
  197. cuda/cccl/headers/include/cuda/__memcpy_async/try_get_barrier_handle.h +0 -1
  198. cuda/cccl/headers/include/cuda/__memory/get_device_address.h +1 -1
  199. cuda/cccl/headers/include/cuda/__memory/ranges_overlap.h +126 -0
  200. cuda/cccl/headers/include/cuda/__memory_resource/any_resource.h +898 -0
  201. cuda/cccl/headers/include/cuda/__memory_resource/device_memory_pool.h +149 -0
  202. cuda/cccl/headers/include/cuda/__memory_resource/get_property.h +3 -3
  203. cuda/cccl/headers/include/cuda/__memory_resource/legacy_managed_memory_resource.h +148 -0
  204. cuda/cccl/headers/include/cuda/__memory_resource/legacy_pinned_memory_resource.h +139 -0
  205. cuda/cccl/headers/include/cuda/__memory_resource/managed_memory_pool.h +146 -0
  206. cuda/cccl/headers/include/cuda/__memory_resource/memory_resource_base.h +578 -0
  207. cuda/cccl/headers/include/cuda/__memory_resource/pinned_memory_pool.h +188 -0
  208. cuda/cccl/headers/include/cuda/__memory_resource/properties.h +3 -3
  209. cuda/cccl/headers/include/cuda/__memory_resource/resource.h +37 -3
  210. cuda/cccl/headers/include/cuda/__numeric/add_overflow.h +13 -3
  211. cuda/cccl/headers/include/cuda/__numeric/div_overflow.h +150 -0
  212. cuda/cccl/headers/include/cuda/__numeric/overflow_cast.h +2 -2
  213. cuda/cccl/headers/include/cuda/__numeric/sub_overflow.h +344 -0
  214. cuda/cccl/headers/include/cuda/__nvtx/nvtx3.h +0 -6
  215. cuda/cccl/headers/include/cuda/__ptx/instructions/shfl_sync.h +1 -1
  216. cuda/cccl/headers/include/cuda/__ptx/pragmas/enable_smem_spilling.h +47 -0
  217. cuda/cccl/headers/include/cuda/{std/__cuda → __runtime}/api_wrapper.h +3 -3
  218. cuda/cccl/headers/include/cuda/__stream/get_stream.h +0 -1
  219. cuda/cccl/headers/include/cuda/{__fwd/barrier_native_handle.h → __stream/internal_streams.h} +17 -15
  220. cuda/cccl/headers/include/cuda/__utility/__basic_any/basic_any_ptr.h +2 -2
  221. cuda/cccl/headers/include/cuda/__utility/__basic_any/basic_any_value.h +1 -0
  222. cuda/cccl/headers/include/cuda/__utility/__basic_any/semiregular.h +1 -0
  223. cuda/cccl/headers/include/cuda/__utility/__basic_any/virtcall.h +2 -1
  224. cuda/cccl/headers/include/cuda/barrier +42 -16
  225. cuda/cccl/headers/include/cuda/memory +1 -0
  226. cuda/cccl/headers/include/cuda/memory_resource +6 -1
  227. cuda/cccl/headers/include/cuda/numeric +2 -0
  228. cuda/cccl/headers/include/cuda/pipeline +3 -2
  229. cuda/cccl/headers/include/cuda/ptx +1 -0
  230. cuda/cccl/headers/include/cuda/std/__algorithm/unique_copy.h +0 -2
  231. cuda/cccl/headers/include/cuda/std/__atomic/api/reference.h +1 -1
  232. cuda/cccl/headers/include/cuda/std/__atomic/functions/cuda_ptx_derived.h +115 -58
  233. cuda/cccl/headers/include/cuda/std/__atomic/functions/cuda_ptx_generated.h +844 -378
  234. cuda/cccl/headers/include/cuda/std/__atomic/functions/cuda_ptx_generated_helper.h +12 -5
  235. cuda/cccl/headers/include/cuda/std/__atomic/functions/host.h +31 -0
  236. cuda/cccl/headers/include/cuda/std/__atomic/types/small.h +10 -0
  237. cuda/cccl/headers/include/cuda/std/__atomic/types.h +2 -3
  238. cuda/cccl/headers/include/cuda/std/__bit/byteswap.h +37 -13
  239. cuda/cccl/headers/include/cuda/std/__cccl/builtin.h +0 -28
  240. cuda/cccl/headers/include/cuda/std/__cccl/dialect.h +7 -0
  241. cuda/cccl/headers/include/cuda/std/__cccl/epilogue.h +10 -0
  242. cuda/cccl/headers/include/cuda/std/__cccl/exceptions.h +2 -45
  243. cuda/cccl/headers/include/cuda/std/__cccl/is_non_narrowing_convertible.h +0 -2
  244. cuda/cccl/headers/include/cuda/std/__cccl/prologue.h +8 -0
  245. cuda/cccl/headers/include/cuda/std/__chrono/calendar.h +0 -2
  246. cuda/cccl/headers/include/cuda/std/__chrono/day.h +0 -2
  247. cuda/cccl/headers/include/cuda/std/__chrono/duration.h +13 -17
  248. cuda/cccl/headers/include/cuda/std/__chrono/file_clock.h +0 -2
  249. cuda/cccl/headers/include/cuda/std/__chrono/high_resolution_clock.h +0 -2
  250. cuda/cccl/headers/include/cuda/std/__chrono/month.h +0 -2
  251. cuda/cccl/headers/include/cuda/std/__chrono/steady_clock.h +0 -2
  252. cuda/cccl/headers/include/cuda/std/__chrono/system_clock.h +0 -2
  253. cuda/cccl/headers/include/cuda/std/__chrono/time_point.h +5 -8
  254. cuda/cccl/headers/include/cuda/std/__chrono/year.h +0 -2
  255. cuda/cccl/headers/include/cuda/std/__cmath/error_functions.h +4 -0
  256. cuda/cccl/headers/include/cuda/std/__cmath/exponential_functions.h +2 -3
  257. cuda/cccl/headers/include/cuda/std/__cmath/fdim.h +4 -0
  258. cuda/cccl/headers/include/cuda/std/__cmath/fma.h +4 -0
  259. cuda/cccl/headers/include/cuda/std/__cmath/fpclassify.h +2 -3
  260. cuda/cccl/headers/include/cuda/std/__cmath/gamma.h +2 -3
  261. cuda/cccl/headers/include/cuda/std/__cmath/hyperbolic_functions.h +2 -3
  262. cuda/cccl/headers/include/cuda/std/__cmath/hypot.h +2 -3
  263. cuda/cccl/headers/include/cuda/std/__cmath/inverse_hyperbolic_functions.h +2 -3
  264. cuda/cccl/headers/include/cuda/std/__cmath/inverse_trigonometric_functions.h +2 -3
  265. cuda/cccl/headers/include/cuda/std/__cmath/isfinite.h +2 -3
  266. cuda/cccl/headers/include/cuda/std/__cmath/isinf.h +2 -3
  267. cuda/cccl/headers/include/cuda/std/__cmath/isnan.h +2 -3
  268. cuda/cccl/headers/include/cuda/std/__cmath/logarithms.h +2 -3
  269. cuda/cccl/headers/include/cuda/std/__cmath/min_max.h +2 -2
  270. cuda/cccl/headers/include/cuda/std/__cmath/remainder.h +4 -0
  271. cuda/cccl/headers/include/cuda/std/__cmath/roots.h +2 -3
  272. cuda/cccl/headers/include/cuda/std/__cmath/rounding_functions.h +2 -3
  273. cuda/cccl/headers/include/cuda/std/__cmath/traits.h +4 -0
  274. cuda/cccl/headers/include/cuda/std/__cmath/trigonometric_functions.h +2 -3
  275. cuda/cccl/headers/include/cuda/std/__complex/complex.h +0 -6
  276. cuda/cccl/headers/include/cuda/std/__complex/exponential_functions.h +2 -2
  277. cuda/cccl/headers/include/cuda/std/__concepts/concept_macros.h +27 -1
  278. cuda/cccl/headers/include/cuda/std/__concepts/equality_comparable.h +2 -4
  279. cuda/cccl/headers/include/cuda/std/__exception/cuda_error.h +15 -36
  280. cuda/cccl/headers/include/cuda/std/__exception/exception_macros.h +93 -0
  281. cuda/cccl/headers/include/cuda/std/{detail/libcxx/include/stdexcept → __exception/throw_error.h} +3 -3
  282. cuda/cccl/headers/include/cuda/std/__expected/expected.h +28 -43
  283. cuda/cccl/headers/include/cuda/std/__expected/unexpected.h +2 -10
  284. cuda/cccl/headers/include/cuda/std/__format/format_arg_store.h +2 -2
  285. cuda/cccl/headers/include/cuda/std/__functional/bind.h +6 -6
  286. cuda/cccl/headers/include/cuda/std/__functional/function.h +2 -6
  287. cuda/cccl/headers/include/cuda/std/__functional/invoke.h +5 -5
  288. cuda/cccl/headers/include/cuda/std/__fwd/allocator.h +5 -0
  289. cuda/cccl/headers/include/cuda/std/__fwd/array.h +2 -2
  290. cuda/cccl/headers/include/cuda/std/__fwd/char_traits.h +12 -0
  291. cuda/cccl/headers/include/cuda/std/__fwd/expected.h +46 -0
  292. cuda/cccl/headers/include/cuda/std/__fwd/get.h +21 -22
  293. cuda/cccl/headers/include/cuda/std/{detail/libcxx/include/iosfwd → __fwd/ios.h} +5 -10
  294. cuda/cccl/headers/include/cuda/std/__fwd/mdspan.h +19 -10
  295. cuda/cccl/headers/include/cuda/std/__fwd/optional.h +2 -2
  296. cuda/cccl/headers/include/cuda/std/__fwd/reference_wrapper.h +5 -0
  297. cuda/cccl/headers/include/cuda/std/__fwd/span.h +2 -2
  298. cuda/cccl/headers/include/cuda/std/__fwd/string.h +7 -0
  299. cuda/cccl/headers/include/cuda/std/__fwd/string_view.h +18 -0
  300. cuda/cccl/headers/include/cuda/std/__fwd/tuple.h +3 -0
  301. cuda/cccl/headers/include/cuda/std/__fwd/unexpected.h +40 -0
  302. cuda/cccl/headers/include/cuda/std/{__type_traits/is_reference_wrapper.h → __fwd/variant.h} +16 -15
  303. cuda/cccl/headers/include/cuda/std/__internal/features.h +14 -0
  304. cuda/cccl/headers/include/cuda/std/__iterator/istream_iterator.h +1 -1
  305. cuda/cccl/headers/include/cuda/std/__iterator/istreambuf_iterator.h +1 -1
  306. cuda/cccl/headers/include/cuda/std/__iterator/iter_swap.h +58 -40
  307. cuda/cccl/headers/include/cuda/std/__iterator/ostream_iterator.h +1 -1
  308. cuda/cccl/headers/include/cuda/std/__iterator/ostreambuf_iterator.h +1 -1
  309. cuda/cccl/headers/include/cuda/std/__iterator/reverse_iterator.h +0 -5
  310. cuda/cccl/headers/include/cuda/std/__limits/numeric_limits.h +4 -18
  311. cuda/cccl/headers/include/cuda/std/__linalg/conj_if_needed.h +1 -2
  312. cuda/cccl/headers/include/cuda/std/__linalg/conjugate_transposed.h +0 -2
  313. cuda/cccl/headers/include/cuda/std/__linalg/conjugated.h +0 -2
  314. cuda/cccl/headers/include/cuda/std/__linalg/scaled.h +0 -4
  315. cuda/cccl/headers/include/cuda/std/__linalg/transposed.h +0 -5
  316. cuda/cccl/headers/include/cuda/std/__mdspan/concepts.h +3 -10
  317. cuda/cccl/headers/include/cuda/std/__mdspan/extents.h +4 -15
  318. cuda/cccl/headers/include/cuda/std/__mdspan/layout_left.h +4 -4
  319. cuda/cccl/headers/include/cuda/std/__mdspan/layout_right.h +4 -4
  320. cuda/cccl/headers/include/cuda/std/__mdspan/layout_stride.h +2 -4
  321. cuda/cccl/headers/include/cuda/std/__mdspan/mdspan.h +3 -3
  322. cuda/cccl/headers/include/cuda/std/__mdspan/submdspan_helper.h +1 -1
  323. cuda/cccl/headers/include/cuda/std/__memory/allocator_arg_t.h +1 -0
  324. cuda/cccl/headers/include/cuda/std/__memory/allocator_traits.h +6 -12
  325. cuda/cccl/headers/include/cuda/std/__memory/construct_at.h +1 -5
  326. cuda/cccl/headers/include/cuda/std/__memory/is_sufficiently_aligned.h +7 -2
  327. cuda/cccl/headers/include/cuda/std/__memory/uninitialized_algorithms.h +1 -0
  328. cuda/cccl/headers/include/cuda/std/__memory/uses_allocator.h +5 -0
  329. cuda/cccl/headers/include/cuda/std/__new/allocate.h +5 -0
  330. cuda/cccl/headers/include/cuda/{__barrier/barrier_native_handle.h → std/__new/device_new.h} +9 -24
  331. cuda/cccl/headers/include/cuda/std/__new_ +1 -0
  332. cuda/cccl/headers/include/cuda/std/__optional/optional.h +5 -4
  333. cuda/cccl/headers/include/cuda/std/__optional/optional_ref.h +4 -4
  334. cuda/cccl/headers/include/cuda/std/__random/linear_congruential_engine.h +1 -1
  335. cuda/cccl/headers/include/cuda/std/__random/philox_engine.h +562 -0
  336. cuda/cccl/headers/include/cuda/std/__random/seed_seq.h +204 -0
  337. cuda/cccl/headers/include/cuda/std/__random_ +2 -0
  338. cuda/cccl/headers/include/cuda/std/__ranges/concepts.h +7 -19
  339. cuda/cccl/headers/include/cuda/std/__ranges/movable_box.h +2 -4
  340. cuda/cccl/headers/include/cuda/std/__ranges/owning_view.h +5 -4
  341. cuda/cccl/headers/include/cuda/std/__ranges/repeat_view.h +1 -1
  342. cuda/cccl/headers/include/cuda/std/__string/string_view.h +5 -5
  343. cuda/cccl/headers/include/cuda/std/__tuple_dir/apply.h +82 -0
  344. cuda/cccl/headers/include/cuda/std/__tuple_dir/get.h +122 -0
  345. cuda/cccl/headers/include/cuda/std/__tuple_dir/sfinae_helpers.h +0 -160
  346. cuda/cccl/headers/include/cuda/std/__tuple_dir/structured_bindings.h +123 -129
  347. cuda/cccl/headers/include/cuda/std/__tuple_dir/tie.h +55 -0
  348. cuda/cccl/headers/include/cuda/std/__tuple_dir/tuple.h +457 -0
  349. cuda/cccl/headers/include/cuda/std/__tuple_dir/tuple_cat.h +158 -0
  350. cuda/cccl/headers/include/cuda/std/__tuple_dir/tuple_constraints.h +286 -0
  351. cuda/cccl/headers/include/cuda/std/__tuple_dir/tuple_element.h +7 -0
  352. cuda/cccl/headers/include/cuda/std/__tuple_dir/tuple_leaf.h +452 -0
  353. cuda/cccl/headers/include/cuda/std/__tuple_dir/tuple_like.h +1 -2
  354. cuda/cccl/headers/include/cuda/std/__type_traits/is_comparable.h +78 -0
  355. cuda/cccl/headers/include/cuda/std/__type_traits/is_convertible.h +1 -1
  356. cuda/cccl/headers/include/cuda/std/__type_traits/is_fully_bounded_array.h +47 -0
  357. cuda/cccl/headers/include/cuda/std/__type_traits/is_swappable.h +0 -2
  358. cuda/cccl/headers/include/cuda/std/__utility/in_place.h +4 -24
  359. cuda/cccl/headers/include/cuda/std/__utility/integer_sequence.h +0 -2
  360. cuda/cccl/headers/include/cuda/std/__utility/pair.h +20 -20
  361. cuda/cccl/headers/include/cuda/std/__utility/rel_ops.h +0 -2
  362. cuda/cccl/headers/include/cuda/std/__variant/bad_variant_access.h +74 -0
  363. cuda/cccl/headers/include/cuda/std/__variant/comparison.h +207 -0
  364. cuda/cccl/headers/include/cuda/std/__variant/get.h +192 -0
  365. cuda/cccl/headers/include/cuda/std/__variant/hash.h +82 -0
  366. cuda/cccl/headers/include/cuda/std/__variant/sfinae_helpers.h +89 -0
  367. cuda/cccl/headers/include/cuda/std/__variant/variant.h +250 -0
  368. cuda/cccl/headers/include/cuda/std/__variant/variant_access.h +70 -0
  369. cuda/cccl/headers/include/cuda/std/__variant/variant_base.h +683 -0
  370. cuda/cccl/headers/include/cuda/std/__variant/variant_constraints.h +135 -0
  371. cuda/cccl/headers/include/cuda/std/__variant/variant_match.h +126 -0
  372. cuda/cccl/headers/include/cuda/std/__variant/variant_traits.h +184 -0
  373. cuda/cccl/headers/include/cuda/std/__variant/variant_visit.h +225 -0
  374. cuda/cccl/headers/include/cuda/std/__variant/visit.h +148 -0
  375. cuda/cccl/headers/include/cuda/std/array +1 -1
  376. cuda/cccl/headers/include/cuda/std/atomic +1 -1
  377. cuda/cccl/headers/include/cuda/std/bitset +2 -10
  378. cuda/cccl/headers/include/cuda/std/detail/libcxx/include/__config +6 -6
  379. cuda/cccl/headers/include/cuda/std/detail/libcxx/include/algorithm +1 -4
  380. cuda/cccl/headers/include/cuda/std/detail/libcxx/include/chrono +3 -6
  381. cuda/cccl/headers/include/cuda/std/functional +1 -1
  382. cuda/cccl/headers/include/cuda/std/initializer_list +8 -0
  383. cuda/cccl/headers/include/cuda/std/inplace_vector +6 -5
  384. cuda/cccl/headers/include/cuda/std/iterator +1 -1
  385. cuda/cccl/headers/include/cuda/std/numbers +0 -2
  386. cuda/cccl/headers/include/cuda/std/ratio +2 -2
  387. cuda/cccl/headers/include/cuda/std/span +2 -2
  388. cuda/cccl/headers/include/cuda/std/string_view +24 -42
  389. cuda/cccl/headers/include/cuda/std/tuple +18 -1
  390. cuda/cccl/headers/include/cuda/std/type_traits +0 -1
  391. cuda/cccl/headers/include/cuda/std/variant +8 -1
  392. cuda/cccl/headers/include/nv/target +2 -6
  393. cuda/cccl/headers/include/thrust/detail/adjacent_difference.inl +15 -2
  394. cuda/cccl/headers/include/thrust/detail/allocator/allocator_traits.h +0 -2
  395. cuda/cccl/headers/include/thrust/detail/allocator/copy_construct_range.h +0 -1
  396. cuda/cccl/headers/include/thrust/detail/allocator/destroy_range.h +0 -1
  397. cuda/cccl/headers/include/thrust/detail/allocator/fill_construct_range.h +0 -2
  398. cuda/cccl/headers/include/thrust/detail/allocator/malloc_allocator.h +0 -2
  399. cuda/cccl/headers/include/thrust/detail/allocator/no_throw_allocator.h +0 -2
  400. cuda/cccl/headers/include/thrust/detail/allocator/tagged_allocator.h +0 -2
  401. cuda/cccl/headers/include/thrust/detail/allocator/temporary_allocator.h +0 -2
  402. cuda/cccl/headers/include/thrust/detail/allocator_aware_execution_policy.h +0 -4
  403. cuda/cccl/headers/include/thrust/detail/binary_search.inl +14 -2
  404. cuda/cccl/headers/include/thrust/detail/complex/arithmetic.h +2 -7
  405. cuda/cccl/headers/include/thrust/detail/complex/c99math.h +2 -8
  406. cuda/cccl/headers/include/thrust/detail/complex/catrig.h +2 -8
  407. cuda/cccl/headers/include/thrust/detail/complex/catrigf.h +2 -8
  408. cuda/cccl/headers/include/thrust/detail/complex/ccosh.h +2 -8
  409. cuda/cccl/headers/include/thrust/detail/complex/ccoshf.h +2 -8
  410. cuda/cccl/headers/include/thrust/detail/complex/cexp.h +2 -7
  411. cuda/cccl/headers/include/thrust/detail/complex/cexpf.h +2 -8
  412. cuda/cccl/headers/include/thrust/detail/complex/clog.h +2 -8
  413. cuda/cccl/headers/include/thrust/detail/complex/clogf.h +2 -8
  414. cuda/cccl/headers/include/thrust/detail/complex/cproj.h +2 -7
  415. cuda/cccl/headers/include/thrust/detail/complex/csinh.h +2 -8
  416. cuda/cccl/headers/include/thrust/detail/complex/csinhf.h +2 -8
  417. cuda/cccl/headers/include/thrust/detail/complex/csqrt.h +2 -8
  418. cuda/cccl/headers/include/thrust/detail/complex/csqrtf.h +2 -8
  419. cuda/cccl/headers/include/thrust/detail/complex/ctanh.h +2 -8
  420. cuda/cccl/headers/include/thrust/detail/complex/ctanhf.h +2 -8
  421. cuda/cccl/headers/include/thrust/detail/complex/math_private.h +2 -8
  422. cuda/cccl/headers/include/thrust/detail/config/device_system.h +2 -0
  423. cuda/cccl/headers/include/thrust/detail/config/host_system.h +2 -0
  424. cuda/cccl/headers/include/thrust/detail/config/namespace.h +0 -1
  425. cuda/cccl/headers/include/thrust/detail/contiguous_storage.h +0 -2
  426. cuda/cccl/headers/include/thrust/detail/contiguous_storage.inl +0 -2
  427. cuda/cccl/headers/include/thrust/detail/copy.h +0 -2
  428. cuda/cccl/headers/include/thrust/detail/copy.inl +14 -4
  429. cuda/cccl/headers/include/thrust/detail/copy_if.inl +14 -2
  430. cuda/cccl/headers/include/thrust/detail/count.inl +14 -2
  431. cuda/cccl/headers/include/thrust/detail/equal.inl +14 -2
  432. cuda/cccl/headers/include/thrust/detail/execute_with_allocator.h +4 -5
  433. cuda/cccl/headers/include/thrust/detail/extrema.inl +14 -2
  434. cuda/cccl/headers/include/thrust/detail/fill.inl +14 -2
  435. cuda/cccl/headers/include/thrust/detail/find.inl +14 -2
  436. cuda/cccl/headers/include/thrust/detail/for_each.inl +14 -2
  437. cuda/cccl/headers/include/thrust/detail/functional/actor.h +2 -5
  438. cuda/cccl/headers/include/thrust/detail/functional/operators.h +2 -5
  439. cuda/cccl/headers/include/thrust/detail/gather.inl +14 -2
  440. cuda/cccl/headers/include/thrust/detail/generate.inl +14 -2
  441. cuda/cccl/headers/include/thrust/detail/get_iterator_value.h +0 -2
  442. cuda/cccl/headers/include/thrust/detail/inner_product.inl +14 -2
  443. cuda/cccl/headers/include/thrust/detail/internal_functional.h +1 -0
  444. cuda/cccl/headers/include/thrust/detail/logical.inl +14 -2
  445. cuda/cccl/headers/include/thrust/detail/malloc_and_free.h +13 -1
  446. cuda/cccl/headers/include/thrust/detail/merge.inl +14 -2
  447. cuda/cccl/headers/include/thrust/detail/mismatch.inl +14 -2
  448. cuda/cccl/headers/include/thrust/detail/overlapped_copy.h +0 -4
  449. cuda/cccl/headers/include/thrust/detail/partition.inl +14 -2
  450. cuda/cccl/headers/include/thrust/detail/random_bijection.h +0 -2
  451. cuda/cccl/headers/include/thrust/detail/range/head_flags.h +0 -2
  452. cuda/cccl/headers/include/thrust/detail/range/tail_flags.h +0 -2
  453. cuda/cccl/headers/include/thrust/detail/raw_reference_cast.h +0 -6
  454. cuda/cccl/headers/include/thrust/detail/reduce.inl +21 -3
  455. cuda/cccl/headers/include/thrust/detail/reference.h +27 -3
  456. cuda/cccl/headers/include/thrust/detail/remove.inl +14 -2
  457. cuda/cccl/headers/include/thrust/detail/replace.inl +14 -2
  458. cuda/cccl/headers/include/thrust/detail/reverse.inl +14 -2
  459. cuda/cccl/headers/include/thrust/detail/scan.inl +21 -3
  460. cuda/cccl/headers/include/thrust/detail/scatter.inl +14 -2
  461. cuda/cccl/headers/include/thrust/detail/sequence.inl +13 -1
  462. cuda/cccl/headers/include/thrust/detail/set_operations.inl +13 -1
  463. cuda/cccl/headers/include/thrust/detail/sort.inl +13 -1
  464. cuda/cccl/headers/include/thrust/detail/static_assert.h +0 -2
  465. cuda/cccl/headers/include/thrust/detail/static_map.h +0 -3
  466. cuda/cccl/headers/include/thrust/detail/swap_ranges.inl +13 -1
  467. cuda/cccl/headers/include/thrust/detail/tabulate.inl +14 -2
  468. cuda/cccl/headers/include/thrust/detail/temporary_array.h +0 -4
  469. cuda/cccl/headers/include/thrust/detail/temporary_array.inl +0 -1
  470. cuda/cccl/headers/include/thrust/detail/temporary_buffer.h +14 -3
  471. cuda/cccl/headers/include/thrust/detail/transform_reduce.inl +13 -1
  472. cuda/cccl/headers/include/thrust/detail/transform_scan.inl +13 -1
  473. cuda/cccl/headers/include/thrust/detail/trivial_sequence.h +0 -2
  474. cuda/cccl/headers/include/thrust/detail/tuple_meta_transform.h +0 -2
  475. cuda/cccl/headers/include/thrust/detail/type_traits/is_call_possible.h +2 -7
  476. cuda/cccl/headers/include/thrust/detail/type_traits/is_commutative.h +0 -2
  477. cuda/cccl/headers/include/thrust/detail/type_traits/is_thrust_pointer.h +0 -4
  478. cuda/cccl/headers/include/thrust/detail/type_traits/pointer_traits.h +0 -4
  479. cuda/cccl/headers/include/thrust/detail/uninitialized_copy.inl +14 -2
  480. cuda/cccl/headers/include/thrust/detail/uninitialized_fill.inl +14 -2
  481. cuda/cccl/headers/include/thrust/detail/unique.inl +21 -3
  482. cuda/cccl/headers/include/thrust/detail/vector_base.h +0 -2
  483. cuda/cccl/headers/include/thrust/detail/vector_base.inl +0 -2
  484. cuda/cccl/headers/include/thrust/execution_policy.h +10 -9
  485. cuda/cccl/headers/include/thrust/functional.h +0 -2
  486. cuda/cccl/headers/include/thrust/iterator/detail/device_system_tag.h +9 -4
  487. cuda/cccl/headers/include/thrust/iterator/detail/host_system_tag.h +8 -4
  488. cuda/cccl/headers/include/thrust/iterator/detail/iterator_adaptor_base.h +0 -1
  489. cuda/cccl/headers/include/thrust/iterator/detail/iterator_category_with_system_and_traversal.h +0 -1
  490. cuda/cccl/headers/include/thrust/iterator/detail/iterator_facade_category.h +0 -1
  491. cuda/cccl/headers/include/thrust/iterator/detail/minimum_system.h +0 -1
  492. cuda/cccl/headers/include/thrust/iterator/detail/tagged_iterator.h +0 -1
  493. cuda/cccl/headers/include/thrust/iterator/detail/tuple_of_iterator_references.h +2 -6
  494. cuda/cccl/headers/include/thrust/iterator/transform_input_output_iterator.h +0 -1
  495. cuda/cccl/headers/include/thrust/iterator/transform_iterator.h +0 -2
  496. cuda/cccl/headers/include/thrust/mr/allocator.h +0 -2
  497. cuda/cccl/headers/include/thrust/mr/device_memory_resource.h +9 -4
  498. cuda/cccl/headers/include/thrust/mr/disjoint_pool.h +10 -10
  499. cuda/cccl/headers/include/thrust/mr/disjoint_sync_pool.h +0 -2
  500. cuda/cccl/headers/include/thrust/mr/disjoint_tls_pool.h +0 -2
  501. cuda/cccl/headers/include/thrust/mr/fancy_pointer_resource.h +0 -2
  502. cuda/cccl/headers/include/thrust/mr/host_memory_resource.h +8 -4
  503. cuda/cccl/headers/include/thrust/mr/memory_resource.h +0 -2
  504. cuda/cccl/headers/include/thrust/mr/new.h +0 -2
  505. cuda/cccl/headers/include/thrust/mr/polymorphic_adaptor.h +0 -2
  506. cuda/cccl/headers/include/thrust/mr/pool.h +10 -10
  507. cuda/cccl/headers/include/thrust/mr/pool_options.h +4 -6
  508. cuda/cccl/headers/include/thrust/mr/sync_pool.h +0 -2
  509. cuda/cccl/headers/include/thrust/mr/tls_pool.h +0 -2
  510. cuda/cccl/headers/include/thrust/mr/validator.h +0 -2
  511. cuda/cccl/headers/include/thrust/per_device_resource.h +13 -1
  512. cuda/cccl/headers/include/thrust/random/detail/discard_block_engine.inl +0 -2
  513. cuda/cccl/headers/include/thrust/random/detail/linear_congruential_engine.inl +0 -2
  514. cuda/cccl/headers/include/thrust/random/detail/linear_congruential_engine_discard.h +2 -9
  515. cuda/cccl/headers/include/thrust/random/detail/linear_feedback_shift_engine.inl +0 -2
  516. cuda/cccl/headers/include/thrust/random/detail/linear_feedback_shift_engine_wordmask.h +2 -9
  517. cuda/cccl/headers/include/thrust/random/detail/mod.h +2 -9
  518. cuda/cccl/headers/include/thrust/random/detail/normal_distribution.inl +0 -2
  519. cuda/cccl/headers/include/thrust/random/detail/normal_distribution_base.h +2 -7
  520. cuda/cccl/headers/include/thrust/random/detail/random_core_access.h +2 -9
  521. cuda/cccl/headers/include/thrust/random/detail/subtract_with_carry_engine.inl +0 -2
  522. cuda/cccl/headers/include/thrust/random/detail/uniform_int_distribution.inl +0 -2
  523. cuda/cccl/headers/include/thrust/random/detail/uniform_real_distribution.inl +0 -2
  524. cuda/cccl/headers/include/thrust/random/detail/xor_combine_engine.inl +0 -2
  525. cuda/cccl/headers/include/thrust/random/discard_block_engine.h +0 -2
  526. cuda/cccl/headers/include/thrust/random/linear_congruential_engine.h +0 -2
  527. cuda/cccl/headers/include/thrust/random/linear_feedback_shift_engine.h +0 -2
  528. cuda/cccl/headers/include/thrust/random/normal_distribution.h +0 -2
  529. cuda/cccl/headers/include/thrust/random/subtract_with_carry_engine.h +0 -2
  530. cuda/cccl/headers/include/thrust/random/uniform_int_distribution.h +0 -2
  531. cuda/cccl/headers/include/thrust/random/uniform_real_distribution.h +0 -2
  532. cuda/cccl/headers/include/thrust/random/xor_combine_engine.h +0 -2
  533. cuda/cccl/headers/include/thrust/random.h +0 -2
  534. cuda/cccl/headers/include/thrust/system/cpp/detail/execution_policy.h +15 -11
  535. cuda/cccl/headers/include/thrust/system/cpp/detail/memory.inl +2 -7
  536. cuda/cccl/headers/include/thrust/system/cpp/memory.h +0 -1
  537. cuda/cccl/headers/include/thrust/system/cpp/memory_resource.h +0 -2
  538. cuda/cccl/headers/include/thrust/system/cpp/pointer.h +0 -2
  539. cuda/cccl/headers/include/thrust/system/cpp/vector.h +0 -1
  540. cuda/cccl/headers/include/thrust/system/cuda/detail/adjacent_difference.h +0 -4
  541. cuda/cccl/headers/include/thrust/system/cuda/detail/copy.h +0 -1
  542. cuda/cccl/headers/include/thrust/system/cuda/detail/copy_if.h +0 -4
  543. cuda/cccl/headers/include/thrust/system/cuda/detail/core/agent_launcher.h +2 -9
  544. cuda/cccl/headers/include/thrust/system/cuda/detail/core/triple_chevron_launch.h +4 -32
  545. cuda/cccl/headers/include/thrust/system/cuda/detail/core/util.h +2 -9
  546. cuda/cccl/headers/include/thrust/system/cuda/detail/count.h +0 -2
  547. cuda/cccl/headers/include/thrust/system/cuda/detail/cross_system.h +0 -2
  548. cuda/cccl/headers/include/thrust/system/cuda/detail/dispatch.h +23 -2
  549. cuda/cccl/headers/include/thrust/system/cuda/detail/equal.h +0 -2
  550. cuda/cccl/headers/include/thrust/system/cuda/detail/error.inl +2 -11
  551. cuda/cccl/headers/include/thrust/system/cuda/detail/execution_policy.h +2 -0
  552. cuda/cccl/headers/include/thrust/system/cuda/detail/extrema.h +0 -4
  553. cuda/cccl/headers/include/thrust/system/cuda/detail/fill.h +0 -1
  554. cuda/cccl/headers/include/thrust/system/cuda/detail/find.h +0 -5
  555. cuda/cccl/headers/include/thrust/system/cuda/detail/for_each.h +0 -1
  556. cuda/cccl/headers/include/thrust/system/cuda/detail/gather.h +0 -2
  557. cuda/cccl/headers/include/thrust/system/cuda/detail/generate.h +0 -2
  558. cuda/cccl/headers/include/thrust/system/cuda/detail/iter_swap.h +0 -1
  559. cuda/cccl/headers/include/thrust/system/cuda/detail/make_unsigned_special.h +2 -8
  560. cuda/cccl/headers/include/thrust/system/cuda/detail/malloc_and_free.h +0 -2
  561. cuda/cccl/headers/include/thrust/system/cuda/detail/memory.inl +0 -2
  562. cuda/cccl/headers/include/thrust/system/cuda/detail/merge.h +2 -26
  563. cuda/cccl/headers/include/thrust/system/cuda/detail/mismatch.h +7 -142
  564. cuda/cccl/headers/include/thrust/system/cuda/detail/parallel_for.h +0 -2
  565. cuda/cccl/headers/include/thrust/system/cuda/detail/partition.h +0 -4
  566. cuda/cccl/headers/include/thrust/system/cuda/detail/per_device_resource.h +0 -2
  567. cuda/cccl/headers/include/thrust/system/cuda/detail/reduce.h +0 -5
  568. cuda/cccl/headers/include/thrust/system/cuda/detail/reduce_by_key.h +0 -4
  569. cuda/cccl/headers/include/thrust/system/cuda/detail/remove.h +0 -2
  570. cuda/cccl/headers/include/thrust/system/cuda/detail/replace.h +0 -1
  571. cuda/cccl/headers/include/thrust/system/cuda/detail/reverse.h +0 -4
  572. cuda/cccl/headers/include/thrust/system/cuda/detail/scan.h +0 -4
  573. cuda/cccl/headers/include/thrust/system/cuda/detail/scan_by_key.h +0 -3
  574. cuda/cccl/headers/include/thrust/system/cuda/detail/scatter.h +0 -2
  575. cuda/cccl/headers/include/thrust/system/cuda/detail/set_operations.h +3 -5
  576. cuda/cccl/headers/include/thrust/system/cuda/detail/sort.h +8 -10
  577. cuda/cccl/headers/include/thrust/system/cuda/detail/temporary_buffer.h +0 -2
  578. cuda/cccl/headers/include/thrust/system/cuda/detail/transform.h +0 -1
  579. cuda/cccl/headers/include/thrust/system/cuda/detail/transform_reduce.h +0 -4
  580. cuda/cccl/headers/include/thrust/system/cuda/detail/transform_scan.h +0 -2
  581. cuda/cccl/headers/include/thrust/system/cuda/detail/uninitialized_copy.h +1 -7
  582. cuda/cccl/headers/include/thrust/system/cuda/detail/uninitialized_fill.h +2 -7
  583. cuda/cccl/headers/include/thrust/system/cuda/detail/unique.h +0 -3
  584. cuda/cccl/headers/include/thrust/system/cuda/detail/unique_by_key.h +0 -4
  585. cuda/cccl/headers/include/thrust/system/cuda/error.h +2 -11
  586. cuda/cccl/headers/include/thrust/system/cuda/memory.h +2 -6
  587. cuda/cccl/headers/include/thrust/system/cuda/memory_resource.h +2 -9
  588. cuda/cccl/headers/include/thrust/system/cuda/pointer.h +2 -7
  589. cuda/cccl/headers/include/thrust/system/cuda/vector.h +2 -6
  590. cuda/cccl/headers/include/thrust/system/detail/bad_alloc.h +0 -2
  591. cuda/cccl/headers/include/thrust/system/detail/errno.h +0 -2
  592. cuda/cccl/headers/include/thrust/system/detail/error_category.inl +0 -4
  593. cuda/cccl/headers/include/thrust/system/detail/error_code.inl +0 -2
  594. cuda/cccl/headers/include/thrust/system/detail/error_condition.inl +0 -2
  595. cuda/cccl/headers/include/thrust/system/detail/generic/adjacent_difference.h +0 -2
  596. cuda/cccl/headers/include/thrust/system/detail/generic/adjacent_difference.inl +0 -2
  597. cuda/cccl/headers/include/thrust/system/detail/generic/binary_search.h +0 -2
  598. cuda/cccl/headers/include/thrust/system/detail/generic/binary_search.inl +0 -3
  599. cuda/cccl/headers/include/thrust/system/detail/generic/copy.h +0 -2
  600. cuda/cccl/headers/include/thrust/system/detail/generic/copy.inl +0 -2
  601. cuda/cccl/headers/include/thrust/system/detail/generic/copy_if.h +0 -2
  602. cuda/cccl/headers/include/thrust/system/detail/generic/copy_if.inl +0 -3
  603. cuda/cccl/headers/include/thrust/system/detail/generic/count.h +0 -2
  604. cuda/cccl/headers/include/thrust/system/detail/generic/count.inl +0 -2
  605. cuda/cccl/headers/include/thrust/system/detail/generic/equal.h +0 -2
  606. cuda/cccl/headers/include/thrust/system/detail/generic/equal.inl +0 -2
  607. cuda/cccl/headers/include/thrust/system/detail/generic/extrema.h +0 -2
  608. cuda/cccl/headers/include/thrust/system/detail/generic/extrema.inl +0 -3
  609. cuda/cccl/headers/include/thrust/system/detail/generic/fill.h +0 -2
  610. cuda/cccl/headers/include/thrust/system/detail/generic/find.h +0 -2
  611. cuda/cccl/headers/include/thrust/system/detail/generic/find.inl +0 -2
  612. cuda/cccl/headers/include/thrust/system/detail/generic/for_each.h +0 -2
  613. cuda/cccl/headers/include/thrust/system/detail/generic/gather.h +0 -2
  614. cuda/cccl/headers/include/thrust/system/detail/generic/gather.inl +0 -2
  615. cuda/cccl/headers/include/thrust/system/detail/generic/generate.h +0 -2
  616. cuda/cccl/headers/include/thrust/system/detail/generic/inner_product.h +0 -2
  617. cuda/cccl/headers/include/thrust/system/detail/generic/inner_product.inl +0 -2
  618. cuda/cccl/headers/include/thrust/system/detail/generic/logical.h +0 -2
  619. cuda/cccl/headers/include/thrust/system/detail/generic/memory.h +0 -2
  620. cuda/cccl/headers/include/thrust/system/detail/generic/memory.inl +0 -3
  621. cuda/cccl/headers/include/thrust/system/detail/generic/merge.h +0 -2
  622. cuda/cccl/headers/include/thrust/system/detail/generic/merge.inl +0 -2
  623. cuda/cccl/headers/include/thrust/system/detail/generic/mismatch.h +0 -2
  624. cuda/cccl/headers/include/thrust/system/detail/generic/mismatch.inl +0 -2
  625. cuda/cccl/headers/include/thrust/system/detail/generic/partition.h +0 -2
  626. cuda/cccl/headers/include/thrust/system/detail/generic/partition.inl +0 -2
  627. cuda/cccl/headers/include/thrust/system/detail/generic/per_device_resource.h +0 -2
  628. cuda/cccl/headers/include/thrust/system/detail/generic/reduce.h +0 -2
  629. cuda/cccl/headers/include/thrust/system/detail/generic/reduce.inl +0 -2
  630. cuda/cccl/headers/include/thrust/system/detail/generic/reduce_by_key.h +0 -2
  631. cuda/cccl/headers/include/thrust/system/detail/generic/reduce_by_key.inl +0 -3
  632. cuda/cccl/headers/include/thrust/system/detail/generic/remove.h +0 -2
  633. cuda/cccl/headers/include/thrust/system/detail/generic/remove.inl +0 -2
  634. cuda/cccl/headers/include/thrust/system/detail/generic/replace.h +0 -2
  635. cuda/cccl/headers/include/thrust/system/detail/generic/replace.inl +0 -3
  636. cuda/cccl/headers/include/thrust/system/detail/generic/reverse.h +0 -2
  637. cuda/cccl/headers/include/thrust/system/detail/generic/reverse.inl +0 -2
  638. cuda/cccl/headers/include/thrust/system/detail/generic/scalar/binary_search.h +0 -2
  639. cuda/cccl/headers/include/thrust/system/detail/generic/scalar/binary_search.inl +0 -2
  640. cuda/cccl/headers/include/thrust/system/detail/generic/scan.h +26 -12
  641. cuda/cccl/headers/include/thrust/system/detail/generic/scan_by_key.h +0 -2
  642. cuda/cccl/headers/include/thrust/system/detail/generic/scan_by_key.inl +0 -3
  643. cuda/cccl/headers/include/thrust/system/detail/generic/scatter.h +0 -2
  644. cuda/cccl/headers/include/thrust/system/detail/generic/scatter.inl +0 -2
  645. cuda/cccl/headers/include/thrust/system/detail/generic/select_system.h +0 -1
  646. cuda/cccl/headers/include/thrust/system/detail/generic/set_operations.h +0 -2
  647. cuda/cccl/headers/include/thrust/system/detail/generic/set_operations.inl +0 -2
  648. cuda/cccl/headers/include/thrust/system/detail/generic/shuffle.h +0 -2
  649. cuda/cccl/headers/include/thrust/system/detail/generic/shuffle.inl +0 -2
  650. cuda/cccl/headers/include/thrust/system/detail/generic/sort.h +0 -2
  651. cuda/cccl/headers/include/thrust/system/detail/generic/sort.inl +0 -2
  652. cuda/cccl/headers/include/thrust/system/detail/generic/swap_ranges.h +0 -2
  653. cuda/cccl/headers/include/thrust/system/detail/generic/swap_ranges.inl +0 -3
  654. cuda/cccl/headers/include/thrust/system/detail/generic/tabulate.h +0 -2
  655. cuda/cccl/headers/include/thrust/system/detail/generic/tabulate.inl +0 -2
  656. cuda/cccl/headers/include/thrust/system/detail/generic/tag.h +0 -2
  657. cuda/cccl/headers/include/thrust/system/detail/generic/temporary_buffer.h +0 -2
  658. cuda/cccl/headers/include/thrust/system/detail/generic/temporary_buffer.inl +0 -2
  659. cuda/cccl/headers/include/thrust/system/detail/generic/transform.h +0 -2
  660. cuda/cccl/headers/include/thrust/system/detail/generic/transform_reduce.h +0 -2
  661. cuda/cccl/headers/include/thrust/system/detail/generic/transform_reduce.inl +0 -2
  662. cuda/cccl/headers/include/thrust/system/detail/generic/transform_scan.h +0 -2
  663. cuda/cccl/headers/include/thrust/system/detail/generic/transform_scan.inl +0 -2
  664. cuda/cccl/headers/include/thrust/system/detail/generic/uninitialized_copy.h +0 -2
  665. cuda/cccl/headers/include/thrust/system/detail/generic/uninitialized_copy.inl +2 -4
  666. cuda/cccl/headers/include/thrust/system/detail/generic/uninitialized_fill.h +0 -2
  667. cuda/cccl/headers/include/thrust/system/detail/generic/uninitialized_fill.inl +0 -3
  668. cuda/cccl/headers/include/thrust/system/detail/generic/unique.h +0 -2
  669. cuda/cccl/headers/include/thrust/system/detail/generic/unique.inl +0 -2
  670. cuda/cccl/headers/include/thrust/system/detail/generic/unique_by_key.h +0 -2
  671. cuda/cccl/headers/include/thrust/system/detail/generic/unique_by_key.inl +0 -2
  672. cuda/cccl/headers/include/thrust/system/detail/internal/decompose.h +0 -2
  673. cuda/cccl/headers/include/thrust/system/detail/sequential/adjacent_difference.h +0 -2
  674. cuda/cccl/headers/include/thrust/system/detail/sequential/assign_value.h +0 -2
  675. cuda/cccl/headers/include/thrust/system/detail/sequential/binary_search.h +0 -2
  676. cuda/cccl/headers/include/thrust/system/detail/sequential/copy.h +76 -5
  677. cuda/cccl/headers/include/thrust/system/detail/sequential/copy_backward.h +0 -2
  678. cuda/cccl/headers/include/thrust/system/detail/sequential/copy_if.h +0 -2
  679. cuda/cccl/headers/include/thrust/system/detail/sequential/extrema.h +0 -2
  680. cuda/cccl/headers/include/thrust/system/detail/sequential/find.h +0 -2
  681. cuda/cccl/headers/include/thrust/system/detail/sequential/for_each.h +0 -2
  682. cuda/cccl/headers/include/thrust/system/detail/sequential/general_copy.h +0 -3
  683. cuda/cccl/headers/include/thrust/system/detail/sequential/get_value.h +0 -2
  684. cuda/cccl/headers/include/thrust/system/detail/sequential/insertion_sort.h +0 -2
  685. cuda/cccl/headers/include/thrust/system/detail/sequential/iter_swap.h +0 -2
  686. cuda/cccl/headers/include/thrust/system/detail/sequential/malloc_and_free.h +0 -2
  687. cuda/cccl/headers/include/thrust/system/detail/sequential/merge.h +78 -6
  688. cuda/cccl/headers/include/thrust/system/detail/sequential/partition.h +0 -4
  689. cuda/cccl/headers/include/thrust/system/detail/sequential/reduce.h +0 -2
  690. cuda/cccl/headers/include/thrust/system/detail/sequential/reduce_by_key.h +0 -2
  691. cuda/cccl/headers/include/thrust/system/detail/sequential/remove.h +0 -2
  692. cuda/cccl/headers/include/thrust/system/detail/sequential/scan.h +0 -2
  693. cuda/cccl/headers/include/thrust/system/detail/sequential/scan_by_key.h +0 -2
  694. cuda/cccl/headers/include/thrust/system/detail/sequential/set_operations.h +0 -2
  695. cuda/cccl/headers/include/thrust/system/detail/sequential/sort.h +67 -6
  696. cuda/cccl/headers/include/thrust/system/detail/sequential/stable_merge_sort.h +310 -11
  697. cuda/cccl/headers/include/thrust/system/detail/sequential/stable_primitive_sort.h +78 -5
  698. cuda/cccl/headers/include/thrust/system/detail/sequential/stable_radix_sort.h +543 -7
  699. cuda/cccl/headers/include/thrust/system/detail/sequential/trivial_copy.h +0 -2
  700. cuda/cccl/headers/include/thrust/system/detail/sequential/unique.h +0 -2
  701. cuda/cccl/headers/include/thrust/system/detail/sequential/unique_by_key.h +0 -2
  702. cuda/cccl/headers/include/thrust/system/detail/system_error.inl +0 -2
  703. cuda/cccl/headers/include/thrust/system/error_code.h +0 -4
  704. cuda/cccl/headers/include/thrust/system/omp/detail/adjacent_difference.h +5 -25
  705. cuda/cccl/headers/include/thrust/system/omp/detail/assign_value.h +2 -15
  706. cuda/cccl/headers/include/thrust/system/omp/detail/binary_search.h +5 -25
  707. cuda/cccl/headers/include/thrust/system/omp/detail/copy.h +40 -29
  708. cuda/cccl/headers/include/thrust/system/omp/detail/copy_if.h +11 -28
  709. cuda/cccl/headers/include/thrust/system/omp/detail/count.h +2 -15
  710. cuda/cccl/headers/include/thrust/system/omp/detail/default_decomposition.h +26 -28
  711. cuda/cccl/headers/include/thrust/system/omp/detail/equal.h +2 -15
  712. cuda/cccl/headers/include/thrust/system/omp/detail/execution_policy.h +18 -13
  713. cuda/cccl/headers/include/thrust/system/omp/detail/extrema.h +5 -25
  714. cuda/cccl/headers/include/thrust/system/omp/detail/fill.h +2 -15
  715. cuda/cccl/headers/include/thrust/system/omp/detail/find.h +5 -25
  716. cuda/cccl/headers/include/thrust/system/omp/detail/for_each.h +47 -30
  717. cuda/cccl/headers/include/thrust/system/omp/detail/gather.h +2 -15
  718. cuda/cccl/headers/include/thrust/system/omp/detail/generate.h +2 -15
  719. cuda/cccl/headers/include/thrust/system/omp/detail/get_value.h +2 -15
  720. cuda/cccl/headers/include/thrust/system/omp/detail/inner_product.h +2 -15
  721. cuda/cccl/headers/include/thrust/system/omp/detail/iter_swap.h +2 -15
  722. cuda/cccl/headers/include/thrust/system/omp/detail/logical.h +2 -15
  723. cuda/cccl/headers/include/thrust/system/omp/detail/malloc_and_free.h +2 -15
  724. cuda/cccl/headers/include/thrust/system/omp/detail/merge.h +2 -15
  725. cuda/cccl/headers/include/thrust/system/omp/detail/mismatch.h +2 -15
  726. cuda/cccl/headers/include/thrust/system/omp/detail/partition.h +26 -31
  727. cuda/cccl/headers/include/thrust/system/omp/detail/per_device_resource.h +2 -15
  728. cuda/cccl/headers/include/thrust/system/omp/detail/pragma_omp.h +2 -26
  729. cuda/cccl/headers/include/thrust/system/omp/detail/reduce.h +35 -27
  730. cuda/cccl/headers/include/thrust/system/omp/detail/reduce_by_key.h +13 -28
  731. cuda/cccl/headers/include/thrust/system/omp/detail/reduce_intervals.h +56 -28
  732. cuda/cccl/headers/include/thrust/system/omp/detail/remove.h +26 -31
  733. cuda/cccl/headers/include/thrust/system/omp/detail/replace.h +2 -15
  734. cuda/cccl/headers/include/thrust/system/omp/detail/reverse.h +2 -15
  735. cuda/cccl/headers/include/thrust/system/omp/detail/scan.h +176 -17
  736. cuda/cccl/headers/include/thrust/system/omp/detail/scan_by_key.h +8 -15
  737. cuda/cccl/headers/include/thrust/system/omp/detail/scatter.h +2 -15
  738. cuda/cccl/headers/include/thrust/system/omp/detail/sequence.h +2 -15
  739. cuda/cccl/headers/include/thrust/system/omp/detail/set_operations.h +2 -15
  740. cuda/cccl/headers/include/thrust/system/omp/detail/sort.h +213 -28
  741. cuda/cccl/headers/include/thrust/system/omp/detail/swap_ranges.h +2 -15
  742. cuda/cccl/headers/include/thrust/system/omp/detail/tabulate.h +2 -15
  743. cuda/cccl/headers/include/thrust/system/omp/detail/temporary_buffer.h +2 -15
  744. cuda/cccl/headers/include/thrust/system/omp/detail/transform.h +2 -15
  745. cuda/cccl/headers/include/thrust/system/omp/detail/transform_reduce.h +2 -15
  746. cuda/cccl/headers/include/thrust/system/omp/detail/transform_scan.h +2 -15
  747. cuda/cccl/headers/include/thrust/system/omp/detail/uninitialized_copy.h +2 -15
  748. cuda/cccl/headers/include/thrust/system/omp/detail/uninitialized_fill.h +2 -15
  749. cuda/cccl/headers/include/thrust/system/omp/detail/unique.h +21 -30
  750. cuda/cccl/headers/include/thrust/system/omp/detail/unique_by_key.h +17 -29
  751. cuda/cccl/headers/include/thrust/system/omp/memory.h +51 -9
  752. cuda/cccl/headers/include/thrust/system/omp/memory_resource.h +3 -7
  753. cuda/cccl/headers/include/thrust/system/omp/pointer.h +3 -7
  754. cuda/cccl/headers/include/thrust/system/omp/vector.h +3 -6
  755. cuda/cccl/headers/include/thrust/system/system_error.h +0 -2
  756. cuda/cccl/headers/include/thrust/system/tbb/detail/adjacent_difference.h +4 -25
  757. cuda/cccl/headers/include/thrust/system/tbb/detail/assign_value.h +2 -15
  758. cuda/cccl/headers/include/thrust/system/tbb/detail/binary_search.h +2 -15
  759. cuda/cccl/headers/include/thrust/system/tbb/detail/copy.h +38 -29
  760. cuda/cccl/headers/include/thrust/system/tbb/detail/copy_if.h +91 -24
  761. cuda/cccl/headers/include/thrust/system/tbb/detail/count.h +2 -15
  762. cuda/cccl/headers/include/thrust/system/tbb/detail/equal.h +2 -15
  763. cuda/cccl/headers/include/thrust/system/tbb/detail/execution_policy.h +17 -13
  764. cuda/cccl/headers/include/thrust/system/tbb/detail/extrema.h +4 -25
  765. cuda/cccl/headers/include/thrust/system/tbb/detail/fill.h +2 -15
  766. cuda/cccl/headers/include/thrust/system/tbb/detail/find.h +4 -25
  767. cuda/cccl/headers/include/thrust/system/tbb/detail/for_each.h +47 -28
  768. cuda/cccl/headers/include/thrust/system/tbb/detail/gather.h +2 -15
  769. cuda/cccl/headers/include/thrust/system/tbb/detail/generate.h +2 -15
  770. cuda/cccl/headers/include/thrust/system/tbb/detail/get_value.h +2 -15
  771. cuda/cccl/headers/include/thrust/system/tbb/detail/inner_product.h +2 -15
  772. cuda/cccl/headers/include/thrust/system/tbb/detail/iter_swap.h +2 -15
  773. cuda/cccl/headers/include/thrust/system/tbb/detail/logical.h +2 -15
  774. cuda/cccl/headers/include/thrust/system/tbb/detail/malloc_and_free.h +2 -15
  775. cuda/cccl/headers/include/thrust/system/tbb/detail/merge.h +254 -29
  776. cuda/cccl/headers/include/thrust/system/tbb/detail/mismatch.h +2 -15
  777. cuda/cccl/headers/include/thrust/system/tbb/detail/partition.h +25 -31
  778. cuda/cccl/headers/include/thrust/system/tbb/detail/per_device_resource.h +2 -15
  779. cuda/cccl/headers/include/thrust/system/tbb/detail/reduce.h +95 -29
  780. cuda/cccl/headers/include/thrust/system/tbb/detail/reduce_by_key.h +345 -28
  781. cuda/cccl/headers/include/thrust/system/tbb/detail/reduce_intervals.h +4 -26
  782. cuda/cccl/headers/include/thrust/system/tbb/detail/remove.h +32 -42
  783. cuda/cccl/headers/include/thrust/system/tbb/detail/replace.h +2 -15
  784. cuda/cccl/headers/include/thrust/system/tbb/detail/reverse.h +2 -15
  785. cuda/cccl/headers/include/thrust/system/tbb/detail/scan.h +265 -30
  786. cuda/cccl/headers/include/thrust/system/tbb/detail/scan_by_key.h +7 -17
  787. cuda/cccl/headers/include/thrust/system/tbb/detail/scatter.h +2 -15
  788. cuda/cccl/headers/include/thrust/system/tbb/detail/sequence.h +2 -15
  789. cuda/cccl/headers/include/thrust/system/tbb/detail/set_operations.h +2 -15
  790. cuda/cccl/headers/include/thrust/system/tbb/detail/sort.h +244 -32
  791. cuda/cccl/headers/include/thrust/system/tbb/detail/swap_ranges.h +2 -15
  792. cuda/cccl/headers/include/thrust/system/tbb/detail/tabulate.h +2 -15
  793. cuda/cccl/headers/include/thrust/system/tbb/detail/temporary_buffer.h +2 -15
  794. cuda/cccl/headers/include/thrust/system/tbb/detail/transform.h +2 -15
  795. cuda/cccl/headers/include/thrust/system/tbb/detail/transform_reduce.h +2 -15
  796. cuda/cccl/headers/include/thrust/system/tbb/detail/transform_scan.h +2 -15
  797. cuda/cccl/headers/include/thrust/system/tbb/detail/uninitialized_copy.h +2 -15
  798. cuda/cccl/headers/include/thrust/system/tbb/detail/uninitialized_fill.h +2 -15
  799. cuda/cccl/headers/include/thrust/system/tbb/detail/unique.h +23 -33
  800. cuda/cccl/headers/include/thrust/system/tbb/detail/unique_by_key.h +16 -29
  801. cuda/cccl/headers/include/thrust/system/tbb/memory.h +52 -24
  802. cuda/cccl/headers/include/thrust/system/tbb/memory_resource.h +4 -22
  803. cuda/cccl/headers/include/thrust/system/tbb/pointer.h +4 -22
  804. cuda/cccl/headers/include/thrust/system/tbb/vector.h +4 -21
  805. cuda/cccl/headers/include/thrust/transform.h +14 -3
  806. cuda/cccl/headers/include/thrust/type_traits/integer_sequence.h +0 -4
  807. cuda/cccl/headers/include/thrust/type_traits/is_contiguous_iterator.h +0 -1
  808. cuda/cccl/headers/include/thrust/type_traits/is_operator_less_or_greater_function_object.h +0 -4
  809. cuda/cccl/headers/include/thrust/type_traits/is_operator_plus_function_object.h +0 -4
  810. cuda/cccl/headers/include/thrust/type_traits/is_trivially_relocatable.h +0 -4
  811. cuda/cccl/headers/include/thrust/universal_allocator.h +8 -0
  812. cuda/cccl/headers/include/thrust/universal_vector.h +9 -0
  813. cuda/cccl/headers/include/thrust/zip_function.h +2 -28
  814. cuda/compute/__init__.py +4 -0
  815. cuda/compute/_bindings.pyi +26 -3
  816. cuda/compute/_bindings_impl.pyx +143 -1
  817. cuda/compute/algorithms/__init__.py +9 -5
  818. cuda/compute/algorithms/_sort/__init__.py +23 -0
  819. cuda/compute/algorithms/{_merge_sort.py → _sort/_merge_sort.py} +10 -10
  820. cuda/compute/algorithms/{_radix_sort.py → _sort/_radix_sort.py} +9 -58
  821. cuda/compute/algorithms/_sort/_segmented_sort.py +288 -0
  822. cuda/compute/algorithms/_sort/_sort_common.py +52 -0
  823. cuda/compute/cu12/_bindings_impl.cpython-313-aarch64-linux-gnu.so +0 -0
  824. cuda/compute/cu12/cccl/libcccl.c.parallel.so +0 -0
  825. cuda/compute/cu13/_bindings_impl.cpython-313-aarch64-linux-gnu.so +0 -0
  826. cuda/compute/cu13/cccl/libcccl.c.parallel.so +0 -0
  827. cuda_cccl-0.3.4.dist-info/METADATA +78 -0
  828. {cuda_cccl-0.3.2.dist-info → cuda_cccl-0.3.4.dist-info}/RECORD +830 -867
  829. cuda/cccl/headers/include/cuda/__memory_resource/resource_ref.h +0 -652
  830. cuda/cccl/headers/include/cuda/std/detail/libcxx/include/tuple +0 -1365
  831. cuda/cccl/headers/include/cuda/std/detail/libcxx/include/variant +0 -2144
  832. cuda/cccl/headers/include/thrust/detail/integer_math.h +0 -113
  833. cuda/cccl/headers/include/thrust/system/detail/adl/adjacent_difference.h +0 -51
  834. cuda/cccl/headers/include/thrust/system/detail/adl/assign_value.h +0 -51
  835. cuda/cccl/headers/include/thrust/system/detail/adl/binary_search.h +0 -51
  836. cuda/cccl/headers/include/thrust/system/detail/adl/copy.h +0 -51
  837. cuda/cccl/headers/include/thrust/system/detail/adl/copy_if.h +0 -52
  838. cuda/cccl/headers/include/thrust/system/detail/adl/count.h +0 -51
  839. cuda/cccl/headers/include/thrust/system/detail/adl/equal.h +0 -51
  840. cuda/cccl/headers/include/thrust/system/detail/adl/extrema.h +0 -51
  841. cuda/cccl/headers/include/thrust/system/detail/adl/fill.h +0 -51
  842. cuda/cccl/headers/include/thrust/system/detail/adl/find.h +0 -51
  843. cuda/cccl/headers/include/thrust/system/detail/adl/for_each.h +0 -51
  844. cuda/cccl/headers/include/thrust/system/detail/adl/gather.h +0 -51
  845. cuda/cccl/headers/include/thrust/system/detail/adl/generate.h +0 -51
  846. cuda/cccl/headers/include/thrust/system/detail/adl/get_value.h +0 -51
  847. cuda/cccl/headers/include/thrust/system/detail/adl/inner_product.h +0 -51
  848. cuda/cccl/headers/include/thrust/system/detail/adl/iter_swap.h +0 -51
  849. cuda/cccl/headers/include/thrust/system/detail/adl/logical.h +0 -51
  850. cuda/cccl/headers/include/thrust/system/detail/adl/malloc_and_free.h +0 -51
  851. cuda/cccl/headers/include/thrust/system/detail/adl/merge.h +0 -51
  852. cuda/cccl/headers/include/thrust/system/detail/adl/mismatch.h +0 -51
  853. cuda/cccl/headers/include/thrust/system/detail/adl/partition.h +0 -51
  854. cuda/cccl/headers/include/thrust/system/detail/adl/per_device_resource.h +0 -51
  855. cuda/cccl/headers/include/thrust/system/detail/adl/reduce.h +0 -51
  856. cuda/cccl/headers/include/thrust/system/detail/adl/reduce_by_key.h +0 -51
  857. cuda/cccl/headers/include/thrust/system/detail/adl/remove.h +0 -51
  858. cuda/cccl/headers/include/thrust/system/detail/adl/replace.h +0 -51
  859. cuda/cccl/headers/include/thrust/system/detail/adl/reverse.h +0 -51
  860. cuda/cccl/headers/include/thrust/system/detail/adl/scan.h +0 -51
  861. cuda/cccl/headers/include/thrust/system/detail/adl/scan_by_key.h +0 -51
  862. cuda/cccl/headers/include/thrust/system/detail/adl/scatter.h +0 -51
  863. cuda/cccl/headers/include/thrust/system/detail/adl/sequence.h +0 -51
  864. cuda/cccl/headers/include/thrust/system/detail/adl/set_operations.h +0 -51
  865. cuda/cccl/headers/include/thrust/system/detail/adl/sort.h +0 -51
  866. cuda/cccl/headers/include/thrust/system/detail/adl/swap_ranges.h +0 -51
  867. cuda/cccl/headers/include/thrust/system/detail/adl/tabulate.h +0 -51
  868. cuda/cccl/headers/include/thrust/system/detail/adl/temporary_buffer.h +0 -51
  869. cuda/cccl/headers/include/thrust/system/detail/adl/transform.h +0 -51
  870. cuda/cccl/headers/include/thrust/system/detail/adl/transform_reduce.h +0 -51
  871. cuda/cccl/headers/include/thrust/system/detail/adl/transform_scan.h +0 -51
  872. cuda/cccl/headers/include/thrust/system/detail/adl/uninitialized_copy.h +0 -51
  873. cuda/cccl/headers/include/thrust/system/detail/adl/uninitialized_fill.h +0 -51
  874. cuda/cccl/headers/include/thrust/system/detail/adl/unique.h +0 -51
  875. cuda/cccl/headers/include/thrust/system/detail/adl/unique_by_key.h +0 -51
  876. cuda/cccl/headers/include/thrust/system/detail/generic/scan.inl +0 -85
  877. cuda/cccl/headers/include/thrust/system/detail/sequential/copy.inl +0 -119
  878. cuda/cccl/headers/include/thrust/system/detail/sequential/merge.inl +0 -145
  879. cuda/cccl/headers/include/thrust/system/detail/sequential/sort.inl +0 -116
  880. cuda/cccl/headers/include/thrust/system/detail/sequential/stable_merge_sort.inl +0 -356
  881. cuda/cccl/headers/include/thrust/system/detail/sequential/stable_primitive_sort.inl +0 -124
  882. cuda/cccl/headers/include/thrust/system/detail/sequential/stable_radix_sort.inl +0 -586
  883. cuda/cccl/headers/include/thrust/system/omp/detail/copy.inl +0 -74
  884. cuda/cccl/headers/include/thrust/system/omp/detail/copy_if.inl +0 -59
  885. cuda/cccl/headers/include/thrust/system/omp/detail/default_decomposition.inl +0 -65
  886. cuda/cccl/headers/include/thrust/system/omp/detail/for_each.inl +0 -87
  887. cuda/cccl/headers/include/thrust/system/omp/detail/memory.inl +0 -93
  888. cuda/cccl/headers/include/thrust/system/omp/detail/partition.inl +0 -102
  889. cuda/cccl/headers/include/thrust/system/omp/detail/reduce.inl +0 -78
  890. cuda/cccl/headers/include/thrust/system/omp/detail/reduce_by_key.inl +0 -65
  891. cuda/cccl/headers/include/thrust/system/omp/detail/reduce_intervals.inl +0 -103
  892. cuda/cccl/headers/include/thrust/system/omp/detail/remove.inl +0 -87
  893. cuda/cccl/headers/include/thrust/system/omp/detail/sort.inl +0 -265
  894. cuda/cccl/headers/include/thrust/system/omp/detail/unique.inl +0 -71
  895. cuda/cccl/headers/include/thrust/system/omp/detail/unique_by_key.inl +0 -75
  896. cuda/cccl/headers/include/thrust/system/tbb/detail/copy.inl +0 -73
  897. cuda/cccl/headers/include/thrust/system/tbb/detail/copy_if.inl +0 -136
  898. cuda/cccl/headers/include/thrust/system/tbb/detail/for_each.inl +0 -91
  899. cuda/cccl/headers/include/thrust/system/tbb/detail/memory.inl +0 -94
  900. cuda/cccl/headers/include/thrust/system/tbb/detail/merge.inl +0 -327
  901. cuda/cccl/headers/include/thrust/system/tbb/detail/partition.inl +0 -98
  902. cuda/cccl/headers/include/thrust/system/tbb/detail/reduce.inl +0 -137
  903. cuda/cccl/headers/include/thrust/system/tbb/detail/reduce_by_key.inl +0 -400
  904. cuda/cccl/headers/include/thrust/system/tbb/detail/remove.inl +0 -87
  905. cuda/cccl/headers/include/thrust/system/tbb/detail/scan.inl +0 -312
  906. cuda/cccl/headers/include/thrust/system/tbb/detail/sort.inl +0 -295
  907. cuda/cccl/headers/include/thrust/system/tbb/detail/unique.inl +0 -71
  908. cuda/cccl/headers/include/thrust/system/tbb/detail/unique_by_key.inl +0 -75
  909. cuda_cccl-0.3.2.dist-info/METADATA +0 -42
  910. {cuda_cccl-0.3.2.dist-info → cuda_cccl-0.3.4.dist-info}/WHEEL +0 -0
  911. {cuda_cccl-0.3.2.dist-info → cuda_cccl-0.3.4.dist-info}/licenses/LICENSE +0 -0
@@ -1,30 +1,6 @@
1
- /******************************************************************************
2
- * Copyright (c) 2011, Duane Merrill. All rights reserved.
3
- * Copyright (c) 2011-2022, NVIDIA CORPORATION. All rights reserved.
4
- *
5
- * Redistribution and use in source and binary forms, with or without
6
- * modification, are permitted provided that the following conditions are met:
7
- * * Redistributions of source code must retain the above copyright
8
- * notice, this list of conditions and the following disclaimer.
9
- * * Redistributions in binary form must reproduce the above copyright
10
- * notice, this list of conditions and the following disclaimer in the
11
- * documentation and/or other materials provided with the distribution.
12
- * * Neither the name of the NVIDIA CORPORATION nor the
13
- * names of its contributors may be used to endorse or promote products
14
- * derived from this software without specific prior written permission.
15
- *
16
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
17
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
18
- * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
19
- * DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
20
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
21
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
23
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
25
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26
- *
27
- ******************************************************************************/
1
+ // SPDX-FileCopyrightText: Copyright (c) 2011, Duane Merrill. All rights reserved.
2
+ // SPDX-FileCopyrightText: Copyright (c) 2011-2022, NVIDIA CORPORATION. All rights reserved.
3
+ // SPDX-License-Identifier: BSD-3
28
4
 
29
5
  //! @file
30
6
  //! cub::DevicePartition provides device-wide, parallel operations for partitioning sequences of data items residing
@@ -1,30 +1,6 @@
1
- /******************************************************************************
2
- * Copyright (c) 2011, Duane Merrill. All rights reserved.
3
- * Copyright (c) 2011-2025, NVIDIA CORPORATION. All rights reserved.
4
- *
5
- * Redistribution and use in source and binary forms, with or without
6
- * modification, are permitted provided that the following conditions are met:
7
- * * Redistributions of source code must retain the above copyright
8
- * notice, this list of conditions and the following disclaimer.
9
- * * Redistributions in binary form must reproduce the above copyright
10
- * notice, this list of conditions and the following disclaimer in the
11
- * documentation and/or other materials provided with the distribution.
12
- * * Neither the name of the NVIDIA CORPORATION nor the
13
- * names of its contributors may be used to endorse or promote products
14
- * derived from this software without specific prior written permission.
15
- *
16
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
17
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19
- * ARE DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
20
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
21
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
23
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
25
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26
- *
27
- ******************************************************************************/
1
+ // SPDX-FileCopyrightText: Copyright (c) 2011, Duane Merrill. All rights reserved.
2
+ // SPDX-FileCopyrightText: Copyright (c) 2011-2025, NVIDIA CORPORATION. All rights reserved.
3
+ // SPDX-License-Identifier: BSD-3
28
4
 
29
5
  //! @file
30
6
  //! cub::DeviceRadixSort provides device-wide, parallel operations for computing a radix sort across a sequence of data
@@ -1,30 +1,6 @@
1
- /******************************************************************************
2
- * Copyright (c) 2011, Duane Merrill. All rights reserved.
3
- * Copyright (c) 2011-2024, NVIDIA CORPORATION. All rights reserved.
4
- *
5
- * Redistribution and use in source and binary forms, with or without
6
- * modification, are permitted provided that the following conditions are met:
7
- * * Redistributions of source code must retain the above copyright
8
- * notice, this list of conditions and the following disclaimer.
9
- * * Redistributions in binary form must reproduce the above copyright
10
- * notice, this list of conditions and the following disclaimer in the
11
- * documentation and/or other materials provided with the distribution.
12
- * * Neither the name of the NVIDIA CORPORATION nor the
13
- * names of its contributors may be used to endorse or promote products
14
- * derived from this software without specific prior written permission.
15
- *
16
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
17
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19
- * ARE DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
20
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
21
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
23
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
25
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26
- *
27
- ******************************************************************************/
1
+ // SPDX-FileCopyrightText: Copyright (c) 2011, Duane Merrill. All rights reserved.
2
+ // SPDX-FileCopyrightText: Copyright (c) 2011-2024, NVIDIA CORPORATION. All rights reserved.
3
+ // SPDX-License-Identifier: BSD-3
28
4
 
29
5
  //! @file
30
6
  //! cub::DeviceReduce provides device-wide, parallel operations for computing a reduction across a sequence of data
@@ -75,14 +51,12 @@ CUB_NAMESPACE_BEGIN
75
51
 
76
52
  namespace detail
77
53
  {
78
-
79
54
  template <typename DeterminismT>
80
55
  inline constexpr bool is_non_deterministic_v =
81
56
  ::cuda::std::is_same_v<DeterminismT, ::cuda::execution::determinism::not_guaranteed_t>;
82
57
 
83
58
  namespace reduce
84
59
  {
85
-
86
60
  struct get_tuning_query_t
87
61
  {};
88
62
 
@@ -495,7 +469,12 @@ public:
495
469
  constexpr auto float_double_plus =
496
470
  gpu_gpu_determinism && detail::is_one_of_v<accum_t, float, double> && detail::is_cuda_std_plus_v<ReductionOpT>;
497
471
 
498
- constexpr auto supported = integral_fallback || float_double_plus || !gpu_gpu_determinism;
472
+ constexpr auto float_double_min_max_fallback =
473
+ gpu_gpu_determinism
474
+ && detail::is_one_of_v<accum_t, float, double> && detail::is_cuda_minimum_maximum_v<ReductionOpT>;
475
+
476
+ constexpr auto supported =
477
+ integral_fallback || float_double_plus || float_double_min_max_fallback || !gpu_gpu_determinism;
499
478
 
500
479
  // gpu_to_gpu determinism is only supported for integral types with cuda operators, or
501
480
  // float and double types with ::cuda::std::plus operator
@@ -522,7 +501,7 @@ public:
522
501
  // If the conditions for gpu-to-gpu determinism or non-deterministic
523
502
  // reduction are not met, we fall back to run-to-run determinism.
524
503
  using determinism_t = ::cuda::std::conditional_t<
525
- (gpu_gpu_determinism && integral_fallback)
504
+ (gpu_gpu_determinism && (integral_fallback || float_double_min_max_fallback))
526
505
  || (no_determinism && !(is_contiguous_fallback && is_plus_fallback && is_4b_or_greater)),
527
506
  ::cuda::execution::determinism::run_to_run_t,
528
507
  default_determinism_t>;
@@ -1,30 +1,6 @@
1
- /******************************************************************************
2
- * Copyright (c) 2011, Duane Merrill. All rights reserved.
3
- * Copyright (c) 2011-2022, NVIDIA CORPORATION. All rights reserved.
4
- *
5
- * Redistribution and use in source and binary forms, with or without
6
- * modification, are permitted provided that the following conditions are met:
7
- * * Redistributions of source code must retain the above copyright
8
- * notice, this list of conditions and the following disclaimer.
9
- * * Redistributions in binary form must reproduce the above copyright
10
- * notice, this list of conditions and the following disclaimer in the
11
- * documentation and/or other materials provided with the distribution.
12
- * * Neither the name of the NVIDIA CORPORATION nor the
13
- * names of its contributors may be used to endorse or promote products
14
- * derived from this software without specific prior written permission.
15
- *
16
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
17
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19
- * ARE DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
20
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
21
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
23
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
25
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26
- *
27
- ******************************************************************************/
1
+ // SPDX-FileCopyrightText: Copyright (c) 2011, Duane Merrill. All rights reserved.
2
+ // SPDX-FileCopyrightText: Copyright (c) 2011-2022, NVIDIA CORPORATION. All rights reserved.
3
+ // SPDX-License-Identifier: BSD-3
28
4
 
29
5
  //! @file
30
6
  //! cub::DeviceRunLengthEncode provides device-wide, parallel operations for computing a run-length encoding across a
@@ -1,30 +1,6 @@
1
- /******************************************************************************
2
- * Copyright (c) 2011, Duane Merrill. All rights reserved.
3
- * Copyright (c) 2011-2022, NVIDIA CORPORATION. All rights reserved.
4
- *
5
- * Redistribution and use in source and binary forms, with or without
6
- * modification, are permitted provided that the following conditions are met:
7
- * * Redistributions of source code must retain the above copyright
8
- * notice, this list of conditions and the following disclaimer.
9
- * * Redistributions in binary form must reproduce the above copyright
10
- * notice, this list of conditions and the following disclaimer in the
11
- * documentation and/or other materials provided with the distribution.
12
- * * Neither the name of the NVIDIA CORPORATION nor the
13
- * names of its contributors may be used to endorse or promote products
14
- * derived from this software without specific prior written permission.
15
- *
16
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
17
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19
- * ARE DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
20
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
21
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
23
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
25
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26
- *
27
- ******************************************************************************/
1
+ // SPDX-FileCopyrightText: Copyright (c) 2011, Duane Merrill. All rights reserved.
2
+ // SPDX-FileCopyrightText: Copyright (c) 2011-2022, NVIDIA CORPORATION. All rights reserved.
3
+ // SPDX-License-Identifier: BSD-3
28
4
 
29
5
  //! @file
30
6
  //! cub::DeviceScan provides device-wide, parallel operations for computing a prefix scan across a sequence of data
@@ -78,7 +54,6 @@ struct default_tuning : tuning<default_tuning>
78
54
  template <typename InputValueT, typename OutputValueT, typename AccumT, typename OffsetT, typename ScanOpT>
79
55
  using fn = policy_hub<InputValueT, OutputValueT, AccumT, OffsetT, ScanOpT>;
80
56
  };
81
-
82
57
  } // namespace detail::scan
83
58
 
84
59
  //! @rst
@@ -128,6 +103,7 @@ struct default_tuning : tuning<default_tuning>
128
103
  //! @endrst
129
104
  struct DeviceScan
130
105
  {
106
+ //! @cond
131
107
  template <typename TuningEnvT,
132
108
  typename InputIteratorT,
133
109
  typename OutputIteratorT,
@@ -169,7 +145,9 @@ struct DeviceScan
169
145
  return dispatch_t::Dispatch(
170
146
  d_temp_storage, temp_storage_bytes, d_in, d_out, scan_op, init, static_cast<offset_t>(num_items), stream);
171
147
  }
148
+ //! @endcond
172
149
 
150
+ //! @cond
173
151
  template <typename InputIteratorT,
174
152
  typename OutputIteratorT,
175
153
  typename ScanOpT,
@@ -241,6 +219,7 @@ struct DeviceScan
241
219
 
242
220
  return deallocate_error;
243
221
  }
222
+ //! @endcond
244
223
 
245
224
  //! @name Exclusive scans
246
225
  //! @{
@@ -353,9 +332,6 @@ struct DeviceScan
353
332
  stream);
354
333
  }
355
334
 
356
- //! @name Exclusive scans
357
- //! @{
358
-
359
335
  //! @rst
360
336
  //! Computes a device-wide exclusive prefix sum.
361
337
  //! The value of ``0`` is applied as the initial value, and is assigned to ``*d_out``.
@@ -370,9 +346,6 @@ struct DeviceScan
370
346
  //! shall not overlap in any other way.
371
347
  //! - @devicestorage
372
348
  //!
373
- //! Snippet
374
- //! +++++++++++++++++++++++++++++++++++++++++++++
375
- //!
376
349
  //! Preconditions
377
350
  //! +++++++++++++
378
351
  //!
@@ -380,6 +353,10 @@ struct DeviceScan
380
353
  //! The range ``[d_in, d_in + num_items)`` and ``[d_out, d_out + num_items)``
381
354
  //! shall not overlap in any other way.
382
355
  //! - ``d_in`` and ``d_out`` must not be null pointers
356
+ //!
357
+ //! Snippet
358
+ //! +++++++++++++++++++++++++++++++++++++++++++++
359
+ //!
383
360
  //! The code snippet below illustrates a user-defined exclusive-scan of a
384
361
  //! device vector of ``float`` data elements.
385
362
  //!
@@ -1086,6 +1063,7 @@ struct DeviceScan
1086
1063
  }
1087
1064
 
1088
1065
  //! @} end member group
1066
+
1089
1067
  //! @name Inclusive scans
1090
1068
  //! @{
1091
1069
 
@@ -1577,6 +1555,10 @@ struct DeviceScan
1577
1555
  {
1578
1556
  return InclusiveScan(d_temp_storage, temp_storage_bytes, d_data, d_data, scan_op, num_items, stream);
1579
1557
  }
1558
+ //! @} end member group
1559
+
1560
+ //! @name Scans by key
1561
+ //! @{
1580
1562
 
1581
1563
  //! @rst
1582
1564
  //! Computes a device-wide exclusive prefix sum-by-key with key equality
@@ -1,30 +1,6 @@
1
- /******************************************************************************
2
- * Copyright (c) 2011, Duane Merrill. All rights reserved.
3
- * Copyright (c) 2011-2022, NVIDIA CORPORATION. All rights reserved.
4
- *
5
- * Redistribution and use in source and binary forms, with or without
6
- * modification, are permitted provided that the following conditions are met:
7
- * * Redistributions of source code must retain the above copyright
8
- * notice, this list of conditions and the following disclaimer.
9
- * * Redistributions in binary form must reproduce the above copyright
10
- * notice, this list of conditions and the following disclaimer in the
11
- * documentation and/or other materials provided with the distribution.
12
- * * Neither the name of the NVIDIA CORPORATION nor the
13
- * names of its contributors may be used to endorse or promote products
14
- * derived from this software without specific prior written permission.
15
- *
16
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
17
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19
- * ARE DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
20
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
21
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
23
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
25
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26
- *
27
- ******************************************************************************/
1
+ // SPDX-FileCopyrightText: Copyright (c) 2011, Duane Merrill. All rights reserved.
2
+ // SPDX-FileCopyrightText: Copyright (c) 2011-2022, NVIDIA CORPORATION. All rights reserved.
3
+ // SPDX-License-Identifier: BSD-3
28
4
 
29
5
  //! @file
30
6
  //! cub::DeviceSegmentedRadixSort provides device-wide, parallel operations for computing a batched radix sort across
@@ -1,30 +1,6 @@
1
- /******************************************************************************
2
- * Copyright (c) 2011, Duane Merrill. All rights reserved.
3
- * Copyright (c) 2011-2022, NVIDIA CORPORATION. All rights reserved.
4
- *
5
- * Redistribution and use in source and binary forms, with or without
6
- * modification, are permitted provided that the following conditions are met:
7
- * * Redistributions of source code must retain the above copyright
8
- * notice, this list of conditions and the following disclaimer.
9
- * * Redistributions in binary form must reproduce the above copyright
10
- * notice, this list of conditions and the following disclaimer in the
11
- * documentation and/or other materials provided with the distribution.
12
- * * Neither the name of the NVIDIA CORPORATION nor the
13
- * names of its contributors may be used to endorse or promote products
14
- * derived from this software without specific prior written permission.
15
- *
16
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
17
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19
- * ARE DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
20
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
21
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
23
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
25
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26
- *
27
- ******************************************************************************/
1
+ // SPDX-FileCopyrightText: Copyright (c) 2011, Duane Merrill. All rights reserved.
2
+ // SPDX-FileCopyrightText: Copyright (c) 2011-2022, NVIDIA CORPORATION. All rights reserved.
3
+ // SPDX-License-Identifier: BSD-3
28
4
 
29
5
  //! @file
30
6
  //! cub::DeviceSegmentedReduce provides device-wide, parallel operations for computing a batched reduction across
@@ -1,29 +1,5 @@
1
- /******************************************************************************
2
- * Copyright (c) 2011-2022, NVIDIA CORPORATION. All rights reserved.
3
- *
4
- * Redistribution and use in source and binary forms, with or without
5
- * modification, are permitted provided that the following conditions are met:
6
- * * Redistributions of source code must retain the above copyright
7
- * notice, this list of conditions and the following disclaimer.
8
- * * Redistributions in binary form must reproduce the above copyright
9
- * notice, this list of conditions and the following disclaimer in the
10
- * documentation and/or other materials provided with the distribution.
11
- * * Neither the name of the NVIDIA CORPORATION nor the
12
- * names of its contributors may be used to endorse or promote products
13
- * derived from this software without specific prior written permission.
14
- *
15
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
16
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
17
- * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
18
- * DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
19
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
20
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
21
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
22
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
23
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
24
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
25
- *
26
- ******************************************************************************/
1
+ // SPDX-FileCopyrightText: Copyright (c) 2011-2022, NVIDIA CORPORATION. All rights reserved.
2
+ // SPDX-License-Identifier: BSD-3
27
3
 
28
4
  //! @file
29
5
  //! cub::DeviceSegmentedSort provides device-wide, parallel operations for computing a batched sort across multiple,
@@ -1,30 +1,6 @@
1
- /******************************************************************************
2
- * Copyright (c) 2011, Duane Merrill. All rights reserved.
3
- * Copyright (c) 2011-2022, NVIDIA CORPORATION. All rights reserved.
4
- *
5
- * Redistribution and use in source and binary forms, with or without
6
- * modification, are permitted provided that the following conditions are met:
7
- * * Redistributions of source code must retain the above copyright
8
- * notice, this list of conditions and the following disclaimer.
9
- * * Redistributions in binary form must reproduce the above copyright
10
- * notice, this list of conditions and the following disclaimer in the
11
- * documentation and/or other materials provided with the distribution.
12
- * * Neither the name of the NVIDIA CORPORATION nor the
13
- * names of its contributors may be used to endorse or promote products
14
- * derived from this software without specific prior written permission.
15
- *
16
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
17
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19
- * ARE DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
20
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
21
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
23
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
25
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26
- *
27
- ******************************************************************************/
1
+ // SPDX-FileCopyrightText: Copyright (c) 2011, Duane Merrill. All rights reserved.
2
+ // SPDX-FileCopyrightText: Copyright (c) 2011-2022, NVIDIA CORPORATION. All rights reserved.
3
+ // SPDX-License-Identifier: BSD-3
28
4
 
29
5
  //! @file
30
6
  //! cub::DeviceSelect provides device-wide, parallel operations for compacting selected items from sequences of data
@@ -1,29 +1,5 @@
1
- /******************************************************************************
2
- * Copyright (c) 2011-2021, NVIDIA CORPORATION. All rights reserved.
3
- *
4
- * Redistribution and use in source and binary forms, with or without
5
- * modification, are permitted provided that the following conditions are met:
6
- * * Redistributions of source code must retain the above copyright
7
- * notice, this list of conditions and the following disclaimer.
8
- * * Redistributions in binary form must reproduce the above copyright
9
- * notice, this list of conditions and the following disclaimer in the
10
- * documentation and/or other materials provided with the distribution.
11
- * * Neither the name of the NVIDIA CORPORATION nor the
12
- * names of its contributors may be used to endorse or promote products
13
- * derived from this software without specific prior written permission.
14
- *
15
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
16
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
17
- * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
18
- * DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
19
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
20
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
21
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
22
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
23
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
24
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
25
- *
26
- ******************************************************************************/
1
+ // SPDX-FileCopyrightText: Copyright (c) 2011-2021, NVIDIA CORPORATION. All rights reserved.
2
+ // SPDX-License-Identifier: BSD-3
27
3
 
28
4
  #pragma once
29
5
 
@@ -55,7 +31,6 @@ CUB_NAMESPACE_BEGIN
55
31
 
56
32
  namespace detail::adjacent_difference
57
33
  {
58
-
59
34
  template <typename AgentDifferenceInitT, typename InputIteratorT, typename InputT, typename OffsetT>
60
35
  CUB_DETAIL_KERNEL_ATTRIBUTES void
61
36
  DeviceAdjacentDifferenceInitKernel(InputIteratorT first, InputT* result, OffsetT num_tiles, int items_per_tile)
@@ -105,7 +80,6 @@ CUB_DETAIL_KERNEL_ATTRIBUTES void DeviceAdjacentDifferenceDifferenceKernel(
105
80
 
106
81
  agent.Process(tile_idx, tile_base);
107
82
  }
108
-
109
83
  } // namespace detail::adjacent_difference
110
84
 
111
85
  enum class ReadOption
@@ -1,29 +1,5 @@
1
- /******************************************************************************
2
- * Copyright (c) 2011-2022, NVIDIA CORPORATION. All rights reserved.
3
- *
4
- * Redistribution and use in source and binary forms, with or without
5
- * modification, are permitted provided that the following conditions are met:
6
- * * Redistributions of source code must retain the above copyright
7
- * notice, this list of conditions and the following disclaimer.
8
- * * Redistributions in binary form must reproduce the above copyright
9
- * notice, this list of conditions and the following disclaimer in the
10
- * documentation and/or other materials provided with the distribution.
11
- * * Neither the name of the NVIDIA CORPORATION nor the
12
- * names of its contributors may be used to endorse or promote products
13
- * derived from this software without specific prior written permission.
14
- *
15
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
16
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
17
- * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
18
- * DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
19
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
20
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
21
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
22
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
23
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
24
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
25
- *
26
- ******************************************************************************/
1
+ // SPDX-FileCopyrightText: Copyright (c) 2011-2022, NVIDIA CORPORATION. All rights reserved.
2
+ // SPDX-License-Identifier: BSD-3
27
3
 
28
4
  /**
29
5
  * \file
@@ -713,7 +689,6 @@ struct DispatchBatchMemcpy
713
689
  return error;
714
690
  }
715
691
  };
716
-
717
692
  } // namespace detail
718
693
 
719
694
  CUB_NAMESPACE_END
@@ -27,7 +27,6 @@ CUB_NAMESPACE_BEGIN
27
27
 
28
28
  namespace detail::copy_mdspan
29
29
  {
30
-
31
30
  template <typename MdspanIn, typename MdspanOut>
32
31
  struct copy_mdspan_t
33
32
  {
@@ -73,7 +72,6 @@ copy(::cuda::std::mdspan<T_In, E_In, L_In, A_In> mdspan_in,
73
72
  // Compatible layouts could use more efficient iteration patterns
74
73
  return cub::DeviceFor::ForEachInExtents(mdspan_in.extents(), copy_mdspan_t{mdspan_in, mdspan_out}, stream);
75
74
  }
76
-
77
75
  } // namespace detail::copy_mdspan
78
76
 
79
77
  CUB_NAMESPACE_END
@@ -1,29 +1,5 @@
1
- /******************************************************************************
2
- * Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved.
3
- *
4
- * Redistribution and use in source and binary forms, with or without
5
- * modification, are permitted provided that the following conditions are met:
6
- * * Redistributions of source code must retain the above copyright
7
- * notice, this list of conditions and the following disclaimer.
8
- * * Redistributions in binary form must reproduce the above copyright
9
- * notice, this list of conditions and the following disclaimer in the
10
- * documentation and/or other materials provided with the distribution.
11
- * * Neither the name of the NVIDIA CORPORATION nor the
12
- * names of its contributors may be used to endorse or promote products
13
- * derived from this software without specific prior written permission.
14
- *
15
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
16
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
17
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
18
- * ARE DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
19
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
20
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
21
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
22
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
23
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
24
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
25
- *
26
- ******************************************************************************/
1
+ // SPDX-FileCopyrightText: Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved.
2
+ // SPDX-License-Identifier: BSD-3
27
3
 
28
4
  #pragma once
29
5
 
@@ -38,7 +14,7 @@
38
14
  #endif // no system header
39
15
 
40
16
  #include <cub/agent/agent_for.cuh>
41
- #include <cub/device/dispatch/kernels/for_each.cuh>
17
+ #include <cub/device/dispatch/kernels/kernel_for_each.cuh>
42
18
  #include <cub/device/dispatch/tuning/tuning_for.cuh>
43
19
  #include <cub/thread/thread_load.cuh>
44
20
  #include <cub/util_device.cuh>
@@ -54,7 +30,6 @@ CUB_NAMESPACE_BEGIN
54
30
 
55
31
  namespace detail::for_each
56
32
  {
57
-
58
33
  // The dispatch layer is in the detail namespace until we figure out tuning API
59
34
  template <class OffsetT, class OpT, class PolicyHubT = policy_hub_t>
60
35
  struct dispatch_t
@@ -192,7 +167,6 @@ struct dispatch_t
192
167
  return error;
193
168
  }
194
169
  };
195
-
196
170
  } // namespace detail::for_each
197
171
 
198
172
  CUB_NAMESPACE_END