cuda-cccl 0.3.1__cp313-cp313-manylinux_2_24_aarch64.whl → 0.3.2__cp313-cp313-manylinux_2_24_aarch64.whl

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

Potentially problematic release.


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

Files changed (185) hide show
  1. cuda/cccl/headers/include/cub/agent/agent_histogram.cuh +354 -572
  2. cuda/cccl/headers/include/cub/block/block_adjacent_difference.cuh +6 -8
  3. cuda/cccl/headers/include/cub/block/block_discontinuity.cuh +24 -14
  4. cuda/cccl/headers/include/cub/block/block_exchange.cuh +5 -0
  5. cuda/cccl/headers/include/cub/block/block_histogram.cuh +4 -0
  6. cuda/cccl/headers/include/cub/block/block_load.cuh +4 -0
  7. cuda/cccl/headers/include/cub/block/block_radix_rank.cuh +1 -0
  8. cuda/cccl/headers/include/cub/block/block_reduce.cuh +1 -0
  9. cuda/cccl/headers/include/cub/block/block_scan.cuh +12 -2
  10. cuda/cccl/headers/include/cub/block/block_store.cuh +3 -2
  11. cuda/cccl/headers/include/cub/detail/mdspan_utils.cuh +34 -30
  12. cuda/cccl/headers/include/cub/detail/ptx-json-parser.h +1 -1
  13. cuda/cccl/headers/include/cub/device/device_for.cuh +118 -40
  14. cuda/cccl/headers/include/cub/device/device_reduce.cuh +6 -7
  15. cuda/cccl/headers/include/cub/device/device_segmented_reduce.cuh +12 -13
  16. cuda/cccl/headers/include/cub/device/device_transform.cuh +122 -91
  17. cuda/cccl/headers/include/cub/device/dispatch/dispatch_merge.cuh +2 -3
  18. cuda/cccl/headers/include/cub/device/dispatch/dispatch_reduce.cuh +4 -3
  19. cuda/cccl/headers/include/cub/device/dispatch/dispatch_reduce_deterministic.cuh +1 -1
  20. cuda/cccl/headers/include/cub/device/dispatch/dispatch_streaming_reduce.cuh +4 -5
  21. cuda/cccl/headers/include/cub/device/dispatch/dispatch_streaming_reduce_by_key.cuh +0 -1
  22. cuda/cccl/headers/include/cub/device/dispatch/dispatch_topk.cuh +3 -5
  23. cuda/cccl/headers/include/cub/device/dispatch/dispatch_transform.cuh +13 -5
  24. cuda/cccl/headers/include/cub/device/dispatch/kernels/for_each.cuh +72 -37
  25. cuda/cccl/headers/include/cub/device/dispatch/kernels/transform.cuh +22 -27
  26. cuda/cccl/headers/include/cub/device/dispatch/tuning/tuning_transform.cuh +61 -70
  27. cuda/cccl/headers/include/cub/thread/thread_reduce.cuh +24 -17
  28. cuda/cccl/headers/include/cub/warp/warp_load.cuh +6 -6
  29. cuda/cccl/headers/include/cub/warp/warp_reduce.cuh +7 -2
  30. cuda/cccl/headers/include/cub/warp/warp_scan.cuh +7 -3
  31. cuda/cccl/headers/include/cub/warp/warp_store.cuh +1 -0
  32. cuda/cccl/headers/include/cuda/__barrier/barrier_block_scope.h +19 -0
  33. cuda/cccl/headers/include/cuda/__cccl_config +1 -0
  34. cuda/cccl/headers/include/cuda/__cmath/fast_modulo_division.h +3 -74
  35. cuda/cccl/headers/include/cuda/__cmath/mul_hi.h +146 -0
  36. cuda/cccl/headers/include/cuda/__complex/get_real_imag.h +0 -4
  37. cuda/cccl/headers/include/cuda/__device/arch_id.h +176 -0
  38. cuda/cccl/headers/include/cuda/__device/arch_traits.h +239 -317
  39. cuda/cccl/headers/include/cuda/__device/attributes.h +4 -3
  40. cuda/cccl/headers/include/cuda/__device/compute_capability.h +171 -0
  41. cuda/cccl/headers/include/cuda/__device/device_ref.h +0 -10
  42. cuda/cccl/headers/include/cuda/__device/physical_device.h +1 -26
  43. cuda/cccl/headers/include/cuda/__event/event.h +26 -26
  44. cuda/cccl/headers/include/cuda/__event/event_ref.h +5 -5
  45. cuda/cccl/headers/include/cuda/__event/timed_event.h +9 -7
  46. cuda/cccl/headers/include/cuda/__fwd/devices.h +4 -4
  47. cuda/cccl/headers/include/cuda/__iterator/constant_iterator.h +46 -31
  48. cuda/cccl/headers/include/cuda/__iterator/strided_iterator.h +79 -47
  49. cuda/cccl/headers/include/cuda/__iterator/tabulate_output_iterator.h +59 -36
  50. cuda/cccl/headers/include/cuda/__iterator/transform_input_output_iterator.h +79 -49
  51. cuda/cccl/headers/include/cuda/__iterator/transform_iterator.h +74 -48
  52. cuda/cccl/headers/include/cuda/__iterator/transform_output_iterator.h +80 -55
  53. cuda/cccl/headers/include/cuda/__iterator/zip_common.h +2 -12
  54. cuda/cccl/headers/include/cuda/__iterator/zip_iterator.h +15 -19
  55. cuda/cccl/headers/include/cuda/__iterator/zip_transform_iterator.h +59 -60
  56. cuda/cccl/headers/include/cuda/__mdspan/host_device_accessor.h +127 -60
  57. cuda/cccl/headers/include/cuda/__mdspan/host_device_mdspan.h +178 -3
  58. cuda/cccl/headers/include/cuda/__mdspan/restrict_accessor.h +38 -8
  59. cuda/cccl/headers/include/cuda/__mdspan/restrict_mdspan.h +67 -1
  60. cuda/cccl/headers/include/cuda/__memory/ptr_in_range.h +93 -0
  61. cuda/cccl/headers/include/cuda/__memory_resource/get_memory_resource.h +4 -4
  62. cuda/cccl/headers/include/cuda/__memory_resource/properties.h +44 -0
  63. cuda/cccl/headers/include/cuda/__memory_resource/resource.h +1 -1
  64. cuda/cccl/headers/include/cuda/__memory_resource/resource_ref.h +4 -6
  65. cuda/cccl/headers/include/cuda/__nvtx/nvtx3.h +2 -1
  66. cuda/cccl/headers/include/cuda/__runtime/ensure_current_context.h +5 -4
  67. cuda/cccl/headers/include/cuda/__stream/stream.h +8 -8
  68. cuda/cccl/headers/include/cuda/__stream/stream_ref.h +17 -16
  69. cuda/cccl/headers/include/cuda/__utility/in_range.h +65 -0
  70. cuda/cccl/headers/include/cuda/cmath +1 -0
  71. cuda/cccl/headers/include/cuda/devices +3 -0
  72. cuda/cccl/headers/include/cuda/memory +1 -0
  73. cuda/cccl/headers/include/cuda/std/__algorithm/equal_range.h +2 -2
  74. cuda/cccl/headers/include/cuda/std/__algorithm/find.h +1 -1
  75. cuda/cccl/headers/include/cuda/std/__algorithm/includes.h +2 -4
  76. cuda/cccl/headers/include/cuda/std/__algorithm/lower_bound.h +1 -1
  77. cuda/cccl/headers/include/cuda/std/__algorithm/make_projected.h +7 -15
  78. cuda/cccl/headers/include/cuda/std/__algorithm/min_element.h +1 -1
  79. cuda/cccl/headers/include/cuda/std/__algorithm/minmax_element.h +1 -2
  80. cuda/cccl/headers/include/cuda/std/__algorithm/partial_sort_copy.h +2 -2
  81. cuda/cccl/headers/include/cuda/std/__algorithm/upper_bound.h +1 -1
  82. cuda/cccl/headers/include/cuda/std/__cccl/algorithm_wrapper.h +36 -0
  83. cuda/cccl/headers/include/cuda/std/__cccl/builtin.h +46 -49
  84. cuda/cccl/headers/include/cuda/std/__cccl/execution_space.h +6 -0
  85. cuda/cccl/headers/include/cuda/std/__cccl/host_std_lib.h +52 -0
  86. cuda/cccl/headers/include/cuda/std/__cccl/memory_wrapper.h +36 -0
  87. cuda/cccl/headers/include/cuda/std/__cccl/numeric_wrapper.h +36 -0
  88. cuda/cccl/headers/include/cuda/std/__cmath/isnan.h +3 -2
  89. cuda/cccl/headers/include/cuda/std/__complex/complex.h +3 -2
  90. cuda/cccl/headers/include/cuda/std/__complex/literals.h +14 -34
  91. cuda/cccl/headers/include/cuda/std/__complex/nvbf16.h +2 -1
  92. cuda/cccl/headers/include/cuda/std/__complex/nvfp16.h +4 -3
  93. cuda/cccl/headers/include/cuda/std/__concepts/invocable.h +2 -2
  94. cuda/cccl/headers/include/cuda/std/__cstdlib/malloc.h +3 -2
  95. cuda/cccl/headers/include/cuda/std/__functional/bind.h +10 -13
  96. cuda/cccl/headers/include/cuda/std/__functional/function.h +5 -8
  97. cuda/cccl/headers/include/cuda/std/__functional/invoke.h +71 -335
  98. cuda/cccl/headers/include/cuda/std/__functional/mem_fn.h +1 -2
  99. cuda/cccl/headers/include/cuda/std/__functional/reference_wrapper.h +3 -3
  100. cuda/cccl/headers/include/cuda/std/__functional/weak_result_type.h +0 -6
  101. cuda/cccl/headers/include/cuda/std/__fwd/allocator.h +13 -0
  102. cuda/cccl/headers/include/cuda/std/__fwd/char_traits.h +13 -0
  103. cuda/cccl/headers/include/cuda/std/__fwd/complex.h +13 -4
  104. cuda/cccl/headers/include/cuda/std/__fwd/mdspan.h +23 -0
  105. cuda/cccl/headers/include/cuda/std/__fwd/pair.h +13 -0
  106. cuda/cccl/headers/include/cuda/std/__fwd/string.h +22 -0
  107. cuda/cccl/headers/include/cuda/std/__fwd/string_view.h +14 -0
  108. cuda/cccl/headers/include/cuda/std/__internal/features.h +0 -5
  109. cuda/cccl/headers/include/cuda/std/__internal/namespaces.h +21 -0
  110. cuda/cccl/headers/include/cuda/std/__iterator/iterator_traits.h +5 -5
  111. cuda/cccl/headers/include/cuda/std/__mdspan/extents.h +7 -1
  112. cuda/cccl/headers/include/cuda/std/__mdspan/mdspan.h +53 -39
  113. cuda/cccl/headers/include/cuda/std/__memory/allocator.h +3 -3
  114. cuda/cccl/headers/include/cuda/std/__memory/construct_at.h +1 -3
  115. cuda/cccl/headers/include/cuda/std/__optional/optional_base.h +1 -0
  116. cuda/cccl/headers/include/cuda/std/__ranges/compressed_movable_box.h +892 -0
  117. cuda/cccl/headers/include/cuda/std/__ranges/movable_box.h +2 -2
  118. cuda/cccl/headers/include/cuda/std/__type_traits/is_primary_template.h +7 -5
  119. cuda/cccl/headers/include/cuda/std/__type_traits/result_of.h +1 -1
  120. cuda/cccl/headers/include/cuda/std/__utility/pair.h +0 -5
  121. cuda/cccl/headers/include/cuda/std/bitset +1 -1
  122. cuda/cccl/headers/include/cuda/std/detail/libcxx/include/__config +15 -12
  123. cuda/cccl/headers/include/cuda/std/detail/libcxx/include/variant +11 -9
  124. cuda/cccl/headers/include/cuda/std/inplace_vector +4 -4
  125. cuda/cccl/headers/include/cuda/std/numbers +5 -0
  126. cuda/cccl/headers/include/cuda/std/string_view +146 -11
  127. cuda/cccl/headers/include/cuda/stream_ref +5 -0
  128. cuda/cccl/headers/include/cuda/utility +1 -0
  129. cuda/cccl/headers/include/nv/target +7 -2
  130. cuda/cccl/headers/include/thrust/allocate_unique.h +1 -1
  131. cuda/cccl/headers/include/thrust/detail/allocator/allocator_traits.h +309 -33
  132. cuda/cccl/headers/include/thrust/detail/allocator/copy_construct_range.h +151 -4
  133. cuda/cccl/headers/include/thrust/detail/allocator/destroy_range.h +60 -3
  134. cuda/cccl/headers/include/thrust/detail/allocator/fill_construct_range.h +45 -3
  135. cuda/cccl/headers/include/thrust/detail/allocator/malloc_allocator.h +31 -6
  136. cuda/cccl/headers/include/thrust/detail/allocator/tagged_allocator.h +29 -16
  137. cuda/cccl/headers/include/thrust/detail/allocator/temporary_allocator.h +41 -4
  138. cuda/cccl/headers/include/thrust/detail/allocator/value_initialize_range.h +42 -4
  139. cuda/cccl/headers/include/thrust/detail/complex/ccosh.h +3 -3
  140. cuda/cccl/headers/include/thrust/detail/internal_functional.h +1 -1
  141. cuda/cccl/headers/include/thrust/detail/memory_algorithms.h +1 -1
  142. cuda/cccl/headers/include/thrust/detail/temporary_array.h +1 -1
  143. cuda/cccl/headers/include/thrust/detail/type_traits.h +1 -1
  144. cuda/cccl/headers/include/thrust/device_delete.h +18 -3
  145. cuda/cccl/headers/include/thrust/device_free.h +16 -3
  146. cuda/cccl/headers/include/thrust/device_new.h +29 -8
  147. cuda/cccl/headers/include/thrust/host_vector.h +1 -1
  148. cuda/cccl/headers/include/thrust/iterator/tabulate_output_iterator.h +5 -2
  149. cuda/cccl/headers/include/thrust/mr/disjoint_pool.h +1 -1
  150. cuda/cccl/headers/include/thrust/mr/pool.h +1 -1
  151. cuda/cccl/headers/include/thrust/system/cuda/detail/find.h +13 -115
  152. cuda/cccl/headers/include/thrust/system/cuda/detail/mismatch.h +8 -2
  153. cuda/cccl/headers/include/thrust/type_traits/is_contiguous_iterator.h +7 -7
  154. cuda/compute/__init__.py +2 -0
  155. cuda/compute/_bindings.pyi +43 -1
  156. cuda/compute/_bindings_impl.pyx +156 -7
  157. cuda/compute/algorithms/_scan.py +108 -36
  158. cuda/compute/algorithms/_transform.py +32 -11
  159. cuda/compute/cu12/_bindings_impl.cpython-313-aarch64-linux-gnu.so +0 -0
  160. cuda/compute/cu12/cccl/libcccl.c.parallel.so +0 -0
  161. cuda/compute/cu13/_bindings_impl.cpython-313-aarch64-linux-gnu.so +0 -0
  162. cuda/compute/cu13/cccl/libcccl.c.parallel.so +0 -0
  163. cuda/compute/iterators/__init__.py +2 -0
  164. cuda/compute/iterators/_factories.py +28 -0
  165. cuda/compute/iterators/_iterators.py +206 -1
  166. cuda/compute/numba_utils.py +2 -2
  167. cuda/compute/typing.py +2 -0
  168. {cuda_cccl-0.3.1.dist-info → cuda_cccl-0.3.2.dist-info}/METADATA +1 -1
  169. {cuda_cccl-0.3.1.dist-info → cuda_cccl-0.3.2.dist-info}/RECORD +171 -175
  170. cuda/cccl/headers/include/thrust/detail/algorithm_wrapper.h +0 -37
  171. cuda/cccl/headers/include/thrust/detail/allocator/allocator_traits.inl +0 -371
  172. cuda/cccl/headers/include/thrust/detail/allocator/copy_construct_range.inl +0 -242
  173. cuda/cccl/headers/include/thrust/detail/allocator/destroy_range.inl +0 -137
  174. cuda/cccl/headers/include/thrust/detail/allocator/fill_construct_range.inl +0 -99
  175. cuda/cccl/headers/include/thrust/detail/allocator/malloc_allocator.inl +0 -68
  176. cuda/cccl/headers/include/thrust/detail/allocator/tagged_allocator.inl +0 -86
  177. cuda/cccl/headers/include/thrust/detail/allocator/temporary_allocator.inl +0 -79
  178. cuda/cccl/headers/include/thrust/detail/allocator/value_initialize_range.inl +0 -98
  179. cuda/cccl/headers/include/thrust/detail/device_delete.inl +0 -52
  180. cuda/cccl/headers/include/thrust/detail/device_free.inl +0 -47
  181. cuda/cccl/headers/include/thrust/detail/device_new.inl +0 -61
  182. cuda/cccl/headers/include/thrust/detail/memory_wrapper.h +0 -40
  183. cuda/cccl/headers/include/thrust/detail/numeric_wrapper.h +0 -37
  184. {cuda_cccl-0.3.1.dist-info → cuda_cccl-0.3.2.dist-info}/WHEEL +0 -0
  185. {cuda_cccl-0.3.1.dist-info → cuda_cccl-0.3.2.dist-info}/licenses/LICENSE +0 -0
@@ -1,61 +0,0 @@
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
- #pragma once
18
-
19
- #include <thrust/detail/config.h>
20
-
21
- #if defined(_CCCL_IMPLICIT_SYSTEM_HEADER_GCC)
22
- # pragma GCC system_header
23
- #elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_CLANG)
24
- # pragma clang system_header
25
- #elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_MSVC)
26
- # pragma system_header
27
- #endif // no system header
28
- #include <thrust/device_malloc.h>
29
- #include <thrust/device_new.h>
30
- #include <thrust/uninitialized_fill.h>
31
-
32
- THRUST_NAMESPACE_BEGIN
33
-
34
- template <typename T>
35
- device_ptr<T> device_new(device_ptr<void> p, const size_t n)
36
- {
37
- // XXX TODO dispatch n null device constructors at p here
38
- // in the meantime, dispatch 1 null host constructor here
39
- // and dispatch n copy constructors
40
- return device_new<T>(p, T(), n);
41
- } // end device_new()
42
-
43
- template <typename T>
44
- device_ptr<T> device_new(device_ptr<void> p, const T& exemplar, const size_t n)
45
- {
46
- device_ptr<T> result(reinterpret_cast<T*>(p.get()));
47
-
48
- // run copy constructors at p here
49
- thrust::uninitialized_fill(result, result + n, exemplar);
50
-
51
- return result;
52
- } // end device_new()
53
-
54
- template <typename T>
55
- device_ptr<T> device_new(const size_t n)
56
- {
57
- // call placement new
58
- return device_new<T>(thrust::device_malloc<T>(n));
59
- } // end device_new()
60
-
61
- THRUST_NAMESPACE_END
@@ -1,40 +0,0 @@
1
- /*
2
- * Copyright 2020 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
- #pragma once
18
-
19
- #include <thrust/detail/config.h>
20
-
21
- #if defined(_CCCL_IMPLICIT_SYSTEM_HEADER_GCC)
22
- # pragma GCC system_header
23
- #elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_CLANG)
24
- # pragma clang system_header
25
- #elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_MSVC)
26
- # pragma system_header
27
- #endif // no system header
28
-
29
- // When a compiler uses Thrust as part of its implementation of Standard C++
30
- // algorithms, a cycle of included files may result when Thrust code tries to
31
- // use a standard algorithm. Having a macro that is defined only when Thrust
32
- // is including an algorithms-related header gives the compiler a chance to
33
- // detect and break the cycle of includes. (<memory> declares several standard
34
- // algorithms, including all of the uninitialized_* algorithms. "_ALGORITHMS_"
35
- // in the macro name is meant generically, not as a specific reference to
36
- // the header <algorithms>.)
37
-
38
- #define THRUST_INCLUDING_ALGORITHMS_HEADER
39
- #include <memory>
40
- #undef THRUST_INCLUDING_ALGORITHMS_HEADER
@@ -1,37 +0,0 @@
1
- /*
2
- * Copyright 2021 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
- #pragma once
18
-
19
- #include <thrust/detail/config.h>
20
-
21
- #if defined(_CCCL_IMPLICIT_SYSTEM_HEADER_GCC)
22
- # pragma GCC system_header
23
- #elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_CLANG)
24
- # pragma clang system_header
25
- #elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_MSVC)
26
- # pragma system_header
27
- #endif // no system header
28
-
29
- // When a compiler uses Thrust as part of its implementation of Standard C++
30
- // algorithms, a cycle of included files may result when Thrust code tries to
31
- // use a standard algorithm. Having a macro that is defined only when Thrust
32
- // is including an algorithms-related header gives the compiler a chance to
33
- // detect and break the cycle of includes.
34
-
35
- #define THRUST_INCLUDING_ALGORITHMS_HEADER
36
- #include <numeric>
37
- #undef THRUST_INCLUDING_ALGORITHMS_HEADER