cuda-cccl 0.4.3__cp312-cp312-manylinux_2_26_x86_64.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.
Files changed (2024) hide show
  1. cuda/cccl/__init__.py +27 -0
  2. cuda/cccl/_cuda_version_utils.py +24 -0
  3. cuda/cccl/cooperative/__init__.py +9 -0
  4. cuda/cccl/cooperative/experimental/__init__.py +24 -0
  5. cuda/cccl/headers/__init__.py +7 -0
  6. cuda/cccl/headers/include/__init__.py +1 -0
  7. cuda/cccl/headers/include/cub/agent/agent_adjacent_difference.cuh +233 -0
  8. cuda/cccl/headers/include/cub/agent/agent_batch_memcpy.cuh +1158 -0
  9. cuda/cccl/headers/include/cub/agent/agent_for.cuh +55 -0
  10. cuda/cccl/headers/include/cub/agent/agent_histogram.cuh +699 -0
  11. cuda/cccl/headers/include/cub/agent/agent_merge.cuh +365 -0
  12. cuda/cccl/headers/include/cub/agent/agent_merge_sort.cuh +721 -0
  13. cuda/cccl/headers/include/cub/agent/agent_radix_sort_downsweep.cuh +756 -0
  14. cuda/cccl/headers/include/cub/agent/agent_radix_sort_histogram.cuh +277 -0
  15. cuda/cccl/headers/include/cub/agent/agent_radix_sort_onesweep.cuh +715 -0
  16. cuda/cccl/headers/include/cub/agent/agent_radix_sort_upsweep.cuh +546 -0
  17. cuda/cccl/headers/include/cub/agent/agent_reduce.cuh +592 -0
  18. cuda/cccl/headers/include/cub/agent/agent_reduce_by_key.cuh +780 -0
  19. cuda/cccl/headers/include/cub/agent/agent_rle.cuh +1092 -0
  20. cuda/cccl/headers/include/cub/agent/agent_scan.cuh +564 -0
  21. cuda/cccl/headers/include/cub/agent/agent_scan_by_key.cuh +448 -0
  22. cuda/cccl/headers/include/cub/agent/agent_segmented_radix_sort.cuh +263 -0
  23. cuda/cccl/headers/include/cub/agent/agent_segmented_scan.cuh +292 -0
  24. cuda/cccl/headers/include/cub/agent/agent_select_if.cuh +1090 -0
  25. cuda/cccl/headers/include/cub/agent/agent_sub_warp_merge_sort.cuh +346 -0
  26. cuda/cccl/headers/include/cub/agent/agent_three_way_partition.cuh +584 -0
  27. cuda/cccl/headers/include/cub/agent/agent_topk.cuh +762 -0
  28. cuda/cccl/headers/include/cub/agent/agent_unique_by_key.cuh +599 -0
  29. cuda/cccl/headers/include/cub/agent/single_pass_scan_operators.cuh +1384 -0
  30. cuda/cccl/headers/include/cub/block/block_adjacent_difference.cuh +939 -0
  31. cuda/cccl/headers/include/cub/block/block_discontinuity.cuh +1200 -0
  32. cuda/cccl/headers/include/cub/block/block_exchange.cuh +1279 -0
  33. cuda/cccl/headers/include/cub/block/block_histogram.cuh +396 -0
  34. cuda/cccl/headers/include/cub/block/block_load.cuh +1269 -0
  35. cuda/cccl/headers/include/cub/block/block_load_to_shared.cuh +437 -0
  36. cuda/cccl/headers/include/cub/block/block_merge_sort.cuh +771 -0
  37. cuda/cccl/headers/include/cub/block/block_radix_rank.cuh +1215 -0
  38. cuda/cccl/headers/include/cub/block/block_radix_sort.cuh +2129 -0
  39. cuda/cccl/headers/include/cub/block/block_raking_layout.cuh +124 -0
  40. cuda/cccl/headers/include/cub/block/block_reduce.cuh +661 -0
  41. cuda/cccl/headers/include/cub/block/block_run_length_decode.cuh +406 -0
  42. cuda/cccl/headers/include/cub/block/block_scan.cuh +2168 -0
  43. cuda/cccl/headers/include/cub/block/block_shuffle.cuh +319 -0
  44. cuda/cccl/headers/include/cub/block/block_store.cuh +1238 -0
  45. cuda/cccl/headers/include/cub/block/radix_rank_sort_operations.cuh +597 -0
  46. cuda/cccl/headers/include/cub/block/specializations/block_histogram_atomic.cuh +62 -0
  47. cuda/cccl/headers/include/cub/block/specializations/block_histogram_sort.cuh +209 -0
  48. cuda/cccl/headers/include/cub/block/specializations/block_reduce_raking.cuh +230 -0
  49. cuda/cccl/headers/include/cub/block/specializations/block_reduce_raking_commutative_only.cuh +207 -0
  50. cuda/cccl/headers/include/cub/block/specializations/block_reduce_warp_reductions.cuh +257 -0
  51. cuda/cccl/headers/include/cub/block/specializations/block_scan_raking.cuh +766 -0
  52. cuda/cccl/headers/include/cub/block/specializations/block_scan_warp_scans.cuh +514 -0
  53. cuda/cccl/headers/include/cub/config.cuh +29 -0
  54. cuda/cccl/headers/include/cub/cub.cuh +96 -0
  55. cuda/cccl/headers/include/cub/detail/array_utils.cuh +54 -0
  56. cuda/cccl/headers/include/cub/detail/choose_offset.cuh +135 -0
  57. cuda/cccl/headers/include/cub/detail/detect_cuda_runtime.cuh +50 -0
  58. cuda/cccl/headers/include/cub/detail/device_double_buffer.cuh +94 -0
  59. cuda/cccl/headers/include/cub/detail/device_memory_resource.cuh +60 -0
  60. cuda/cccl/headers/include/cub/detail/env_dispatch.cuh +87 -0
  61. cuda/cccl/headers/include/cub/detail/fast_modulo_division.cuh +227 -0
  62. cuda/cccl/headers/include/cub/detail/integer_utils.cuh +87 -0
  63. cuda/cccl/headers/include/cub/detail/launcher/cuda_driver.cuh +149 -0
  64. cuda/cccl/headers/include/cub/detail/launcher/cuda_runtime.cuh +103 -0
  65. cuda/cccl/headers/include/cub/detail/mdspan_utils.cuh +112 -0
  66. cuda/cccl/headers/include/cub/detail/ptx-json/array.cuh +41 -0
  67. cuda/cccl/headers/include/cub/detail/ptx-json/json.cuh +39 -0
  68. cuda/cccl/headers/include/cub/detail/ptx-json/object.cuh +71 -0
  69. cuda/cccl/headers/include/cub/detail/ptx-json/string.cuh +79 -0
  70. cuda/cccl/headers/include/cub/detail/ptx-json/value.cuh +95 -0
  71. cuda/cccl/headers/include/cub/detail/ptx-json-parser.cuh +39 -0
  72. cuda/cccl/headers/include/cub/detail/rfa.cuh +706 -0
  73. cuda/cccl/headers/include/cub/detail/strong_load.cuh +163 -0
  74. cuda/cccl/headers/include/cub/detail/strong_store.cuh +194 -0
  75. cuda/cccl/headers/include/cub/detail/temporary_storage.cuh +377 -0
  76. cuda/cccl/headers/include/cub/detail/type_traits.cuh +185 -0
  77. cuda/cccl/headers/include/cub/detail/uninitialized_copy.cuh +48 -0
  78. cuda/cccl/headers/include/cub/detail/unsafe_bitcast.cuh +33 -0
  79. cuda/cccl/headers/include/cub/device/device_adjacent_difference.cuh +572 -0
  80. cuda/cccl/headers/include/cub/device/device_copy.cuh +276 -0
  81. cuda/cccl/headers/include/cub/device/device_for.cuh +1061 -0
  82. cuda/cccl/headers/include/cub/device/device_histogram.cuh +1485 -0
  83. cuda/cccl/headers/include/cub/device/device_memcpy.cuh +171 -0
  84. cuda/cccl/headers/include/cub/device/device_merge.cuh +203 -0
  85. cuda/cccl/headers/include/cub/device/device_merge_sort.cuh +955 -0
  86. cuda/cccl/headers/include/cub/device/device_partition.cuh +644 -0
  87. cuda/cccl/headers/include/cub/device/device_radix_sort.cuh +3413 -0
  88. cuda/cccl/headers/include/cub/device/device_reduce.cuh +2303 -0
  89. cuda/cccl/headers/include/cub/device/device_run_length_encode.cuh +346 -0
  90. cuda/cccl/headers/include/cub/device/device_scan.cuh +2152 -0
  91. cuda/cccl/headers/include/cub/device/device_segmented_radix_sort.cuh +1472 -0
  92. cuda/cccl/headers/include/cub/device/device_segmented_reduce.cuh +1635 -0
  93. cuda/cccl/headers/include/cub/device/device_segmented_scan.cuh +1398 -0
  94. cuda/cccl/headers/include/cub/device/device_segmented_sort.cuh +2787 -0
  95. cuda/cccl/headers/include/cub/device/device_select.cuh +1204 -0
  96. cuda/cccl/headers/include/cub/device/device_topk.cuh +521 -0
  97. cuda/cccl/headers/include/cub/device/device_transform.cuh +666 -0
  98. cuda/cccl/headers/include/cub/device/dispatch/dispatch_adjacent_difference.cuh +289 -0
  99. cuda/cccl/headers/include/cub/device/dispatch/dispatch_batch_memcpy.cuh +694 -0
  100. cuda/cccl/headers/include/cub/device/dispatch/dispatch_common.cuh +50 -0
  101. cuda/cccl/headers/include/cub/device/dispatch/dispatch_copy_mdspan.cuh +77 -0
  102. cuda/cccl/headers/include/cub/device/dispatch/dispatch_fixed_size_segmented_reduce.cuh +349 -0
  103. cuda/cccl/headers/include/cub/device/dispatch/dispatch_for.cuh +160 -0
  104. cuda/cccl/headers/include/cub/device/dispatch/dispatch_histogram.cuh +1849 -0
  105. cuda/cccl/headers/include/cub/device/dispatch/dispatch_merge.cuh +317 -0
  106. cuda/cccl/headers/include/cub/device/dispatch/dispatch_merge_sort.cuh +429 -0
  107. cuda/cccl/headers/include/cub/device/dispatch/dispatch_radix_sort.cuh +1066 -0
  108. cuda/cccl/headers/include/cub/device/dispatch/dispatch_reduce.cuh +830 -0
  109. cuda/cccl/headers/include/cub/device/dispatch/dispatch_reduce_by_key.cuh +629 -0
  110. cuda/cccl/headers/include/cub/device/dispatch/dispatch_reduce_deterministic.cuh +479 -0
  111. cuda/cccl/headers/include/cub/device/dispatch/dispatch_reduce_nondeterministic.cuh +256 -0
  112. cuda/cccl/headers/include/cub/device/dispatch/dispatch_rle.cuh +603 -0
  113. cuda/cccl/headers/include/cub/device/dispatch/dispatch_scan.cuh +447 -0
  114. cuda/cccl/headers/include/cub/device/dispatch/dispatch_scan_by_key.cuh +545 -0
  115. cuda/cccl/headers/include/cub/device/dispatch/dispatch_segmented_radix_sort.cuh +638 -0
  116. cuda/cccl/headers/include/cub/device/dispatch/dispatch_segmented_reduce.cuh +410 -0
  117. cuda/cccl/headers/include/cub/device/dispatch/dispatch_segmented_scan.cuh +278 -0
  118. cuda/cccl/headers/include/cub/device/dispatch/dispatch_segmented_sort.cuh +899 -0
  119. cuda/cccl/headers/include/cub/device/dispatch/dispatch_select_if.cuh +831 -0
  120. cuda/cccl/headers/include/cub/device/dispatch/dispatch_streaming_reduce.cuh +321 -0
  121. cuda/cccl/headers/include/cub/device/dispatch/dispatch_streaming_reduce_by_key.cuh +454 -0
  122. cuda/cccl/headers/include/cub/device/dispatch/dispatch_three_way_partition.cuh +364 -0
  123. cuda/cccl/headers/include/cub/device/dispatch/dispatch_topk.cuh +626 -0
  124. cuda/cccl/headers/include/cub/device/dispatch/dispatch_transform.cuh +527 -0
  125. cuda/cccl/headers/include/cub/device/dispatch/dispatch_unique_by_key.cuh +472 -0
  126. cuda/cccl/headers/include/cub/device/dispatch/kernels/kernel_for_each.cuh +259 -0
  127. cuda/cccl/headers/include/cub/device/dispatch/kernels/kernel_histogram.cuh +669 -0
  128. cuda/cccl/headers/include/cub/device/dispatch/kernels/kernel_merge_sort.cuh +332 -0
  129. cuda/cccl/headers/include/cub/device/dispatch/kernels/kernel_radix_sort.cuh +553 -0
  130. cuda/cccl/headers/include/cub/device/dispatch/kernels/kernel_reduce.cuh +584 -0
  131. cuda/cccl/headers/include/cub/device/dispatch/kernels/kernel_scan.cuh +178 -0
  132. cuda/cccl/headers/include/cub/device/dispatch/kernels/kernel_segmented_radix_sort.cuh +262 -0
  133. cuda/cccl/headers/include/cub/device/dispatch/kernels/kernel_segmented_reduce.cuh +295 -0
  134. cuda/cccl/headers/include/cub/device/dispatch/kernels/kernel_segmented_scan.cuh +77 -0
  135. cuda/cccl/headers/include/cub/device/dispatch/kernels/kernel_segmented_sort.cuh +521 -0
  136. cuda/cccl/headers/include/cub/device/dispatch/kernels/kernel_three_way_partition.cuh +200 -0
  137. cuda/cccl/headers/include/cub/device/dispatch/kernels/kernel_transform.cuh +1049 -0
  138. cuda/cccl/headers/include/cub/device/dispatch/kernels/kernel_unique_by_key.cuh +175 -0
  139. cuda/cccl/headers/include/cub/device/dispatch/tuning/common.cuh +97 -0
  140. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_adjacent_difference.cuh +43 -0
  141. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_batch_memcpy.cuh +94 -0
  142. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_for.cuh +34 -0
  143. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_histogram.cuh +268 -0
  144. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_merge.cuh +108 -0
  145. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_merge_sort.cuh +100 -0
  146. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_radix_sort.cuh +1045 -0
  147. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_reduce.cuh +681 -0
  148. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_reduce_by_key.cuh +918 -0
  149. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_run_length_encode.cuh +647 -0
  150. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_scan.cuh +571 -0
  151. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_scan_by_key.cuh +986 -0
  152. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_segmented_scan.cuh +108 -0
  153. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_segmented_sort.cuh +373 -0
  154. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_select_if.cuh +1563 -0
  155. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_three_way_partition.cuh +415 -0
  156. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_topk.cuh +84 -0
  157. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_transform.cuh +476 -0
  158. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_unique_by_key.cuh +858 -0
  159. cuda/cccl/headers/include/cub/grid/grid_even_share.cuh +203 -0
  160. cuda/cccl/headers/include/cub/grid/grid_mapping.cuh +82 -0
  161. cuda/cccl/headers/include/cub/grid/grid_queue.cuh +175 -0
  162. cuda/cccl/headers/include/cub/iterator/arg_index_input_iterator.cuh +230 -0
  163. cuda/cccl/headers/include/cub/iterator/cache_modified_input_iterator.cuh +235 -0
  164. cuda/cccl/headers/include/cub/iterator/cache_modified_output_iterator.cuh +226 -0
  165. cuda/cccl/headers/include/cub/iterator/tex_obj_input_iterator.cuh +293 -0
  166. cuda/cccl/headers/include/cub/thread/thread_load.cuh +353 -0
  167. cuda/cccl/headers/include/cub/thread/thread_operators.cuh +664 -0
  168. cuda/cccl/headers/include/cub/thread/thread_reduce.cuh +525 -0
  169. cuda/cccl/headers/include/cub/thread/thread_scan.cuh +472 -0
  170. cuda/cccl/headers/include/cub/thread/thread_search.cuh +214 -0
  171. cuda/cccl/headers/include/cub/thread/thread_simd.cuh +456 -0
  172. cuda/cccl/headers/include/cub/thread/thread_sort.cuh +78 -0
  173. cuda/cccl/headers/include/cub/thread/thread_store.cuh +341 -0
  174. cuda/cccl/headers/include/cub/util_allocator.cuh +897 -0
  175. cuda/cccl/headers/include/cub/util_arch.cuh +176 -0
  176. cuda/cccl/headers/include/cub/util_cpp_dialect.cuh +71 -0
  177. cuda/cccl/headers/include/cub/util_debug.cuh +183 -0
  178. cuda/cccl/headers/include/cub/util_device.cuh +838 -0
  179. cuda/cccl/headers/include/cub/util_macro.cuh +73 -0
  180. cuda/cccl/headers/include/cub/util_math.cuh +92 -0
  181. cuda/cccl/headers/include/cub/util_namespace.cuh +152 -0
  182. cuda/cccl/headers/include/cub/util_policy_wrapper_t.cuh +31 -0
  183. cuda/cccl/headers/include/cub/util_ptx.cuh +483 -0
  184. cuda/cccl/headers/include/cub/util_temporary_storage.cuh +93 -0
  185. cuda/cccl/headers/include/cub/util_type.cuh +1084 -0
  186. cuda/cccl/headers/include/cub/util_vsmem.cuh +227 -0
  187. cuda/cccl/headers/include/cub/version.cuh +65 -0
  188. cuda/cccl/headers/include/cub/warp/specializations/warp_exchange_shfl.cuh +304 -0
  189. cuda/cccl/headers/include/cub/warp/specializations/warp_exchange_smem.cuh +152 -0
  190. cuda/cccl/headers/include/cub/warp/specializations/warp_reduce_shfl.cuh +567 -0
  191. cuda/cccl/headers/include/cub/warp/specializations/warp_reduce_smem.cuh +378 -0
  192. cuda/cccl/headers/include/cub/warp/specializations/warp_scan_shfl.cuh +922 -0
  193. cuda/cccl/headers/include/cub/warp/specializations/warp_scan_smem.cuh +691 -0
  194. cuda/cccl/headers/include/cub/warp/warp_exchange.cuh +381 -0
  195. cuda/cccl/headers/include/cub/warp/warp_load.cuh +591 -0
  196. cuda/cccl/headers/include/cub/warp/warp_merge_sort.cuh +145 -0
  197. cuda/cccl/headers/include/cub/warp/warp_reduce.cuh +810 -0
  198. cuda/cccl/headers/include/cub/warp/warp_scan.cuh +1863 -0
  199. cuda/cccl/headers/include/cub/warp/warp_store.cuh +498 -0
  200. cuda/cccl/headers/include/cub/warp/warp_utils.cuh +59 -0
  201. cuda/cccl/headers/include/cuda/__algorithm/common.h +68 -0
  202. cuda/cccl/headers/include/cuda/__algorithm/copy.h +199 -0
  203. cuda/cccl/headers/include/cuda/__algorithm/fill.h +110 -0
  204. cuda/cccl/headers/include/cuda/__annotated_ptr/access_property.h +165 -0
  205. cuda/cccl/headers/include/cuda/__annotated_ptr/access_property_encoding.h +171 -0
  206. cuda/cccl/headers/include/cuda/__annotated_ptr/annotated_ptr.h +216 -0
  207. cuda/cccl/headers/include/cuda/__annotated_ptr/annotated_ptr_base.h +100 -0
  208. cuda/cccl/headers/include/cuda/__annotated_ptr/apply_access_property.h +83 -0
  209. cuda/cccl/headers/include/cuda/__annotated_ptr/associate_access_property.h +128 -0
  210. cuda/cccl/headers/include/cuda/__annotated_ptr/createpolicy.h +210 -0
  211. cuda/cccl/headers/include/cuda/__atomic/atomic.h +145 -0
  212. cuda/cccl/headers/include/cuda/__barrier/async_contract_fulfillment.h +39 -0
  213. cuda/cccl/headers/include/cuda/__barrier/barrier.h +65 -0
  214. cuda/cccl/headers/include/cuda/__barrier/barrier_arrive_tx.h +101 -0
  215. cuda/cccl/headers/include/cuda/__barrier/barrier_block_scope.h +528 -0
  216. cuda/cccl/headers/include/cuda/__barrier/barrier_expect_tx.h +73 -0
  217. cuda/cccl/headers/include/cuda/__barrier/barrier_thread_scope.h +60 -0
  218. cuda/cccl/headers/include/cuda/__bit/bit_reverse.h +198 -0
  219. cuda/cccl/headers/include/cuda/__bit/bitfield.h +121 -0
  220. cuda/cccl/headers/include/cuda/__bit/bitmask.h +89 -0
  221. cuda/cccl/headers/include/cuda/__cccl_config +38 -0
  222. cuda/cccl/headers/include/cuda/__cmath/ceil_div.h +123 -0
  223. cuda/cccl/headers/include/cuda/__cmath/fast_modulo_division.h +178 -0
  224. cuda/cccl/headers/include/cuda/__cmath/ilog.h +194 -0
  225. cuda/cccl/headers/include/cuda/__cmath/ipow.h +111 -0
  226. cuda/cccl/headers/include/cuda/__cmath/isqrt.h +80 -0
  227. cuda/cccl/headers/include/cuda/__cmath/mul_hi.h +145 -0
  228. cuda/cccl/headers/include/cuda/__cmath/neg.h +47 -0
  229. cuda/cccl/headers/include/cuda/__cmath/pow2.h +74 -0
  230. cuda/cccl/headers/include/cuda/__cmath/round_down.h +102 -0
  231. cuda/cccl/headers/include/cuda/__cmath/round_up.h +104 -0
  232. cuda/cccl/headers/include/cuda/__cmath/sincos.h +134 -0
  233. cuda/cccl/headers/include/cuda/__cmath/uabs.h +57 -0
  234. cuda/cccl/headers/include/cuda/__complex/complex.h +238 -0
  235. cuda/cccl/headers/include/cuda/__complex/get_real_imag.h +89 -0
  236. cuda/cccl/headers/include/cuda/__complex/traits.h +64 -0
  237. cuda/cccl/headers/include/cuda/__complex_ +28 -0
  238. cuda/cccl/headers/include/cuda/__container/buffer.h +891 -0
  239. cuda/cccl/headers/include/cuda/__container/heterogeneous_iterator.h +436 -0
  240. cuda/cccl/headers/include/cuda/__container/uninitialized_async_buffer.h +416 -0
  241. cuda/cccl/headers/include/cuda/__device/all_devices.h +140 -0
  242. cuda/cccl/headers/include/cuda/__device/arch_id.h +194 -0
  243. cuda/cccl/headers/include/cuda/__device/arch_traits.h +553 -0
  244. cuda/cccl/headers/include/cuda/__device/attributes.h +772 -0
  245. cuda/cccl/headers/include/cuda/__device/compute_capability.h +172 -0
  246. cuda/cccl/headers/include/cuda/__device/device_ref.h +168 -0
  247. cuda/cccl/headers/include/cuda/__device/physical_device.h +178 -0
  248. cuda/cccl/headers/include/cuda/__driver/driver_api.h +1041 -0
  249. cuda/cccl/headers/include/cuda/__event/event.h +171 -0
  250. cuda/cccl/headers/include/cuda/__event/event_ref.h +157 -0
  251. cuda/cccl/headers/include/cuda/__event/timed_event.h +120 -0
  252. cuda/cccl/headers/include/cuda/__execution/determinism.h +89 -0
  253. cuda/cccl/headers/include/cuda/__execution/output_ordering.h +87 -0
  254. cuda/cccl/headers/include/cuda/__execution/policy.h +53 -0
  255. cuda/cccl/headers/include/cuda/__execution/require.h +75 -0
  256. cuda/cccl/headers/include/cuda/__execution/tune.h +70 -0
  257. cuda/cccl/headers/include/cuda/__functional/address_stability.h +131 -0
  258. cuda/cccl/headers/include/cuda/__functional/for_each_canceled.h +321 -0
  259. cuda/cccl/headers/include/cuda/__functional/maximum.h +77 -0
  260. cuda/cccl/headers/include/cuda/__functional/minimum.h +77 -0
  261. cuda/cccl/headers/include/cuda/__functional/minimum_maximum_common.h +52 -0
  262. cuda/cccl/headers/include/cuda/__functional/proclaim_return_type.h +106 -0
  263. cuda/cccl/headers/include/cuda/__fwd/barrier.h +38 -0
  264. cuda/cccl/headers/include/cuda/__fwd/complex.h +48 -0
  265. cuda/cccl/headers/include/cuda/__fwd/devices.h +44 -0
  266. cuda/cccl/headers/include/cuda/__fwd/execution_policy.h +47 -0
  267. cuda/cccl/headers/include/cuda/__fwd/get_stream.h +38 -0
  268. cuda/cccl/headers/include/cuda/__fwd/pipeline.h +37 -0
  269. cuda/cccl/headers/include/cuda/__fwd/zip_iterator.h +58 -0
  270. cuda/cccl/headers/include/cuda/__hierarchy/dimensions.h +162 -0
  271. cuda/cccl/headers/include/cuda/__hierarchy/hierarchy_dimensions.h +986 -0
  272. cuda/cccl/headers/include/cuda/__hierarchy/hierarchy_levels.h +494 -0
  273. cuda/cccl/headers/include/cuda/__hierarchy/level_dimensions.h +225 -0
  274. cuda/cccl/headers/include/cuda/__iterator/constant_iterator.h +315 -0
  275. cuda/cccl/headers/include/cuda/__iterator/counting_iterator.h +490 -0
  276. cuda/cccl/headers/include/cuda/__iterator/discard_iterator.h +324 -0
  277. cuda/cccl/headers/include/cuda/__iterator/permutation_iterator.h +456 -0
  278. cuda/cccl/headers/include/cuda/__iterator/shuffle_iterator.h +334 -0
  279. cuda/cccl/headers/include/cuda/__iterator/strided_iterator.h +418 -0
  280. cuda/cccl/headers/include/cuda/__iterator/tabulate_output_iterator.h +367 -0
  281. cuda/cccl/headers/include/cuda/__iterator/transform_input_output_iterator.h +528 -0
  282. cuda/cccl/headers/include/cuda/__iterator/transform_iterator.h +527 -0
  283. cuda/cccl/headers/include/cuda/__iterator/transform_output_iterator.h +486 -0
  284. cuda/cccl/headers/include/cuda/__iterator/zip_common.h +147 -0
  285. cuda/cccl/headers/include/cuda/__iterator/zip_function.h +114 -0
  286. cuda/cccl/headers/include/cuda/__iterator/zip_iterator.h +555 -0
  287. cuda/cccl/headers/include/cuda/__iterator/zip_transform_iterator.h +589 -0
  288. cuda/cccl/headers/include/cuda/__latch/latch.h +44 -0
  289. cuda/cccl/headers/include/cuda/__launch/configuration.h +754 -0
  290. cuda/cccl/headers/include/cuda/__launch/host_launch.h +115 -0
  291. cuda/cccl/headers/include/cuda/__launch/launch.h +334 -0
  292. cuda/cccl/headers/include/cuda/__mdspan/host_device_accessor.h +531 -0
  293. cuda/cccl/headers/include/cuda/__mdspan/host_device_mdspan.h +239 -0
  294. cuda/cccl/headers/include/cuda/__mdspan/restrict_accessor.h +152 -0
  295. cuda/cccl/headers/include/cuda/__mdspan/restrict_mdspan.h +118 -0
  296. cuda/cccl/headers/include/cuda/__mdspan/shared_memory_accessor.h +208 -0
  297. cuda/cccl/headers/include/cuda/__mdspan/shared_memory_mdspan.h +129 -0
  298. cuda/cccl/headers/include/cuda/__memcpy_async/check_preconditions.h +79 -0
  299. cuda/cccl/headers/include/cuda/__memcpy_async/completion_mechanism.h +47 -0
  300. cuda/cccl/headers/include/cuda/__memcpy_async/cp_async_bulk_shared_global.h +77 -0
  301. cuda/cccl/headers/include/cuda/__memcpy_async/cp_async_fallback.h +72 -0
  302. cuda/cccl/headers/include/cuda/__memcpy_async/cp_async_shared_global.h +148 -0
  303. cuda/cccl/headers/include/cuda/__memcpy_async/dispatch_memcpy_async.h +165 -0
  304. cuda/cccl/headers/include/cuda/__memcpy_async/elect_one.h +52 -0
  305. cuda/cccl/headers/include/cuda/__memcpy_async/is_local_smem_barrier.h +53 -0
  306. cuda/cccl/headers/include/cuda/__memcpy_async/memcpy_async.h +179 -0
  307. cuda/cccl/headers/include/cuda/__memcpy_async/memcpy_async_barrier.h +99 -0
  308. cuda/cccl/headers/include/cuda/__memcpy_async/memcpy_async_tx.h +102 -0
  309. cuda/cccl/headers/include/cuda/__memcpy_async/memcpy_completion.h +164 -0
  310. cuda/cccl/headers/include/cuda/__memcpy_async/try_get_barrier_handle.h +57 -0
  311. cuda/cccl/headers/include/cuda/__memory/address_space.h +256 -0
  312. cuda/cccl/headers/include/cuda/__memory/align_down.h +77 -0
  313. cuda/cccl/headers/include/cuda/__memory/align_up.h +77 -0
  314. cuda/cccl/headers/include/cuda/__memory/aligned_size.h +61 -0
  315. cuda/cccl/headers/include/cuda/__memory/check_address.h +111 -0
  316. cuda/cccl/headers/include/cuda/__memory/discard_memory.h +64 -0
  317. cuda/cccl/headers/include/cuda/__memory/get_device_address.h +58 -0
  318. cuda/cccl/headers/include/cuda/__memory/is_aligned.h +60 -0
  319. cuda/cccl/headers/include/cuda/__memory/is_pointer_accessible.h +278 -0
  320. cuda/cccl/headers/include/cuda/__memory/ptr_in_range.h +92 -0
  321. cuda/cccl/headers/include/cuda/__memory/ptr_rebind.h +75 -0
  322. cuda/cccl/headers/include/cuda/__memory/ranges_overlap.h +125 -0
  323. cuda/cccl/headers/include/cuda/__memory_pool/device_memory_pool.h +166 -0
  324. cuda/cccl/headers/include/cuda/__memory_pool/managed_memory_pool.h +161 -0
  325. cuda/cccl/headers/include/cuda/__memory_pool/memory_pool_base.h +644 -0
  326. cuda/cccl/headers/include/cuda/__memory_pool/pinned_memory_pool.h +218 -0
  327. cuda/cccl/headers/include/cuda/__memory_resource/any_resource.h +882 -0
  328. cuda/cccl/headers/include/cuda/__memory_resource/get_memory_resource.h +82 -0
  329. cuda/cccl/headers/include/cuda/__memory_resource/get_property.h +153 -0
  330. cuda/cccl/headers/include/cuda/__memory_resource/legacy_managed_memory_resource.h +148 -0
  331. cuda/cccl/headers/include/cuda/__memory_resource/legacy_pinned_memory_resource.h +141 -0
  332. cuda/cccl/headers/include/cuda/__memory_resource/properties.h +130 -0
  333. cuda/cccl/headers/include/cuda/__memory_resource/resource.h +135 -0
  334. cuda/cccl/headers/include/cuda/__memory_resource/shared_resource.h +261 -0
  335. cuda/cccl/headers/include/cuda/__memory_resource/synchronous_resource_adapter.h +136 -0
  336. cuda/cccl/headers/include/cuda/__numeric/add_overflow.h +331 -0
  337. cuda/cccl/headers/include/cuda/__numeric/div_overflow.h +150 -0
  338. cuda/cccl/headers/include/cuda/__numeric/narrow.h +108 -0
  339. cuda/cccl/headers/include/cuda/__numeric/overflow_cast.h +59 -0
  340. cuda/cccl/headers/include/cuda/__numeric/overflow_result.h +43 -0
  341. cuda/cccl/headers/include/cuda/__numeric/sub_overflow.h +359 -0
  342. cuda/cccl/headers/include/cuda/__nvtx/nvtx.h +120 -0
  343. cuda/cccl/headers/include/cuda/__nvtx/nvtx3.h +2977 -0
  344. cuda/cccl/headers/include/cuda/__ptx/instructions/barrier_cluster.h +43 -0
  345. cuda/cccl/headers/include/cuda/__ptx/instructions/bfind.h +41 -0
  346. cuda/cccl/headers/include/cuda/__ptx/instructions/bmsk.h +41 -0
  347. cuda/cccl/headers/include/cuda/__ptx/instructions/clusterlaunchcontrol.h +41 -0
  348. cuda/cccl/headers/include/cuda/__ptx/instructions/cp_async_bulk.h +44 -0
  349. cuda/cccl/headers/include/cuda/__ptx/instructions/cp_async_bulk_commit_group.h +43 -0
  350. cuda/cccl/headers/include/cuda/__ptx/instructions/cp_async_bulk_tensor.h +45 -0
  351. cuda/cccl/headers/include/cuda/__ptx/instructions/cp_async_bulk_wait_group.h +43 -0
  352. cuda/cccl/headers/include/cuda/__ptx/instructions/cp_async_mbarrier_arrive.h +42 -0
  353. cuda/cccl/headers/include/cuda/__ptx/instructions/cp_reduce_async_bulk.h +60 -0
  354. cuda/cccl/headers/include/cuda/__ptx/instructions/cp_reduce_async_bulk_tensor.h +43 -0
  355. cuda/cccl/headers/include/cuda/__ptx/instructions/elect_sync.h +41 -0
  356. cuda/cccl/headers/include/cuda/__ptx/instructions/exit.h +41 -0
  357. cuda/cccl/headers/include/cuda/__ptx/instructions/fence.h +49 -0
  358. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/barrier_cluster.h +115 -0
  359. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/bfind.h +190 -0
  360. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/bmsk.h +54 -0
  361. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/clusterlaunchcontrol.h +240 -0
  362. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/cp_async_bulk.h +245 -0
  363. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/cp_async_bulk_commit_group.h +25 -0
  364. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/cp_async_bulk_multicast.h +52 -0
  365. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/cp_async_bulk_tensor.h +977 -0
  366. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/cp_async_bulk_tensor_gather_scatter.h +302 -0
  367. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/cp_async_bulk_tensor_multicast.h +631 -0
  368. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/cp_async_bulk_wait_group.h +46 -0
  369. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/cp_async_mbarrier_arrive.h +26 -0
  370. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/cp_async_mbarrier_arrive_noinc.h +26 -0
  371. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/cp_reduce_async_bulk.h +1470 -0
  372. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/cp_reduce_async_bulk_bf16.h +132 -0
  373. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/cp_reduce_async_bulk_f16.h +132 -0
  374. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/cp_reduce_async_bulk_tensor.h +601 -0
  375. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/elect_sync.h +36 -0
  376. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/exit.h +25 -0
  377. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/fence.h +208 -0
  378. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/fence_mbarrier_init.h +31 -0
  379. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/fence_proxy_alias.h +25 -0
  380. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/fence_proxy_async.h +58 -0
  381. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/fence_proxy_async_generic_sync_restrict.h +64 -0
  382. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/fence_proxy_tensormap_generic.h +102 -0
  383. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/fence_sync_restrict.h +64 -0
  384. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/get_sreg.h +949 -0
  385. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/getctarank.h +32 -0
  386. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/ld.h +5542 -0
  387. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/mbarrier_arrive.h +399 -0
  388. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/mbarrier_arrive_expect_tx.h +184 -0
  389. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/mbarrier_arrive_no_complete.h +34 -0
  390. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/mbarrier_expect_tx.h +102 -0
  391. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/mbarrier_init.h +27 -0
  392. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/mbarrier_inval.h +26 -0
  393. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/mbarrier_test_wait.h +143 -0
  394. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/mbarrier_test_wait_parity.h +144 -0
  395. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/mbarrier_try_wait.h +286 -0
  396. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/mbarrier_try_wait_parity.h +290 -0
  397. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/multimem_ld_reduce.h +2202 -0
  398. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/multimem_red.h +1362 -0
  399. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/multimem_st.h +236 -0
  400. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/prmt.h +230 -0
  401. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/red_async.h +460 -0
  402. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/setmaxnreg.h +58 -0
  403. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/shl.h +96 -0
  404. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/shr.h +168 -0
  405. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/st.h +1490 -0
  406. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/st_async.h +123 -0
  407. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/st_bulk.h +31 -0
  408. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/tcgen05_alloc.h +120 -0
  409. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/tcgen05_commit.h +91 -0
  410. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/tcgen05_cp.h +693 -0
  411. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/tcgen05_fence.h +50 -0
  412. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/tcgen05_ld.h +11437 -0
  413. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/tcgen05_mma.h +6513 -0
  414. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/tcgen05_mma_ws.h +6726 -0
  415. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/tcgen05_shift.h +40 -0
  416. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/tcgen05_st.h +4767 -0
  417. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/tcgen05_wait.h +48 -0
  418. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/tensormap_cp_fenceproxy.h +71 -0
  419. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/tensormap_replace.h +886 -0
  420. cuda/cccl/headers/include/cuda/__ptx/instructions/generated/trap.h +25 -0
  421. cuda/cccl/headers/include/cuda/__ptx/instructions/get_sreg.h +43 -0
  422. cuda/cccl/headers/include/cuda/__ptx/instructions/getctarank.h +43 -0
  423. cuda/cccl/headers/include/cuda/__ptx/instructions/ld.h +41 -0
  424. cuda/cccl/headers/include/cuda/__ptx/instructions/mbarrier_arrive.h +45 -0
  425. cuda/cccl/headers/include/cuda/__ptx/instructions/mbarrier_expect_tx.h +41 -0
  426. cuda/cccl/headers/include/cuda/__ptx/instructions/mbarrier_init.h +43 -0
  427. cuda/cccl/headers/include/cuda/__ptx/instructions/mbarrier_inval.h +41 -0
  428. cuda/cccl/headers/include/cuda/__ptx/instructions/mbarrier_wait.h +46 -0
  429. cuda/cccl/headers/include/cuda/__ptx/instructions/multimem_ld_reduce.h +41 -0
  430. cuda/cccl/headers/include/cuda/__ptx/instructions/multimem_red.h +41 -0
  431. cuda/cccl/headers/include/cuda/__ptx/instructions/multimem_st.h +41 -0
  432. cuda/cccl/headers/include/cuda/__ptx/instructions/prmt.h +41 -0
  433. cuda/cccl/headers/include/cuda/__ptx/instructions/red_async.h +43 -0
  434. cuda/cccl/headers/include/cuda/__ptx/instructions/setmaxnreg.h +41 -0
  435. cuda/cccl/headers/include/cuda/__ptx/instructions/shfl_sync.h +244 -0
  436. cuda/cccl/headers/include/cuda/__ptx/instructions/shl.h +41 -0
  437. cuda/cccl/headers/include/cuda/__ptx/instructions/shr.h +41 -0
  438. cuda/cccl/headers/include/cuda/__ptx/instructions/st.h +41 -0
  439. cuda/cccl/headers/include/cuda/__ptx/instructions/st_async.h +43 -0
  440. cuda/cccl/headers/include/cuda/__ptx/instructions/st_bulk.h +41 -0
  441. cuda/cccl/headers/include/cuda/__ptx/instructions/tcgen05_alloc.h +41 -0
  442. cuda/cccl/headers/include/cuda/__ptx/instructions/tcgen05_commit.h +41 -0
  443. cuda/cccl/headers/include/cuda/__ptx/instructions/tcgen05_cp.h +41 -0
  444. cuda/cccl/headers/include/cuda/__ptx/instructions/tcgen05_fence.h +41 -0
  445. cuda/cccl/headers/include/cuda/__ptx/instructions/tcgen05_ld.h +41 -0
  446. cuda/cccl/headers/include/cuda/__ptx/instructions/tcgen05_mma.h +41 -0
  447. cuda/cccl/headers/include/cuda/__ptx/instructions/tcgen05_mma_ws.h +41 -0
  448. cuda/cccl/headers/include/cuda/__ptx/instructions/tcgen05_shift.h +41 -0
  449. cuda/cccl/headers/include/cuda/__ptx/instructions/tcgen05_st.h +41 -0
  450. cuda/cccl/headers/include/cuda/__ptx/instructions/tcgen05_wait.h +41 -0
  451. cuda/cccl/headers/include/cuda/__ptx/instructions/tensormap_cp_fenceproxy.h +43 -0
  452. cuda/cccl/headers/include/cuda/__ptx/instructions/tensormap_replace.h +43 -0
  453. cuda/cccl/headers/include/cuda/__ptx/instructions/trap.h +41 -0
  454. cuda/cccl/headers/include/cuda/__ptx/pragmas/enable_smem_spilling.h +47 -0
  455. cuda/cccl/headers/include/cuda/__ptx/ptx_dot_variants.h +230 -0
  456. cuda/cccl/headers/include/cuda/__ptx/ptx_helper_functions.h +178 -0
  457. cuda/cccl/headers/include/cuda/__random/feistel_bijection.h +105 -0
  458. cuda/cccl/headers/include/cuda/__random/pcg_engine.h +398 -0
  459. cuda/cccl/headers/include/cuda/__random/random_bijection.h +88 -0
  460. cuda/cccl/headers/include/cuda/__runtime/api_wrapper.h +62 -0
  461. cuda/cccl/headers/include/cuda/__runtime/ensure_current_context.h +99 -0
  462. cuda/cccl/headers/include/cuda/__runtime/types.h +41 -0
  463. cuda/cccl/headers/include/cuda/__semaphore/counting_semaphore.h +53 -0
  464. cuda/cccl/headers/include/cuda/__stream/get_stream.h +109 -0
  465. cuda/cccl/headers/include/cuda/__stream/internal_streams.h +49 -0
  466. cuda/cccl/headers/include/cuda/__stream/invalid_stream.h +47 -0
  467. cuda/cccl/headers/include/cuda/__stream/launch_transform.h +193 -0
  468. cuda/cccl/headers/include/cuda/__stream/stream.h +145 -0
  469. cuda/cccl/headers/include/cuda/__stream/stream_ref.h +356 -0
  470. cuda/cccl/headers/include/cuda/__tma/make_tma_descriptor.h +657 -0
  471. cuda/cccl/headers/include/cuda/__type_traits/is_floating_point.h +47 -0
  472. cuda/cccl/headers/include/cuda/__type_traits/is_instantiable_with.h +47 -0
  473. cuda/cccl/headers/include/cuda/__type_traits/is_specialization_of.h +37 -0
  474. cuda/cccl/headers/include/cuda/__type_traits/vector_type.h +355 -0
  475. cuda/cccl/headers/include/cuda/__utility/__basic_any/access.h +88 -0
  476. cuda/cccl/headers/include/cuda/__utility/__basic_any/any_cast.h +83 -0
  477. cuda/cccl/headers/include/cuda/__utility/__basic_any/basic_any_base.h +148 -0
  478. cuda/cccl/headers/include/cuda/__utility/__basic_any/basic_any_from.h +96 -0
  479. cuda/cccl/headers/include/cuda/__utility/__basic_any/basic_any_fwd.h +128 -0
  480. cuda/cccl/headers/include/cuda/__utility/__basic_any/basic_any_ptr.h +304 -0
  481. cuda/cccl/headers/include/cuda/__utility/__basic_any/basic_any_ref.h +337 -0
  482. cuda/cccl/headers/include/cuda/__utility/__basic_any/basic_any_value.h +611 -0
  483. cuda/cccl/headers/include/cuda/__utility/__basic_any/conversions.h +170 -0
  484. cuda/cccl/headers/include/cuda/__utility/__basic_any/dynamic_any_cast.h +147 -0
  485. cuda/cccl/headers/include/cuda/__utility/__basic_any/interfaces.h +359 -0
  486. cuda/cccl/headers/include/cuda/__utility/__basic_any/iset.h +142 -0
  487. cuda/cccl/headers/include/cuda/__utility/__basic_any/overrides.h +64 -0
  488. cuda/cccl/headers/include/cuda/__utility/__basic_any/rtti.h +256 -0
  489. cuda/cccl/headers/include/cuda/__utility/__basic_any/semiregular.h +323 -0
  490. cuda/cccl/headers/include/cuda/__utility/__basic_any/storage.h +79 -0
  491. cuda/cccl/headers/include/cuda/__utility/__basic_any/tagged_ptr.h +58 -0
  492. cuda/cccl/headers/include/cuda/__utility/__basic_any/virtcall.h +162 -0
  493. cuda/cccl/headers/include/cuda/__utility/__basic_any/virtual_functions.h +183 -0
  494. cuda/cccl/headers/include/cuda/__utility/__basic_any/virtual_ptrs.h +80 -0
  495. cuda/cccl/headers/include/cuda/__utility/__basic_any/virtual_tables.h +155 -0
  496. cuda/cccl/headers/include/cuda/__utility/basic_any.h +507 -0
  497. cuda/cccl/headers/include/cuda/__utility/immovable.h +50 -0
  498. cuda/cccl/headers/include/cuda/__utility/in_range.h +65 -0
  499. cuda/cccl/headers/include/cuda/__utility/inherit.h +36 -0
  500. cuda/cccl/headers/include/cuda/__utility/no_init.h +29 -0
  501. cuda/cccl/headers/include/cuda/__utility/static_for.h +79 -0
  502. cuda/cccl/headers/include/cuda/__warp/lane_mask.h +326 -0
  503. cuda/cccl/headers/include/cuda/__warp/warp_match_all.h +65 -0
  504. cuda/cccl/headers/include/cuda/__warp/warp_shuffle.h +251 -0
  505. cuda/cccl/headers/include/cuda/access_property +26 -0
  506. cuda/cccl/headers/include/cuda/algorithm +28 -0
  507. cuda/cccl/headers/include/cuda/annotated_ptr +29 -0
  508. cuda/cccl/headers/include/cuda/atomic +27 -0
  509. cuda/cccl/headers/include/cuda/barrier +293 -0
  510. cuda/cccl/headers/include/cuda/bit +29 -0
  511. cuda/cccl/headers/include/cuda/buffer +27 -0
  512. cuda/cccl/headers/include/cuda/cmath +38 -0
  513. cuda/cccl/headers/include/cuda/devices +33 -0
  514. cuda/cccl/headers/include/cuda/discard_memory +32 -0
  515. cuda/cccl/headers/include/cuda/functional +32 -0
  516. cuda/cccl/headers/include/cuda/hierarchy +28 -0
  517. cuda/cccl/headers/include/cuda/iterator +39 -0
  518. cuda/cccl/headers/include/cuda/latch +27 -0
  519. cuda/cccl/headers/include/cuda/launch +28 -0
  520. cuda/cccl/headers/include/cuda/mdspan +29 -0
  521. cuda/cccl/headers/include/cuda/memory +37 -0
  522. cuda/cccl/headers/include/cuda/memory_pool +27 -0
  523. cuda/cccl/headers/include/cuda/memory_resource +41 -0
  524. cuda/cccl/headers/include/cuda/numeric +31 -0
  525. cuda/cccl/headers/include/cuda/pipeline +580 -0
  526. cuda/cccl/headers/include/cuda/ptx +131 -0
  527. cuda/cccl/headers/include/cuda/semaphore +31 -0
  528. cuda/cccl/headers/include/cuda/std/__algorithm/adjacent_find.h +59 -0
  529. cuda/cccl/headers/include/cuda/std/__algorithm/all_of.h +45 -0
  530. cuda/cccl/headers/include/cuda/std/__algorithm/any_of.h +45 -0
  531. cuda/cccl/headers/include/cuda/std/__algorithm/binary_search.h +53 -0
  532. cuda/cccl/headers/include/cuda/std/__algorithm/clamp.h +48 -0
  533. cuda/cccl/headers/include/cuda/std/__algorithm/comp.h +58 -0
  534. cuda/cccl/headers/include/cuda/std/__algorithm/comp_ref_type.h +85 -0
  535. cuda/cccl/headers/include/cuda/std/__algorithm/copy.h +143 -0
  536. cuda/cccl/headers/include/cuda/std/__algorithm/copy_backward.h +80 -0
  537. cuda/cccl/headers/include/cuda/std/__algorithm/copy_if.h +47 -0
  538. cuda/cccl/headers/include/cuda/std/__algorithm/copy_n.h +73 -0
  539. cuda/cccl/headers/include/cuda/std/__algorithm/count.h +49 -0
  540. cuda/cccl/headers/include/cuda/std/__algorithm/count_if.h +49 -0
  541. cuda/cccl/headers/include/cuda/std/__algorithm/equal.h +128 -0
  542. cuda/cccl/headers/include/cuda/std/__algorithm/equal_range.h +101 -0
  543. cuda/cccl/headers/include/cuda/std/__algorithm/fill.h +58 -0
  544. cuda/cccl/headers/include/cuda/std/__algorithm/fill_n.h +51 -0
  545. cuda/cccl/headers/include/cuda/std/__algorithm/find.h +62 -0
  546. cuda/cccl/headers/include/cuda/std/__algorithm/find_end.h +225 -0
  547. cuda/cccl/headers/include/cuda/std/__algorithm/find_first_of.h +73 -0
  548. cuda/cccl/headers/include/cuda/std/__algorithm/find_if.h +46 -0
  549. cuda/cccl/headers/include/cuda/std/__algorithm/find_if_not.h +46 -0
  550. cuda/cccl/headers/include/cuda/std/__algorithm/for_each.h +42 -0
  551. cuda/cccl/headers/include/cuda/std/__algorithm/for_each_n.h +48 -0
  552. cuda/cccl/headers/include/cuda/std/__algorithm/generate.h +41 -0
  553. cuda/cccl/headers/include/cuda/std/__algorithm/generate_n.h +46 -0
  554. cuda/cccl/headers/include/cuda/std/__algorithm/half_positive.h +49 -0
  555. cuda/cccl/headers/include/cuda/std/__algorithm/in_fun_result.h +55 -0
  556. cuda/cccl/headers/include/cuda/std/__algorithm/includes.h +90 -0
  557. cuda/cccl/headers/include/cuda/std/__algorithm/inplace_merge.h +293 -0
  558. cuda/cccl/headers/include/cuda/std/__algorithm/is_heap.h +50 -0
  559. cuda/cccl/headers/include/cuda/std/__algorithm/is_heap_until.h +83 -0
  560. cuda/cccl/headers/include/cuda/std/__algorithm/is_partitioned.h +57 -0
  561. cuda/cccl/headers/include/cuda/std/__algorithm/is_permutation.h +252 -0
  562. cuda/cccl/headers/include/cuda/std/__algorithm/is_sorted.h +49 -0
  563. cuda/cccl/headers/include/cuda/std/__algorithm/is_sorted_until.h +68 -0
  564. cuda/cccl/headers/include/cuda/std/__algorithm/iter_swap.h +82 -0
  565. cuda/cccl/headers/include/cuda/std/__algorithm/iterator_operations.h +185 -0
  566. cuda/cccl/headers/include/cuda/std/__algorithm/lexicographical_compare.h +68 -0
  567. cuda/cccl/headers/include/cuda/std/__algorithm/lower_bound.h +82 -0
  568. cuda/cccl/headers/include/cuda/std/__algorithm/make_heap.h +70 -0
  569. cuda/cccl/headers/include/cuda/std/__algorithm/make_projected.h +88 -0
  570. cuda/cccl/headers/include/cuda/std/__algorithm/max.h +62 -0
  571. cuda/cccl/headers/include/cuda/std/__algorithm/max_element.h +67 -0
  572. cuda/cccl/headers/include/cuda/std/__algorithm/merge.h +89 -0
  573. cuda/cccl/headers/include/cuda/std/__algorithm/min.h +62 -0
  574. cuda/cccl/headers/include/cuda/std/__algorithm/min_element.h +87 -0
  575. cuda/cccl/headers/include/cuda/std/__algorithm/minmax.h +66 -0
  576. cuda/cccl/headers/include/cuda/std/__algorithm/minmax_element.h +139 -0
  577. cuda/cccl/headers/include/cuda/std/__algorithm/mismatch.h +83 -0
  578. cuda/cccl/headers/include/cuda/std/__algorithm/move.h +91 -0
  579. cuda/cccl/headers/include/cuda/std/__algorithm/move_backward.h +84 -0
  580. cuda/cccl/headers/include/cuda/std/__algorithm/next_permutation.h +88 -0
  581. cuda/cccl/headers/include/cuda/std/__algorithm/none_of.h +45 -0
  582. cuda/cccl/headers/include/cuda/std/__algorithm/nth_element.h +309 -0
  583. cuda/cccl/headers/include/cuda/std/__algorithm/partial_sort.h +102 -0
  584. cuda/cccl/headers/include/cuda/std/__algorithm/partial_sort_copy.h +122 -0
  585. cuda/cccl/headers/include/cuda/std/__algorithm/partition.h +120 -0
  586. cuda/cccl/headers/include/cuda/std/__algorithm/partition_copy.h +59 -0
  587. cuda/cccl/headers/include/cuda/std/__algorithm/partition_point.h +61 -0
  588. cuda/cccl/headers/include/cuda/std/__algorithm/pop_heap.h +93 -0
  589. cuda/cccl/headers/include/cuda/std/__algorithm/prev_permutation.h +88 -0
  590. cuda/cccl/headers/include/cuda/std/__algorithm/push_heap.h +100 -0
  591. cuda/cccl/headers/include/cuda/std/__algorithm/ranges_find_if.h +78 -0
  592. cuda/cccl/headers/include/cuda/std/__algorithm/ranges_find_if_not.h +85 -0
  593. cuda/cccl/headers/include/cuda/std/__algorithm/ranges_for_each.h +84 -0
  594. cuda/cccl/headers/include/cuda/std/__algorithm/ranges_for_each_n.h +68 -0
  595. cuda/cccl/headers/include/cuda/std/__algorithm/ranges_iterator_concept.h +65 -0
  596. cuda/cccl/headers/include/cuda/std/__algorithm/ranges_min.h +97 -0
  597. cuda/cccl/headers/include/cuda/std/__algorithm/ranges_min_element.h +68 -0
  598. cuda/cccl/headers/include/cuda/std/__algorithm/remove.h +55 -0
  599. cuda/cccl/headers/include/cuda/std/__algorithm/remove_copy.h +47 -0
  600. cuda/cccl/headers/include/cuda/std/__algorithm/remove_copy_if.h +47 -0
  601. cuda/cccl/headers/include/cuda/std/__algorithm/remove_if.h +56 -0
  602. cuda/cccl/headers/include/cuda/std/__algorithm/replace.h +45 -0
  603. cuda/cccl/headers/include/cuda/std/__algorithm/replace_copy.h +54 -0
  604. cuda/cccl/headers/include/cuda/std/__algorithm/replace_copy_if.h +50 -0
  605. cuda/cccl/headers/include/cuda/std/__algorithm/replace_if.h +45 -0
  606. cuda/cccl/headers/include/cuda/std/__algorithm/reverse.h +81 -0
  607. cuda/cccl/headers/include/cuda/std/__algorithm/reverse_copy.h +43 -0
  608. cuda/cccl/headers/include/cuda/std/__algorithm/rotate.h +261 -0
  609. cuda/cccl/headers/include/cuda/std/__algorithm/rotate_copy.h +40 -0
  610. cuda/cccl/headers/include/cuda/std/__algorithm/sample.h +116 -0
  611. cuda/cccl/headers/include/cuda/std/__algorithm/search.h +185 -0
  612. cuda/cccl/headers/include/cuda/std/__algorithm/search_n.h +163 -0
  613. cuda/cccl/headers/include/cuda/std/__algorithm/set_difference.h +95 -0
  614. cuda/cccl/headers/include/cuda/std/__algorithm/set_intersection.h +122 -0
  615. cuda/cccl/headers/include/cuda/std/__algorithm/set_symmetric_difference.h +134 -0
  616. cuda/cccl/headers/include/cuda/std/__algorithm/set_union.h +128 -0
  617. cuda/cccl/headers/include/cuda/std/__algorithm/shift_left.h +84 -0
  618. cuda/cccl/headers/include/cuda/std/__algorithm/shift_right.h +144 -0
  619. cuda/cccl/headers/include/cuda/std/__algorithm/shuffle.h +71 -0
  620. cuda/cccl/headers/include/cuda/std/__algorithm/sift_down.h +139 -0
  621. cuda/cccl/headers/include/cuda/std/__algorithm/sort.h +1097 -0
  622. cuda/cccl/headers/include/cuda/std/__algorithm/sort_heap.h +70 -0
  623. cuda/cccl/headers/include/cuda/std/__algorithm/stable_partition.h +359 -0
  624. cuda/cccl/headers/include/cuda/std/__algorithm/stable_sort.h +321 -0
  625. cuda/cccl/headers/include/cuda/std/__algorithm/swap_ranges.h +78 -0
  626. cuda/cccl/headers/include/cuda/std/__algorithm/transform.h +59 -0
  627. cuda/cccl/headers/include/cuda/std/__algorithm/unique.h +76 -0
  628. cuda/cccl/headers/include/cuda/std/__algorithm/unique_copy.h +153 -0
  629. cuda/cccl/headers/include/cuda/std/__algorithm/unwrap_iter.h +95 -0
  630. cuda/cccl/headers/include/cuda/std/__algorithm/unwrap_range.h +126 -0
  631. cuda/cccl/headers/include/cuda/std/__algorithm/upper_bound.h +83 -0
  632. cuda/cccl/headers/include/cuda/std/__atomic/api/common.h +192 -0
  633. cuda/cccl/headers/include/cuda/std/__atomic/api/owned.h +136 -0
  634. cuda/cccl/headers/include/cuda/std/__atomic/api/reference.h +118 -0
  635. cuda/cccl/headers/include/cuda/std/__atomic/functions/common.h +58 -0
  636. cuda/cccl/headers/include/cuda/std/__atomic/functions/cuda_local.h +208 -0
  637. cuda/cccl/headers/include/cuda/std/__atomic/functions/cuda_ptx_derived.h +458 -0
  638. cuda/cccl/headers/include/cuda/std/__atomic/functions/cuda_ptx_generated.h +4436 -0
  639. cuda/cccl/headers/include/cuda/std/__atomic/functions/cuda_ptx_generated_helper.h +184 -0
  640. cuda/cccl/headers/include/cuda/std/__atomic/functions/host.h +242 -0
  641. cuda/cccl/headers/include/cuda/std/__atomic/functions.h +33 -0
  642. cuda/cccl/headers/include/cuda/std/__atomic/order.h +158 -0
  643. cuda/cccl/headers/include/cuda/std/__atomic/platform/msvc_to_builtins.h +654 -0
  644. cuda/cccl/headers/include/cuda/std/__atomic/platform.h +93 -0
  645. cuda/cccl/headers/include/cuda/std/__atomic/scopes.h +105 -0
  646. cuda/cccl/headers/include/cuda/std/__atomic/types/base.h +242 -0
  647. cuda/cccl/headers/include/cuda/std/__atomic/types/common.h +103 -0
  648. cuda/cccl/headers/include/cuda/std/__atomic/types/locked.h +225 -0
  649. cuda/cccl/headers/include/cuda/std/__atomic/types/reference.h +72 -0
  650. cuda/cccl/headers/include/cuda/std/__atomic/types/small.h +238 -0
  651. cuda/cccl/headers/include/cuda/std/__atomic/types.h +51 -0
  652. cuda/cccl/headers/include/cuda/std/__atomic/wait/notify_wait.h +95 -0
  653. cuda/cccl/headers/include/cuda/std/__atomic/wait/polling.h +65 -0
  654. cuda/cccl/headers/include/cuda/std/__barrier/barrier.h +227 -0
  655. cuda/cccl/headers/include/cuda/std/__barrier/empty_completion.h +37 -0
  656. cuda/cccl/headers/include/cuda/std/__barrier/poll_tester.h +82 -0
  657. cuda/cccl/headers/include/cuda/std/__bit/bit_cast.h +81 -0
  658. cuda/cccl/headers/include/cuda/std/__bit/blsr.h +51 -0
  659. cuda/cccl/headers/include/cuda/std/__bit/byteswap.h +209 -0
  660. cuda/cccl/headers/include/cuda/std/__bit/countl.h +191 -0
  661. cuda/cccl/headers/include/cuda/std/__bit/countr.h +202 -0
  662. cuda/cccl/headers/include/cuda/std/__bit/endian.h +39 -0
  663. cuda/cccl/headers/include/cuda/std/__bit/has_single_bit.h +43 -0
  664. cuda/cccl/headers/include/cuda/std/__bit/integral.h +125 -0
  665. cuda/cccl/headers/include/cuda/std/__bit/popcount.h +172 -0
  666. cuda/cccl/headers/include/cuda/std/__bit/reference.h +1272 -0
  667. cuda/cccl/headers/include/cuda/std/__bit/rotate.h +185 -0
  668. cuda/cccl/headers/include/cuda/std/__cccl/algorithm_wrapper.h +36 -0
  669. cuda/cccl/headers/include/cuda/std/__cccl/architecture.h +78 -0
  670. cuda/cccl/headers/include/cuda/std/__cccl/assert.h +161 -0
  671. cuda/cccl/headers/include/cuda/std/__cccl/attributes.h +206 -0
  672. cuda/cccl/headers/include/cuda/std/__cccl/builtin.h +494 -0
  673. cuda/cccl/headers/include/cuda/std/__cccl/compiler.h +213 -0
  674. cuda/cccl/headers/include/cuda/std/__cccl/cuda_capabilities.h +51 -0
  675. cuda/cccl/headers/include/cuda/std/__cccl/cuda_toolkit.h +56 -0
  676. cuda/cccl/headers/include/cuda/std/__cccl/deprecated.h +87 -0
  677. cuda/cccl/headers/include/cuda/std/__cccl/diagnostic.h +131 -0
  678. cuda/cccl/headers/include/cuda/std/__cccl/dialect.h +197 -0
  679. cuda/cccl/headers/include/cuda/std/__cccl/epilogue.h +355 -0
  680. cuda/cccl/headers/include/cuda/std/__cccl/exceptions.h +36 -0
  681. cuda/cccl/headers/include/cuda/std/__cccl/execution_space.h +74 -0
  682. cuda/cccl/headers/include/cuda/std/__cccl/extended_data_types.h +139 -0
  683. cuda/cccl/headers/include/cuda/std/__cccl/host_std_lib.h +59 -0
  684. cuda/cccl/headers/include/cuda/std/__cccl/is_non_narrowing_convertible.h +71 -0
  685. cuda/cccl/headers/include/cuda/std/__cccl/memory_wrapper.h +36 -0
  686. cuda/cccl/headers/include/cuda/std/__cccl/numeric_wrapper.h +36 -0
  687. cuda/cccl/headers/include/cuda/std/__cccl/os.h +54 -0
  688. cuda/cccl/headers/include/cuda/std/__cccl/preprocessor.h +1288 -0
  689. cuda/cccl/headers/include/cuda/std/__cccl/prologue.h +312 -0
  690. cuda/cccl/headers/include/cuda/std/__cccl/ptx_isa.h +363 -0
  691. cuda/cccl/headers/include/cuda/std/__cccl/rtti.h +72 -0
  692. cuda/cccl/headers/include/cuda/std/__cccl/sequence_access.h +87 -0
  693. cuda/cccl/headers/include/cuda/std/__cccl/system_header.h +38 -0
  694. cuda/cccl/headers/include/cuda/std/__cccl/unreachable.h +31 -0
  695. cuda/cccl/headers/include/cuda/std/__cccl/version.h +26 -0
  696. cuda/cccl/headers/include/cuda/std/__cccl/visibility.h +171 -0
  697. cuda/cccl/headers/include/cuda/std/__charconv/chars_format.h +81 -0
  698. cuda/cccl/headers/include/cuda/std/__charconv/from_chars.h +171 -0
  699. cuda/cccl/headers/include/cuda/std/__charconv/from_chars_result.h +56 -0
  700. cuda/cccl/headers/include/cuda/std/__charconv/to_chars.h +192 -0
  701. cuda/cccl/headers/include/cuda/std/__charconv/to_chars_result.h +56 -0
  702. cuda/cccl/headers/include/cuda/std/__chrono/calendar.h +52 -0
  703. cuda/cccl/headers/include/cuda/std/__chrono/day.h +160 -0
  704. cuda/cccl/headers/include/cuda/std/__chrono/duration.h +499 -0
  705. cuda/cccl/headers/include/cuda/std/__chrono/file_clock.h +53 -0
  706. cuda/cccl/headers/include/cuda/std/__chrono/high_resolution_clock.h +44 -0
  707. cuda/cccl/headers/include/cuda/std/__chrono/month.h +185 -0
  708. cuda/cccl/headers/include/cuda/std/__chrono/steady_clock.h +58 -0
  709. cuda/cccl/headers/include/cuda/std/__chrono/system_clock.h +78 -0
  710. cuda/cccl/headers/include/cuda/std/__chrono/time_point.h +255 -0
  711. cuda/cccl/headers/include/cuda/std/__chrono/year.h +184 -0
  712. cuda/cccl/headers/include/cuda/std/__cmath/abs.h +127 -0
  713. cuda/cccl/headers/include/cuda/std/__cmath/copysign.h +88 -0
  714. cuda/cccl/headers/include/cuda/std/__cmath/error_functions.h +204 -0
  715. cuda/cccl/headers/include/cuda/std/__cmath/exponential_functions.h +783 -0
  716. cuda/cccl/headers/include/cuda/std/__cmath/fdim.h +122 -0
  717. cuda/cccl/headers/include/cuda/std/__cmath/fma.h +129 -0
  718. cuda/cccl/headers/include/cuda/std/__cmath/fpclassify.h +230 -0
  719. cuda/cccl/headers/include/cuda/std/__cmath/gamma.h +204 -0
  720. cuda/cccl/headers/include/cuda/std/__cmath/hyperbolic_functions.h +285 -0
  721. cuda/cccl/headers/include/cuda/std/__cmath/hypot.h +220 -0
  722. cuda/cccl/headers/include/cuda/std/__cmath/inverse_hyperbolic_functions.h +285 -0
  723. cuda/cccl/headers/include/cuda/std/__cmath/inverse_trigonometric_functions.h +370 -0
  724. cuda/cccl/headers/include/cuda/std/__cmath/isfinite.h +166 -0
  725. cuda/cccl/headers/include/cuda/std/__cmath/isinf.h +203 -0
  726. cuda/cccl/headers/include/cuda/std/__cmath/isnan.h +184 -0
  727. cuda/cccl/headers/include/cuda/std/__cmath/isnormal.h +138 -0
  728. cuda/cccl/headers/include/cuda/std/__cmath/lerp.h +101 -0
  729. cuda/cccl/headers/include/cuda/std/__cmath/logarithms.h +533 -0
  730. cuda/cccl/headers/include/cuda/std/__cmath/min_max.h +287 -0
  731. cuda/cccl/headers/include/cuda/std/__cmath/modulo.h +208 -0
  732. cuda/cccl/headers/include/cuda/std/__cmath/nan.h +54 -0
  733. cuda/cccl/headers/include/cuda/std/__cmath/remainder.h +210 -0
  734. cuda/cccl/headers/include/cuda/std/__cmath/roots.h +198 -0
  735. cuda/cccl/headers/include/cuda/std/__cmath/rounding_functions.h +983 -0
  736. cuda/cccl/headers/include/cuda/std/__cmath/signbit.h +56 -0
  737. cuda/cccl/headers/include/cuda/std/__cmath/traits.h +242 -0
  738. cuda/cccl/headers/include/cuda/std/__cmath/trigonometric_functions.h +327 -0
  739. cuda/cccl/headers/include/cuda/std/__complex/arg.h +84 -0
  740. cuda/cccl/headers/include/cuda/std/__complex/complex.h +669 -0
  741. cuda/cccl/headers/include/cuda/std/__complex/exponential_functions.h +403 -0
  742. cuda/cccl/headers/include/cuda/std/__complex/hyperbolic_functions.h +119 -0
  743. cuda/cccl/headers/include/cuda/std/__complex/inverse_hyperbolic_functions.h +522 -0
  744. cuda/cccl/headers/include/cuda/std/__complex/inverse_trigonometric_functions.h +131 -0
  745. cuda/cccl/headers/include/cuda/std/__complex/literals.h +86 -0
  746. cuda/cccl/headers/include/cuda/std/__complex/logarithms.h +302 -0
  747. cuda/cccl/headers/include/cuda/std/__complex/math.h +161 -0
  748. cuda/cccl/headers/include/cuda/std/__complex/nvbf16.h +323 -0
  749. cuda/cccl/headers/include/cuda/std/__complex/nvfp16.h +322 -0
  750. cuda/cccl/headers/include/cuda/std/__complex/roots.h +214 -0
  751. cuda/cccl/headers/include/cuda/std/__complex/trigonometric_functions.h +61 -0
  752. cuda/cccl/headers/include/cuda/std/__complex/tuple.h +107 -0
  753. cuda/cccl/headers/include/cuda/std/__complex/vector_support.h +130 -0
  754. cuda/cccl/headers/include/cuda/std/__concepts/arithmetic.h +56 -0
  755. cuda/cccl/headers/include/cuda/std/__concepts/assignable.h +64 -0
  756. cuda/cccl/headers/include/cuda/std/__concepts/boolean_testable.h +63 -0
  757. cuda/cccl/headers/include/cuda/std/__concepts/class_or_enum.h +45 -0
  758. cuda/cccl/headers/include/cuda/std/__concepts/common_reference_with.h +69 -0
  759. cuda/cccl/headers/include/cuda/std/__concepts/common_with.h +82 -0
  760. cuda/cccl/headers/include/cuda/std/__concepts/concept_macros.h +385 -0
  761. cuda/cccl/headers/include/cuda/std/__concepts/constructible.h +174 -0
  762. cuda/cccl/headers/include/cuda/std/__concepts/convertible_to.h +70 -0
  763. cuda/cccl/headers/include/cuda/std/__concepts/copyable.h +60 -0
  764. cuda/cccl/headers/include/cuda/std/__concepts/derived_from.h +56 -0
  765. cuda/cccl/headers/include/cuda/std/__concepts/destructible.h +76 -0
  766. cuda/cccl/headers/include/cuda/std/__concepts/different_from.h +38 -0
  767. cuda/cccl/headers/include/cuda/std/__concepts/equality_comparable.h +98 -0
  768. cuda/cccl/headers/include/cuda/std/__concepts/invocable.h +80 -0
  769. cuda/cccl/headers/include/cuda/std/__concepts/movable.h +58 -0
  770. cuda/cccl/headers/include/cuda/std/__concepts/predicate.h +54 -0
  771. cuda/cccl/headers/include/cuda/std/__concepts/regular.h +54 -0
  772. cuda/cccl/headers/include/cuda/std/__concepts/relation.h +77 -0
  773. cuda/cccl/headers/include/cuda/std/__concepts/same_as.h +39 -0
  774. cuda/cccl/headers/include/cuda/std/__concepts/semiregular.h +54 -0
  775. cuda/cccl/headers/include/cuda/std/__concepts/swappable.h +206 -0
  776. cuda/cccl/headers/include/cuda/std/__concepts/totally_ordered.h +101 -0
  777. cuda/cccl/headers/include/cuda/std/__cstddef/byte.h +113 -0
  778. cuda/cccl/headers/include/cuda/std/__cstddef/types.h +52 -0
  779. cuda/cccl/headers/include/cuda/std/__cstdlib/abs.h +57 -0
  780. cuda/cccl/headers/include/cuda/std/__cstdlib/aligned_alloc.h +66 -0
  781. cuda/cccl/headers/include/cuda/std/__cstdlib/div.h +96 -0
  782. cuda/cccl/headers/include/cuda/std/__cstdlib/malloc.h +70 -0
  783. cuda/cccl/headers/include/cuda/std/__cstring/memcpy.h +61 -0
  784. cuda/cccl/headers/include/cuda/std/__cstring/memset.h +46 -0
  785. cuda/cccl/headers/include/cuda/std/__exception/cuda_error.h +110 -0
  786. cuda/cccl/headers/include/cuda/std/__exception/exception_macros.h +108 -0
  787. cuda/cccl/headers/include/cuda/std/__exception/format_error.h +62 -0
  788. cuda/cccl/headers/include/cuda/std/__exception/msg_storage.h +41 -0
  789. cuda/cccl/headers/include/cuda/std/__exception/terminate.h +74 -0
  790. cuda/cccl/headers/include/cuda/std/__exception/throw_error.h +120 -0
  791. cuda/cccl/headers/include/cuda/std/__execution/env.h +455 -0
  792. cuda/cccl/headers/include/cuda/std/__execution/policy.h +90 -0
  793. cuda/cccl/headers/include/cuda/std/__expected/bad_expected_access.h +127 -0
  794. cuda/cccl/headers/include/cuda/std/__expected/expected.h +1941 -0
  795. cuda/cccl/headers/include/cuda/std/__expected/expected_base.h +1051 -0
  796. cuda/cccl/headers/include/cuda/std/__expected/unexpect.h +37 -0
  797. cuda/cccl/headers/include/cuda/std/__expected/unexpected.h +164 -0
  798. cuda/cccl/headers/include/cuda/std/__floating_point/arithmetic.h +56 -0
  799. cuda/cccl/headers/include/cuda/std/__floating_point/cast.h +812 -0
  800. cuda/cccl/headers/include/cuda/std/__floating_point/cccl_fp.h +125 -0
  801. cuda/cccl/headers/include/cuda/std/__floating_point/common_type.h +48 -0
  802. cuda/cccl/headers/include/cuda/std/__floating_point/constants.h +375 -0
  803. cuda/cccl/headers/include/cuda/std/__floating_point/conversion_rank_order.h +124 -0
  804. cuda/cccl/headers/include/cuda/std/__floating_point/cuda_fp_types.h +116 -0
  805. cuda/cccl/headers/include/cuda/std/__floating_point/decompose.h +126 -0
  806. cuda/cccl/headers/include/cuda/std/__floating_point/format.h +162 -0
  807. cuda/cccl/headers/include/cuda/std/__floating_point/fp.h +40 -0
  808. cuda/cccl/headers/include/cuda/std/__floating_point/mask.h +78 -0
  809. cuda/cccl/headers/include/cuda/std/__floating_point/native_type.h +81 -0
  810. cuda/cccl/headers/include/cuda/std/__floating_point/overflow_handler.h +139 -0
  811. cuda/cccl/headers/include/cuda/std/__floating_point/properties.h +229 -0
  812. cuda/cccl/headers/include/cuda/std/__floating_point/storage.h +248 -0
  813. cuda/cccl/headers/include/cuda/std/__floating_point/traits.h +172 -0
  814. cuda/cccl/headers/include/cuda/std/__format/buffer.h +48 -0
  815. cuda/cccl/headers/include/cuda/std/__format/concepts.h +69 -0
  816. cuda/cccl/headers/include/cuda/std/__format/format_arg.h +282 -0
  817. cuda/cccl/headers/include/cuda/std/__format/format_arg_store.h +279 -0
  818. cuda/cccl/headers/include/cuda/std/__format/format_args.h +122 -0
  819. cuda/cccl/headers/include/cuda/std/__format/format_context.h +93 -0
  820. cuda/cccl/headers/include/cuda/std/__format/format_error.h +76 -0
  821. cuda/cccl/headers/include/cuda/std/__format/format_integral.h +237 -0
  822. cuda/cccl/headers/include/cuda/std/__format/format_parse_context.h +124 -0
  823. cuda/cccl/headers/include/cuda/std/__format/format_spec_parser.h +1265 -0
  824. cuda/cccl/headers/include/cuda/std/__format/formatter.h +59 -0
  825. cuda/cccl/headers/include/cuda/std/__format/formatters/bool.h +101 -0
  826. cuda/cccl/headers/include/cuda/std/__format/formatters/char.h +124 -0
  827. cuda/cccl/headers/include/cuda/std/__format/formatters/fp.h +101 -0
  828. cuda/cccl/headers/include/cuda/std/__format/formatters/int.h +174 -0
  829. cuda/cccl/headers/include/cuda/std/__format/formatters/ptr.h +104 -0
  830. cuda/cccl/headers/include/cuda/std/__format/formatters/str.h +178 -0
  831. cuda/cccl/headers/include/cuda/std/__format/output_utils.h +272 -0
  832. cuda/cccl/headers/include/cuda/std/__format/parse_arg_id.h +138 -0
  833. cuda/cccl/headers/include/cuda/std/__format_ +45 -0
  834. cuda/cccl/headers/include/cuda/std/__functional/binary_function.h +63 -0
  835. cuda/cccl/headers/include/cuda/std/__functional/binary_negate.h +65 -0
  836. cuda/cccl/headers/include/cuda/std/__functional/bind.h +334 -0
  837. cuda/cccl/headers/include/cuda/std/__functional/bind_back.h +81 -0
  838. cuda/cccl/headers/include/cuda/std/__functional/bind_front.h +74 -0
  839. cuda/cccl/headers/include/cuda/std/__functional/binder1st.h +74 -0
  840. cuda/cccl/headers/include/cuda/std/__functional/binder2nd.h +74 -0
  841. cuda/cccl/headers/include/cuda/std/__functional/compose.h +69 -0
  842. cuda/cccl/headers/include/cuda/std/__functional/default_searcher.h +76 -0
  843. cuda/cccl/headers/include/cuda/std/__functional/function.h +1271 -0
  844. cuda/cccl/headers/include/cuda/std/__functional/hash.h +649 -0
  845. cuda/cccl/headers/include/cuda/std/__functional/identity.h +57 -0
  846. cuda/cccl/headers/include/cuda/std/__functional/invoke.h +298 -0
  847. cuda/cccl/headers/include/cuda/std/__functional/is_transparent.h +41 -0
  848. cuda/cccl/headers/include/cuda/std/__functional/mem_fn.h +66 -0
  849. cuda/cccl/headers/include/cuda/std/__functional/mem_fun_ref.h +211 -0
  850. cuda/cccl/headers/include/cuda/std/__functional/not_fn.h +120 -0
  851. cuda/cccl/headers/include/cuda/std/__functional/operations.h +535 -0
  852. cuda/cccl/headers/include/cuda/std/__functional/perfect_forward.h +128 -0
  853. cuda/cccl/headers/include/cuda/std/__functional/pointer_to_binary_function.h +64 -0
  854. cuda/cccl/headers/include/cuda/std/__functional/pointer_to_unary_function.h +63 -0
  855. cuda/cccl/headers/include/cuda/std/__functional/ranges_operations.h +113 -0
  856. cuda/cccl/headers/include/cuda/std/__functional/reference_wrapper.h +114 -0
  857. cuda/cccl/headers/include/cuda/std/__functional/unary_function.h +62 -0
  858. cuda/cccl/headers/include/cuda/std/__functional/unary_negate.h +65 -0
  859. cuda/cccl/headers/include/cuda/std/__functional/unwrap_ref.h +56 -0
  860. cuda/cccl/headers/include/cuda/std/__functional/weak_result_type.h +262 -0
  861. cuda/cccl/headers/include/cuda/std/__fwd/allocator.h +53 -0
  862. cuda/cccl/headers/include/cuda/std/__fwd/array.h +42 -0
  863. cuda/cccl/headers/include/cuda/std/__fwd/char_traits.h +74 -0
  864. cuda/cccl/headers/include/cuda/std/__fwd/complex.h +75 -0
  865. cuda/cccl/headers/include/cuda/std/__fwd/execution_policy.h +73 -0
  866. cuda/cccl/headers/include/cuda/std/__fwd/expected.h +46 -0
  867. cuda/cccl/headers/include/cuda/std/__fwd/format.h +84 -0
  868. cuda/cccl/headers/include/cuda/std/__fwd/fp.h +37 -0
  869. cuda/cccl/headers/include/cuda/std/__fwd/get.h +122 -0
  870. cuda/cccl/headers/include/cuda/std/__fwd/hash.h +34 -0
  871. cuda/cccl/headers/include/cuda/std/__fwd/ios.h +123 -0
  872. cuda/cccl/headers/include/cuda/std/__fwd/iterator.h +43 -0
  873. cuda/cccl/headers/include/cuda/std/__fwd/mdspan.h +122 -0
  874. cuda/cccl/headers/include/cuda/std/__fwd/memory_resource.h +37 -0
  875. cuda/cccl/headers/include/cuda/std/__fwd/optional.h +39 -0
  876. cuda/cccl/headers/include/cuda/std/__fwd/pair.h +47 -0
  877. cuda/cccl/headers/include/cuda/std/__fwd/reference_wrapper.h +39 -0
  878. cuda/cccl/headers/include/cuda/std/__fwd/span.h +45 -0
  879. cuda/cccl/headers/include/cuda/std/__fwd/string.h +112 -0
  880. cuda/cccl/headers/include/cuda/std/__fwd/string_view.h +91 -0
  881. cuda/cccl/headers/include/cuda/std/__fwd/subrange.h +55 -0
  882. cuda/cccl/headers/include/cuda/std/__fwd/tuple.h +37 -0
  883. cuda/cccl/headers/include/cuda/std/__fwd/unexpected.h +40 -0
  884. cuda/cccl/headers/include/cuda/std/__fwd/variant.h +51 -0
  885. cuda/cccl/headers/include/cuda/std/__internal/atomic.h +55 -0
  886. cuda/cccl/headers/include/cuda/std/__internal/cpp_dialect.h +44 -0
  887. cuda/cccl/headers/include/cuda/std/__internal/features.h +104 -0
  888. cuda/cccl/headers/include/cuda/std/__internal/namespaces.h +132 -0
  889. cuda/cccl/headers/include/cuda/std/__internal/pstl_config.h +32 -0
  890. cuda/cccl/headers/include/cuda/std/__internal/thread_api.h +58 -0
  891. cuda/cccl/headers/include/cuda/std/__internal/version.h +52 -0
  892. cuda/cccl/headers/include/cuda/std/__iterator/access.h +128 -0
  893. cuda/cccl/headers/include/cuda/std/__iterator/advance.h +227 -0
  894. cuda/cccl/headers/include/cuda/std/__iterator/back_insert_iterator.h +164 -0
  895. cuda/cccl/headers/include/cuda/std/__iterator/bounded_iter.h +253 -0
  896. cuda/cccl/headers/include/cuda/std/__iterator/concepts.h +645 -0
  897. cuda/cccl/headers/include/cuda/std/__iterator/counted_iterator.h +465 -0
  898. cuda/cccl/headers/include/cuda/std/__iterator/data.h +61 -0
  899. cuda/cccl/headers/include/cuda/std/__iterator/default_sentinel.h +36 -0
  900. cuda/cccl/headers/include/cuda/std/__iterator/distance.h +124 -0
  901. cuda/cccl/headers/include/cuda/std/__iterator/empty.h +53 -0
  902. cuda/cccl/headers/include/cuda/std/__iterator/erase_if_container.h +53 -0
  903. cuda/cccl/headers/include/cuda/std/__iterator/front_insert_iterator.h +100 -0
  904. cuda/cccl/headers/include/cuda/std/__iterator/incrementable_traits.h +143 -0
  905. cuda/cccl/headers/include/cuda/std/__iterator/indirectly_comparable.h +55 -0
  906. cuda/cccl/headers/include/cuda/std/__iterator/insert_iterator.h +107 -0
  907. cuda/cccl/headers/include/cuda/std/__iterator/istream_iterator.h +146 -0
  908. cuda/cccl/headers/include/cuda/std/__iterator/istreambuf_iterator.h +161 -0
  909. cuda/cccl/headers/include/cuda/std/__iterator/iter_move.h +161 -0
  910. cuda/cccl/headers/include/cuda/std/__iterator/iter_swap.h +181 -0
  911. cuda/cccl/headers/include/cuda/std/__iterator/iterator.h +44 -0
  912. cuda/cccl/headers/include/cuda/std/__iterator/iterator_traits.h +847 -0
  913. cuda/cccl/headers/include/cuda/std/__iterator/mergeable.h +72 -0
  914. cuda/cccl/headers/include/cuda/std/__iterator/move_iterator.h +432 -0
  915. cuda/cccl/headers/include/cuda/std/__iterator/move_sentinel.h +73 -0
  916. cuda/cccl/headers/include/cuda/std/__iterator/next.h +101 -0
  917. cuda/cccl/headers/include/cuda/std/__iterator/ostream_iterator.h +95 -0
  918. cuda/cccl/headers/include/cuda/std/__iterator/ostreambuf_iterator.h +100 -0
  919. cuda/cccl/headers/include/cuda/std/__iterator/permutable.h +54 -0
  920. cuda/cccl/headers/include/cuda/std/__iterator/prev.h +90 -0
  921. cuda/cccl/headers/include/cuda/std/__iterator/projected.h +61 -0
  922. cuda/cccl/headers/include/cuda/std/__iterator/readable_traits.h +156 -0
  923. cuda/cccl/headers/include/cuda/std/__iterator/reverse_access.h +142 -0
  924. cuda/cccl/headers/include/cuda/std/__iterator/reverse_iterator.h +366 -0
  925. cuda/cccl/headers/include/cuda/std/__iterator/size.h +69 -0
  926. cuda/cccl/headers/include/cuda/std/__iterator/sortable.h +55 -0
  927. cuda/cccl/headers/include/cuda/std/__iterator/unreachable_sentinel.h +84 -0
  928. cuda/cccl/headers/include/cuda/std/__iterator/wrap_iter.h +245 -0
  929. cuda/cccl/headers/include/cuda/std/__latch/latch.h +88 -0
  930. cuda/cccl/headers/include/cuda/std/__limits/numeric_limits.h +603 -0
  931. cuda/cccl/headers/include/cuda/std/__limits/numeric_limits_ext.h +753 -0
  932. cuda/cccl/headers/include/cuda/std/__linalg/conj_if_needed.h +76 -0
  933. cuda/cccl/headers/include/cuda/std/__linalg/conjugate_transposed.h +52 -0
  934. cuda/cccl/headers/include/cuda/std/__linalg/conjugated.h +136 -0
  935. cuda/cccl/headers/include/cuda/std/__linalg/scaled.h +128 -0
  936. cuda/cccl/headers/include/cuda/std/__linalg/transposed.h +315 -0
  937. cuda/cccl/headers/include/cuda/std/__mdspan/aligned_accessor.h +97 -0
  938. cuda/cccl/headers/include/cuda/std/__mdspan/concepts.h +137 -0
  939. cuda/cccl/headers/include/cuda/std/__mdspan/default_accessor.h +73 -0
  940. cuda/cccl/headers/include/cuda/std/__mdspan/empty_base.h +348 -0
  941. cuda/cccl/headers/include/cuda/std/__mdspan/extents.h +749 -0
  942. cuda/cccl/headers/include/cuda/std/__mdspan/layout_left.h +314 -0
  943. cuda/cccl/headers/include/cuda/std/__mdspan/layout_right.h +307 -0
  944. cuda/cccl/headers/include/cuda/std/__mdspan/layout_stride.h +598 -0
  945. cuda/cccl/headers/include/cuda/std/__mdspan/mdspan.h +515 -0
  946. cuda/cccl/headers/include/cuda/std/__mdspan/submdspan_extents.h +190 -0
  947. cuda/cccl/headers/include/cuda/std/__mdspan/submdspan_helper.h +187 -0
  948. cuda/cccl/headers/include/cuda/std/__mdspan/submdspan_mapping.h +339 -0
  949. cuda/cccl/headers/include/cuda/std/__memory/addressof.h +90 -0
  950. cuda/cccl/headers/include/cuda/std/__memory/align.h +67 -0
  951. cuda/cccl/headers/include/cuda/std/__memory/allocate_at_least.h +82 -0
  952. cuda/cccl/headers/include/cuda/std/__memory/allocation_guard.h +100 -0
  953. cuda/cccl/headers/include/cuda/std/__memory/allocator.h +327 -0
  954. cuda/cccl/headers/include/cuda/std/__memory/allocator_arg_t.h +85 -0
  955. cuda/cccl/headers/include/cuda/std/__memory/allocator_destructor.h +59 -0
  956. cuda/cccl/headers/include/cuda/std/__memory/allocator_traits.h +517 -0
  957. cuda/cccl/headers/include/cuda/std/__memory/assume_aligned.h +59 -0
  958. cuda/cccl/headers/include/cuda/std/__memory/builtin_new_allocator.h +87 -0
  959. cuda/cccl/headers/include/cuda/std/__memory/compressed_pair.h +225 -0
  960. cuda/cccl/headers/include/cuda/std/__memory/construct_at.h +241 -0
  961. cuda/cccl/headers/include/cuda/std/__memory/destruct_n.h +91 -0
  962. cuda/cccl/headers/include/cuda/std/__memory/is_sufficiently_aligned.h +51 -0
  963. cuda/cccl/headers/include/cuda/std/__memory/pointer_traits.h +246 -0
  964. cuda/cccl/headers/include/cuda/std/__memory/runtime_assume_aligned.h +62 -0
  965. cuda/cccl/headers/include/cuda/std/__memory/temporary_buffer.h +99 -0
  966. cuda/cccl/headers/include/cuda/std/__memory/uninitialized_algorithms.h +678 -0
  967. cuda/cccl/headers/include/cuda/std/__memory/unique_ptr.h +765 -0
  968. cuda/cccl/headers/include/cuda/std/__memory/uses_allocator.h +59 -0
  969. cuda/cccl/headers/include/cuda/std/__memory/voidify.h +41 -0
  970. cuda/cccl/headers/include/cuda/std/__memory_ +34 -0
  971. cuda/cccl/headers/include/cuda/std/__new/allocate.h +131 -0
  972. cuda/cccl/headers/include/cuda/std/__new/bad_alloc.h +57 -0
  973. cuda/cccl/headers/include/cuda/std/__new/device_new.h +30 -0
  974. cuda/cccl/headers/include/cuda/std/__new/launder.h +53 -0
  975. cuda/cccl/headers/include/cuda/std/__new_ +30 -0
  976. cuda/cccl/headers/include/cuda/std/__numeric/accumulate.h +56 -0
  977. cuda/cccl/headers/include/cuda/std/__numeric/adjacent_difference.h +72 -0
  978. cuda/cccl/headers/include/cuda/std/__numeric/exclusive_scan.h +66 -0
  979. cuda/cccl/headers/include/cuda/std/__numeric/gcd_lcm.h +78 -0
  980. cuda/cccl/headers/include/cuda/std/__numeric/inclusive_scan.h +73 -0
  981. cuda/cccl/headers/include/cuda/std/__numeric/inner_product.h +62 -0
  982. cuda/cccl/headers/include/cuda/std/__numeric/iota.h +42 -0
  983. cuda/cccl/headers/include/cuda/std/__numeric/midpoint.h +97 -0
  984. cuda/cccl/headers/include/cuda/std/__numeric/partial_sum.h +69 -0
  985. cuda/cccl/headers/include/cuda/std/__numeric/reduce.h +60 -0
  986. cuda/cccl/headers/include/cuda/std/__numeric/transform_exclusive_scan.h +51 -0
  987. cuda/cccl/headers/include/cuda/std/__numeric/transform_inclusive_scan.h +65 -0
  988. cuda/cccl/headers/include/cuda/std/__numeric/transform_reduce.h +72 -0
  989. cuda/cccl/headers/include/cuda/std/__optional/bad_optional_access.h +74 -0
  990. cuda/cccl/headers/include/cuda/std/__optional/hash.h +53 -0
  991. cuda/cccl/headers/include/cuda/std/__optional/make_optional.h +61 -0
  992. cuda/cccl/headers/include/cuda/std/__optional/nullopt.h +43 -0
  993. cuda/cccl/headers/include/cuda/std/__optional/optional.h +861 -0
  994. cuda/cccl/headers/include/cuda/std/__optional/optional_base.h +439 -0
  995. cuda/cccl/headers/include/cuda/std/__optional/optional_ref.h +324 -0
  996. cuda/cccl/headers/include/cuda/std/__pstl/cuda/for_each_n.h +97 -0
  997. cuda/cccl/headers/include/cuda/std/__pstl/dispatch.h +123 -0
  998. cuda/cccl/headers/include/cuda/std/__pstl/for_each.h +71 -0
  999. cuda/cccl/headers/include/cuda/std/__pstl/for_each_n.h +68 -0
  1000. cuda/cccl/headers/include/cuda/std/__random/bernoulli_distribution.h +173 -0
  1001. cuda/cccl/headers/include/cuda/std/__random/binomial_distribution.h +254 -0
  1002. cuda/cccl/headers/include/cuda/std/__random/cauchy_distribution.h +192 -0
  1003. cuda/cccl/headers/include/cuda/std/__random/chi_squared_distribution.h +179 -0
  1004. cuda/cccl/headers/include/cuda/std/__random/exponential_distribution.h +187 -0
  1005. cuda/cccl/headers/include/cuda/std/__random/extreme_value_distribution.h +196 -0
  1006. cuda/cccl/headers/include/cuda/std/__random/fisher_f_distribution.h +196 -0
  1007. cuda/cccl/headers/include/cuda/std/__random/gamma_distribution.h +257 -0
  1008. cuda/cccl/headers/include/cuda/std/__random/generate_canonical.h +56 -0
  1009. cuda/cccl/headers/include/cuda/std/__random/geometric_distribution.h +179 -0
  1010. cuda/cccl/headers/include/cuda/std/__random/is_seed_sequence.h +39 -0
  1011. cuda/cccl/headers/include/cuda/std/__random/is_valid.h +70 -0
  1012. cuda/cccl/headers/include/cuda/std/__random/linear_congruential_engine.h +398 -0
  1013. cuda/cccl/headers/include/cuda/std/__random/lognormal_distribution.h +174 -0
  1014. cuda/cccl/headers/include/cuda/std/__random/negative_binomial_distribution.h +212 -0
  1015. cuda/cccl/headers/include/cuda/std/__random/normal_distribution.h +232 -0
  1016. cuda/cccl/headers/include/cuda/std/__random/philox_engine.h +562 -0
  1017. cuda/cccl/headers/include/cuda/std/__random/poisson_distribution.h +338 -0
  1018. cuda/cccl/headers/include/cuda/std/__random/seed_seq.h +204 -0
  1019. cuda/cccl/headers/include/cuda/std/__random/student_t_distribution.h +186 -0
  1020. cuda/cccl/headers/include/cuda/std/__random/uniform_int_distribution.h +341 -0
  1021. cuda/cccl/headers/include/cuda/std/__random/uniform_real_distribution.h +192 -0
  1022. cuda/cccl/headers/include/cuda/std/__random/weibull_distribution.h +189 -0
  1023. cuda/cccl/headers/include/cuda/std/__random_ +47 -0
  1024. cuda/cccl/headers/include/cuda/std/__ranges/access.h +303 -0
  1025. cuda/cccl/headers/include/cuda/std/__ranges/all.h +98 -0
  1026. cuda/cccl/headers/include/cuda/std/__ranges/compressed_movable_box.h +889 -0
  1027. cuda/cccl/headers/include/cuda/std/__ranges/concepts.h +302 -0
  1028. cuda/cccl/headers/include/cuda/std/__ranges/counted.h +90 -0
  1029. cuda/cccl/headers/include/cuda/std/__ranges/dangling.h +54 -0
  1030. cuda/cccl/headers/include/cuda/std/__ranges/data.h +136 -0
  1031. cuda/cccl/headers/include/cuda/std/__ranges/drop_view.h +389 -0
  1032. cuda/cccl/headers/include/cuda/std/__ranges/empty.h +109 -0
  1033. cuda/cccl/headers/include/cuda/std/__ranges/empty_view.h +77 -0
  1034. cuda/cccl/headers/include/cuda/std/__ranges/enable_borrowed_range.h +41 -0
  1035. cuda/cccl/headers/include/cuda/std/__ranges/enable_view.h +78 -0
  1036. cuda/cccl/headers/include/cuda/std/__ranges/from_range.h +36 -0
  1037. cuda/cccl/headers/include/cuda/std/__ranges/iota_view.h +264 -0
  1038. cuda/cccl/headers/include/cuda/std/__ranges/movable_box.h +409 -0
  1039. cuda/cccl/headers/include/cuda/std/__ranges/non_propagating_cache.h +210 -0
  1040. cuda/cccl/headers/include/cuda/std/__ranges/owning_view.h +163 -0
  1041. cuda/cccl/headers/include/cuda/std/__ranges/range_adaptor.h +111 -0
  1042. cuda/cccl/headers/include/cuda/std/__ranges/rbegin.h +175 -0
  1043. cuda/cccl/headers/include/cuda/std/__ranges/ref_view.h +121 -0
  1044. cuda/cccl/headers/include/cuda/std/__ranges/rend.h +182 -0
  1045. cuda/cccl/headers/include/cuda/std/__ranges/repeat_view.h +346 -0
  1046. cuda/cccl/headers/include/cuda/std/__ranges/single_view.h +155 -0
  1047. cuda/cccl/headers/include/cuda/std/__ranges/size.h +201 -0
  1048. cuda/cccl/headers/include/cuda/std/__ranges/subrange.h +510 -0
  1049. cuda/cccl/headers/include/cuda/std/__ranges/take_view.h +472 -0
  1050. cuda/cccl/headers/include/cuda/std/__ranges/take_while_view.h +259 -0
  1051. cuda/cccl/headers/include/cuda/std/__ranges/transform_view.h +522 -0
  1052. cuda/cccl/headers/include/cuda/std/__ranges/unwrap_end.h +52 -0
  1053. cuda/cccl/headers/include/cuda/std/__ranges/view_interface.h +183 -0
  1054. cuda/cccl/headers/include/cuda/std/__ranges/views.h +38 -0
  1055. cuda/cccl/headers/include/cuda/std/__semaphore/atomic_semaphore.h +234 -0
  1056. cuda/cccl/headers/include/cuda/std/__semaphore/counting_semaphore.h +51 -0
  1057. cuda/cccl/headers/include/cuda/std/__string/char_traits.h +190 -0
  1058. cuda/cccl/headers/include/cuda/std/__string/constexpr_c_functions.h +580 -0
  1059. cuda/cccl/headers/include/cuda/std/__string/helper_functions.h +296 -0
  1060. cuda/cccl/headers/include/cuda/std/__string/string_view.h +244 -0
  1061. cuda/cccl/headers/include/cuda/std/__string_ +29 -0
  1062. cuda/cccl/headers/include/cuda/std/__system_error/errc.h +51 -0
  1063. cuda/cccl/headers/include/cuda/std/__system_error_ +26 -0
  1064. cuda/cccl/headers/include/cuda/std/__thread/threading_support.h +106 -0
  1065. cuda/cccl/headers/include/cuda/std/__thread/threading_support_cuda.h +47 -0
  1066. cuda/cccl/headers/include/cuda/std/__thread/threading_support_external.h +41 -0
  1067. cuda/cccl/headers/include/cuda/std/__thread/threading_support_pthread.h +143 -0
  1068. cuda/cccl/headers/include/cuda/std/__thread/threading_support_win32.h +87 -0
  1069. cuda/cccl/headers/include/cuda/std/__tuple_dir/apply.h +82 -0
  1070. cuda/cccl/headers/include/cuda/std/__tuple_dir/get.h +122 -0
  1071. cuda/cccl/headers/include/cuda/std/__tuple_dir/ignore.h +51 -0
  1072. cuda/cccl/headers/include/cuda/std/__tuple_dir/make_tuple_types.h +120 -0
  1073. cuda/cccl/headers/include/cuda/std/__tuple_dir/sfinae_helpers.h +100 -0
  1074. cuda/cccl/headers/include/cuda/std/__tuple_dir/structured_bindings.h +212 -0
  1075. cuda/cccl/headers/include/cuda/std/__tuple_dir/tie.h +55 -0
  1076. cuda/cccl/headers/include/cuda/std/__tuple_dir/tuple.h +457 -0
  1077. cuda/cccl/headers/include/cuda/std/__tuple_dir/tuple_cat.h +158 -0
  1078. cuda/cccl/headers/include/cuda/std/__tuple_dir/tuple_constraints.h +286 -0
  1079. cuda/cccl/headers/include/cuda/std/__tuple_dir/tuple_element.h +77 -0
  1080. cuda/cccl/headers/include/cuda/std/__tuple_dir/tuple_indices.h +44 -0
  1081. cuda/cccl/headers/include/cuda/std/__tuple_dir/tuple_leaf.h +452 -0
  1082. cuda/cccl/headers/include/cuda/std/__tuple_dir/tuple_like.h +83 -0
  1083. cuda/cccl/headers/include/cuda/std/__tuple_dir/tuple_like_ext.h +68 -0
  1084. cuda/cccl/headers/include/cuda/std/__tuple_dir/tuple_size.h +79 -0
  1085. cuda/cccl/headers/include/cuda/std/__tuple_dir/tuple_types.h +35 -0
  1086. cuda/cccl/headers/include/cuda/std/__tuple_dir/vector_types.h +290 -0
  1087. cuda/cccl/headers/include/cuda/std/__type_traits/add_const.h +40 -0
  1088. cuda/cccl/headers/include/cuda/std/__type_traits/add_cv.h +40 -0
  1089. cuda/cccl/headers/include/cuda/std/__type_traits/add_lvalue_reference.h +62 -0
  1090. cuda/cccl/headers/include/cuda/std/__type_traits/add_pointer.h +65 -0
  1091. cuda/cccl/headers/include/cuda/std/__type_traits/add_rvalue_reference.h +62 -0
  1092. cuda/cccl/headers/include/cuda/std/__type_traits/add_volatile.h +40 -0
  1093. cuda/cccl/headers/include/cuda/std/__type_traits/aligned_storage.h +155 -0
  1094. cuda/cccl/headers/include/cuda/std/__type_traits/aligned_union.h +62 -0
  1095. cuda/cccl/headers/include/cuda/std/__type_traits/alignment_of.h +41 -0
  1096. cuda/cccl/headers/include/cuda/std/__type_traits/always_false.h +35 -0
  1097. cuda/cccl/headers/include/cuda/std/__type_traits/can_extract_key.h +68 -0
  1098. cuda/cccl/headers/include/cuda/std/__type_traits/common_reference.h +262 -0
  1099. cuda/cccl/headers/include/cuda/std/__type_traits/common_type.h +173 -0
  1100. cuda/cccl/headers/include/cuda/std/__type_traits/conditional.h +65 -0
  1101. cuda/cccl/headers/include/cuda/std/__type_traits/conjunction.h +67 -0
  1102. cuda/cccl/headers/include/cuda/std/__type_traits/copy_cv.h +50 -0
  1103. cuda/cccl/headers/include/cuda/std/__type_traits/copy_cvref.h +148 -0
  1104. cuda/cccl/headers/include/cuda/std/__type_traits/decay.h +83 -0
  1105. cuda/cccl/headers/include/cuda/std/__type_traits/dependent_type.h +35 -0
  1106. cuda/cccl/headers/include/cuda/std/__type_traits/disjunction.h +77 -0
  1107. cuda/cccl/headers/include/cuda/std/__type_traits/enable_if.h +43 -0
  1108. cuda/cccl/headers/include/cuda/std/__type_traits/extent.h +68 -0
  1109. cuda/cccl/headers/include/cuda/std/__type_traits/fold.h +47 -0
  1110. cuda/cccl/headers/include/cuda/std/__type_traits/has_unique_object_representation.h +46 -0
  1111. cuda/cccl/headers/include/cuda/std/__type_traits/has_virtual_destructor.h +42 -0
  1112. cuda/cccl/headers/include/cuda/std/__type_traits/integral_constant.h +62 -0
  1113. cuda/cccl/headers/include/cuda/std/__type_traits/is_abstract.h +42 -0
  1114. cuda/cccl/headers/include/cuda/std/__type_traits/is_aggregate.h +42 -0
  1115. cuda/cccl/headers/include/cuda/std/__type_traits/is_allocator.h +46 -0
  1116. cuda/cccl/headers/include/cuda/std/__type_traits/is_arithmetic.h +42 -0
  1117. cuda/cccl/headers/include/cuda/std/__type_traits/is_array.h +62 -0
  1118. cuda/cccl/headers/include/cuda/std/__type_traits/is_assignable.h +78 -0
  1119. cuda/cccl/headers/include/cuda/std/__type_traits/is_base_of.h +42 -0
  1120. cuda/cccl/headers/include/cuda/std/__type_traits/is_bounded_array.h +44 -0
  1121. cuda/cccl/headers/include/cuda/std/__type_traits/is_callable.h +60 -0
  1122. cuda/cccl/headers/include/cuda/std/__type_traits/is_char_like_type.h +38 -0
  1123. cuda/cccl/headers/include/cuda/std/__type_traits/is_class.h +42 -0
  1124. cuda/cccl/headers/include/cuda/std/__type_traits/is_comparable.h +78 -0
  1125. cuda/cccl/headers/include/cuda/std/__type_traits/is_compound.h +58 -0
  1126. cuda/cccl/headers/include/cuda/std/__type_traits/is_const.h +56 -0
  1127. cuda/cccl/headers/include/cuda/std/__type_traits/is_constant_evaluated.h +49 -0
  1128. cuda/cccl/headers/include/cuda/std/__type_traits/is_constructible.h +174 -0
  1129. cuda/cccl/headers/include/cuda/std/__type_traits/is_convertible.h +211 -0
  1130. cuda/cccl/headers/include/cuda/std/__type_traits/is_copy_assignable.h +43 -0
  1131. cuda/cccl/headers/include/cuda/std/__type_traits/is_copy_constructible.h +43 -0
  1132. cuda/cccl/headers/include/cuda/std/__type_traits/is_core_convertible.h +47 -0
  1133. cuda/cccl/headers/include/cuda/std/__type_traits/is_corresponding_member.h +42 -0
  1134. cuda/cccl/headers/include/cuda/std/__type_traits/is_default_constructible.h +40 -0
  1135. cuda/cccl/headers/include/cuda/std/__type_traits/is_destructible.h +115 -0
  1136. cuda/cccl/headers/include/cuda/std/__type_traits/is_empty.h +42 -0
  1137. cuda/cccl/headers/include/cuda/std/__type_traits/is_enum.h +42 -0
  1138. cuda/cccl/headers/include/cuda/std/__type_traits/is_execution_policy.h +63 -0
  1139. cuda/cccl/headers/include/cuda/std/__type_traits/is_extended_arithmetic.h +38 -0
  1140. cuda/cccl/headers/include/cuda/std/__type_traits/is_extended_floating_point.h +79 -0
  1141. cuda/cccl/headers/include/cuda/std/__type_traits/is_final.h +42 -0
  1142. cuda/cccl/headers/include/cuda/std/__type_traits/is_floating_point.h +53 -0
  1143. cuda/cccl/headers/include/cuda/std/__type_traits/is_fully_bounded_array.h +47 -0
  1144. cuda/cccl/headers/include/cuda/std/__type_traits/is_function.h +61 -0
  1145. cuda/cccl/headers/include/cuda/std/__type_traits/is_fundamental.h +56 -0
  1146. cuda/cccl/headers/include/cuda/std/__type_traits/is_implicitly_default_constructible.h +57 -0
  1147. cuda/cccl/headers/include/cuda/std/__type_traits/is_integer.h +45 -0
  1148. cuda/cccl/headers/include/cuda/std/__type_traits/is_integral.h +123 -0
  1149. cuda/cccl/headers/include/cuda/std/__type_traits/is_layout_compatible.h +45 -0
  1150. cuda/cccl/headers/include/cuda/std/__type_traits/is_literal_type.h +42 -0
  1151. cuda/cccl/headers/include/cuda/std/__type_traits/is_member_function_pointer.h +79 -0
  1152. cuda/cccl/headers/include/cuda/std/__type_traits/is_member_object_pointer.h +57 -0
  1153. cuda/cccl/headers/include/cuda/std/__type_traits/is_member_pointer.h +57 -0
  1154. cuda/cccl/headers/include/cuda/std/__type_traits/is_move_assignable.h +43 -0
  1155. cuda/cccl/headers/include/cuda/std/__type_traits/is_move_constructible.h +42 -0
  1156. cuda/cccl/headers/include/cuda/std/__type_traits/is_nothrow_assignable.h +70 -0
  1157. cuda/cccl/headers/include/cuda/std/__type_traits/is_nothrow_constructible.h +72 -0
  1158. cuda/cccl/headers/include/cuda/std/__type_traits/is_nothrow_convertible.h +59 -0
  1159. cuda/cccl/headers/include/cuda/std/__type_traits/is_nothrow_copy_assignable.h +60 -0
  1160. cuda/cccl/headers/include/cuda/std/__type_traits/is_nothrow_copy_constructible.h +43 -0
  1161. cuda/cccl/headers/include/cuda/std/__type_traits/is_nothrow_default_constructible.h +54 -0
  1162. cuda/cccl/headers/include/cuda/std/__type_traits/is_nothrow_destructible.h +82 -0
  1163. cuda/cccl/headers/include/cuda/std/__type_traits/is_nothrow_move_assignable.h +60 -0
  1164. cuda/cccl/headers/include/cuda/std/__type_traits/is_nothrow_move_constructible.h +42 -0
  1165. cuda/cccl/headers/include/cuda/std/__type_traits/is_null_pointer.h +43 -0
  1166. cuda/cccl/headers/include/cuda/std/__type_traits/is_object.h +57 -0
  1167. cuda/cccl/headers/include/cuda/std/__type_traits/is_one_of.h +37 -0
  1168. cuda/cccl/headers/include/cuda/std/__type_traits/is_pod.h +42 -0
  1169. cuda/cccl/headers/include/cuda/std/__type_traits/is_pointer.h +60 -0
  1170. cuda/cccl/headers/include/cuda/std/__type_traits/is_pointer_interconvertible_base_of.h +84 -0
  1171. cuda/cccl/headers/include/cuda/std/__type_traits/is_pointer_interconvertible_with_class.h +42 -0
  1172. cuda/cccl/headers/include/cuda/std/__type_traits/is_polymorphic.h +42 -0
  1173. cuda/cccl/headers/include/cuda/std/__type_traits/is_primary_template.h +121 -0
  1174. cuda/cccl/headers/include/cuda/std/__type_traits/is_reference.h +95 -0
  1175. cuda/cccl/headers/include/cuda/std/__type_traits/is_referenceable.h +55 -0
  1176. cuda/cccl/headers/include/cuda/std/__type_traits/is_same.h +88 -0
  1177. cuda/cccl/headers/include/cuda/std/__type_traits/is_scalar.h +60 -0
  1178. cuda/cccl/headers/include/cuda/std/__type_traits/is_scoped_enum.h +49 -0
  1179. cuda/cccl/headers/include/cuda/std/__type_traits/is_signed.h +65 -0
  1180. cuda/cccl/headers/include/cuda/std/__type_traits/is_signed_integer.h +59 -0
  1181. cuda/cccl/headers/include/cuda/std/__type_traits/is_standard_layout.h +42 -0
  1182. cuda/cccl/headers/include/cuda/std/__type_traits/is_swappable.h +200 -0
  1183. cuda/cccl/headers/include/cuda/std/__type_traits/is_trivial.h +42 -0
  1184. cuda/cccl/headers/include/cuda/std/__type_traits/is_trivially_assignable.h +43 -0
  1185. cuda/cccl/headers/include/cuda/std/__type_traits/is_trivially_constructible.h +43 -0
  1186. cuda/cccl/headers/include/cuda/std/__type_traits/is_trivially_copy_assignable.h +46 -0
  1187. cuda/cccl/headers/include/cuda/std/__type_traits/is_trivially_copy_constructible.h +45 -0
  1188. cuda/cccl/headers/include/cuda/std/__type_traits/is_trivially_copyable.h +42 -0
  1189. cuda/cccl/headers/include/cuda/std/__type_traits/is_trivially_default_constructible.h +42 -0
  1190. cuda/cccl/headers/include/cuda/std/__type_traits/is_trivially_destructible.h +58 -0
  1191. cuda/cccl/headers/include/cuda/std/__type_traits/is_trivially_move_assignable.h +45 -0
  1192. cuda/cccl/headers/include/cuda/std/__type_traits/is_trivially_move_constructible.h +44 -0
  1193. cuda/cccl/headers/include/cuda/std/__type_traits/is_unbounded_array.h +43 -0
  1194. cuda/cccl/headers/include/cuda/std/__type_traits/is_union.h +42 -0
  1195. cuda/cccl/headers/include/cuda/std/__type_traits/is_unsigned.h +66 -0
  1196. cuda/cccl/headers/include/cuda/std/__type_traits/is_unsigned_integer.h +59 -0
  1197. cuda/cccl/headers/include/cuda/std/__type_traits/is_valid_expansion.h +41 -0
  1198. cuda/cccl/headers/include/cuda/std/__type_traits/is_void.h +55 -0
  1199. cuda/cccl/headers/include/cuda/std/__type_traits/is_volatile.h +56 -0
  1200. cuda/cccl/headers/include/cuda/std/__type_traits/lazy.h +35 -0
  1201. cuda/cccl/headers/include/cuda/std/__type_traits/make_const_lvalue_ref.h +36 -0
  1202. cuda/cccl/headers/include/cuda/std/__type_traits/make_nbit_int.h +107 -0
  1203. cuda/cccl/headers/include/cuda/std/__type_traits/make_signed.h +140 -0
  1204. cuda/cccl/headers/include/cuda/std/__type_traits/make_unsigned.h +151 -0
  1205. cuda/cccl/headers/include/cuda/std/__type_traits/maybe_const.h +36 -0
  1206. cuda/cccl/headers/include/cuda/std/__type_traits/nat.h +39 -0
  1207. cuda/cccl/headers/include/cuda/std/__type_traits/negation.h +44 -0
  1208. cuda/cccl/headers/include/cuda/std/__type_traits/num_bits.h +122 -0
  1209. cuda/cccl/headers/include/cuda/std/__type_traits/promote.h +163 -0
  1210. cuda/cccl/headers/include/cuda/std/__type_traits/rank.h +60 -0
  1211. cuda/cccl/headers/include/cuda/std/__type_traits/reference_constructs_from_temporary.h +57 -0
  1212. cuda/cccl/headers/include/cuda/std/__type_traits/reference_converts_from_temporary.h +56 -0
  1213. cuda/cccl/headers/include/cuda/std/__type_traits/remove_all_extents.h +66 -0
  1214. cuda/cccl/headers/include/cuda/std/__type_traits/remove_const.h +59 -0
  1215. cuda/cccl/headers/include/cuda/std/__type_traits/remove_const_ref.h +37 -0
  1216. cuda/cccl/headers/include/cuda/std/__type_traits/remove_cv.h +57 -0
  1217. cuda/cccl/headers/include/cuda/std/__type_traits/remove_cvref.h +57 -0
  1218. cuda/cccl/headers/include/cuda/std/__type_traits/remove_extent.h +65 -0
  1219. cuda/cccl/headers/include/cuda/std/__type_traits/remove_pointer.h +73 -0
  1220. cuda/cccl/headers/include/cuda/std/__type_traits/remove_reference.h +72 -0
  1221. cuda/cccl/headers/include/cuda/std/__type_traits/remove_volatile.h +58 -0
  1222. cuda/cccl/headers/include/cuda/std/__type_traits/result_of.h +47 -0
  1223. cuda/cccl/headers/include/cuda/std/__type_traits/type_identity.h +40 -0
  1224. cuda/cccl/headers/include/cuda/std/__type_traits/type_list.h +1067 -0
  1225. cuda/cccl/headers/include/cuda/std/__type_traits/type_set.h +131 -0
  1226. cuda/cccl/headers/include/cuda/std/__type_traits/underlying_type.h +52 -0
  1227. cuda/cccl/headers/include/cuda/std/__type_traits/void_t.h +34 -0
  1228. cuda/cccl/headers/include/cuda/std/__utility/as_const.h +73 -0
  1229. cuda/cccl/headers/include/cuda/std/__utility/auto_cast.h +34 -0
  1230. cuda/cccl/headers/include/cuda/std/__utility/cmp.h +114 -0
  1231. cuda/cccl/headers/include/cuda/std/__utility/convert_to_integral.h +101 -0
  1232. cuda/cccl/headers/include/cuda/std/__utility/ctad_support.h +27 -0
  1233. cuda/cccl/headers/include/cuda/std/__utility/declval.h +76 -0
  1234. cuda/cccl/headers/include/cuda/std/__utility/delegate_constructors.h +51 -0
  1235. cuda/cccl/headers/include/cuda/std/__utility/exception_guard.h +162 -0
  1236. cuda/cccl/headers/include/cuda/std/__utility/exchange.h +46 -0
  1237. cuda/cccl/headers/include/cuda/std/__utility/forward.h +82 -0
  1238. cuda/cccl/headers/include/cuda/std/__utility/forward_like.h +82 -0
  1239. cuda/cccl/headers/include/cuda/std/__utility/in_place.h +86 -0
  1240. cuda/cccl/headers/include/cuda/std/__utility/integer_sequence.h +249 -0
  1241. cuda/cccl/headers/include/cuda/std/__utility/monostate.h +99 -0
  1242. cuda/cccl/headers/include/cuda/std/__utility/move.h +126 -0
  1243. cuda/cccl/headers/include/cuda/std/__utility/pair.h +791 -0
  1244. cuda/cccl/headers/include/cuda/std/__utility/piecewise_construct.h +37 -0
  1245. cuda/cccl/headers/include/cuda/std/__utility/pod_tuple.h +425 -0
  1246. cuda/cccl/headers/include/cuda/std/__utility/priority_tag.h +40 -0
  1247. cuda/cccl/headers/include/cuda/std/__utility/rel_ops.h +61 -0
  1248. cuda/cccl/headers/include/cuda/std/__utility/swap.h +64 -0
  1249. cuda/cccl/headers/include/cuda/std/__utility/to_underlying.h +40 -0
  1250. cuda/cccl/headers/include/cuda/std/__utility/typeid.h +421 -0
  1251. cuda/cccl/headers/include/cuda/std/__utility/undefined.h +34 -0
  1252. cuda/cccl/headers/include/cuda/std/__utility/unreachable.h +37 -0
  1253. cuda/cccl/headers/include/cuda/std/__variant/bad_variant_access.h +74 -0
  1254. cuda/cccl/headers/include/cuda/std/__variant/comparison.h +207 -0
  1255. cuda/cccl/headers/include/cuda/std/__variant/get.h +192 -0
  1256. cuda/cccl/headers/include/cuda/std/__variant/hash.h +82 -0
  1257. cuda/cccl/headers/include/cuda/std/__variant/sfinae_helpers.h +89 -0
  1258. cuda/cccl/headers/include/cuda/std/__variant/variant.h +250 -0
  1259. cuda/cccl/headers/include/cuda/std/__variant/variant_access.h +70 -0
  1260. cuda/cccl/headers/include/cuda/std/__variant/variant_base.h +683 -0
  1261. cuda/cccl/headers/include/cuda/std/__variant/variant_constraints.h +135 -0
  1262. cuda/cccl/headers/include/cuda/std/__variant/variant_match.h +126 -0
  1263. cuda/cccl/headers/include/cuda/std/__variant/variant_traits.h +184 -0
  1264. cuda/cccl/headers/include/cuda/std/__variant/variant_visit.h +225 -0
  1265. cuda/cccl/headers/include/cuda/std/__variant/visit.h +148 -0
  1266. cuda/cccl/headers/include/cuda/std/algorithm +138 -0
  1267. cuda/cccl/headers/include/cuda/std/array +519 -0
  1268. cuda/cccl/headers/include/cuda/std/atomic +810 -0
  1269. cuda/cccl/headers/include/cuda/std/barrier +42 -0
  1270. cuda/cccl/headers/include/cuda/std/bit +35 -0
  1271. cuda/cccl/headers/include/cuda/std/bitset +986 -0
  1272. cuda/cccl/headers/include/cuda/std/cassert +28 -0
  1273. cuda/cccl/headers/include/cuda/std/ccomplex +15 -0
  1274. cuda/cccl/headers/include/cuda/std/cfloat +59 -0
  1275. cuda/cccl/headers/include/cuda/std/charconv +31 -0
  1276. cuda/cccl/headers/include/cuda/std/chrono +26 -0
  1277. cuda/cccl/headers/include/cuda/std/climits +61 -0
  1278. cuda/cccl/headers/include/cuda/std/cmath +87 -0
  1279. cuda/cccl/headers/include/cuda/std/complex +50 -0
  1280. cuda/cccl/headers/include/cuda/std/concepts +48 -0
  1281. cuda/cccl/headers/include/cuda/std/cstddef +28 -0
  1282. cuda/cccl/headers/include/cuda/std/cstdint +178 -0
  1283. cuda/cccl/headers/include/cuda/std/cstdlib +31 -0
  1284. cuda/cccl/headers/include/cuda/std/cstring +110 -0
  1285. cuda/cccl/headers/include/cuda/std/ctime +155 -0
  1286. cuda/cccl/headers/include/cuda/std/detail/__config +22 -0
  1287. cuda/cccl/headers/include/cuda/std/detail/libcxx/include/chrono +2506 -0
  1288. cuda/cccl/headers/include/cuda/std/execution +29 -0
  1289. cuda/cccl/headers/include/cuda/std/expected +30 -0
  1290. cuda/cccl/headers/include/cuda/std/functional +56 -0
  1291. cuda/cccl/headers/include/cuda/std/initializer_list +44 -0
  1292. cuda/cccl/headers/include/cuda/std/inplace_vector +2171 -0
  1293. cuda/cccl/headers/include/cuda/std/iterator +70 -0
  1294. cuda/cccl/headers/include/cuda/std/latch +34 -0
  1295. cuda/cccl/headers/include/cuda/std/limits +28 -0
  1296. cuda/cccl/headers/include/cuda/std/linalg +30 -0
  1297. cuda/cccl/headers/include/cuda/std/mdspan +38 -0
  1298. cuda/cccl/headers/include/cuda/std/memory +40 -0
  1299. cuda/cccl/headers/include/cuda/std/numbers +344 -0
  1300. cuda/cccl/headers/include/cuda/std/numeric +41 -0
  1301. cuda/cccl/headers/include/cuda/std/optional +31 -0
  1302. cuda/cccl/headers/include/cuda/std/ranges +70 -0
  1303. cuda/cccl/headers/include/cuda/std/ratio +416 -0
  1304. cuda/cccl/headers/include/cuda/std/semaphore +31 -0
  1305. cuda/cccl/headers/include/cuda/std/source_location +107 -0
  1306. cuda/cccl/headers/include/cuda/std/span +599 -0
  1307. cuda/cccl/headers/include/cuda/std/string_view +924 -0
  1308. cuda/cccl/headers/include/cuda/std/tuple +43 -0
  1309. cuda/cccl/headers/include/cuda/std/type_traits +176 -0
  1310. cuda/cccl/headers/include/cuda/std/utility +70 -0
  1311. cuda/cccl/headers/include/cuda/std/variant +32 -0
  1312. cuda/cccl/headers/include/cuda/std/version +240 -0
  1313. cuda/cccl/headers/include/cuda/stream +32 -0
  1314. cuda/cccl/headers/include/cuda/stream_ref +59 -0
  1315. cuda/cccl/headers/include/cuda/tma +25 -0
  1316. cuda/cccl/headers/include/cuda/type_traits +27 -0
  1317. cuda/cccl/headers/include/cuda/utility +28 -0
  1318. cuda/cccl/headers/include/cuda/version +16 -0
  1319. cuda/cccl/headers/include/cuda/warp +28 -0
  1320. cuda/cccl/headers/include/cuda/work_stealing +26 -0
  1321. cuda/cccl/headers/include/nv/detail/__preprocessor +169 -0
  1322. cuda/cccl/headers/include/nv/detail/__target_macros +739 -0
  1323. cuda/cccl/headers/include/nv/target +241 -0
  1324. cuda/cccl/headers/include/thrust/addressof.h +22 -0
  1325. cuda/cccl/headers/include/thrust/adjacent_difference.h +254 -0
  1326. cuda/cccl/headers/include/thrust/advance.h +60 -0
  1327. cuda/cccl/headers/include/thrust/allocate_unique.h +301 -0
  1328. cuda/cccl/headers/include/thrust/binary_search.h +1911 -0
  1329. cuda/cccl/headers/include/thrust/complex.h +859 -0
  1330. cuda/cccl/headers/include/thrust/copy.h +506 -0
  1331. cuda/cccl/headers/include/thrust/count.h +245 -0
  1332. cuda/cccl/headers/include/thrust/detail/adjacent_difference.inl +108 -0
  1333. cuda/cccl/headers/include/thrust/detail/alignment.h +81 -0
  1334. cuda/cccl/headers/include/thrust/detail/allocator/allocator_traits.h +629 -0
  1335. cuda/cccl/headers/include/thrust/detail/allocator/copy_construct_range.h +193 -0
  1336. cuda/cccl/headers/include/thrust/detail/allocator/destroy_range.h +95 -0
  1337. cuda/cccl/headers/include/thrust/detail/allocator/fill_construct_range.h +79 -0
  1338. cuda/cccl/headers/include/thrust/detail/allocator/malloc_allocator.h +76 -0
  1339. cuda/cccl/headers/include/thrust/detail/allocator/no_throw_allocator.h +74 -0
  1340. cuda/cccl/headers/include/thrust/detail/allocator/tagged_allocator.h +113 -0
  1341. cuda/cccl/headers/include/thrust/detail/allocator/temporary_allocator.h +114 -0
  1342. cuda/cccl/headers/include/thrust/detail/allocator/value_initialize_range.h +77 -0
  1343. cuda/cccl/headers/include/thrust/detail/allocator_aware_execution_policy.h +96 -0
  1344. cuda/cccl/headers/include/thrust/detail/binary_search.inl +537 -0
  1345. cuda/cccl/headers/include/thrust/detail/caching_allocator.h +47 -0
  1346. cuda/cccl/headers/include/thrust/detail/complex/arithmetic.h +210 -0
  1347. cuda/cccl/headers/include/thrust/detail/complex/catrig.h +877 -0
  1348. cuda/cccl/headers/include/thrust/detail/complex/catrigf.h +591 -0
  1349. cuda/cccl/headers/include/thrust/detail/complex/ccosh.h +234 -0
  1350. cuda/cccl/headers/include/thrust/detail/complex/ccoshf.h +162 -0
  1351. cuda/cccl/headers/include/thrust/detail/complex/cexp.h +194 -0
  1352. cuda/cccl/headers/include/thrust/detail/complex/cexpf.h +170 -0
  1353. cuda/cccl/headers/include/thrust/detail/complex/clog.h +222 -0
  1354. cuda/cccl/headers/include/thrust/detail/complex/clogf.h +209 -0
  1355. cuda/cccl/headers/include/thrust/detail/complex/complex.inl +263 -0
  1356. cuda/cccl/headers/include/thrust/detail/complex/cpow.h +53 -0
  1357. cuda/cccl/headers/include/thrust/detail/complex/cproj.h +75 -0
  1358. cuda/cccl/headers/include/thrust/detail/complex/csinh.h +228 -0
  1359. cuda/cccl/headers/include/thrust/detail/complex/csinhf.h +169 -0
  1360. cuda/cccl/headers/include/thrust/detail/complex/csqrt.h +178 -0
  1361. cuda/cccl/headers/include/thrust/detail/complex/csqrtf.h +174 -0
  1362. cuda/cccl/headers/include/thrust/detail/complex/ctanh.h +212 -0
  1363. cuda/cccl/headers/include/thrust/detail/complex/ctanhf.h +136 -0
  1364. cuda/cccl/headers/include/thrust/detail/complex/math_private.h +130 -0
  1365. cuda/cccl/headers/include/thrust/detail/complex/stream.h +73 -0
  1366. cuda/cccl/headers/include/thrust/detail/config/compiler.h +38 -0
  1367. cuda/cccl/headers/include/thrust/detail/config/config.h +43 -0
  1368. cuda/cccl/headers/include/thrust/detail/config/cpp_dialect.h +78 -0
  1369. cuda/cccl/headers/include/thrust/detail/config/device_system.h +57 -0
  1370. cuda/cccl/headers/include/thrust/detail/config/host_system.h +50 -0
  1371. cuda/cccl/headers/include/thrust/detail/config/memory_resource.h +41 -0
  1372. cuda/cccl/headers/include/thrust/detail/config/namespace.h +164 -0
  1373. cuda/cccl/headers/include/thrust/detail/config/simple_defines.h +48 -0
  1374. cuda/cccl/headers/include/thrust/detail/config.h +36 -0
  1375. cuda/cccl/headers/include/thrust/detail/contiguous_storage.h +227 -0
  1376. cuda/cccl/headers/include/thrust/detail/contiguous_storage.inl +272 -0
  1377. cuda/cccl/headers/include/thrust/detail/copy.h +70 -0
  1378. cuda/cccl/headers/include/thrust/detail/copy.inl +146 -0
  1379. cuda/cccl/headers/include/thrust/detail/copy_if.h +62 -0
  1380. cuda/cccl/headers/include/thrust/detail/copy_if.inl +114 -0
  1381. cuda/cccl/headers/include/thrust/detail/count.h +55 -0
  1382. cuda/cccl/headers/include/thrust/detail/count.inl +101 -0
  1383. cuda/cccl/headers/include/thrust/detail/device_ptr.inl +48 -0
  1384. cuda/cccl/headers/include/thrust/detail/equal.inl +105 -0
  1385. cuda/cccl/headers/include/thrust/detail/event_error.h +160 -0
  1386. cuda/cccl/headers/include/thrust/detail/execute_with_allocator.h +79 -0
  1387. cuda/cccl/headers/include/thrust/detail/execute_with_allocator_fwd.h +61 -0
  1388. cuda/cccl/headers/include/thrust/detail/execution_policy.h +120 -0
  1389. cuda/cccl/headers/include/thrust/detail/extrema.inl +196 -0
  1390. cuda/cccl/headers/include/thrust/detail/fill.inl +97 -0
  1391. cuda/cccl/headers/include/thrust/detail/find.inl +125 -0
  1392. cuda/cccl/headers/include/thrust/detail/for_each.inl +96 -0
  1393. cuda/cccl/headers/include/thrust/detail/function.h +49 -0
  1394. cuda/cccl/headers/include/thrust/detail/functional/actor.h +213 -0
  1395. cuda/cccl/headers/include/thrust/detail/functional/operators.h +384 -0
  1396. cuda/cccl/headers/include/thrust/detail/gather.inl +185 -0
  1397. cuda/cccl/headers/include/thrust/detail/generate.inl +97 -0
  1398. cuda/cccl/headers/include/thrust/detail/get_iterator_value.h +60 -0
  1399. cuda/cccl/headers/include/thrust/detail/inner_product.inl +130 -0
  1400. cuda/cccl/headers/include/thrust/detail/internal_functional.h +335 -0
  1401. cuda/cccl/headers/include/thrust/detail/logical.inl +125 -0
  1402. cuda/cccl/headers/include/thrust/detail/malloc_and_free.h +89 -0
  1403. cuda/cccl/headers/include/thrust/detail/malloc_and_free_fwd.h +45 -0
  1404. cuda/cccl/headers/include/thrust/detail/memory_algorithms.h +208 -0
  1405. cuda/cccl/headers/include/thrust/detail/merge.inl +288 -0
  1406. cuda/cccl/headers/include/thrust/detail/mismatch.inl +107 -0
  1407. cuda/cccl/headers/include/thrust/detail/nvtx_policy.h +41 -0
  1408. cuda/cccl/headers/include/thrust/detail/overlapped_copy.h +120 -0
  1409. cuda/cccl/headers/include/thrust/detail/partition.inl +390 -0
  1410. cuda/cccl/headers/include/thrust/detail/pointer.h +313 -0
  1411. cuda/cccl/headers/include/thrust/detail/preprocessor.h +652 -0
  1412. cuda/cccl/headers/include/thrust/detail/random_bijection.h +177 -0
  1413. cuda/cccl/headers/include/thrust/detail/range/head_flags.h +114 -0
  1414. cuda/cccl/headers/include/thrust/detail/range/tail_flags.h +128 -0
  1415. cuda/cccl/headers/include/thrust/detail/raw_pointer_cast.h +52 -0
  1416. cuda/cccl/headers/include/thrust/detail/raw_reference_cast.h +191 -0
  1417. cuda/cccl/headers/include/thrust/detail/reduce.inl +396 -0
  1418. cuda/cccl/headers/include/thrust/detail/reference.h +521 -0
  1419. cuda/cccl/headers/include/thrust/detail/reference_forward_declaration.h +35 -0
  1420. cuda/cccl/headers/include/thrust/detail/remove.inl +225 -0
  1421. cuda/cccl/headers/include/thrust/detail/replace.inl +243 -0
  1422. cuda/cccl/headers/include/thrust/detail/reverse.inl +100 -0
  1423. cuda/cccl/headers/include/thrust/detail/scan.inl +536 -0
  1424. cuda/cccl/headers/include/thrust/detail/scatter.inl +169 -0
  1425. cuda/cccl/headers/include/thrust/detail/seq.h +66 -0
  1426. cuda/cccl/headers/include/thrust/detail/sequence.inl +121 -0
  1427. cuda/cccl/headers/include/thrust/detail/set_operations.inl +993 -0
  1428. cuda/cccl/headers/include/thrust/detail/shuffle.inl +86 -0
  1429. cuda/cccl/headers/include/thrust/detail/sort.inl +385 -0
  1430. cuda/cccl/headers/include/thrust/detail/static_assert.h +56 -0
  1431. cuda/cccl/headers/include/thrust/detail/static_map.h +164 -0
  1432. cuda/cccl/headers/include/thrust/detail/swap_ranges.inl +77 -0
  1433. cuda/cccl/headers/include/thrust/detail/tabulate.inl +74 -0
  1434. cuda/cccl/headers/include/thrust/detail/temporary_array.h +150 -0
  1435. cuda/cccl/headers/include/thrust/detail/temporary_array.inl +121 -0
  1436. cuda/cccl/headers/include/thrust/detail/temporary_buffer.h +93 -0
  1437. cuda/cccl/headers/include/thrust/detail/transform_reduce.inl +81 -0
  1438. cuda/cccl/headers/include/thrust/detail/transform_scan.inl +173 -0
  1439. cuda/cccl/headers/include/thrust/detail/trivial_sequence.h +128 -0
  1440. cuda/cccl/headers/include/thrust/detail/tuple_meta_transform.h +59 -0
  1441. cuda/cccl/headers/include/thrust/detail/type_deduction.h +61 -0
  1442. cuda/cccl/headers/include/thrust/detail/type_traits/has_member_function.h +50 -0
  1443. cuda/cccl/headers/include/thrust/detail/type_traits/has_nested_type.h +43 -0
  1444. cuda/cccl/headers/include/thrust/detail/type_traits/is_call_possible.h +162 -0
  1445. cuda/cccl/headers/include/thrust/detail/type_traits/is_commutative.h +67 -0
  1446. cuda/cccl/headers/include/thrust/detail/type_traits/is_metafunction_defined.h +39 -0
  1447. cuda/cccl/headers/include/thrust/detail/type_traits/is_thrust_pointer.h +55 -0
  1448. cuda/cccl/headers/include/thrust/detail/type_traits/iterator/is_output_iterator.h +48 -0
  1449. cuda/cccl/headers/include/thrust/detail/type_traits/minimum_type.h +91 -0
  1450. cuda/cccl/headers/include/thrust/detail/type_traits/pointer_traits.h +332 -0
  1451. cuda/cccl/headers/include/thrust/detail/type_traits.h +143 -0
  1452. cuda/cccl/headers/include/thrust/detail/uninitialized_copy.inl +102 -0
  1453. cuda/cccl/headers/include/thrust/detail/uninitialized_fill.inl +97 -0
  1454. cuda/cccl/headers/include/thrust/detail/unique.inl +391 -0
  1455. cuda/cccl/headers/include/thrust/detail/use_default.h +34 -0
  1456. cuda/cccl/headers/include/thrust/detail/vector_base.h +613 -0
  1457. cuda/cccl/headers/include/thrust/detail/vector_base.inl +1216 -0
  1458. cuda/cccl/headers/include/thrust/device_allocator.h +134 -0
  1459. cuda/cccl/headers/include/thrust/device_delete.h +74 -0
  1460. cuda/cccl/headers/include/thrust/device_free.h +85 -0
  1461. cuda/cccl/headers/include/thrust/device_make_unique.h +56 -0
  1462. cuda/cccl/headers/include/thrust/device_malloc.h +84 -0
  1463. cuda/cccl/headers/include/thrust/device_malloc_allocator.h +190 -0
  1464. cuda/cccl/headers/include/thrust/device_new.h +112 -0
  1465. cuda/cccl/headers/include/thrust/device_new_allocator.h +179 -0
  1466. cuda/cccl/headers/include/thrust/device_ptr.h +196 -0
  1467. cuda/cccl/headers/include/thrust/device_reference.h +983 -0
  1468. cuda/cccl/headers/include/thrust/device_vector.h +576 -0
  1469. cuda/cccl/headers/include/thrust/distance.h +44 -0
  1470. cuda/cccl/headers/include/thrust/equal.h +247 -0
  1471. cuda/cccl/headers/include/thrust/execution_policy.h +252 -0
  1472. cuda/cccl/headers/include/thrust/extrema.h +657 -0
  1473. cuda/cccl/headers/include/thrust/fill.h +200 -0
  1474. cuda/cccl/headers/include/thrust/find.h +382 -0
  1475. cuda/cccl/headers/include/thrust/for_each.h +261 -0
  1476. cuda/cccl/headers/include/thrust/functional.h +399 -0
  1477. cuda/cccl/headers/include/thrust/gather.h +464 -0
  1478. cuda/cccl/headers/include/thrust/generate.h +193 -0
  1479. cuda/cccl/headers/include/thrust/host_vector.h +576 -0
  1480. cuda/cccl/headers/include/thrust/inner_product.h +264 -0
  1481. cuda/cccl/headers/include/thrust/iterator/constant_iterator.h +221 -0
  1482. cuda/cccl/headers/include/thrust/iterator/counting_iterator.h +338 -0
  1483. cuda/cccl/headers/include/thrust/iterator/detail/any_assign.h +48 -0
  1484. cuda/cccl/headers/include/thrust/iterator/detail/any_system_tag.h +43 -0
  1485. cuda/cccl/headers/include/thrust/iterator/detail/device_system_tag.h +43 -0
  1486. cuda/cccl/headers/include/thrust/iterator/detail/host_system_tag.h +42 -0
  1487. cuda/cccl/headers/include/thrust/iterator/detail/iterator_adaptor_base.h +83 -0
  1488. cuda/cccl/headers/include/thrust/iterator/detail/iterator_category_to_system.h +60 -0
  1489. cuda/cccl/headers/include/thrust/iterator/detail/iterator_category_to_traversal.h +65 -0
  1490. cuda/cccl/headers/include/thrust/iterator/detail/iterator_category_with_system_and_traversal.h +56 -0
  1491. cuda/cccl/headers/include/thrust/iterator/detail/iterator_facade_category.h +184 -0
  1492. cuda/cccl/headers/include/thrust/iterator/detail/minimum_system.h +55 -0
  1493. cuda/cccl/headers/include/thrust/iterator/detail/normal_iterator.h +69 -0
  1494. cuda/cccl/headers/include/thrust/iterator/detail/retag.h +104 -0
  1495. cuda/cccl/headers/include/thrust/iterator/detail/tagged_iterator.h +80 -0
  1496. cuda/cccl/headers/include/thrust/iterator/detail/tuple_of_iterator_references.h +171 -0
  1497. cuda/cccl/headers/include/thrust/iterator/discard_iterator.h +163 -0
  1498. cuda/cccl/headers/include/thrust/iterator/iterator_adaptor.h +251 -0
  1499. cuda/cccl/headers/include/thrust/iterator/iterator_categories.h +211 -0
  1500. cuda/cccl/headers/include/thrust/iterator/iterator_facade.h +659 -0
  1501. cuda/cccl/headers/include/thrust/iterator/iterator_traits.h +334 -0
  1502. cuda/cccl/headers/include/thrust/iterator/iterator_traversal_tags.h +64 -0
  1503. cuda/cccl/headers/include/thrust/iterator/offset_iterator.h +194 -0
  1504. cuda/cccl/headers/include/thrust/iterator/permutation_iterator.h +204 -0
  1505. cuda/cccl/headers/include/thrust/iterator/retag.h +72 -0
  1506. cuda/cccl/headers/include/thrust/iterator/reverse_iterator.h +51 -0
  1507. cuda/cccl/headers/include/thrust/iterator/shuffle_iterator.h +190 -0
  1508. cuda/cccl/headers/include/thrust/iterator/strided_iterator.h +152 -0
  1509. cuda/cccl/headers/include/thrust/iterator/tabulate_output_iterator.h +152 -0
  1510. cuda/cccl/headers/include/thrust/iterator/transform_input_output_iterator.h +225 -0
  1511. cuda/cccl/headers/include/thrust/iterator/transform_iterator.h +353 -0
  1512. cuda/cccl/headers/include/thrust/iterator/transform_output_iterator.h +190 -0
  1513. cuda/cccl/headers/include/thrust/iterator/zip_iterator.h +365 -0
  1514. cuda/cccl/headers/include/thrust/logical.h +290 -0
  1515. cuda/cccl/headers/include/thrust/memory.h +299 -0
  1516. cuda/cccl/headers/include/thrust/merge.h +726 -0
  1517. cuda/cccl/headers/include/thrust/mismatch.h +262 -0
  1518. cuda/cccl/headers/include/thrust/mr/allocator.h +227 -0
  1519. cuda/cccl/headers/include/thrust/mr/device_memory_resource.h +46 -0
  1520. cuda/cccl/headers/include/thrust/mr/disjoint_pool.h +526 -0
  1521. cuda/cccl/headers/include/thrust/mr/disjoint_sync_pool.h +116 -0
  1522. cuda/cccl/headers/include/thrust/mr/disjoint_tls_pool.h +65 -0
  1523. cuda/cccl/headers/include/thrust/mr/fancy_pointer_resource.h +65 -0
  1524. cuda/cccl/headers/include/thrust/mr/host_memory_resource.h +42 -0
  1525. cuda/cccl/headers/include/thrust/mr/memory_resource.h +215 -0
  1526. cuda/cccl/headers/include/thrust/mr/new.h +98 -0
  1527. cuda/cccl/headers/include/thrust/mr/polymorphic_adaptor.h +61 -0
  1528. cuda/cccl/headers/include/thrust/mr/pool.h +526 -0
  1529. cuda/cccl/headers/include/thrust/mr/pool_options.h +172 -0
  1530. cuda/cccl/headers/include/thrust/mr/sync_pool.h +112 -0
  1531. cuda/cccl/headers/include/thrust/mr/tls_pool.h +62 -0
  1532. cuda/cccl/headers/include/thrust/mr/universal_memory_resource.h +29 -0
  1533. cuda/cccl/headers/include/thrust/mr/validator.h +54 -0
  1534. cuda/cccl/headers/include/thrust/pair.h +102 -0
  1535. cuda/cccl/headers/include/thrust/partition.h +1392 -0
  1536. cuda/cccl/headers/include/thrust/per_device_resource.h +110 -0
  1537. cuda/cccl/headers/include/thrust/random/detail/discard_block_engine.inl +182 -0
  1538. cuda/cccl/headers/include/thrust/random/detail/linear_congruential_engine.inl +153 -0
  1539. cuda/cccl/headers/include/thrust/random/detail/linear_congruential_engine_discard.h +97 -0
  1540. cuda/cccl/headers/include/thrust/random/detail/linear_feedback_shift_engine.inl +149 -0
  1541. cuda/cccl/headers/include/thrust/random/detail/linear_feedback_shift_engine_wordmask.h +46 -0
  1542. cuda/cccl/headers/include/thrust/random/detail/mod.h +94 -0
  1543. cuda/cccl/headers/include/thrust/random/detail/normal_distribution.inl +185 -0
  1544. cuda/cccl/headers/include/thrust/random/detail/normal_distribution_base.h +157 -0
  1545. cuda/cccl/headers/include/thrust/random/detail/random_core_access.h +56 -0
  1546. cuda/cccl/headers/include/thrust/random/detail/subtract_with_carry_engine.inl +199 -0
  1547. cuda/cccl/headers/include/thrust/random/detail/uniform_int_distribution.inl +196 -0
  1548. cuda/cccl/headers/include/thrust/random/detail/uniform_real_distribution.inl +198 -0
  1549. cuda/cccl/headers/include/thrust/random/detail/xor_combine_engine.inl +181 -0
  1550. cuda/cccl/headers/include/thrust/random/detail/xor_combine_engine_max.h +186 -0
  1551. cuda/cccl/headers/include/thrust/random/discard_block_engine.h +238 -0
  1552. cuda/cccl/headers/include/thrust/random/linear_congruential_engine.h +287 -0
  1553. cuda/cccl/headers/include/thrust/random/linear_feedback_shift_engine.h +215 -0
  1554. cuda/cccl/headers/include/thrust/random/normal_distribution.h +256 -0
  1555. cuda/cccl/headers/include/thrust/random/subtract_with_carry_engine.h +245 -0
  1556. cuda/cccl/headers/include/thrust/random/uniform_int_distribution.h +259 -0
  1557. cuda/cccl/headers/include/thrust/random/uniform_real_distribution.h +257 -0
  1558. cuda/cccl/headers/include/thrust/random/xor_combine_engine.h +253 -0
  1559. cuda/cccl/headers/include/thrust/random.h +118 -0
  1560. cuda/cccl/headers/include/thrust/reduce.h +1114 -0
  1561. cuda/cccl/headers/include/thrust/remove.h +768 -0
  1562. cuda/cccl/headers/include/thrust/replace.h +826 -0
  1563. cuda/cccl/headers/include/thrust/reverse.h +215 -0
  1564. cuda/cccl/headers/include/thrust/scan.h +1671 -0
  1565. cuda/cccl/headers/include/thrust/scatter.h +446 -0
  1566. cuda/cccl/headers/include/thrust/sequence.h +277 -0
  1567. cuda/cccl/headers/include/thrust/set_operations.h +3027 -0
  1568. cuda/cccl/headers/include/thrust/shuffle.h +182 -0
  1569. cuda/cccl/headers/include/thrust/sort.h +1320 -0
  1570. cuda/cccl/headers/include/thrust/swap.h +147 -0
  1571. cuda/cccl/headers/include/thrust/system/cpp/detail/adjacent_difference.h +30 -0
  1572. cuda/cccl/headers/include/thrust/system/cpp/detail/assign_value.h +30 -0
  1573. cuda/cccl/headers/include/thrust/system/cpp/detail/binary_search.h +32 -0
  1574. cuda/cccl/headers/include/thrust/system/cpp/detail/copy.h +30 -0
  1575. cuda/cccl/headers/include/thrust/system/cpp/detail/copy_if.h +30 -0
  1576. cuda/cccl/headers/include/thrust/system/cpp/detail/count.h +29 -0
  1577. cuda/cccl/headers/include/thrust/system/cpp/detail/equal.h +29 -0
  1578. cuda/cccl/headers/include/thrust/system/cpp/detail/execution_policy.h +113 -0
  1579. cuda/cccl/headers/include/thrust/system/cpp/detail/extrema.h +30 -0
  1580. cuda/cccl/headers/include/thrust/system/cpp/detail/fill.h +29 -0
  1581. cuda/cccl/headers/include/thrust/system/cpp/detail/find.h +30 -0
  1582. cuda/cccl/headers/include/thrust/system/cpp/detail/for_each.h +30 -0
  1583. cuda/cccl/headers/include/thrust/system/cpp/detail/gather.h +29 -0
  1584. cuda/cccl/headers/include/thrust/system/cpp/detail/generate.h +29 -0
  1585. cuda/cccl/headers/include/thrust/system/cpp/detail/get_value.h +30 -0
  1586. cuda/cccl/headers/include/thrust/system/cpp/detail/inner_product.h +29 -0
  1587. cuda/cccl/headers/include/thrust/system/cpp/detail/iter_swap.h +30 -0
  1588. cuda/cccl/headers/include/thrust/system/cpp/detail/logical.h +29 -0
  1589. cuda/cccl/headers/include/thrust/system/cpp/detail/malloc_and_free.h +30 -0
  1590. cuda/cccl/headers/include/thrust/system/cpp/detail/memory.inl +55 -0
  1591. cuda/cccl/headers/include/thrust/system/cpp/detail/merge.h +30 -0
  1592. cuda/cccl/headers/include/thrust/system/cpp/detail/mismatch.h +29 -0
  1593. cuda/cccl/headers/include/thrust/system/cpp/detail/partition.h +30 -0
  1594. cuda/cccl/headers/include/thrust/system/cpp/detail/per_device_resource.h +29 -0
  1595. cuda/cccl/headers/include/thrust/system/cpp/detail/reduce.h +30 -0
  1596. cuda/cccl/headers/include/thrust/system/cpp/detail/reduce_by_key.h +30 -0
  1597. cuda/cccl/headers/include/thrust/system/cpp/detail/remove.h +30 -0
  1598. cuda/cccl/headers/include/thrust/system/cpp/detail/replace.h +29 -0
  1599. cuda/cccl/headers/include/thrust/system/cpp/detail/reverse.h +29 -0
  1600. cuda/cccl/headers/include/thrust/system/cpp/detail/scan.h +30 -0
  1601. cuda/cccl/headers/include/thrust/system/cpp/detail/scan_by_key.h +30 -0
  1602. cuda/cccl/headers/include/thrust/system/cpp/detail/scatter.h +29 -0
  1603. cuda/cccl/headers/include/thrust/system/cpp/detail/sequence.h +29 -0
  1604. cuda/cccl/headers/include/thrust/system/cpp/detail/set_operations.h +30 -0
  1605. cuda/cccl/headers/include/thrust/system/cpp/detail/sort.h +30 -0
  1606. cuda/cccl/headers/include/thrust/system/cpp/detail/swap_ranges.h +29 -0
  1607. cuda/cccl/headers/include/thrust/system/cpp/detail/tabulate.h +29 -0
  1608. cuda/cccl/headers/include/thrust/system/cpp/detail/temporary_buffer.h +29 -0
  1609. cuda/cccl/headers/include/thrust/system/cpp/detail/transform.h +29 -0
  1610. cuda/cccl/headers/include/thrust/system/cpp/detail/transform_reduce.h +29 -0
  1611. cuda/cccl/headers/include/thrust/system/cpp/detail/transform_scan.h +29 -0
  1612. cuda/cccl/headers/include/thrust/system/cpp/detail/uninitialized_copy.h +29 -0
  1613. cuda/cccl/headers/include/thrust/system/cpp/detail/uninitialized_fill.h +29 -0
  1614. cuda/cccl/headers/include/thrust/system/cpp/detail/unique.h +30 -0
  1615. cuda/cccl/headers/include/thrust/system/cpp/detail/unique_by_key.h +30 -0
  1616. cuda/cccl/headers/include/thrust/system/cpp/execution_policy.h +63 -0
  1617. cuda/cccl/headers/include/thrust/system/cpp/memory.h +105 -0
  1618. cuda/cccl/headers/include/thrust/system/cpp/memory_resource.h +70 -0
  1619. cuda/cccl/headers/include/thrust/system/cpp/pointer.h +118 -0
  1620. cuda/cccl/headers/include/thrust/system/cpp/vector.h +95 -0
  1621. cuda/cccl/headers/include/thrust/system/cuda/config.h +126 -0
  1622. cuda/cccl/headers/include/thrust/system/cuda/detail/adjacent_difference.h +218 -0
  1623. cuda/cccl/headers/include/thrust/system/cuda/detail/assign_value.h +124 -0
  1624. cuda/cccl/headers/include/thrust/system/cuda/detail/binary_search.h +29 -0
  1625. cuda/cccl/headers/include/thrust/system/cuda/detail/cdp_dispatch.h +72 -0
  1626. cuda/cccl/headers/include/thrust/system/cuda/detail/copy.h +272 -0
  1627. cuda/cccl/headers/include/thrust/system/cuda/detail/copy_if.h +251 -0
  1628. cuda/cccl/headers/include/thrust/system/cuda/detail/core/agent_launcher.h +280 -0
  1629. cuda/cccl/headers/include/thrust/system/cuda/detail/core/triple_chevron_launch.h +162 -0
  1630. cuda/cccl/headers/include/thrust/system/cuda/detail/core/util.h +578 -0
  1631. cuda/cccl/headers/include/thrust/system/cuda/detail/count.h +75 -0
  1632. cuda/cccl/headers/include/thrust/system/cuda/detail/cross_system.h +241 -0
  1633. cuda/cccl/headers/include/thrust/system/cuda/detail/dispatch.h +230 -0
  1634. cuda/cccl/headers/include/thrust/system/cuda/detail/equal.h +62 -0
  1635. cuda/cccl/headers/include/thrust/system/cuda/detail/error.inl +87 -0
  1636. cuda/cccl/headers/include/thrust/system/cuda/detail/execution_policy.h +266 -0
  1637. cuda/cccl/headers/include/thrust/system/cuda/detail/extrema.h +473 -0
  1638. cuda/cccl/headers/include/thrust/system/cuda/detail/fill.h +99 -0
  1639. cuda/cccl/headers/include/thrust/system/cuda/detail/find.h +165 -0
  1640. cuda/cccl/headers/include/thrust/system/cuda/detail/for_each.h +83 -0
  1641. cuda/cccl/headers/include/thrust/system/cuda/detail/gather.h +89 -0
  1642. cuda/cccl/headers/include/thrust/system/cuda/detail/generate.h +59 -0
  1643. cuda/cccl/headers/include/thrust/system/cuda/detail/get_value.h +65 -0
  1644. cuda/cccl/headers/include/thrust/system/cuda/detail/inner_product.h +77 -0
  1645. cuda/cccl/headers/include/thrust/system/cuda/detail/iter_swap.h +79 -0
  1646. cuda/cccl/headers/include/thrust/system/cuda/detail/logical.h +29 -0
  1647. cuda/cccl/headers/include/thrust/system/cuda/detail/make_unsigned_special.h +55 -0
  1648. cuda/cccl/headers/include/thrust/system/cuda/detail/malloc_and_free.h +119 -0
  1649. cuda/cccl/headers/include/thrust/system/cuda/detail/memory.inl +55 -0
  1650. cuda/cccl/headers/include/thrust/system/cuda/detail/merge.h +205 -0
  1651. cuda/cccl/headers/include/thrust/system/cuda/detail/mismatch.h +88 -0
  1652. cuda/cccl/headers/include/thrust/system/cuda/detail/parallel_for.h +79 -0
  1653. cuda/cccl/headers/include/thrust/system/cuda/detail/partition.h +401 -0
  1654. cuda/cccl/headers/include/thrust/system/cuda/detail/per_device_resource.h +70 -0
  1655. cuda/cccl/headers/include/thrust/system/cuda/detail/reduce.h +774 -0
  1656. cuda/cccl/headers/include/thrust/system/cuda/detail/reduce_by_key.h +994 -0
  1657. cuda/cccl/headers/include/thrust/system/cuda/detail/remove.h +105 -0
  1658. cuda/cccl/headers/include/thrust/system/cuda/detail/replace.h +121 -0
  1659. cuda/cccl/headers/include/thrust/system/cuda/detail/reverse.h +83 -0
  1660. cuda/cccl/headers/include/thrust/system/cuda/detail/scan.h +340 -0
  1661. cuda/cccl/headers/include/thrust/system/cuda/detail/scan_by_key.h +412 -0
  1662. cuda/cccl/headers/include/thrust/system/cuda/detail/scatter.h +90 -0
  1663. cuda/cccl/headers/include/thrust/system/cuda/detail/sequence.h +29 -0
  1664. cuda/cccl/headers/include/thrust/system/cuda/detail/set_operations.h +1722 -0
  1665. cuda/cccl/headers/include/thrust/system/cuda/detail/sort.h +473 -0
  1666. cuda/cccl/headers/include/thrust/system/cuda/detail/swap_ranges.h +99 -0
  1667. cuda/cccl/headers/include/thrust/system/cuda/detail/tabulate.h +62 -0
  1668. cuda/cccl/headers/include/thrust/system/cuda/detail/temporary_buffer.h +132 -0
  1669. cuda/cccl/headers/include/thrust/system/cuda/detail/terminate.h +53 -0
  1670. cuda/cccl/headers/include/thrust/system/cuda/detail/transform.h +428 -0
  1671. cuda/cccl/headers/include/thrust/system/cuda/detail/transform_reduce.h +139 -0
  1672. cuda/cccl/headers/include/thrust/system/cuda/detail/transform_scan.h +117 -0
  1673. cuda/cccl/headers/include/thrust/system/cuda/detail/uninitialized_copy.h +114 -0
  1674. cuda/cccl/headers/include/thrust/system/cuda/detail/uninitialized_fill.h +102 -0
  1675. cuda/cccl/headers/include/thrust/system/cuda/detail/unique.h +288 -0
  1676. cuda/cccl/headers/include/thrust/system/cuda/detail/unique_by_key.h +307 -0
  1677. cuda/cccl/headers/include/thrust/system/cuda/detail/util.h +253 -0
  1678. cuda/cccl/headers/include/thrust/system/cuda/error.h +159 -0
  1679. cuda/cccl/headers/include/thrust/system/cuda/execution_policy.h +15 -0
  1680. cuda/cccl/headers/include/thrust/system/cuda/memory.h +118 -0
  1681. cuda/cccl/headers/include/thrust/system/cuda/memory_resource.h +115 -0
  1682. cuda/cccl/headers/include/thrust/system/cuda/pointer.h +155 -0
  1683. cuda/cccl/headers/include/thrust/system/cuda/vector.h +104 -0
  1684. cuda/cccl/headers/include/thrust/system/detail/bad_alloc.h +59 -0
  1685. cuda/cccl/headers/include/thrust/system/detail/errno.h +118 -0
  1686. cuda/cccl/headers/include/thrust/system/detail/error_category.inl +298 -0
  1687. cuda/cccl/headers/include/thrust/system/detail/error_code.inl +171 -0
  1688. cuda/cccl/headers/include/thrust/system/detail/error_condition.inl +119 -0
  1689. cuda/cccl/headers/include/thrust/system/detail/generic/adjacent_difference.h +51 -0
  1690. cuda/cccl/headers/include/thrust/system/detail/generic/adjacent_difference.inl +77 -0
  1691. cuda/cccl/headers/include/thrust/system/detail/generic/binary_search.h +159 -0
  1692. cuda/cccl/headers/include/thrust/system/detail/generic/binary_search.inl +370 -0
  1693. cuda/cccl/headers/include/thrust/system/detail/generic/copy.h +43 -0
  1694. cuda/cccl/headers/include/thrust/system/detail/generic/copy.inl +62 -0
  1695. cuda/cccl/headers/include/thrust/system/detail/generic/copy_if.h +56 -0
  1696. cuda/cccl/headers/include/thrust/system/detail/generic/copy_if.inl +145 -0
  1697. cuda/cccl/headers/include/thrust/system/detail/generic/count.h +46 -0
  1698. cuda/cccl/headers/include/thrust/system/detail/generic/count.inl +82 -0
  1699. cuda/cccl/headers/include/thrust/system/detail/generic/equal.h +47 -0
  1700. cuda/cccl/headers/include/thrust/system/detail/generic/equal.inl +58 -0
  1701. cuda/cccl/headers/include/thrust/system/detail/generic/extrema.h +65 -0
  1702. cuda/cccl/headers/include/thrust/system/detail/generic/extrema.inl +246 -0
  1703. cuda/cccl/headers/include/thrust/system/detail/generic/fill.h +52 -0
  1704. cuda/cccl/headers/include/thrust/system/detail/generic/find.h +47 -0
  1705. cuda/cccl/headers/include/thrust/system/detail/generic/find.inl +135 -0
  1706. cuda/cccl/headers/include/thrust/system/detail/generic/for_each.h +56 -0
  1707. cuda/cccl/headers/include/thrust/system/detail/generic/gather.h +71 -0
  1708. cuda/cccl/headers/include/thrust/system/detail/generic/gather.inl +94 -0
  1709. cuda/cccl/headers/include/thrust/system/detail/generic/generate.h +43 -0
  1710. cuda/cccl/headers/include/thrust/system/detail/generic/generate.inl +64 -0
  1711. cuda/cccl/headers/include/thrust/system/detail/generic/inner_product.h +58 -0
  1712. cuda/cccl/headers/include/thrust/system/detail/generic/inner_product.inl +70 -0
  1713. cuda/cccl/headers/include/thrust/system/detail/generic/logical.h +57 -0
  1714. cuda/cccl/headers/include/thrust/system/detail/generic/memory.h +61 -0
  1715. cuda/cccl/headers/include/thrust/system/detail/generic/memory.inl +83 -0
  1716. cuda/cccl/headers/include/thrust/system/detail/generic/merge.h +97 -0
  1717. cuda/cccl/headers/include/thrust/system/detail/generic/merge.inl +146 -0
  1718. cuda/cccl/headers/include/thrust/system/detail/generic/mismatch.h +47 -0
  1719. cuda/cccl/headers/include/thrust/system/detail/generic/mismatch.inl +67 -0
  1720. cuda/cccl/headers/include/thrust/system/detail/generic/partition.h +127 -0
  1721. cuda/cccl/headers/include/thrust/system/detail/generic/partition.inl +208 -0
  1722. cuda/cccl/headers/include/thrust/system/detail/generic/per_device_resource.h +41 -0
  1723. cuda/cccl/headers/include/thrust/system/detail/generic/reduce.h +69 -0
  1724. cuda/cccl/headers/include/thrust/system/detail/generic/reduce.inl +98 -0
  1725. cuda/cccl/headers/include/thrust/system/detail/generic/reduce_by_key.h +81 -0
  1726. cuda/cccl/headers/include/thrust/system/detail/generic/reduce_by_key.inl +183 -0
  1727. cuda/cccl/headers/include/thrust/system/detail/generic/remove.h +84 -0
  1728. cuda/cccl/headers/include/thrust/system/detail/generic/remove.inl +119 -0
  1729. cuda/cccl/headers/include/thrust/system/detail/generic/replace.h +93 -0
  1730. cuda/cccl/headers/include/thrust/system/detail/generic/replace.inl +172 -0
  1731. cuda/cccl/headers/include/thrust/system/detail/generic/reverse.h +46 -0
  1732. cuda/cccl/headers/include/thrust/system/detail/generic/reverse.inl +65 -0
  1733. cuda/cccl/headers/include/thrust/system/detail/generic/scalar/binary_search.h +61 -0
  1734. cuda/cccl/headers/include/thrust/system/detail/generic/scalar/binary_search.inl +125 -0
  1735. cuda/cccl/headers/include/thrust/system/detail/generic/scan.h +86 -0
  1736. cuda/cccl/headers/include/thrust/system/detail/generic/scan_by_key.h +124 -0
  1737. cuda/cccl/headers/include/thrust/system/detail/generic/scan_by_key.inl +229 -0
  1738. cuda/cccl/headers/include/thrust/system/detail/generic/scatter.h +71 -0
  1739. cuda/cccl/headers/include/thrust/system/detail/generic/scatter.inl +83 -0
  1740. cuda/cccl/headers/include/thrust/system/detail/generic/select_system.h +105 -0
  1741. cuda/cccl/headers/include/thrust/system/detail/generic/sequence.h +70 -0
  1742. cuda/cccl/headers/include/thrust/system/detail/generic/set_operations.h +281 -0
  1743. cuda/cccl/headers/include/thrust/system/detail/generic/set_operations.inl +474 -0
  1744. cuda/cccl/headers/include/thrust/system/detail/generic/shuffle.h +52 -0
  1745. cuda/cccl/headers/include/thrust/system/detail/generic/shuffle.inl +123 -0
  1746. cuda/cccl/headers/include/thrust/system/detail/generic/sort.h +111 -0
  1747. cuda/cccl/headers/include/thrust/system/detail/generic/sort.inl +176 -0
  1748. cuda/cccl/headers/include/thrust/system/detail/generic/swap_ranges.h +42 -0
  1749. cuda/cccl/headers/include/thrust/system/detail/generic/swap_ranges.inl +73 -0
  1750. cuda/cccl/headers/include/thrust/system/detail/generic/tabulate.h +39 -0
  1751. cuda/cccl/headers/include/thrust/system/detail/generic/tabulate.inl +54 -0
  1752. cuda/cccl/headers/include/thrust/system/detail/generic/tag.h +45 -0
  1753. cuda/cccl/headers/include/thrust/system/detail/generic/temporary_buffer.h +53 -0
  1754. cuda/cccl/headers/include/thrust/system/detail/generic/temporary_buffer.inl +81 -0
  1755. cuda/cccl/headers/include/thrust/system/detail/generic/transform.h +393 -0
  1756. cuda/cccl/headers/include/thrust/system/detail/generic/transform_reduce.h +48 -0
  1757. cuda/cccl/headers/include/thrust/system/detail/generic/transform_reduce.inl +54 -0
  1758. cuda/cccl/headers/include/thrust/system/detail/generic/transform_scan.h +78 -0
  1759. cuda/cccl/headers/include/thrust/system/detail/generic/transform_scan.inl +111 -0
  1760. cuda/cccl/headers/include/thrust/system/detail/generic/uninitialized_copy.h +43 -0
  1761. cuda/cccl/headers/include/thrust/system/detail/generic/uninitialized_copy.inl +164 -0
  1762. cuda/cccl/headers/include/thrust/system/detail/generic/uninitialized_fill.h +43 -0
  1763. cuda/cccl/headers/include/thrust/system/detail/generic/uninitialized_fill.inl +112 -0
  1764. cuda/cccl/headers/include/thrust/system/detail/generic/unique.h +69 -0
  1765. cuda/cccl/headers/include/thrust/system/detail/generic/unique.inl +112 -0
  1766. cuda/cccl/headers/include/thrust/system/detail/generic/unique_by_key.h +80 -0
  1767. cuda/cccl/headers/include/thrust/system/detail/generic/unique_by_key.inl +124 -0
  1768. cuda/cccl/headers/include/thrust/system/detail/internal/decompose.h +115 -0
  1769. cuda/cccl/headers/include/thrust/system/detail/sequential/adjacent_difference.h +68 -0
  1770. cuda/cccl/headers/include/thrust/system/detail/sequential/assign_value.h +40 -0
  1771. cuda/cccl/headers/include/thrust/system/detail/sequential/binary_search.h +136 -0
  1772. cuda/cccl/headers/include/thrust/system/detail/sequential/copy.h +120 -0
  1773. cuda/cccl/headers/include/thrust/system/detail/sequential/copy_backward.h +47 -0
  1774. cuda/cccl/headers/include/thrust/system/detail/sequential/copy_if.h +69 -0
  1775. cuda/cccl/headers/include/thrust/system/detail/sequential/count.h +29 -0
  1776. cuda/cccl/headers/include/thrust/system/detail/sequential/equal.h +29 -0
  1777. cuda/cccl/headers/include/thrust/system/detail/sequential/execution_policy.h +52 -0
  1778. cuda/cccl/headers/include/thrust/system/detail/sequential/extrema.h +109 -0
  1779. cuda/cccl/headers/include/thrust/system/detail/sequential/fill.h +29 -0
  1780. cuda/cccl/headers/include/thrust/system/detail/sequential/find.h +60 -0
  1781. cuda/cccl/headers/include/thrust/system/detail/sequential/for_each.h +72 -0
  1782. cuda/cccl/headers/include/thrust/system/detail/sequential/gather.h +29 -0
  1783. cuda/cccl/headers/include/thrust/system/detail/sequential/general_copy.h +120 -0
  1784. cuda/cccl/headers/include/thrust/system/detail/sequential/generate.h +29 -0
  1785. cuda/cccl/headers/include/thrust/system/detail/sequential/get_value.h +41 -0
  1786. cuda/cccl/headers/include/thrust/system/detail/sequential/inner_product.h +29 -0
  1787. cuda/cccl/headers/include/thrust/system/detail/sequential/insertion_sort.h +139 -0
  1788. cuda/cccl/headers/include/thrust/system/detail/sequential/iter_swap.h +43 -0
  1789. cuda/cccl/headers/include/thrust/system/detail/sequential/logical.h +29 -0
  1790. cuda/cccl/headers/include/thrust/system/detail/sequential/malloc_and_free.h +48 -0
  1791. cuda/cccl/headers/include/thrust/system/detail/sequential/merge.h +147 -0
  1792. cuda/cccl/headers/include/thrust/system/detail/sequential/mismatch.h +29 -0
  1793. cuda/cccl/headers/include/thrust/system/detail/sequential/partition.h +298 -0
  1794. cuda/cccl/headers/include/thrust/system/detail/sequential/per_device_resource.h +29 -0
  1795. cuda/cccl/headers/include/thrust/system/detail/sequential/reduce.h +62 -0
  1796. cuda/cccl/headers/include/thrust/system/detail/sequential/reduce_by_key.h +97 -0
  1797. cuda/cccl/headers/include/thrust/system/detail/sequential/remove.h +177 -0
  1798. cuda/cccl/headers/include/thrust/system/detail/sequential/replace.h +29 -0
  1799. cuda/cccl/headers/include/thrust/system/detail/sequential/reverse.h +29 -0
  1800. cuda/cccl/headers/include/thrust/system/detail/sequential/scan.h +152 -0
  1801. cuda/cccl/headers/include/thrust/system/detail/sequential/scan_by_key.h +143 -0
  1802. cuda/cccl/headers/include/thrust/system/detail/sequential/scatter.h +29 -0
  1803. cuda/cccl/headers/include/thrust/system/detail/sequential/sequence.h +29 -0
  1804. cuda/cccl/headers/include/thrust/system/detail/sequential/set_operations.h +204 -0
  1805. cuda/cccl/headers/include/thrust/system/detail/sequential/sort.h +120 -0
  1806. cuda/cccl/headers/include/thrust/system/detail/sequential/stable_merge_sort.h +353 -0
  1807. cuda/cccl/headers/include/thrust/system/detail/sequential/stable_primitive_sort.h +121 -0
  1808. cuda/cccl/headers/include/thrust/system/detail/sequential/stable_radix_sort.h +584 -0
  1809. cuda/cccl/headers/include/thrust/system/detail/sequential/swap_ranges.h +29 -0
  1810. cuda/cccl/headers/include/thrust/system/detail/sequential/tabulate.h +29 -0
  1811. cuda/cccl/headers/include/thrust/system/detail/sequential/temporary_buffer.h +29 -0
  1812. cuda/cccl/headers/include/thrust/system/detail/sequential/transform.h +29 -0
  1813. cuda/cccl/headers/include/thrust/system/detail/sequential/transform_reduce.h +29 -0
  1814. cuda/cccl/headers/include/thrust/system/detail/sequential/transform_scan.h +29 -0
  1815. cuda/cccl/headers/include/thrust/system/detail/sequential/trivial_copy.h +56 -0
  1816. cuda/cccl/headers/include/thrust/system/detail/sequential/uninitialized_copy.h +29 -0
  1817. cuda/cccl/headers/include/thrust/system/detail/sequential/uninitialized_fill.h +29 -0
  1818. cuda/cccl/headers/include/thrust/system/detail/sequential/unique.h +112 -0
  1819. cuda/cccl/headers/include/thrust/system/detail/sequential/unique_by_key.h +105 -0
  1820. cuda/cccl/headers/include/thrust/system/detail/system_error.inl +106 -0
  1821. cuda/cccl/headers/include/thrust/system/error_code.h +508 -0
  1822. cuda/cccl/headers/include/thrust/system/omp/detail/adjacent_difference.h +34 -0
  1823. cuda/cccl/headers/include/thrust/system/omp/detail/assign_value.h +17 -0
  1824. cuda/cccl/headers/include/thrust/system/omp/detail/binary_search.h +57 -0
  1825. cuda/cccl/headers/include/thrust/system/omp/detail/copy.h +61 -0
  1826. cuda/cccl/headers/include/thrust/system/omp/detail/copy_if.h +39 -0
  1827. cuda/cccl/headers/include/thrust/system/omp/detail/count.h +17 -0
  1828. cuda/cccl/headers/include/thrust/system/omp/detail/default_decomposition.h +48 -0
  1829. cuda/cccl/headers/include/thrust/system/omp/detail/equal.h +17 -0
  1830. cuda/cccl/headers/include/thrust/system/omp/detail/execution_policy.h +132 -0
  1831. cuda/cccl/headers/include/thrust/system/omp/detail/extrema.h +46 -0
  1832. cuda/cccl/headers/include/thrust/system/omp/detail/fill.h +17 -0
  1833. cuda/cccl/headers/include/thrust/system/omp/detail/find.h +33 -0
  1834. cuda/cccl/headers/include/thrust/system/omp/detail/for_each.h +74 -0
  1835. cuda/cccl/headers/include/thrust/system/omp/detail/gather.h +17 -0
  1836. cuda/cccl/headers/include/thrust/system/omp/detail/generate.h +17 -0
  1837. cuda/cccl/headers/include/thrust/system/omp/detail/get_value.h +17 -0
  1838. cuda/cccl/headers/include/thrust/system/omp/detail/inner_product.h +17 -0
  1839. cuda/cccl/headers/include/thrust/system/omp/detail/iter_swap.h +17 -0
  1840. cuda/cccl/headers/include/thrust/system/omp/detail/logical.h +17 -0
  1841. cuda/cccl/headers/include/thrust/system/omp/detail/malloc_and_free.h +17 -0
  1842. cuda/cccl/headers/include/thrust/system/omp/detail/merge.h +17 -0
  1843. cuda/cccl/headers/include/thrust/system/omp/detail/mismatch.h +17 -0
  1844. cuda/cccl/headers/include/thrust/system/omp/detail/partition.h +84 -0
  1845. cuda/cccl/headers/include/thrust/system/omp/detail/per_device_resource.h +16 -0
  1846. cuda/cccl/headers/include/thrust/system/omp/detail/pragma_omp.h +30 -0
  1847. cuda/cccl/headers/include/thrust/system/omp/detail/reduce.h +63 -0
  1848. cuda/cccl/headers/include/thrust/system/omp/detail/reduce_by_key.h +48 -0
  1849. cuda/cccl/headers/include/thrust/system/omp/detail/reduce_intervals.h +87 -0
  1850. cuda/cccl/headers/include/thrust/system/omp/detail/remove.h +67 -0
  1851. cuda/cccl/headers/include/thrust/system/omp/detail/replace.h +17 -0
  1852. cuda/cccl/headers/include/thrust/system/omp/detail/reverse.h +17 -0
  1853. cuda/cccl/headers/include/thrust/system/omp/detail/scan.h +216 -0
  1854. cuda/cccl/headers/include/thrust/system/omp/detail/scan_by_key.h +23 -0
  1855. cuda/cccl/headers/include/thrust/system/omp/detail/scatter.h +17 -0
  1856. cuda/cccl/headers/include/thrust/system/omp/detail/sequence.h +17 -0
  1857. cuda/cccl/headers/include/thrust/system/omp/detail/set_operations.h +17 -0
  1858. cuda/cccl/headers/include/thrust/system/omp/detail/sort.h +245 -0
  1859. cuda/cccl/headers/include/thrust/system/omp/detail/swap_ranges.h +17 -0
  1860. cuda/cccl/headers/include/thrust/system/omp/detail/tabulate.h +17 -0
  1861. cuda/cccl/headers/include/thrust/system/omp/detail/temporary_buffer.h +16 -0
  1862. cuda/cccl/headers/include/thrust/system/omp/detail/transform.h +17 -0
  1863. cuda/cccl/headers/include/thrust/system/omp/detail/transform_reduce.h +17 -0
  1864. cuda/cccl/headers/include/thrust/system/omp/detail/transform_scan.h +17 -0
  1865. cuda/cccl/headers/include/thrust/system/omp/detail/uninitialized_copy.h +17 -0
  1866. cuda/cccl/headers/include/thrust/system/omp/detail/uninitialized_fill.h +17 -0
  1867. cuda/cccl/headers/include/thrust/system/omp/detail/unique.h +52 -0
  1868. cuda/cccl/headers/include/thrust/system/omp/detail/unique_by_key.h +56 -0
  1869. cuda/cccl/headers/include/thrust/system/omp/execution_policy.h +62 -0
  1870. cuda/cccl/headers/include/thrust/system/omp/memory.h +153 -0
  1871. cuda/cccl/headers/include/thrust/system/omp/memory_resource.h +71 -0
  1872. cuda/cccl/headers/include/thrust/system/omp/pointer.h +120 -0
  1873. cuda/cccl/headers/include/thrust/system/omp/vector.h +96 -0
  1874. cuda/cccl/headers/include/thrust/system/system_error.h +183 -0
  1875. cuda/cccl/headers/include/thrust/system/tbb/detail/adjacent_difference.h +33 -0
  1876. cuda/cccl/headers/include/thrust/system/tbb/detail/assign_value.h +17 -0
  1877. cuda/cccl/headers/include/thrust/system/tbb/detail/binary_search.h +17 -0
  1878. cuda/cccl/headers/include/thrust/system/tbb/detail/copy.h +59 -0
  1879. cuda/cccl/headers/include/thrust/system/tbb/detail/copy_if.h +117 -0
  1880. cuda/cccl/headers/include/thrust/system/tbb/detail/count.h +17 -0
  1881. cuda/cccl/headers/include/thrust/system/tbb/detail/equal.h +17 -0
  1882. cuda/cccl/headers/include/thrust/system/tbb/detail/execution_policy.h +113 -0
  1883. cuda/cccl/headers/include/thrust/system/tbb/detail/extrema.h +45 -0
  1884. cuda/cccl/headers/include/thrust/system/tbb/detail/fill.h +17 -0
  1885. cuda/cccl/headers/include/thrust/system/tbb/detail/find.h +28 -0
  1886. cuda/cccl/headers/include/thrust/system/tbb/detail/for_each.h +72 -0
  1887. cuda/cccl/headers/include/thrust/system/tbb/detail/gather.h +17 -0
  1888. cuda/cccl/headers/include/thrust/system/tbb/detail/generate.h +17 -0
  1889. cuda/cccl/headers/include/thrust/system/tbb/detail/get_value.h +17 -0
  1890. cuda/cccl/headers/include/thrust/system/tbb/detail/inner_product.h +17 -0
  1891. cuda/cccl/headers/include/thrust/system/tbb/detail/iter_swap.h +17 -0
  1892. cuda/cccl/headers/include/thrust/system/tbb/detail/logical.h +17 -0
  1893. cuda/cccl/headers/include/thrust/system/tbb/detail/malloc_and_free.h +17 -0
  1894. cuda/cccl/headers/include/thrust/system/tbb/detail/merge.h +302 -0
  1895. cuda/cccl/headers/include/thrust/system/tbb/detail/mismatch.h +17 -0
  1896. cuda/cccl/headers/include/thrust/system/tbb/detail/partition.h +79 -0
  1897. cuda/cccl/headers/include/thrust/system/tbb/detail/per_device_resource.h +16 -0
  1898. cuda/cccl/headers/include/thrust/system/tbb/detail/reduce.h +121 -0
  1899. cuda/cccl/headers/include/thrust/system/tbb/detail/reduce_by_key.h +378 -0
  1900. cuda/cccl/headers/include/thrust/system/tbb/detail/reduce_intervals.h +118 -0
  1901. cuda/cccl/headers/include/thrust/system/tbb/detail/remove.h +66 -0
  1902. cuda/cccl/headers/include/thrust/system/tbb/detail/replace.h +17 -0
  1903. cuda/cccl/headers/include/thrust/system/tbb/detail/reverse.h +17 -0
  1904. cuda/cccl/headers/include/thrust/system/tbb/detail/scan.h +294 -0
  1905. cuda/cccl/headers/include/thrust/system/tbb/detail/scan_by_key.h +20 -0
  1906. cuda/cccl/headers/include/thrust/system/tbb/detail/scatter.h +17 -0
  1907. cuda/cccl/headers/include/thrust/system/tbb/detail/sequence.h +17 -0
  1908. cuda/cccl/headers/include/thrust/system/tbb/detail/set_operations.h +17 -0
  1909. cuda/cccl/headers/include/thrust/system/tbb/detail/sort.h +273 -0
  1910. cuda/cccl/headers/include/thrust/system/tbb/detail/swap_ranges.h +17 -0
  1911. cuda/cccl/headers/include/thrust/system/tbb/detail/tabulate.h +17 -0
  1912. cuda/cccl/headers/include/thrust/system/tbb/detail/temporary_buffer.h +16 -0
  1913. cuda/cccl/headers/include/thrust/system/tbb/detail/transform.h +17 -0
  1914. cuda/cccl/headers/include/thrust/system/tbb/detail/transform_reduce.h +17 -0
  1915. cuda/cccl/headers/include/thrust/system/tbb/detail/transform_scan.h +17 -0
  1916. cuda/cccl/headers/include/thrust/system/tbb/detail/uninitialized_copy.h +17 -0
  1917. cuda/cccl/headers/include/thrust/system/tbb/detail/uninitialized_fill.h +17 -0
  1918. cuda/cccl/headers/include/thrust/system/tbb/detail/unique.h +49 -0
  1919. cuda/cccl/headers/include/thrust/system/tbb/detail/unique_by_key.h +55 -0
  1920. cuda/cccl/headers/include/thrust/system/tbb/execution_policy.h +62 -0
  1921. cuda/cccl/headers/include/thrust/system/tbb/memory.h +139 -0
  1922. cuda/cccl/headers/include/thrust/system/tbb/memory_resource.h +57 -0
  1923. cuda/cccl/headers/include/thrust/system/tbb/pointer.h +106 -0
  1924. cuda/cccl/headers/include/thrust/system/tbb/vector.h +82 -0
  1925. cuda/cccl/headers/include/thrust/system_error.h +57 -0
  1926. cuda/cccl/headers/include/thrust/tabulate.h +125 -0
  1927. cuda/cccl/headers/include/thrust/transform.h +1056 -0
  1928. cuda/cccl/headers/include/thrust/transform_reduce.h +190 -0
  1929. cuda/cccl/headers/include/thrust/transform_scan.h +442 -0
  1930. cuda/cccl/headers/include/thrust/tuple.h +139 -0
  1931. cuda/cccl/headers/include/thrust/type_traits/integer_sequence.h +256 -0
  1932. cuda/cccl/headers/include/thrust/type_traits/is_contiguous_iterator.h +156 -0
  1933. cuda/cccl/headers/include/thrust/type_traits/is_execution_policy.h +65 -0
  1934. cuda/cccl/headers/include/thrust/type_traits/is_operator_less_or_greater_function_object.h +180 -0
  1935. cuda/cccl/headers/include/thrust/type_traits/is_operator_plus_function_object.h +112 -0
  1936. cuda/cccl/headers/include/thrust/type_traits/is_trivially_relocatable.h +333 -0
  1937. cuda/cccl/headers/include/thrust/type_traits/logical_metafunctions.h +42 -0
  1938. cuda/cccl/headers/include/thrust/type_traits/unwrap_contiguous_iterator.h +63 -0
  1939. cuda/cccl/headers/include/thrust/uninitialized_copy.h +300 -0
  1940. cuda/cccl/headers/include/thrust/uninitialized_fill.h +268 -0
  1941. cuda/cccl/headers/include/thrust/unique.h +1089 -0
  1942. cuda/cccl/headers/include/thrust/universal_allocator.h +101 -0
  1943. cuda/cccl/headers/include/thrust/universal_ptr.h +34 -0
  1944. cuda/cccl/headers/include/thrust/universal_vector.h +80 -0
  1945. cuda/cccl/headers/include/thrust/version.h +93 -0
  1946. cuda/cccl/headers/include/thrust/zip_function.h +149 -0
  1947. cuda/cccl/headers/include_paths.py +51 -0
  1948. cuda/cccl/headers/lib/cmake/cccl/cccl-config-version.cmake +25 -0
  1949. cuda/cccl/headers/lib/cmake/cccl/cccl-config.cmake +143 -0
  1950. cuda/cccl/headers/lib/cmake/cub/cub-config-version.cmake +29 -0
  1951. cuda/cccl/headers/lib/cmake/cub/cub-config.cmake +172 -0
  1952. cuda/cccl/headers/lib/cmake/cub/cub-header-search.cmake +15 -0
  1953. cuda/cccl/headers/lib/cmake/libcudacxx/libcudacxx-config-version.cmake +37 -0
  1954. cuda/cccl/headers/lib/cmake/libcudacxx/libcudacxx-config.cmake +297 -0
  1955. cuda/cccl/headers/lib/cmake/libcudacxx/libcudacxx-header-search.cmake +15 -0
  1956. cuda/cccl/headers/lib/cmake/thrust/FindTBB.cmake +498 -0
  1957. cuda/cccl/headers/lib/cmake/thrust/README.md +258 -0
  1958. cuda/cccl/headers/lib/cmake/thrust/thrust-config-version.cmake +37 -0
  1959. cuda/cccl/headers/lib/cmake/thrust/thrust-config.cmake +983 -0
  1960. cuda/cccl/headers/lib/cmake/thrust/thrust-header-search.cmake +15 -0
  1961. cuda/cccl/parallel/__init__.py +9 -0
  1962. cuda/cccl/parallel/experimental/__init__.py +24 -0
  1963. cuda/cccl/py.typed +0 -0
  1964. cuda/compute/__init__.py +91 -0
  1965. cuda/compute/_bindings.py +79 -0
  1966. cuda/compute/_bindings.pyi +516 -0
  1967. cuda/compute/_bindings_impl.pyx +2470 -0
  1968. cuda/compute/_caching.py +83 -0
  1969. cuda/compute/_cccl_interop.py +354 -0
  1970. cuda/compute/_odr_helpers.py +238 -0
  1971. cuda/compute/_utils/__init__.py +0 -0
  1972. cuda/compute/_utils/protocols.py +145 -0
  1973. cuda/compute/_utils/temp_storage_buffer.py +87 -0
  1974. cuda/compute/algorithms/__init__.py +62 -0
  1975. cuda/compute/algorithms/_histogram.py +243 -0
  1976. cuda/compute/algorithms/_reduce.py +205 -0
  1977. cuda/compute/algorithms/_scan.py +344 -0
  1978. cuda/compute/algorithms/_segmented_reduce.py +265 -0
  1979. cuda/compute/algorithms/_select.py +196 -0
  1980. cuda/compute/algorithms/_sort/__init__.py +23 -0
  1981. cuda/compute/algorithms/_sort/_merge_sort.py +235 -0
  1982. cuda/compute/algorithms/_sort/_radix_sort.py +263 -0
  1983. cuda/compute/algorithms/_sort/_segmented_sort.py +288 -0
  1984. cuda/compute/algorithms/_sort/_sort_common.py +52 -0
  1985. cuda/compute/algorithms/_three_way_partition.py +292 -0
  1986. cuda/compute/algorithms/_transform.py +317 -0
  1987. cuda/compute/algorithms/_unique_by_key.py +259 -0
  1988. cuda/compute/cccl/.gitkeep +0 -0
  1989. cuda/compute/cu12/_bindings_impl.cpython-312-x86_64-linux-gnu.so +0 -0
  1990. cuda/compute/cu12/cccl/libcccl.c.parallel.so +0 -0
  1991. cuda/compute/cu13/_bindings_impl.cpython-312-x86_64-linux-gnu.so +0 -0
  1992. cuda/compute/cu13/cccl/libcccl.c.parallel.so +0 -0
  1993. cuda/compute/determinism.py +3 -0
  1994. cuda/compute/iterators/__init__.py +23 -0
  1995. cuda/compute/iterators/_factories.py +251 -0
  1996. cuda/compute/iterators/_iterators.py +680 -0
  1997. cuda/compute/iterators/_permutation_iterator.py +266 -0
  1998. cuda/compute/iterators/_zip_iterator.py +268 -0
  1999. cuda/compute/numba_utils.py +54 -0
  2000. cuda/compute/op.py +140 -0
  2001. cuda/compute/struct.py +520 -0
  2002. cuda/compute/typing.py +36 -0
  2003. cuda/coop/__init__.py +8 -0
  2004. cuda/coop/_caching.py +48 -0
  2005. cuda/coop/_common.py +275 -0
  2006. cuda/coop/_nvrtc.py +92 -0
  2007. cuda/coop/_scan_op.py +181 -0
  2008. cuda/coop/_types.py +937 -0
  2009. cuda/coop/_typing.py +107 -0
  2010. cuda/coop/block/__init__.py +39 -0
  2011. cuda/coop/block/_block_exchange.py +251 -0
  2012. cuda/coop/block/_block_load_store.py +215 -0
  2013. cuda/coop/block/_block_merge_sort.py +125 -0
  2014. cuda/coop/block/_block_radix_sort.py +214 -0
  2015. cuda/coop/block/_block_reduce.py +294 -0
  2016. cuda/coop/block/_block_scan.py +983 -0
  2017. cuda/coop/warp/__init__.py +9 -0
  2018. cuda/coop/warp/_warp_merge_sort.py +92 -0
  2019. cuda/coop/warp/_warp_reduce.py +153 -0
  2020. cuda/coop/warp/_warp_scan.py +78 -0
  2021. cuda_cccl-0.4.3.dist-info/METADATA +84 -0
  2022. cuda_cccl-0.4.3.dist-info/RECORD +2024 -0
  2023. cuda_cccl-0.4.3.dist-info/WHEEL +5 -0
  2024. cuda_cccl-0.4.3.dist-info/licenses/LICENSE +1 -0
@@ -0,0 +1,1392 @@
1
+ /*
2
+ * Copyright 2008-2013 NVIDIA Corporation
3
+ *
4
+ * Licensed under the Apache License, Version 2.0 (the "License");
5
+ * you may not use this file except in compliance with the License.
6
+ * You may obtain a copy of the License at
7
+ *
8
+ * http://www.apache.org/licenses/LICENSE-2.0
9
+ *
10
+ * Unless required by applicable law or agreed to in writing, software
11
+ * distributed under the License is distributed on an "AS IS" BASIS,
12
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13
+ * See the License for the specific language governing permissions and
14
+ * limitations under the License.
15
+ */
16
+
17
+ /*! \file partition.h
18
+ * \brief Reorganizes a range based on a predicate
19
+ */
20
+
21
+ #pragma once
22
+
23
+ #include <thrust/detail/config.h>
24
+
25
+ #if defined(_CCCL_IMPLICIT_SYSTEM_HEADER_GCC)
26
+ # pragma GCC system_header
27
+ #elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_CLANG)
28
+ # pragma clang system_header
29
+ #elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_MSVC)
30
+ # pragma system_header
31
+ #endif // no system header
32
+ #include <thrust/detail/execution_policy.h>
33
+
34
+ #include <cuda/std/__utility/pair.h>
35
+
36
+ THRUST_NAMESPACE_BEGIN
37
+
38
+ /*! \addtogroup reordering
39
+ * \ingroup algorithms
40
+ * \{
41
+ *
42
+ * \addtogroup partitioning
43
+ * \ingroup reordering
44
+ * \{
45
+ */
46
+
47
+ /*! \p partition reorders the elements <tt>[first, last)</tt> based on the function
48
+ * object \p pred, such that all of the elements that satisfy \p pred precede the
49
+ * elements that fail to satisfy it. The postcondition is that, for some iterator
50
+ * \c middle in the range <tt>[first, last)</tt>, <tt>pred(*i)</tt> is \c true for every
51
+ * iterator \c i in the range <tt>[first,middle)</tt> and \c false for every iterator
52
+ * \c i in the range <tt>[middle, last)</tt>. The return value of \p partition is
53
+ * \c middle.
54
+ *
55
+ * Note that the relative order of elements in the two reordered sequences is not
56
+ * necessarily the same as it was in the original sequence. A different algorithm,
57
+ * \p stable_partition, does guarantee to preserve the relative order.
58
+ *
59
+ * The algorithm's execution is parallelized as determined by \p exec.
60
+ *
61
+ * \param exec The execution policy to use for parallelization.
62
+ * \param first The beginning of the sequence to reorder.
63
+ * \param last The end of the sequence to reorder.
64
+ * \param pred A function object which decides to which partition each element of the
65
+ * sequence <tt>[first, last)</tt> belongs.
66
+ * \return An iterator referring to the first element of the second partition, that is,
67
+ * the sequence of the elements which do not satisfy \p pred.
68
+ *
69
+ * \tparam DerivedPolicy The name of the derived execution policy.
70
+ * \tparam ForwardIterator is a model of <a href="https://en.cppreference.com/w/cpp/iterator/forward_iterator">Forward
71
+ * Iterator</a>, and \p ForwardIterator's \c value_type is convertible to \p Predicate's argument type, and \p
72
+ * ForwardIterator is mutable. \tparam Predicate is a model of <a
73
+ * href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
74
+ *
75
+ * The following code snippet demonstrates how to use \p partition to reorder a
76
+ * sequence so that even numbers precede odd numbers using the \p thrust::host execution policy for parallelization:
77
+ *
78
+ * \code
79
+ * #include <thrust/partition.h>
80
+ * #include <thrust/execution_policy.h>
81
+ * ...
82
+ * struct is_even
83
+ * {
84
+ * __host__ __device__
85
+ * bool operator()(const int &x)
86
+ * {
87
+ * return (x % 2) == 0;
88
+ * }
89
+ * };
90
+ * ...
91
+ * int A[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
92
+ * const int N = sizeof(A)/sizeof(int);
93
+ * thrust::partition(thrust::host,
94
+ * A, A + N,
95
+ * is_even());
96
+ * // A is now {2, 4, 6, 8, 10, 1, 3, 5, 7, 9}
97
+ * \endcode
98
+ *
99
+ * \see https://en.cppreference.com/w/cpp/algorithm/partition
100
+ * \see \p stable_partition
101
+ * \see \p partition_copy
102
+ */
103
+ template <typename DerivedPolicy, typename ForwardIterator, typename Predicate>
104
+ _CCCL_HOST_DEVICE ForwardIterator partition(
105
+ const thrust::detail::execution_policy_base<DerivedPolicy>& exec,
106
+ ForwardIterator first,
107
+ ForwardIterator last,
108
+ Predicate pred);
109
+
110
+ /*! \p partition reorders the elements <tt>[first, last)</tt> based on the function
111
+ * object \p pred, such that all of the elements that satisfy \p pred precede the
112
+ * elements that fail to satisfy it. The postcondition is that, for some iterator
113
+ * \c middle in the range <tt>[first, last)</tt>, <tt>pred(*i)</tt> is \c true for every
114
+ * iterator \c i in the range <tt>[first,middle)</tt> and \c false for every iterator
115
+ * \c i in the range <tt>[middle, last)</tt>. The return value of \p partition is
116
+ * \c middle.
117
+ *
118
+ * Note that the relative order of elements in the two reordered sequences is not
119
+ * necessarily the same as it was in the original sequence. A different algorithm,
120
+ * \p stable_partition, does guarantee to preserve the relative order.
121
+ *
122
+ * \param first The beginning of the sequence to reorder.
123
+ * \param last The end of the sequence to reorder.
124
+ * \param pred A function object which decides to which partition each element of the
125
+ * sequence <tt>[first, last)</tt> belongs.
126
+ * \return An iterator referring to the first element of the second partition, that is,
127
+ * the sequence of the elements which do not satisfy \p pred.
128
+ *
129
+ * \tparam ForwardIterator is a model of <a href="https://en.cppreference.com/w/cpp/iterator/forward_iterator">Forward
130
+ * Iterator</a>, and \p ForwardIterator's \c value_type is convertible to \p Predicate's argument type, and \p
131
+ * ForwardIterator is mutable. \tparam Predicate is a model of <a
132
+ * href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
133
+ *
134
+ * The following code snippet demonstrates how to use \p partition to reorder a
135
+ * sequence so that even numbers precede odd numbers.
136
+ *
137
+ * \code
138
+ * #include <thrust/partition.h>
139
+ * ...
140
+ * struct is_even
141
+ * {
142
+ * __host__ __device__
143
+ * bool operator()(const int &x)
144
+ * {
145
+ * return (x % 2) == 0;
146
+ * }
147
+ * };
148
+ * ...
149
+ * int A[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
150
+ * const int N = sizeof(A)/sizeof(int);
151
+ * thrust::partition(A, A + N,
152
+ * is_even());
153
+ * // A is now {2, 4, 6, 8, 10, 1, 3, 5, 7, 9}
154
+ * \endcode
155
+ *
156
+ * \see https://en.cppreference.com/w/cpp/algorithm/partition
157
+ * \see \p stable_partition
158
+ * \see \p partition_copy
159
+ */
160
+ template <typename ForwardIterator, typename Predicate>
161
+ ForwardIterator partition(ForwardIterator first, ForwardIterator last, Predicate pred);
162
+
163
+ /*! \p partition reorders the elements <tt>[first, last)</tt> based on the function
164
+ * object \p pred applied to a stencil range <tt>[stencil, stencil + (last - first))</tt>,
165
+ * such that all of the elements whose corresponding stencil element satisfies \p pred precede all of the elements
166
+ * whose corresponding stencil element fails to satisfy it. The postcondition is that, for some iterator \c middle in
167
+ * the range <tt>[first, last)</tt>, <tt>pred(*stencil_i)</tt> is \c true for every iterator \c stencil_i in the range
168
+ * <tt>[stencil,stencil + (middle - first))</tt> and \c false for every iterator \c stencil_i in the range
169
+ * <tt>[stencil + (middle - first), stencil + (last - first))</tt>.
170
+ * The return value of \p stable_partition is \c middle.
171
+ *
172
+ * Note that the relative order of elements in the two reordered sequences is not
173
+ * necessarily the same as it was in the original sequence. A different algorithm,
174
+ * \p stable_partition, does guarantee to preserve the relative order.
175
+ *
176
+ * The algorithm's execution is parallelized as determined by \p exec.
177
+ *
178
+ * \param exec The execution policy to use for parallelization.
179
+ * \param first The beginning of the sequence to reorder.
180
+ * \param last The end of the sequence to reorder.
181
+ * \param stencil The beginning of the stencil sequence.
182
+ * \param pred A function object which decides to which partition each element of the
183
+ * sequence <tt>[first, last)</tt> belongs.
184
+ * \return An iterator referring to the first element of the second partition, that is,
185
+ * the sequence of the elements whose stencil elements do not satisfy \p pred.
186
+ *
187
+ * \tparam DerivedPolicy The name of the derived execution policy.
188
+ * \tparam ForwardIterator is a model of <a href="https://en.cppreference.com/w/cpp/iterator/forward_iterator">Forward
189
+ * Iterator</a>, and \p ForwardIterator is mutable. \tparam InputIterator is a model of <a
190
+ * href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input Iterator</a>, and \p InputIterator's \c
191
+ * value_type is convertible to \p Predicate's argument type. \tparam Predicate is a model of <a
192
+ * href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
193
+ *
194
+ * \pre The ranges <tt>[first,last)</tt> and <tt>[stencil, stencil + (last - first))</tt> shall not overlap.
195
+ *
196
+ * The following code snippet demonstrates how to use \p partition to reorder a
197
+ * sequence so that even numbers precede odd numbers using the \p thrust::host execution policy for parallelization:
198
+ *
199
+ * \code
200
+ * #include <thrust/partition.h>
201
+ * #include <thrust/execution_policy.h>
202
+ * ...
203
+ * struct is_even
204
+ * {
205
+ * __host__ __device__
206
+ * bool operator()(const int &x)
207
+ * {
208
+ * return (x % 2) == 0;
209
+ * }
210
+ * };
211
+ * ...
212
+ * int A[] = {0, 1, 0, 1, 0, 1, 0, 1, 0, 1};
213
+ * int S[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
214
+ * const int N = sizeof(A)/sizeof(int);
215
+ * thrust::partition(thrust::host, A, A + N, S, is_even());
216
+ * // A is now {1, 1, 1, 1, 1, 0, 0, 0, 0, 0}
217
+ * // S is unmodified
218
+ * \endcode
219
+ *
220
+ * \see https://en.cppreference.com/w/cpp/algorithm/partition
221
+ * \see \p stable_partition
222
+ * \see \p partition_copy
223
+ */
224
+ template <typename DerivedPolicy, typename ForwardIterator, typename InputIterator, typename Predicate>
225
+ _CCCL_HOST_DEVICE ForwardIterator partition(
226
+ const thrust::detail::execution_policy_base<DerivedPolicy>& exec,
227
+ ForwardIterator first,
228
+ ForwardIterator last,
229
+ InputIterator stencil,
230
+ Predicate pred);
231
+
232
+ /*! \p partition reorders the elements <tt>[first, last)</tt> based on the function
233
+ * object \p pred applied to a stencil range <tt>[stencil, stencil + (last - first))</tt>,
234
+ * such that all of the elements whose corresponding stencil element satisfies \p pred precede all of the elements
235
+ * whose corresponding stencil element fails to satisfy it. The postcondition is that, for some iterator \c middle in
236
+ * the range <tt>[first, last)</tt>, <tt>pred(*stencil_i)</tt> is \c true for every iterator \c stencil_i in the range
237
+ * <tt>[stencil,stencil + (middle - first))</tt> and \c false for every iterator \c stencil_i in the range
238
+ * <tt>[stencil + (middle - first), stencil + (last - first))</tt>.
239
+ * The return value of \p stable_partition is \c middle.
240
+ *
241
+ * Note that the relative order of elements in the two reordered sequences is not
242
+ * necessarily the same as it was in the original sequence. A different algorithm,
243
+ * \p stable_partition, does guarantee to preserve the relative order.
244
+ *
245
+ * \param first The beginning of the sequence to reorder.
246
+ * \param last The end of the sequence to reorder.
247
+ * \param stencil The beginning of the stencil sequence.
248
+ * \param pred A function object which decides to which partition each element of the
249
+ * sequence <tt>[first, last)</tt> belongs.
250
+ * \return An iterator referring to the first element of the second partition, that is,
251
+ * the sequence of the elements whose stencil elements do not satisfy \p pred.
252
+ *
253
+ * \tparam ForwardIterator is a model of <a href="https://en.cppreference.com/w/cpp/iterator/forward_iterator">Forward
254
+ * Iterator</a>, and \p ForwardIterator is mutable. \tparam InputIterator is a model of <a
255
+ * href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input Iterator</a>, and \p InputIterator's \c
256
+ * value_type is convertible to \p Predicate's argument type. \tparam Predicate is a model of <a
257
+ * href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
258
+ *
259
+ * \pre The ranges <tt>[first,last)</tt> and <tt>[stencil, stencil + (last - first))</tt> shall not overlap.
260
+ *
261
+ * The following code snippet demonstrates how to use \p partition to reorder a
262
+ * sequence so that even numbers precede odd numbers.
263
+ *
264
+ * \code
265
+ * #include <thrust/partition.h>
266
+ * ...
267
+ * struct is_even
268
+ * {
269
+ * __host__ __device__
270
+ * bool operator()(const int &x)
271
+ * {
272
+ * return (x % 2) == 0;
273
+ * }
274
+ * };
275
+ * ...
276
+ * int A[] = {0, 1, 0, 1, 0, 1, 0, 1, 0, 1};
277
+ * int S[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
278
+ * const int N = sizeof(A)/sizeof(int);
279
+ * thrust::partition(A, A + N, S, is_even());
280
+ * // A is now {1, 1, 1, 1, 1, 0, 0, 0, 0, 0}
281
+ * // S is unmodified
282
+ * \endcode
283
+ *
284
+ * \see https://en.cppreference.com/w/cpp/algorithm/partition
285
+ * \see \p stable_partition
286
+ * \see \p partition_copy
287
+ */
288
+ template <typename ForwardIterator, typename InputIterator, typename Predicate>
289
+ ForwardIterator partition(ForwardIterator first, ForwardIterator last, InputIterator stencil, Predicate pred);
290
+
291
+ /*! \p partition_copy differs from \p partition only in that the reordered
292
+ * sequence is written to different output sequences, rather than in place.
293
+ *
294
+ * \p partition_copy copies the elements <tt>[first, last)</tt> based on the
295
+ * function object \p pred. All of the elements that satisfy \p pred are copied
296
+ * to the range beginning at \p out_true and all the elements that fail to satisfy it
297
+ * are copied to the range beginning at \p out_false.
298
+ *
299
+ * The algorithm's execution is parallelized as determined by \p exec.
300
+ *
301
+ * \param exec The execution policy to use for parallelization.
302
+ * \param first The beginning of the sequence to reorder.
303
+ * \param last The end of the sequence to reorder.
304
+ * \param out_true The destination of the resulting sequence of elements which satisfy \p pred.
305
+ * \param out_false The destination of the resulting sequence of elements which fail to satisfy \p pred.
306
+ * \param pred A function object which decides to which partition each element of the
307
+ * sequence <tt>[first, last)</tt> belongs.
308
+ * \return A \p pair p such that <tt>p.first</tt> is the end of the output range beginning
309
+ * at \p out_true and <tt>p.second</tt> is the end of the output range beginning at
310
+ * \p out_false.
311
+ *
312
+ * \tparam DerivedPolicy The name of the derived execution policy.
313
+ * \tparam InputIterator is a model of <a href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input
314
+ * Iterator</a>, and \p InputIterator's \c value_type is convertible to \p Predicate's argument type and \p
315
+ * InputIterator's \c value_type is convertible to \p OutputIterator1 and \p OutputIterator2's \c value_types. \tparam
316
+ * OutputIterator1 is a model of <a href="https://en.cppreference.com/w/cpp/iterator/output_iterator">Output
317
+ * Iterator</a>. \tparam OutputIterator2 is a model of <a
318
+ * href="https://en.cppreference.com/w/cpp/iterator/output_iterator">Output Iterator</a>. \tparam Predicate is a model
319
+ * of <a href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
320
+ *
321
+ * \pre The input range shall not overlap with either output range.
322
+ *
323
+ * The following code snippet demonstrates how to use \p partition_copy to separate a
324
+ * sequence into two output sequences of even and odd numbers using the \p thrust::host execution policy for
325
+ * parallelization:
326
+ *
327
+ * \code
328
+ * #include <thrust/partition.h>
329
+ * #include <thrust/execution_policy.h>
330
+ * ...
331
+ * struct is_even
332
+ * {
333
+ * __host__ __device__
334
+ * bool operator()(const int &x)
335
+ * {
336
+ * return (x % 2) == 0;
337
+ * }
338
+ * };
339
+ * ...
340
+ * int A[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
341
+ * int result[10];
342
+ * const int N = sizeof(A)/sizeof(int);
343
+ * int *evens = result;
344
+ * int *odds = result + 5;
345
+ * thrust::partition_copy(thrust::host, A, A + N, evens, odds, is_even());
346
+ * // A remains {1, 2, 3, 4, 5, 6, 7, 8, 9, 10}
347
+ * // result is now {2, 4, 6, 8, 10, 1, 3, 5, 7, 9}
348
+ * // evens points to {2, 4, 6, 8, 10}
349
+ * // odds points to {1, 3, 5, 7, 9}
350
+ * \endcode
351
+ *
352
+ * \note The relative order of elements in the two reordered sequences is not
353
+ * necessarily the same as it was in the original sequence. A different algorithm,
354
+ * \p stable_partition_copy, does guarantee to preserve the relative order.
355
+ *
356
+ * \see http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2569.pdf
357
+ * \see \p stable_partition_copy
358
+ * \see \p partition
359
+ */
360
+ template <typename DerivedPolicy,
361
+ typename InputIterator,
362
+ typename OutputIterator1,
363
+ typename OutputIterator2,
364
+ typename Predicate>
365
+ _CCCL_HOST_DEVICE ::cuda::std::pair<OutputIterator1, OutputIterator2> partition_copy(
366
+ const thrust::detail::execution_policy_base<DerivedPolicy>& exec,
367
+ InputIterator first,
368
+ InputIterator last,
369
+ OutputIterator1 out_true,
370
+ OutputIterator2 out_false,
371
+ Predicate pred);
372
+
373
+ /*! \p partition_copy differs from \p partition only in that the reordered
374
+ * sequence is written to different output sequences, rather than in place.
375
+ *
376
+ * \p partition_copy copies the elements <tt>[first, last)</tt> based on the
377
+ * function object \p pred. All of the elements that satisfy \p pred are copied
378
+ * to the range beginning at \p out_true and all the elements that fail to satisfy it
379
+ * are copied to the range beginning at \p out_false.
380
+ *
381
+ * \param first The beginning of the sequence to reorder.
382
+ * \param last The end of the sequence to reorder.
383
+ * \param out_true The destination of the resulting sequence of elements which satisfy \p pred.
384
+ * \param out_false The destination of the resulting sequence of elements which fail to satisfy \p pred.
385
+ * \param pred A function object which decides to which partition each element of the
386
+ * sequence <tt>[first, last)</tt> belongs.
387
+ * \return A \p pair p such that <tt>p.first</tt> is the end of the output range beginning
388
+ * at \p out_true and <tt>p.second</tt> is the end of the output range beginning at
389
+ * \p out_false.
390
+ *
391
+ * \tparam InputIterator is a model of <a href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input
392
+ * Iterator</a>, and \p InputIterator's \c value_type is convertible to \p Predicate's argument type and \p
393
+ * InputIterator's \c value_type is convertible to \p OutputIterator1 and \p OutputIterator2's \c value_types. \tparam
394
+ * OutputIterator1 is a model of <a href="https://en.cppreference.com/w/cpp/iterator/output_iterator">Output
395
+ * Iterator</a>. \tparam OutputIterator2 is a model of <a
396
+ * href="https://en.cppreference.com/w/cpp/iterator/output_iterator">Output Iterator</a>. \tparam Predicate is a model
397
+ * of <a href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
398
+ *
399
+ * \pre The input range shall not overlap with either output range.
400
+ *
401
+ * The following code snippet demonstrates how to use \p partition_copy to separate a
402
+ * sequence into two output sequences of even and odd numbers.
403
+ *
404
+ * \code
405
+ * #include <thrust/partition.h>
406
+ * ...
407
+ * struct is_even
408
+ * {
409
+ * __host__ __device__
410
+ * bool operator()(const int &x)
411
+ * {
412
+ * return (x % 2) == 0;
413
+ * }
414
+ * };
415
+ * ...
416
+ * int A[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
417
+ * int result[10];
418
+ * const int N = sizeof(A)/sizeof(int);
419
+ * int *evens = result;
420
+ * int *odds = result + 5;
421
+ * thrust::partition_copy(A, A + N, evens, odds, is_even());
422
+ * // A remains {1, 2, 3, 4, 5, 6, 7, 8, 9, 10}
423
+ * // result is now {2, 4, 6, 8, 10, 1, 3, 5, 7, 9}
424
+ * // evens points to {2, 4, 6, 8, 10}
425
+ * // odds points to {1, 3, 5, 7, 9}
426
+ * \endcode
427
+ *
428
+ * \note The relative order of elements in the two reordered sequences is not
429
+ * necessarily the same as it was in the original sequence. A different algorithm,
430
+ * \p stable_partition_copy, does guarantee to preserve the relative order.
431
+ *
432
+ * \see http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2569.pdf
433
+ * \see \p stable_partition_copy
434
+ * \see \p partition
435
+ */
436
+ template <typename InputIterator, typename OutputIterator1, typename OutputIterator2, typename Predicate>
437
+ ::cuda::std::pair<OutputIterator1, OutputIterator2> partition_copy(
438
+ InputIterator first, InputIterator last, OutputIterator1 out_true, OutputIterator2 out_false, Predicate pred);
439
+
440
+ /*! \p partition_copy differs from \p partition only in that the reordered
441
+ * sequence is written to different output sequences, rather than in place.
442
+ *
443
+ * \p partition_copy copies the elements <tt>[first, last)</tt> based on the
444
+ * function object \p pred which is applied to a range of stencil elements. All of the elements
445
+ * whose corresponding stencil element satisfies \p pred are copied to the range beginning at \p out_true
446
+ * and all the elements whose stencil element fails to satisfy it are copied to the range beginning
447
+ * at \p out_false.
448
+ *
449
+ * The algorithm's execution is parallelized as determined by \p exec.
450
+ *
451
+ * \param exec The execution policy to use for parallelization.
452
+ * \param first The beginning of the sequence to reorder.
453
+ * \param last The end of the sequence to reorder.
454
+ * \param stencil The beginning of the stencil sequence.
455
+ * \param out_true The destination of the resulting sequence of elements which satisfy \p pred.
456
+ * \param out_false The destination of the resulting sequence of elements which fail to satisfy \p pred.
457
+ * \param pred A function object which decides to which partition each element of the
458
+ * sequence <tt>[first, last)</tt> belongs.
459
+ * \return A \p pair p such that <tt>p.first</tt> is the end of the output range beginning
460
+ * at \p out_true and <tt>p.second</tt> is the end of the output range beginning at
461
+ * \p out_false.
462
+ *
463
+ * \tparam DerivedPolicy The name of the derived execution policy.
464
+ * \tparam InputIterator1 is a model of <a href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input
465
+ * Iterator</a>, and \p InputIterator's \c value_type is convertible to \p OutputIterator1 and \p OutputIterator2's \c
466
+ * value_types. \tparam InputIterator2 is a model of <a
467
+ * href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input Iterator</a>, and \p InputIterator2's \c
468
+ * value_type is convertible to \p Predicate's argument type. \tparam OutputIterator1 is a model of <a
469
+ * href="https://en.cppreference.com/w/cpp/iterator/output_iterator">Output Iterator</a>. \tparam OutputIterator2 is a
470
+ * model of <a href="https://en.cppreference.com/w/cpp/iterator/output_iterator">Output Iterator</a>. \tparam Predicate
471
+ * is a model of <a href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
472
+ *
473
+ * \pre The input ranges shall not overlap with either output range.
474
+ *
475
+ * The following code snippet demonstrates how to use \p partition_copy to separate a
476
+ * sequence into two output sequences of even and odd numbers using the \p thrust::host execution
477
+ * policy for parallelization.
478
+ *
479
+ * \code
480
+ * #include <thrust/partition.h>
481
+ * #include <thrust/functional.h>
482
+ * #include <thrust/execution_policy.h>
483
+ * ...
484
+ * int A[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
485
+ * int S[] = {0, 1, 0, 1, 0, 1, 0, 1, 0, 1};
486
+ * int result[10];
487
+ * const int N = sizeof(A)/sizeof(int);
488
+ * int *evens = result;
489
+ * int *odds = result + 5;
490
+ * thrust::stable_partition_copy(thrust::host, A, A + N, S, evens, odds, ::cuda::std::identity{});
491
+ * // A remains {1, 2, 3, 4, 5, 6, 7, 8, 9, 10}
492
+ * // S remains {0, 1, 0, 1, 0, 1, 0, 1, 0, 1}
493
+ * // result is now {2, 4, 6, 8, 10, 1, 3, 5, 7, 9}
494
+ * // evens points to {2, 4, 6, 8, 10}
495
+ * // odds points to {1, 3, 5, 7, 9}
496
+ * \endcode
497
+ *
498
+ * \note The relative order of elements in the two reordered sequences is not
499
+ * necessarily the same as it was in the original sequence. A different algorithm,
500
+ * \p stable_partition_copy, does guarantee to preserve the relative order.
501
+ *
502
+ * \see http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2569.pdf
503
+ * \see \p stable_partition_copy
504
+ * \see \p partition
505
+ */
506
+ template <typename DerivedPolicy,
507
+ typename InputIterator1,
508
+ typename InputIterator2,
509
+ typename OutputIterator1,
510
+ typename OutputIterator2,
511
+ typename Predicate>
512
+ _CCCL_HOST_DEVICE ::cuda::std::pair<OutputIterator1, OutputIterator2> partition_copy(
513
+ const thrust::detail::execution_policy_base<DerivedPolicy>& exec,
514
+ InputIterator1 first,
515
+ InputIterator1 last,
516
+ InputIterator2 stencil,
517
+ OutputIterator1 out_true,
518
+ OutputIterator2 out_false,
519
+ Predicate pred);
520
+
521
+ /*! \p partition_copy differs from \p partition only in that the reordered
522
+ * sequence is written to different output sequences, rather than in place.
523
+ *
524
+ * \p partition_copy copies the elements <tt>[first, last)</tt> based on the
525
+ * function object \p pred which is applied to a range of stencil elements. All of the elements
526
+ * whose corresponding stencil element satisfies \p pred are copied to the range beginning at \p out_true
527
+ * and all the elements whose stencil element fails to satisfy it are copied to the range beginning
528
+ * at \p out_false.
529
+ *
530
+ * \param first The beginning of the sequence to reorder.
531
+ * \param last The end of the sequence to reorder.
532
+ * \param stencil The beginning of the stencil sequence.
533
+ * \param out_true The destination of the resulting sequence of elements which satisfy \p pred.
534
+ * \param out_false The destination of the resulting sequence of elements which fail to satisfy \p pred.
535
+ * \param pred A function object which decides to which partition each element of the
536
+ * sequence <tt>[first, last)</tt> belongs.
537
+ * \return A \p pair p such that <tt>p.first</tt> is the end of the output range beginning
538
+ * at \p out_true and <tt>p.second</tt> is the end of the output range beginning at
539
+ * \p out_false.
540
+ *
541
+ * \tparam InputIterator1 is a model of <a href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input
542
+ * Iterator</a>, and \p InputIterator's \c value_type is convertible to \p OutputIterator1 and \p OutputIterator2's \c
543
+ * value_types. \tparam InputIterator2 is a model of <a
544
+ * href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input Iterator</a>, and \p InputIterator2's \c
545
+ * value_type is convertible to \p Predicate's argument type. \tparam OutputIterator1 is a model of <a
546
+ * href="https://en.cppreference.com/w/cpp/iterator/output_iterator">Output Iterator</a>. \tparam OutputIterator2 is a
547
+ * model of <a href="https://en.cppreference.com/w/cpp/iterator/output_iterator">Output Iterator</a>. \tparam Predicate
548
+ * is a model of <a href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
549
+ *
550
+ * \pre The input ranges shall not overlap with either output range.
551
+ *
552
+ * The following code snippet demonstrates how to use \p partition_copy to separate a
553
+ * sequence into two output sequences of even and odd numbers.
554
+ *
555
+ * \code
556
+ * #include <thrust/partition.h>
557
+ * #include <thrust/functional.h>
558
+ * ...
559
+ * int A[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
560
+ * int S[] = {0, 1, 0, 1, 0, 1, 0, 1, 0, 1};
561
+ * int result[10];
562
+ * const int N = sizeof(A)/sizeof(int);
563
+ * int *evens = result;
564
+ * int *odds = result + 5;
565
+ * thrust::stable_partition_copy(A, A + N, S, evens, odds, ::cuda::std::identity{});
566
+ * // A remains {1, 2, 3, 4, 5, 6, 7, 8, 9, 10}
567
+ * // S remains {0, 1, 0, 1, 0, 1, 0, 1, 0, 1}
568
+ * // result is now {2, 4, 6, 8, 10, 1, 3, 5, 7, 9}
569
+ * // evens points to {2, 4, 6, 8, 10}
570
+ * // odds points to {1, 3, 5, 7, 9}
571
+ * \endcode
572
+ *
573
+ * \note The relative order of elements in the two reordered sequences is not
574
+ * necessarily the same as it was in the original sequence. A different algorithm,
575
+ * \p stable_partition_copy, does guarantee to preserve the relative order.
576
+ *
577
+ * \see http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2569.pdf
578
+ * \see \p stable_partition_copy
579
+ * \see \p partition
580
+ */
581
+ template <typename InputIterator1,
582
+ typename InputIterator2,
583
+ typename OutputIterator1,
584
+ typename OutputIterator2,
585
+ typename Predicate>
586
+ ::cuda::std::pair<OutputIterator1, OutputIterator2> partition_copy(
587
+ InputIterator1 first,
588
+ InputIterator1 last,
589
+ InputIterator2 stencil,
590
+ OutputIterator1 out_true,
591
+ OutputIterator2 out_false,
592
+ Predicate pred);
593
+
594
+ /*! \p stable_partition is much like \p partition : it reorders the elements in the
595
+ * range <tt>[first, last)</tt> based on the function object \p pred, such that all of
596
+ * the elements that satisfy \p pred precede all of the elements that fail to satisfy
597
+ * it. The postcondition is that, for some iterator \p middle in the range
598
+ * <tt>[first, last)</tt>, <tt>pred(*i)</tt> is \c true for every iterator \c i in the
599
+ * range <tt>[first,middle)</tt> and \c false for every iterator \c i in the range
600
+ * <tt>[middle, last)</tt>. The return value of \p stable_partition is \c middle.
601
+ *
602
+ * \p stable_partition differs from \p partition in that \p stable_partition is
603
+ * guaranteed to preserve relative order. That is, if \c x and \c y are elements in
604
+ * <tt>[first, last)</tt>, and \c stencil_x and \c stencil_y are the stencil elements
605
+ * in corresponding positions within <tt>[stencil, stencil + (last - first))</tt>,
606
+ * and <tt>pred(stencil_x) == pred(stencil_y)</tt>, and if \c x precedes
607
+ * \c y, then it will still be true after \p stable_partition that \c x precedes \c y.
608
+ *
609
+ * The algorithm's execution is parallelized as determined by \p exec.
610
+ *
611
+ * \param exec The execution policy to use for parallelization.
612
+ * \param first The first element of the sequence to reorder.
613
+ * \param last One position past the last element of the sequence to reorder.
614
+ * \param pred A function object which decides to which partition each element of the
615
+ * sequence <tt>[first, last)</tt> belongs.
616
+ * \return An iterator referring to the first element of the second partition, that is,
617
+ * the sequence of the elements which do not satisfy pred.
618
+ *
619
+ * \tparam DerivedPolicy The name of the derived execution policy.
620
+ * \tparam ForwardIterator is a model of <a href="https://en.cppreference.com/w/cpp/iterator/forward_iterator">Forward
621
+ * Iterator</a>, and \p ForwardIterator's \c value_type is convertible to \p Predicate's argument type, and \p
622
+ * ForwardIterator is mutable. \tparam Predicate is a model of <a
623
+ * href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
624
+ *
625
+ * The following code snippet demonstrates how to use \p stable_partition to reorder a
626
+ * sequence so that even numbers precede odd numbers using the \p thrust::host execution policy for parallelization:
627
+ *
628
+ * \code
629
+ * #include <thrust/partition.h>
630
+ * #include <thrust/execution_policy.h>
631
+ * ...
632
+ * struct is_even
633
+ * {
634
+ * __host__ __device__
635
+ * bool operator()(const int &x)
636
+ * {
637
+ * return (x % 2) == 0;
638
+ * }
639
+ * };
640
+ * ...
641
+ * int A[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
642
+ * const int N = sizeof(A)/sizeof(int);
643
+ * thrust::stable_partition(thrust::host,
644
+ * A, A + N,
645
+ * is_even());
646
+ * // A is now {2, 4, 6, 8, 10, 1, 3, 5, 7, 9}
647
+ * \endcode
648
+ *
649
+ * \see https://en.cppreference.com/w/cpp/algorithm/stable_partition
650
+ * \see \p partition
651
+ * \see \p stable_partition_copy
652
+ */
653
+ template <typename DerivedPolicy, typename ForwardIterator, typename Predicate>
654
+ _CCCL_HOST_DEVICE ForwardIterator stable_partition(
655
+ const thrust::detail::execution_policy_base<DerivedPolicy>& exec,
656
+ ForwardIterator first,
657
+ ForwardIterator last,
658
+ Predicate pred);
659
+
660
+ /*! \p stable_partition is much like \p partition : it reorders the elements in the
661
+ * range <tt>[first, last)</tt> based on the function object \p pred, such that all of
662
+ * the elements that satisfy \p pred precede all of the elements that fail to satisfy
663
+ * it. The postcondition is that, for some iterator \p middle in the range
664
+ * <tt>[first, last)</tt>, <tt>pred(*i)</tt> is \c true for every iterator \c i in the
665
+ * range <tt>[first,middle)</tt> and \c false for every iterator \c i in the range
666
+ * <tt>[middle, last)</tt>. The return value of \p stable_partition is \c middle.
667
+ *
668
+ * \p stable_partition differs from \p partition in that \p stable_partition is
669
+ * guaranteed to preserve relative order. That is, if \c x and \c y are elements in
670
+ * <tt>[first, last)</tt>, and \c stencil_x and \c stencil_y are the stencil elements
671
+ * in corresponding positions within <tt>[stencil, stencil + (last - first))</tt>,
672
+ * and <tt>pred(stencil_x) == pred(stencil_y)</tt>, and if \c x precedes
673
+ * \c y, then it will still be true after \p stable_partition that \c x precedes \c y.
674
+ *
675
+ * \param first The first element of the sequence to reorder.
676
+ * \param last One position past the last element of the sequence to reorder.
677
+ * \param pred A function object which decides to which partition each element of the
678
+ * sequence <tt>[first, last)</tt> belongs.
679
+ * \return An iterator referring to the first element of the second partition, that is,
680
+ * the sequence of the elements which do not satisfy pred.
681
+ *
682
+ * \tparam ForwardIterator is a model of <a href="https://en.cppreference.com/w/cpp/iterator/forward_iterator">Forward
683
+ * Iterator</a>, and \p ForwardIterator's \c value_type is convertible to \p Predicate's argument type, and \p
684
+ * ForwardIterator is mutable. \tparam Predicate is a model of <a
685
+ * href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
686
+ *
687
+ * The following code snippet demonstrates how to use \p stable_partition to reorder a
688
+ * sequence so that even numbers precede odd numbers.
689
+ *
690
+ * \code
691
+ * #include <thrust/partition.h>
692
+ * ...
693
+ * struct is_even
694
+ * {
695
+ * __host__ __device__
696
+ * bool operator()(const int &x)
697
+ * {
698
+ * return (x % 2) == 0;
699
+ * }
700
+ * };
701
+ * ...
702
+ * int A[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
703
+ * const int N = sizeof(A)/sizeof(int);
704
+ * thrust::stable_partition(A, A + N,
705
+ * is_even());
706
+ * // A is now {2, 4, 6, 8, 10, 1, 3, 5, 7, 9}
707
+ * \endcode
708
+ *
709
+ * \see https://en.cppreference.com/w/cpp/algorithm/stable_partition
710
+ * \see \p partition
711
+ * \see \p stable_partition_copy
712
+ */
713
+ template <typename ForwardIterator, typename Predicate>
714
+ ForwardIterator stable_partition(ForwardIterator first, ForwardIterator last, Predicate pred);
715
+
716
+ /*! \p stable_partition is much like \p partition: it reorders the elements in the
717
+ * range <tt>[first, last)</tt> based on the function object \p pred applied to a stencil
718
+ * range <tt>[stencil, stencil + (last - first))</tt>, such that all of
719
+ * the elements whose corresponding stencil element satisfies \p pred precede all of the elements whose
720
+ * corresponding stencil element fails to satisfy it. The postcondition is that, for some iterator
721
+ * \c middle in the range <tt>[first, last)</tt>, <tt>pred(*stencil_i)</tt> is \c true for every iterator
722
+ * \c stencil_i in the range <tt>[stencil,stencil + (middle - first))</tt> and \c false for every iterator \c stencil_i
723
+ * in the range <tt>[stencil + (middle - first), stencil + (last - first))</tt>.
724
+ * The return value of \p stable_partition is \c middle.
725
+ *
726
+ * \p stable_partition differs from \p partition in that \p stable_partition is
727
+ * guaranteed to preserve relative order. That is, if \c x and \c y are elements in
728
+ * <tt>[first, last)</tt>, such that <tt>pred(x) == pred(y)</tt>, and if \c x precedes
729
+ * \c y, then it will still be true after \p stable_partition that \c x precedes \c y.
730
+ *
731
+ * The algorithm's execution is parallelized as determined by \p exec.
732
+ *
733
+ * \param exec The execution policy to use for parallelization.
734
+ * \param first The first element of the sequence to reorder.
735
+ * \param last One position past the last element of the sequence to reorder.
736
+ * \param stencil The beginning of the stencil sequence.
737
+ * \param pred A function object which decides to which partition each element of the
738
+ * sequence <tt>[first, last)</tt> belongs.
739
+ * \return An iterator referring to the first element of the second partition, that is,
740
+ * the sequence of the elements whose stencil elements do not satisfy \p pred.
741
+ *
742
+ * \tparam DerivedPolicy The name of the derived execution policy.
743
+ * \tparam ForwardIterator is a model of <a href="https://en.cppreference.com/w/cpp/iterator/forward_iterator">Forward
744
+ * Iterator</a>, and \p ForwardIterator is mutable. \tparam InputIterator is a model of <a
745
+ * href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input Iterator</a>, and \p InputIterator's \c
746
+ * value_type is convertible to \p Predicate's argument type. \tparam Predicate is a model of <a
747
+ * href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
748
+ *
749
+ * \pre The range <tt>[first, last)</tt> shall not overlap with the range <tt>[stencil, stencil + (last - first))</tt>.
750
+ *
751
+ * The following code snippet demonstrates how to use \p stable_partition to reorder a
752
+ * sequence so that even numbers precede odd numbers using the \p thrust::host execution policy for parallelization:
753
+ *
754
+ * \code
755
+ * #include <thrust/partition.h>
756
+ * #include <thrust/execution_policy.h>
757
+ * ...
758
+ * struct is_even
759
+ * {
760
+ * __host__ __device__
761
+ * bool operator()(const int &x)
762
+ * {
763
+ * return (x % 2) == 0;
764
+ * }
765
+ * };
766
+ * ...
767
+ * int A[] = {0, 1, 0, 1, 0, 1, 0, 1, 0, 1};
768
+ * int S[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
769
+ * const int N = sizeof(A)/sizeof(int);
770
+ * thrust::stable_partition(thrust::host, A, A + N, S, is_even());
771
+ * // A is now {1, 1, 1, 1, 1, 0, 0, 0, 0, 0}
772
+ * // S is unmodified
773
+ * \endcode
774
+ *
775
+ * \see https://en.cppreference.com/w/cpp/algorithm/stable_partition
776
+ * \see \p partition
777
+ * \see \p stable_partition_copy
778
+ */
779
+ template <typename DerivedPolicy, typename ForwardIterator, typename InputIterator, typename Predicate>
780
+ _CCCL_HOST_DEVICE ForwardIterator stable_partition(
781
+ const thrust::detail::execution_policy_base<DerivedPolicy>& exec,
782
+ ForwardIterator first,
783
+ ForwardIterator last,
784
+ InputIterator stencil,
785
+ Predicate pred);
786
+
787
+ /*! \p stable_partition is much like \p partition: it reorders the elements in the
788
+ * range <tt>[first, last)</tt> based on the function object \p pred applied to a stencil
789
+ * range <tt>[stencil, stencil + (last - first))</tt>, such that all of
790
+ * the elements whose corresponding stencil element satisfies \p pred precede all of the elements whose
791
+ * corresponding stencil element fails to satisfy it. The postcondition is that, for some iterator
792
+ * \c middle in the range <tt>[first, last)</tt>, <tt>pred(*stencil_i)</tt> is \c true for every iterator
793
+ * \c stencil_i in the range <tt>[stencil,stencil + (middle - first))</tt> and \c false for every iterator \c stencil_i
794
+ * in the range <tt>[stencil + (middle - first), stencil + (last - first))</tt>.
795
+ * The return value of \p stable_partition is \c middle.
796
+ *
797
+ * \p stable_partition differs from \p partition in that \p stable_partition is
798
+ * guaranteed to preserve relative order. That is, if \c x and \c y are elements in
799
+ * <tt>[first, last)</tt>, such that <tt>pred(x) == pred(y)</tt>, and if \c x precedes
800
+ * \c y, then it will still be true after \p stable_partition that \c x precedes \c y.
801
+ *
802
+ * \param first The first element of the sequence to reorder.
803
+ * \param last One position past the last element of the sequence to reorder.
804
+ * \param stencil The beginning of the stencil sequence.
805
+ * \param pred A function object which decides to which partition each element of the
806
+ * sequence <tt>[first, last)</tt> belongs.
807
+ * \return An iterator referring to the first element of the second partition, that is,
808
+ * the sequence of the elements whose stencil elements do not satisfy \p pred.
809
+ *
810
+ * \tparam ForwardIterator is a model of <a href="https://en.cppreference.com/w/cpp/iterator/forward_iterator">Forward
811
+ * Iterator</a>, and \p ForwardIterator is mutable. \tparam InputIterator is a model of <a
812
+ * href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input Iterator</a>, and \p InputIterator's \c
813
+ * value_type is convertible to \p Predicate's argument type. \tparam Predicate is a model of <a
814
+ * href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
815
+ *
816
+ * \pre The range <tt>[first, last)</tt> shall not overlap with the range <tt>[stencil, stencil + (last - first))</tt>.
817
+ *
818
+ * The following code snippet demonstrates how to use \p stable_partition to reorder a
819
+ * sequence so that even numbers precede odd numbers.
820
+ *
821
+ * \code
822
+ * #include <thrust/partition.h>
823
+ * ...
824
+ * struct is_even
825
+ * {
826
+ * __host__ __device__
827
+ * bool operator()(const int &x)
828
+ * {
829
+ * return (x % 2) == 0;
830
+ * }
831
+ * };
832
+ * ...
833
+ * int A[] = {0, 1, 0, 1, 0, 1, 0, 1, 0, 1};
834
+ * int S[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
835
+ * const int N = sizeof(A)/sizeof(int);
836
+ * thrust::stable_partition(A, A + N, S, is_even());
837
+ * // A is now {1, 1, 1, 1, 1, 0, 0, 0, 0, 0}
838
+ * // S is unmodified
839
+ * \endcode
840
+ *
841
+ * \see https://en.cppreference.com/w/cpp/algorithm/stable_partition
842
+ * \see \p partition
843
+ * \see \p stable_partition_copy
844
+ */
845
+ template <typename ForwardIterator, typename InputIterator, typename Predicate>
846
+ ForwardIterator stable_partition(ForwardIterator first, ForwardIterator last, InputIterator stencil, Predicate pred);
847
+
848
+ /*! \p stable_partition_copy differs from \p stable_partition only in that the reordered
849
+ * sequence is written to different output sequences, rather than in place.
850
+ *
851
+ * \p stable_partition_copy copies the elements <tt>[first, last)</tt> based on the
852
+ * function object \p pred. All of the elements that satisfy \p pred are copied
853
+ * to the range beginning at \p out_true and all the elements that fail to satisfy it
854
+ * are copied to the range beginning at \p out_false.
855
+ *
856
+ * \p stable_partition_copy differs from \p partition_copy in that
857
+ * \p stable_partition_copy is guaranteed to preserve relative order. That is, if
858
+ * \c x and \c y are elements in <tt>[first, last)</tt>, such that
859
+ * <tt>pred(x) == pred(y)</tt>, and if \c x precedes \c y, then it will still be true
860
+ * after \p stable_partition_copy that \c x precedes \c y in the output.
861
+ *
862
+ * The algorithm's execution is parallelized as determined by \p exec.
863
+ *
864
+ * \param exec The execution policy to use for parallelization.
865
+ * \param first The first element of the sequence to reorder.
866
+ * \param last One position past the last element of the sequence to reorder.
867
+ * \param out_true The destination of the resulting sequence of elements which satisfy \p pred.
868
+ * \param out_false The destination of the resulting sequence of elements which fail to satisfy \p pred.
869
+ * \param pred A function object which decides to which partition each element of the
870
+ * sequence <tt>[first, last)</tt> belongs.
871
+ * \return A \p pair p such that <tt>p.first</tt> is the end of the output range beginning
872
+ * at \p out_true and <tt>p.second</tt> is the end of the output range beginning at
873
+ * \p out_false.
874
+ *
875
+ * \tparam DerivedPolicy The name of the derived execution policy.
876
+ * \tparam InputIterator is a model of <a href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input
877
+ * Iterator</a>, and \p InputIterator's \c value_type is convertible to \p Predicate's argument type and \p
878
+ * InputIterator's \c value_type is convertible to \p OutputIterator1 and \p OutputIterator2's \c value_types. \tparam
879
+ * OutputIterator1 is a model of <a href="https://en.cppreference.com/w/cpp/iterator/output_iterator">Output
880
+ * Iterator</a>. \tparam OutputIterator2 is a model of <a
881
+ * href="https://en.cppreference.com/w/cpp/iterator/output_iterator">Output Iterator</a>. \tparam Predicate is a model
882
+ * of <a href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
883
+ *
884
+ * \pre The input ranges shall not overlap with either output range.
885
+ *
886
+ * The following code snippet demonstrates how to use \p stable_partition_copy to
887
+ * reorder a sequence so that even numbers precede odd numbers using the \p thrust::host execution policy for
888
+ * parallelization:
889
+ *
890
+ * \code
891
+ * #include <thrust/partition.h>
892
+ * #include <thrust/execution_policy.h>
893
+ * ...
894
+ * struct is_even
895
+ * {
896
+ * __host__ __device__
897
+ * bool operator()(const int &x)
898
+ * {
899
+ * return (x % 2) == 0;
900
+ * }
901
+ * };
902
+ * ...
903
+ * int A[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
904
+ * int result[10];
905
+ * const int N = sizeof(A)/sizeof(int);
906
+ * int *evens = result;
907
+ * int *odds = result + 5;
908
+ * thrust::stable_partition_copy(thrust::host, A, A + N, evens, odds, is_even());
909
+ * // A remains {1, 2, 3, 4, 5, 6, 7, 8, 9, 10}
910
+ * // result is now {2, 4, 6, 8, 10, 1, 3, 5, 7, 9}
911
+ * // evens points to {2, 4, 6, 8, 10}
912
+ * // odds points to {1, 3, 5, 7, 9}
913
+ * \endcode
914
+ *
915
+ * \see http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2569.pdf
916
+ * \see \p partition_copy
917
+ * \see \p stable_partition
918
+ */
919
+ template <typename DerivedPolicy,
920
+ typename InputIterator,
921
+ typename OutputIterator1,
922
+ typename OutputIterator2,
923
+ typename Predicate>
924
+ _CCCL_HOST_DEVICE ::cuda::std::pair<OutputIterator1, OutputIterator2> stable_partition_copy(
925
+ const thrust::detail::execution_policy_base<DerivedPolicy>& exec,
926
+ InputIterator first,
927
+ InputIterator last,
928
+ OutputIterator1 out_true,
929
+ OutputIterator2 out_false,
930
+ Predicate pred);
931
+
932
+ /*! \p stable_partition_copy differs from \p stable_partition only in that the reordered
933
+ * sequence is written to different output sequences, rather than in place.
934
+ *
935
+ * \p stable_partition_copy copies the elements <tt>[first, last)</tt> based on the
936
+ * function object \p pred. All of the elements that satisfy \p pred are copied
937
+ * to the range beginning at \p out_true and all the elements that fail to satisfy it
938
+ * are copied to the range beginning at \p out_false.
939
+ *
940
+ * \p stable_partition_copy differs from \p partition_copy in that
941
+ * \p stable_partition_copy is guaranteed to preserve relative order. That is, if
942
+ * \c x and \c y are elements in <tt>[first, last)</tt>, such that
943
+ * <tt>pred(x) == pred(y)</tt>, and if \c x precedes \c y, then it will still be true
944
+ * after \p stable_partition_copy that \c x precedes \c y in the output.
945
+ *
946
+ * \param first The first element of the sequence to reorder.
947
+ * \param last One position past the last element of the sequence to reorder.
948
+ * \param out_true The destination of the resulting sequence of elements which satisfy \p pred.
949
+ * \param out_false The destination of the resulting sequence of elements which fail to satisfy \p pred.
950
+ * \param pred A function object which decides to which partition each element of the
951
+ * sequence <tt>[first, last)</tt> belongs.
952
+ * \return A \p pair p such that <tt>p.first</tt> is the end of the output range beginning
953
+ * at \p out_true and <tt>p.second</tt> is the end of the output range beginning at
954
+ * \p out_false.
955
+ *
956
+ * \tparam InputIterator is a model of <a href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input
957
+ * Iterator</a>, and \p InputIterator's \c value_type is convertible to \p Predicate's argument type and \p
958
+ * InputIterator's \c value_type is convertible to \p OutputIterator1 and \p OutputIterator2's \c value_types. \tparam
959
+ * OutputIterator1 is a model of <a href="https://en.cppreference.com/w/cpp/iterator/output_iterator">Output
960
+ * Iterator</a>. \tparam OutputIterator2 is a model of <a
961
+ * href="https://en.cppreference.com/w/cpp/iterator/output_iterator">Output Iterator</a>. \tparam Predicate is a model
962
+ * of <a href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
963
+ *
964
+ * \pre The input ranges shall not overlap with either output range.
965
+ *
966
+ * The following code snippet demonstrates how to use \p stable_partition_copy to
967
+ * reorder a sequence so that even numbers precede odd numbers.
968
+ *
969
+ * \code
970
+ * #include <thrust/partition.h>
971
+ * ...
972
+ * struct is_even
973
+ * {
974
+ * __host__ __device__
975
+ * bool operator()(const int &x)
976
+ * {
977
+ * return (x % 2) == 0;
978
+ * }
979
+ * };
980
+ * ...
981
+ * int A[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
982
+ * int result[10];
983
+ * const int N = sizeof(A)/sizeof(int);
984
+ * int *evens = result;
985
+ * int *odds = result + 5;
986
+ * thrust::stable_partition_copy(A, A + N, evens, odds, is_even());
987
+ * // A remains {1, 2, 3, 4, 5, 6, 7, 8, 9, 10}
988
+ * // result is now {2, 4, 6, 8, 10, 1, 3, 5, 7, 9}
989
+ * // evens points to {2, 4, 6, 8, 10}
990
+ * // odds points to {1, 3, 5, 7, 9}
991
+ * \endcode
992
+ *
993
+ * \see http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2569.pdf
994
+ * \see \p partition_copy
995
+ * \see \p stable_partition
996
+ */
997
+ template <typename InputIterator, typename OutputIterator1, typename OutputIterator2, typename Predicate>
998
+ ::cuda::std::pair<OutputIterator1, OutputIterator2> stable_partition_copy(
999
+ InputIterator first, InputIterator last, OutputIterator1 out_true, OutputIterator2 out_false, Predicate pred);
1000
+
1001
+ /*! \p stable_partition_copy differs from \p stable_partition only in that the reordered
1002
+ * sequence is written to different output sequences, rather than in place.
1003
+ *
1004
+ * \p stable_partition_copy copies the elements <tt>[first, last)</tt> based on the
1005
+ * function object \p pred which is applied to a range of stencil elements. All of the elements
1006
+ * whose corresponding stencil element satisfies \p pred are copied to the range beginning at \p out_true
1007
+ * and all the elements whose stencil element fails to satisfy it are copied to the range beginning
1008
+ * at \p out_false.
1009
+ *
1010
+ * \p stable_partition_copy differs from \p partition_copy in that
1011
+ * \p stable_partition_copy is guaranteed to preserve relative order. That is, if
1012
+ * \c x and \c y are elements in <tt>[first, last)</tt>, such that
1013
+ * <tt>pred(x) == pred(y)</tt>, and if \c x precedes \c y, then it will still be true
1014
+ * after \p stable_partition_copy that \c x precedes \c y in the output.
1015
+ *
1016
+ * The algorithm's execution is parallelized as determined by \p exec.
1017
+ *
1018
+ * \param exec The execution policy to use for parallelization.
1019
+ * \param first The first element of the sequence to reorder.
1020
+ * \param last One position past the last element of the sequence to reorder.
1021
+ * \param stencil The beginning of the stencil sequence.
1022
+ * \param out_true The destination of the resulting sequence of elements which satisfy \p pred.
1023
+ * \param out_false The destination of the resulting sequence of elements which fail to satisfy \p pred.
1024
+ * \param pred A function object which decides to which partition each element of the
1025
+ * sequence <tt>[first, last)</tt> belongs.
1026
+ * \return A \p pair p such that <tt>p.first</tt> is the end of the output range beginning
1027
+ * at \p out_true and <tt>p.second</tt> is the end of the output range beginning at
1028
+ * \p out_false.
1029
+ *
1030
+ * \tparam DerivedPolicy The name of the derived execution policy.
1031
+ * \tparam InputIterator1 is a model of <a href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input
1032
+ * Iterator</a>, and \p InputIterator's \c value_type is convertible to \p OutputIterator1 and \p OutputIterator2's \c
1033
+ * value_types. \tparam InputIterator2 is a model of <a
1034
+ * href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input Iterator</a>, and \p InputIterator2's \c
1035
+ * value_type is convertible to \p Predicate's argument type. \tparam OutputIterator1 is a model of <a
1036
+ * href="https://en.cppreference.com/w/cpp/iterator/output_iterator">Output Iterator</a>. \tparam OutputIterator2 is a
1037
+ * model of <a href="https://en.cppreference.com/w/cpp/iterator/output_iterator">Output Iterator</a>. \tparam Predicate
1038
+ * is a model of <a href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
1039
+ *
1040
+ * \pre The input ranges shall not overlap with either output range.
1041
+ *
1042
+ * The following code snippet demonstrates how to use \p stable_partition_copy to
1043
+ * reorder a sequence so that even numbers precede odd numbers using the \p thrust::host execution policy for
1044
+ * parallelization:
1045
+ *
1046
+ * \code
1047
+ * #include <thrust/partition.h>
1048
+ * #include <thrust/functional.h>
1049
+ * #include <thrust/execution_policy.h>
1050
+ * ...
1051
+ * int A[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
1052
+ * int S[] = {0, 1, 0, 1, 0, 1, 0, 1, 0, 1};
1053
+ * int result[10];
1054
+ * const int N = sizeof(A)/sizeof(int);
1055
+ * int *evens = result;
1056
+ * int *odds = result + 5;
1057
+ * thrust::stable_partition_copy(thrust::host, A, A + N, S, evens, odds, ::cuda::std::identity{});
1058
+ * // A remains {1, 2, 3, 4, 5, 6, 7, 8, 9, 10}
1059
+ * // S remains {0, 1, 0, 1, 0, 1, 0, 1, 0, 1}
1060
+ * // result is now {2, 4, 6, 8, 10, 1, 3, 5, 7, 9}
1061
+ * // evens points to {2, 4, 6, 8, 10}
1062
+ * // odds points to {1, 3, 5, 7, 9}
1063
+ * \endcode
1064
+ *
1065
+ * \see http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2569.pdf
1066
+ * \see \p partition_copy
1067
+ * \see \p stable_partition
1068
+ */
1069
+ template <typename DerivedPolicy,
1070
+ typename InputIterator1,
1071
+ typename InputIterator2,
1072
+ typename OutputIterator1,
1073
+ typename OutputIterator2,
1074
+ typename Predicate>
1075
+ _CCCL_HOST_DEVICE ::cuda::std::pair<OutputIterator1, OutputIterator2> stable_partition_copy(
1076
+ const thrust::detail::execution_policy_base<DerivedPolicy>& exec,
1077
+ InputIterator1 first,
1078
+ InputIterator1 last,
1079
+ InputIterator2 stencil,
1080
+ OutputIterator1 out_true,
1081
+ OutputIterator2 out_false,
1082
+ Predicate pred);
1083
+
1084
+ /*! \p stable_partition_copy differs from \p stable_partition only in that the reordered
1085
+ * sequence is written to different output sequences, rather than in place.
1086
+ *
1087
+ * \p stable_partition_copy copies the elements <tt>[first, last)</tt> based on the
1088
+ * function object \p pred which is applied to a range of stencil elements. All of the elements
1089
+ * whose corresponding stencil element satisfies \p pred are copied to the range beginning at \p out_true
1090
+ * and all the elements whose stencil element fails to satisfy it are copied to the range beginning
1091
+ * at \p out_false.
1092
+ *
1093
+ * \p stable_partition_copy differs from \p partition_copy in that
1094
+ * \p stable_partition_copy is guaranteed to preserve relative order. That is, if
1095
+ * \c x and \c y are elements in <tt>[first, last)</tt>, such that
1096
+ * <tt>pred(x) == pred(y)</tt>, and if \c x precedes \c y, then it will still be true
1097
+ * after \p stable_partition_copy that \c x precedes \c y in the output.
1098
+ *
1099
+ * \param first The first element of the sequence to reorder.
1100
+ * \param last One position past the last element of the sequence to reorder.
1101
+ * \param stencil The beginning of the stencil sequence.
1102
+ * \param out_true The destination of the resulting sequence of elements which satisfy \p pred.
1103
+ * \param out_false The destination of the resulting sequence of elements which fail to satisfy \p pred.
1104
+ * \param pred A function object which decides to which partition each element of the
1105
+ * sequence <tt>[first, last)</tt> belongs.
1106
+ * \return A \p pair p such that <tt>p.first</tt> is the end of the output range beginning
1107
+ * at \p out_true and <tt>p.second</tt> is the end of the output range beginning at
1108
+ * \p out_false.
1109
+ *
1110
+ * \tparam InputIterator1 is a model of <a href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input
1111
+ * Iterator</a>, and \p InputIterator's \c value_type is convertible to \p OutputIterator1 and \p OutputIterator2's \c
1112
+ * value_types. \tparam InputIterator2 is a model of <a
1113
+ * href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input Iterator</a>, and \p InputIterator2's \c
1114
+ * value_type is convertible to \p Predicate's argument type. \tparam OutputIterator1 is a model of <a
1115
+ * href="https://en.cppreference.com/w/cpp/iterator/output_iterator">Output Iterator</a>. \tparam OutputIterator2 is a
1116
+ * model of <a href="https://en.cppreference.com/w/cpp/iterator/output_iterator">Output Iterator</a>. \tparam Predicate
1117
+ * is a model of <a href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
1118
+ *
1119
+ * \pre The input ranges shall not overlap with either output range.
1120
+ *
1121
+ * The following code snippet demonstrates how to use \p stable_partition_copy to
1122
+ * reorder a sequence so that even numbers precede odd numbers.
1123
+ *
1124
+ * \code
1125
+ * #include <thrust/partition.h>
1126
+ * #include <thrust/functional.h>
1127
+ * ...
1128
+ * int A[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
1129
+ * int S[] = {0, 1, 0, 1, 0, 1, 0, 1, 0, 1};
1130
+ * int result[10];
1131
+ * const int N = sizeof(A)/sizeof(int);
1132
+ * int *evens = result;
1133
+ * int *odds = result + 5;
1134
+ * thrust::stable_partition_copy(A, A + N, S, evens, odds, ::cuda::std::identity{});
1135
+ * // A remains {1, 2, 3, 4, 5, 6, 7, 8, 9, 10}
1136
+ * // S remains {0, 1, 0, 1, 0, 1, 0, 1, 0, 1}
1137
+ * // result is now {2, 4, 6, 8, 10, 1, 3, 5, 7, 9}
1138
+ * // evens points to {2, 4, 6, 8, 10}
1139
+ * // odds points to {1, 3, 5, 7, 9}
1140
+ * \endcode
1141
+ *
1142
+ * \see http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2569.pdf
1143
+ * \see \p partition_copy
1144
+ * \see \p stable_partition
1145
+ */
1146
+ template <typename InputIterator1,
1147
+ typename InputIterator2,
1148
+ typename OutputIterator1,
1149
+ typename OutputIterator2,
1150
+ typename Predicate>
1151
+ ::cuda::std::pair<OutputIterator1, OutputIterator2> stable_partition_copy(
1152
+ InputIterator1 first,
1153
+ InputIterator1 last,
1154
+ InputIterator2 stencil,
1155
+ OutputIterator1 out_true,
1156
+ OutputIterator2 out_false,
1157
+ Predicate pred);
1158
+
1159
+ /*!
1160
+ * \} end group partitioning
1161
+ */
1162
+
1163
+ /*!
1164
+ * \} end group reordering
1165
+ */
1166
+
1167
+ /*! \addtogroup searching
1168
+ * \{
1169
+ */
1170
+
1171
+ /*! \p partition_point returns an iterator pointing to the end of the true
1172
+ * partition of a partitioned range. \p partition_point requires the input range
1173
+ * <tt>[first,last)</tt> to be a partition; that is, all elements which satisfy
1174
+ * <tt>pred</tt> shall appear before those that do not.
1175
+ *
1176
+ * The algorithm's execution is parallelized as determined by \p exec.
1177
+ *
1178
+ * \param exec The execution policy to use for parallelization.
1179
+ * \param first The beginning of the range to consider.
1180
+ * \param last The end of the range to consider.
1181
+ * \param pred A function object which decides to which partition each element of the
1182
+ * range <tt>[first, last)</tt> belongs.
1183
+ * \return An iterator \c mid such that <tt>all_of(first, mid, pred)</tt>
1184
+ * and <tt>none_of(mid, last, pred)</tt> are both true.
1185
+ *
1186
+ * \tparam DerivedPolicy The name of the derived execution policy.
1187
+ * \tparam ForwardIterator is a model of <a href="https://en.cppreference.com/w/cpp/iterator/forward_iterator">Forward
1188
+ * Iterator</a>, and \p ForwardIterator's \c value_type is convertible to \p Predicate's argument type. \tparam
1189
+ * Predicate is a model of <a href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
1190
+ *
1191
+ * \pre The range <tt>[first, last)</tt> shall be partitioned by \p pred.
1192
+ *
1193
+ * \note Though similar, \p partition_point is not redundant with \p find_if_not.
1194
+ * \p partition_point's precondition provides an opportunity for a
1195
+ * faster implementation.
1196
+ *
1197
+ * \code
1198
+ * #include <thrust/partition.h>
1199
+ * #include <thrust/execution_policy.h>
1200
+ *
1201
+ * struct is_even
1202
+ * {
1203
+ * __host__ __device__
1204
+ * bool operator()(const int &x)
1205
+ * {
1206
+ * return (x % 2) == 0;
1207
+ * }
1208
+ * };
1209
+ *
1210
+ * ...
1211
+ *
1212
+ * int A[] = {2, 4, 6, 8, 10, 1, 3, 5, 7, 9};
1213
+ * int * B = thrust::partition_point(thrust::host, A, A + 10, is_even());
1214
+ * // B - A is 5
1215
+ * // [A, B) contains only even values
1216
+ * \endcode
1217
+ *
1218
+ * \see \p partition
1219
+ * \see \p find_if_not
1220
+ */
1221
+ template <typename DerivedPolicy, typename ForwardIterator, typename Predicate>
1222
+ _CCCL_HOST_DEVICE ForwardIterator partition_point(
1223
+ const thrust::detail::execution_policy_base<DerivedPolicy>& exec,
1224
+ ForwardIterator first,
1225
+ ForwardIterator last,
1226
+ Predicate pred);
1227
+
1228
+ /*! \p partition_point returns an iterator pointing to the end of the true
1229
+ * partition of a partitioned range. \p partition_point requires the input range
1230
+ * <tt>[first,last)</tt> to be a partition; that is, all elements which satisfy
1231
+ * <tt>pred</tt> shall appear before those that do not.
1232
+ * \param first The beginning of the range to consider.
1233
+ * \param last The end of the range to consider.
1234
+ * \param pred A function object which decides to which partition each element of the
1235
+ * range <tt>[first, last)</tt> belongs.
1236
+ * \return An iterator \c mid such that <tt>all_of(first, mid, pred)</tt>
1237
+ * and <tt>none_of(mid, last, pred)</tt> are both true.
1238
+ *
1239
+ * \tparam ForwardIterator is a model of <a href="https://en.cppreference.com/w/cpp/iterator/forward_iterator">Forward
1240
+ * Iterator</a>, and \p ForwardIterator's \c value_type is convertible to \p Predicate's argument type. \tparam
1241
+ * Predicate is a model of <a href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
1242
+ *
1243
+ * \pre The range <tt>[first, last)</tt> shall be partitioned by \p pred.
1244
+ *
1245
+ * \note Though similar, \p partition_point is not redundant with \p find_if_not.
1246
+ * \p partition_point's precondition provides an opportunity for a
1247
+ * faster implementation.
1248
+ *
1249
+ * \code
1250
+ * #include <thrust/partition.h>
1251
+ *
1252
+ * struct is_even
1253
+ * {
1254
+ * __host__ __device__
1255
+ * bool operator()(const int &x)
1256
+ * {
1257
+ * return (x % 2) == 0;
1258
+ * }
1259
+ * };
1260
+ *
1261
+ * ...
1262
+ *
1263
+ * int A[] = {2, 4, 6, 8, 10, 1, 3, 5, 7, 9};
1264
+ * int * B = thrust::partition_point(A, A + 10, is_even());
1265
+ * // B - A is 5
1266
+ * // [A, B) contains only even values
1267
+ * \endcode
1268
+ *
1269
+ * \see \p partition
1270
+ * \see \p find_if_not
1271
+ */
1272
+ template <typename ForwardIterator, typename Predicate>
1273
+ ForwardIterator partition_point(ForwardIterator first, ForwardIterator last, Predicate pred);
1274
+
1275
+ /*!
1276
+ * \} end group searching
1277
+ */
1278
+
1279
+ /*! \addtogroup reductions
1280
+ * \{
1281
+ * \addtogroup predicates
1282
+ * \{
1283
+ */
1284
+
1285
+ /*! \p is_partitioned returns \c true if the given range
1286
+ * is partitioned with respect to a predicate, and \c false otherwise.
1287
+ *
1288
+ * Specifically, \p is_partitioned returns \c true if <tt>[first, last)</tt>
1289
+ * is empty of if <tt>[first, last)</tt> is partitioned by \p pred, i.e. if
1290
+ * all elements that satisfy \p pred appear before those that do not.
1291
+ *
1292
+ * The algorithm's execution is parallelized as determined by \p exec.
1293
+ *
1294
+ * \param exec The execution policy to use for parallelization.
1295
+ * \param first The beginning of the range to consider.
1296
+ * \param last The end of the range to consider.
1297
+ * \param pred A function object which decides to which partition each element of the
1298
+ * range <tt>[first, last)</tt> belongs.
1299
+ * \return \c true if the range <tt>[first, last)</tt> is partitioned with respect
1300
+ * to \p pred, or if <tt>[first, last)</tt> is empty. \c false, otherwise.
1301
+ *
1302
+ * \tparam DerivedPolicy The name of the derived execution policy.
1303
+ * \tparam InputIterator is a model of <a href="https://en.cppreference.com/w/cpp/iterator/forward_iterator">Input
1304
+ * Iterator</a>, and \p InputIterator's \c value_type is convertible to \p Predicate's argument type. \tparam
1305
+ * Predicate is a model of <a href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
1306
+ *
1307
+ * \code
1308
+ * #include <thrust/partition.h>
1309
+ * #include <thrust/execution_policy.h>
1310
+ *
1311
+ * struct is_even
1312
+ * {
1313
+ * __host__ __device__
1314
+ * bool operator()(const int &x)
1315
+ * {
1316
+ * return (x % 2) == 0;
1317
+ * }
1318
+ * };
1319
+ *
1320
+ * ...
1321
+ *
1322
+ * int A[] = {2, 4, 6, 8, 10, 1, 3, 5, 7, 9};
1323
+ * int B[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
1324
+ *
1325
+ * thrust::is_partitioned(thrust::host, A, A + 10, is_even()); // returns true
1326
+ * thrust::is_partitioned(thrust::host, B, B + 10, is_even()); // returns false
1327
+ * \endcode
1328
+ *
1329
+ * \see \p partition
1330
+ */
1331
+ template <typename DerivedPolicy, typename InputIterator, typename Predicate>
1332
+ _CCCL_HOST_DEVICE bool is_partitioned(
1333
+ const thrust::detail::execution_policy_base<DerivedPolicy>& exec,
1334
+ InputIterator first,
1335
+ InputIterator last,
1336
+ Predicate pred);
1337
+
1338
+ /*! \p is_partitioned returns \c true if the given range
1339
+ * is partitioned with respect to a predicate, and \c false otherwise.
1340
+ *
1341
+ * Specifically, \p is_partitioned returns \c true if <tt>[first, last)</tt>
1342
+ * is empty of if <tt>[first, last)</tt> is partitioned by \p pred, i.e. if
1343
+ * all elements that satisfy \p pred appear before those that do not.
1344
+ *
1345
+ * \param first The beginning of the range to consider.
1346
+ * \param last The end of the range to consider.
1347
+ * \param pred A function object which decides to which partition each element of the
1348
+ * range <tt>[first, last)</tt> belongs.
1349
+ * \return \c true if the range <tt>[first, last)</tt> is partitioned with respect
1350
+ * to \p pred, or if <tt>[first, last)</tt> is empty. \c false, otherwise.
1351
+ *
1352
+ * \tparam InputIterator is a model of <a href="https://en.cppreference.com/w/cpp/iterator/forward_iterator">Input
1353
+ * Iterator</a>, and \p InputIterator's \c value_type is convertible to \p Predicate's argument type. \tparam
1354
+ * Predicate is a model of <a href="https://en.cppreference.com/w/cpp/concepts/predicate">Predicate</a>.
1355
+ *
1356
+ * \code
1357
+ * #include <thrust/partition.h>
1358
+ *
1359
+ * struct is_even
1360
+ * {
1361
+ * __host__ __device__
1362
+ * bool operator()(const int &x)
1363
+ * {
1364
+ * return (x % 2) == 0;
1365
+ * }
1366
+ * };
1367
+ *
1368
+ * ...
1369
+ *
1370
+ * int A[] = {2, 4, 6, 8, 10, 1, 3, 5, 7, 9};
1371
+ * int B[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
1372
+ *
1373
+ * thrust::is_partitioned(A, A + 10, is_even()); // returns true
1374
+ * thrust::is_partitioned(B, B + 10, is_even()); // returns false
1375
+ * \endcode
1376
+ *
1377
+ * \see \p partition
1378
+ */
1379
+ template <typename InputIterator, typename Predicate>
1380
+ bool is_partitioned(InputIterator first, InputIterator last, Predicate pred);
1381
+
1382
+ /*!
1383
+ * \} end group predicates
1384
+ */
1385
+
1386
+ /*!
1387
+ * \} end group reductions
1388
+ */
1389
+
1390
+ THRUST_NAMESPACE_END
1391
+
1392
+ #include <thrust/detail/partition.inl>