From ebb50a6bbe5700febe4aa8bb4b295b77f6d2f5d5 Mon Sep 17 00:00:00 2001 From: dumerrill Date: Mon, 13 Apr 2015 13:58:27 -0400 Subject: [PATCH] 1.4.1 doc gen Former-commit-id: 7daf6e8583ca79b64306c09a44c0fe649dad3bad --- CHANGE_LOG.TXT | 14 + README.md | 12 +- cub/device/device_spmv.cuh | 4 +- docs/download_cub.html | 6 +- docs/html/CHANGE_LOG.TXT | 16 +- docs/html/annotated.html | 56 +- .../arg__index__input__iterator_8cuh.html | 4 +- ...g__index__input__iterator_8cuh_source.html | 79 +- docs/html/block__discontinuity_8cuh.html | 2 +- .../block__discontinuity_8cuh_source.html | 2 +- docs/html/block__exchange_8cuh.html | 2 +- ...__exchange_8cuh_source.html.REMOVED.git-id | 2 +- docs/html/block__histogram_8cuh.html | 2 +- docs/html/block__histogram_8cuh_source.html | 2 +- docs/html/block__load_8cuh.html | 2 +- ...lock__load_8cuh_source.html.REMOVED.git-id | 2 +- docs/html/block__radix__sort_8cuh.html | 2 +- docs/html/block__radix__sort_8cuh_source.html | 4 +- docs/html/block__reduce_8cuh.html | 2 +- docs/html/block__reduce_8cuh_source.html | 2 +- docs/html/block__scan_8cuh.html | 2 +- ...lock__scan_8cuh_source.html.REMOVED.git-id | 2 +- docs/html/block__store_8cuh.html | 2 +- docs/html/block__store_8cuh_source.html | 2 +- ...cache__modified__input__iterator_8cuh.html | 2 +- ...modified__input__iterator_8cuh_source.html | 10 +- ...ache__modified__output__iterator_8cuh.html | 2 +- ...odified__output__iterator_8cuh_source.html | 6 +- ..._1_1_arg_index_input_iterator-members.html | 4 +- ...classcub_1_1_arg_index_input_iterator.html | 30 +- ...sscub_1_1_block_discontinuity-members.html | 2 +- .../classcub_1_1_block_discontinuity.html | 2 +- .../classcub_1_1_block_exchange-members.html | 2 +- docs/html/classcub_1_1_block_exchange.html | 2 +- .../classcub_1_1_block_histogram-members.html | 2 +- docs/html/classcub_1_1_block_histogram.html | 2 +- .../html/classcub_1_1_block_load-members.html | 2 +- docs/html/classcub_1_1_block_load.html | 12 +- ...classcub_1_1_block_radix_sort-members.html | 2 +- docs/html/classcub_1_1_block_radix_sort.html | 2 +- .../classcub_1_1_block_reduce-members.html | 2 +- docs/html/classcub_1_1_block_reduce.html | 2 +- .../html/classcub_1_1_block_scan-members.html | 2 +- ...lasscub_1_1_block_scan.html.REMOVED.git-id | 2 +- .../classcub_1_1_block_store-members.html | 2 +- docs/html/classcub_1_1_block_store.html | 2 +- ...cache_modified_input_iterator-members.html | 8 +- ...cub_1_1_cache_modified_input_iterator.html | 31 +- ...ache_modified_output_iterator-members.html | 2 +- ...ub_1_1_cache_modified_output_iterator.html | 2 +- ...b_1_1_constant_input_iterator-members.html | 2 +- .../classcub_1_1_constant_input_iterator.html | 2 +- ...b_1_1_counting_input_iterator-members.html | 2 +- .../classcub_1_1_counting_input_iterator.html | 2 +- .../classcub_1_1_swizzle_scan_op-members.html | 2 +- docs/html/classcub_1_1_swizzle_scan_op.html | 2 +- ...ub_1_1_tex_obj_input_iterator-members.html | 4 +- .../classcub_1_1_tex_obj_input_iterator.html | 16 +- ...ub_1_1_tex_ref_input_iterator-members.html | 9 +- .../classcub_1_1_tex_ref_input_iterator.html | 20 +- ..._1_1_transform_input_iterator-members.html | 2 +- ...classcub_1_1_transform_input_iterator.html | 2 +- .../classcub_1_1_warp_reduce-members.html | 2 +- docs/html/classcub_1_1_warp_reduce.html | 2 +- docs/html/classcub_1_1_warp_scan-members.html | 2 +- ...classcub_1_1_warp_scan.html.REMOVED.git-id | 2 +- docs/html/classes.html | 62 +- docs/html/constant__input__iterator_8cuh.html | 2 +- ...constant__input__iterator_8cuh_source.html | 2 +- docs/html/counting__input__iterator_8cuh.html | 2 +- ...counting__input__iterator_8cuh_source.html | 2 +- docs/html/cub_8cuh.html | 7 +- docs/html/cub_8cuh_source.html | 90 +- docs/html/device__histogram_8cuh.html | 2 +- docs/html/device__histogram_8cuh_source.html | 2 +- docs/html/device__partition_8cuh.html | 2 +- docs/html/device__partition_8cuh_source.html | 2 +- docs/html/device__radix__sort_8cuh.html | 2 +- .../html/device__radix__sort_8cuh_source.html | 2 +- docs/html/device__reduce_8cuh.html | 2 +- docs/html/device__reduce_8cuh_source.html | 8 +- .../device__run__length__encode_8cuh.html | 2 +- ...vice__run__length__encode_8cuh_source.html | 2 +- docs/html/device__scan_8cuh.html | 2 +- docs/html/device__scan_8cuh_source.html | 2 +- docs/html/device__select_8cuh.html | 2 +- docs/html/device__select_8cuh_source.html | 2 +- docs/html/device__spmv_8cuh.html | 2 +- docs/html/device__spmv_8cuh_source.html | 30 +- .../dir_011e1c944d88f71be72e1e24a5fda7cf.html | 2 +- .../dir_18fc672d63781b5a743137aee24ff656.html | 2 +- .../dir_80932b4cec52750ff92b1a1912314cf5.html | 2 +- .../dir_bb50a5ef59f19d030d06415663184d05.html | 2 +- .../dir_cb3a671affffe7eeb3fdf5ae58e42cc8.html | 2 +- .../dir_d583f216f1aafe19404e836b0c097ad2.html | 2 +- docs/html/download_cub.html | 6 +- .../example_block_radix_sort_8cu-example.html | 2 +- .../example_block_reduce_8cu-example.html | 2 +- docs/html/example_block_scan_8cu-example.html | 2 +- .../example_device_histogram_8cu-example.html | 4 +- ..._device_partition_flagged_8cu-example.html | 2 +- ...ample_device_partition_if_8cu-example.html | 2 +- ...example_device_radix_sort_8cu-example.html | 2 +- .../example_device_reduce_8cu-example.html | 2 +- .../html/example_device_scan_8cu-example.html | 2 +- ...ple_device_select_flagged_8cu-example.html | 2 +- .../example_device_select_if_8cu-example.html | 2 +- ...mple_device_select_unique_8cu-example.html | 2 +- docs/html/examples.html | 2 +- docs/html/files.html | 2 +- docs/html/functions.html | 4 +- docs/html/functions_0x62.html | 6 +- docs/html/functions_0x63.html | 7 +- docs/html/functions_0x64.html | 2 +- docs/html/functions_0x65.html | 2 +- docs/html/functions_0x66.html | 2 +- docs/html/functions_0x68.html | 2 +- docs/html/functions_0x69.html | 13 +- docs/html/functions_0x6b.html | 2 +- docs/html/functions_0x6c.html | 2 +- docs/html/functions_0x6d.html | 2 +- docs/html/functions_0x6e.html | 2 +- docs/html/functions_0x6f.html | 50 +- docs/html/functions_0x70.html | 2 +- docs/html/functions_0x72.html | 11 +- docs/html/functions_0x73.html | 2 +- docs/html/functions_0x74.html | 9 +- docs/html/functions_0x75.html | 2 +- docs/html/functions_0x76.html | 15 +- docs/html/functions_0x77.html | 2 +- docs/html/functions_0x7e.html | 2 +- docs/html/functions_func.html | 2 +- docs/html/functions_func_0x62.html | 6 +- docs/html/functions_func_0x63.html | 4 +- docs/html/functions_func_0x64.html | 2 +- docs/html/functions_func_0x65.html | 2 +- docs/html/functions_func_0x66.html | 2 +- docs/html/functions_func_0x68.html | 2 +- docs/html/functions_func_0x69.html | 12 +- docs/html/functions_func_0x6c.html | 2 +- docs/html/functions_func_0x6d.html | 2 +- docs/html/functions_func_0x6e.html | 2 +- docs/html/functions_func_0x6f.html | 38 +- docs/html/functions_func_0x72.html | 8 +- docs/html/functions_func_0x73.html | 2 +- docs/html/functions_func_0x74.html | 5 +- docs/html/functions_func_0x75.html | 2 +- docs/html/functions_func_0x77.html | 2 +- docs/html/functions_func_0x7e.html | 2 +- docs/html/functions_rela.html | 2 +- docs/html/functions_type.html | 16 +- docs/html/functions_vars.html | 15 +- docs/html/globals.html | 2 +- docs/html/globals_defs.html | 2 +- docs/html/group___block_module.html | 2 +- docs/html/group___device_module.html | 2 +- docs/html/group___primitive_module.html | 6 +- docs/html/group___util_io.html | 14 +- docs/html/group___util_iterator.html | 4 +- docs/html/group___util_mgmt.html | 2 +- docs/html/group___util_module.html | 37 +- docs/html/group___util_ptx.html | 4 +- docs/html/group___warp_module.html | 70 +- docs/html/hierarchy.html | 141 ++- docs/html/index.html | 13 +- docs/html/modules.html | 6 +- docs/html/namespacecub.html.REMOVED.git-id | 2 +- docs/html/namespacemembers.html | 15 +- docs/html/namespacemembers_enum.html | 5 +- docs/html/namespacemembers_eval.html | 2 +- docs/html/namespacemembers_func.html | 12 +- docs/html/namespaces.html | 2 +- docs/html/search/all_61.js | 2 +- docs/html/search/all_62.js | 11 +- docs/html/search/all_63.js | 3 +- docs/html/search/all_69.js | 4 +- docs/html/search/all_6e.js | 4 +- docs/html/search/all_6f.js | 14 +- docs/html/search/all_72.js | 7 +- docs/html/search/all_73.js | 6 +- docs/html/search/all_74.js | 29 +- docs/html/search/all_76.js | 4 +- docs/html/search/classes_62.js | 3 - docs/html/search/classes_69.js | 3 +- docs/html/search/classes_6e.js | 4 +- docs/html/search/classes_72.js | 4 +- docs/html/search/classes_74.js | 23 +- docs/html/search/enums_63.js | 3 +- docs/html/search/functions_62.js | 2 +- docs/html/search/functions_63.js | 2 +- docs/html/search/functions_69.js | 3 +- docs/html/search/functions_6f.js | 10 +- docs/html/search/functions_72.js | 3 +- docs/html/search/functions_73.js | 6 +- docs/html/search/functions_74.js | 1 - docs/html/search/search.js | 4 +- docs/html/search/typedefs_6f.html | 26 - docs/html/search/typedefs_6f.js | 4 - docs/html/search/typedefs_74.js | 3 +- docs/html/search/typedefs_76.js | 2 +- docs/html/search/variables_61.js | 2 +- docs/html/search/variables_63.html | 26 - docs/html/search/variables_63.js | 4 - docs/html/search/variables_6f.js | 3 +- docs/html/search/variables_76.js | 2 +- docs/html/structcub_1_1_arg_max-members.html | 4 +- docs/html/structcub_1_1_arg_max.html | 14 +- docs/html/structcub_1_1_arg_min-members.html | 4 +- docs/html/structcub_1_1_arg_min.html | 14 +- ...iscontinuity_1_1_temp_storage-members.html | 2 +- ..._block_discontinuity_1_1_temp_storage.html | 6 +- ...ock_exchange_1_1_temp_storage-members.html | 2 +- ...b_1_1_block_exchange_1_1_temp_storage.html | 6 +- ...ck_histogram_1_1_temp_storage-members.html | 2 +- ..._1_1_block_histogram_1_1_temp_storage.html | 6 +- ...01_d_5ea8dad2df262b118ec77ecff8dc9dd3.html | 2 +- ...00_01_d_u_m_m_y_01_4_1_1_temp_storage.html | 8 +- ..._o_s_26aa8cf86896512ffa4e7866d1071b26.html | 2 +- ..._o_s_402c3164d23f1ec647db5dad06a54584.html | 8 +- ..._o_s_b58863673477c12a4e46def6747d1835.html | 2 +- ..._o_s_e4c36dfe8f549604998f6c46cc8fbd1d.html | 8 +- ...1_block_load_1_1_temp_storage-members.html | 2 +- ...ctcub_1_1_block_load_1_1_temp_storage.html | 8 +- ...k_radix_sort_1_1_temp_storage-members.html | 2 +- ...1_1_block_radix_sort_1_1_temp_storage.html | 6 +- ...block_reduce_1_1_temp_storage-members.html | 2 +- ...cub_1_1_block_reduce_1_1_temp_storage.html | 6 +- ...1_block_scan_1_1_temp_storage-members.html | 2 +- ...ctcub_1_1_block_scan_1_1_temp_storage.html | 8 +- ..._00_07dc8a0abd37bbc1ba3abf8440890a6c0.html | 2 +- ..._00_09dfae03f13932c7dbdb41be30a5767ba.html | 6 +- ..._s_p_1336264f25bcb4cda6dbe142b2fec3e9.html | 2 +- ..._s_p_263becc1ca5b47586740c2f7bb0d0145.html | 6 +- ..._s_p_2a6ef8c29850a6a6dfbf5e4acbc50c1f.html | 2 +- ..._s_p_8d170856b7ed1df0ed565731a681b449.html | 6 +- ..._block_store_1_1_temp_storage-members.html | 2 +- ...tcub_1_1_block_store_1_1_temp_storage.html | 6 +- ..._1_1_caching_device_allocator-members.html | 2 +- ...tructcub_1_1_caching_device_allocator.html | 2 +- docs/html/structcub_1_1_cast-members.html | 2 +- docs/html/structcub_1_1_cast.html | 2 +- docs/html/structcub_1_1_cub_vector.html | 2 +- ...tructcub_1_1_device_histogram-members.html | 2 +- ...b_1_1_device_histogram.html.REMOVED.git-id | 2 +- ...tructcub_1_1_device_partition-members.html | 2 +- docs/html/structcub_1_1_device_partition.html | 6 +- ...ructcub_1_1_device_radix_sort-members.html | 2 +- .../html/structcub_1_1_device_radix_sort.html | 18 +- .../structcub_1_1_device_reduce-members.html | 2 +- docs/html/structcub_1_1_device_reduce.html | 32 +- ..._1_1_device_run_length_encode-members.html | 2 +- ...tructcub_1_1_device_run_length_encode.html | 6 +- .../structcub_1_1_device_scan-members.html | 2 +- docs/html/structcub_1_1_device_scan.html | 10 +- .../structcub_1_1_device_select-members.html | 2 +- docs/html/structcub_1_1_device_select.html | 8 +- .../structcub_1_1_device_spmv-members.html | 4 +- docs/html/structcub_1_1_device_spmv.html | 40 +- .../structcub_1_1_double_buffer-members.html | 2 +- docs/html/structcub_1_1_double_buffer.html | 6 +- docs/html/structcub_1_1_equality-members.html | 2 +- docs/html/structcub_1_1_equality.html | 2 +- docs/html/structcub_1_1_equals-members.html | 2 +- docs/html/structcub_1_1_equals.html | 2 +- docs/html/structcub_1_1_if-members.html | 2 +- docs/html/structcub_1_1_if.html | 2 +- .../structcub_1_1_inequality-members.html | 2 +- docs/html/structcub_1_1_inequality.html | 2 +- ...uctcub_1_1_inequality_wrapper-members.html | 2 +- .../structcub_1_1_inequality_wrapper.html | 2 +- .../html/structcub_1_1_int2_type-members.html | 2 +- docs/html/structcub_1_1_int2_type.html | 2 +- ... => structcub_1_1_is_pointer-members.html} | 12 +- docs/html/structcub_1_1_is_pointer.html | 136 +++ ...=> structcub_1_1_is_volatile-members.html} | 12 +- docs/html/structcub_1_1_is_volatile.html | 136 +++ ...tructcub_1_1_item_offset_pair-members.html | 126 --- .../structcub_1_1_key_value_pair-members.html | 13 +- docs/html/structcub_1_1_key_value_pair.html | 18 +- docs/html/structcub_1_1_log2-members.html | 2 +- docs/html/structcub_1_1_log2.html | 4 +- docs/html/structcub_1_1_max-members.html | 2 +- docs/html/structcub_1_1_max.html | 2 +- docs/html/structcub_1_1_min-members.html | 2 +- docs/html/structcub_1_1_min.html | 2 +- docs/html/structcub_1_1_null_type.html | 2 +- docs/html/structcub_1_1_numeric_traits.html | 149 ---- docs/html/structcub_1_1_numeric_traits.png | Bin 968 -> 0 bytes .../structcub_1_1_power_of_two-members.html | 2 +- docs/html/structcub_1_1_power_of_two.html | 4 +- ...ructcub_1_1_reduce_by_key_op-members.html} | 15 +- ...ml => structcub_1_1_reduce_by_key_op.html} | 70 +- ...tcub_1_1_reduce_by_segment_op-members.html | 122 +++ ...> structcub_1_1_reduce_by_segment_op.html} | 130 +-- ...uctcub_1_1_remove_qualifiers-members.html} | 12 +- ...l => structcub_1_1_remove_qualifiers.html} | 39 +- docs/html/structcub_1_1_sum-members.html | 2 +- docs/html/structcub_1_1_sum.html | 2 +- docs/html/structcub_1_1_traits.html | 150 ---- docs/html/structcub_1_1_traits.png | Bin 1763 -> 0 bytes .../structcub_1_1_uninitialized-members.html | 2 +- docs/html/structcub_1_1_uninitialized.html | 2 +- ..._warp_reduce_1_1_temp_storage-members.html | 2 +- ...tcub_1_1_warp_reduce_1_1_temp_storage.html | 6 +- ..._1_warp_scan_1_1_temp_storage-members.html | 2 +- ...uctcub_1_1_warp_scan_1_1_temp_storage.html | 6 +- docs/html/tex__obj__input__iterator_8cuh.html | 2 +- ...tex__obj__input__iterator_8cuh_source.html | 67 +- docs/html/tex__ref__input__iterator_8cuh.html | 2 +- ...tex__ref__input__iterator_8cuh_source.html | 233 ++--- docs/html/thread__load_8cuh.html | 2 +- docs/html/thread__load_8cuh_source.html | 252 +++--- docs/html/thread__operators_8cuh.html | 9 +- docs/html/thread__operators_8cuh_source.html | 112 ++- docs/html/thread__store_8cuh.html | 2 +- docs/html/thread__store_8cuh_source.html | 231 ++--- .../html/transform__input__iterator_8cuh.html | 2 +- ...ransform__input__iterator_8cuh_source.html | 2 +- docs/html/util__allocator_8cuh_source.html | 2 +- docs/html/util__arch_8cuh.html | 2 +- docs/html/util__arch_8cuh_source.html | 4 +- docs/html/util__debug_8cuh.html | 2 +- docs/html/util__debug_8cuh_source.html | 46 +- docs/html/util__device_8cuh.html | 2 +- docs/html/util__device_8cuh_source.html | 2 +- docs/html/util__ptx_8cuh.html | 33 +- docs/html/util__ptx_8cuh_source.html | 843 ++++++++++-------- docs/html/util__type_8cuh.html | 30 +- ...util__type_8cuh_source.html.REMOVED.git-id | 2 +- docs/html/warp__reduce_8cuh.html | 2 +- docs/html/warp__reduce_8cuh_source.html | 2 +- docs/html/warp__scan_8cuh.html | 2 +- docs/html/warp__scan_8cuh_source.html | 4 +- docs/mainpage.dox | 13 +- test/test_block_histogram.cu | 4 +- test/test_block_load_store.cu | 6 +- test/test_block_radix_sort.cu | 4 +- test/test_block_reduce.cu | 5 +- test/test_block_scan.cu | 6 +- test/test_iterator.cu | 6 +- test/test_warp_reduce.cu | 2 +- test/test_warp_scan.cu | 2 +- 342 files changed, 2547 insertions(+), 2480 deletions(-) delete mode 100644 docs/html/search/typedefs_6f.html delete mode 100644 docs/html/search/typedefs_6f.js delete mode 100644 docs/html/search/variables_63.html delete mode 100644 docs/html/search/variables_63.js rename docs/html/{structcub_1_1_traits-members.html => structcub_1_1_is_pointer-members.html} (79%) create mode 100644 docs/html/structcub_1_1_is_pointer.html rename docs/html/{classcub_1_1_reduce_by_segment_op-members.html => structcub_1_1_is_volatile-members.html} (78%) create mode 100644 docs/html/structcub_1_1_is_volatile.html delete mode 100644 docs/html/structcub_1_1_item_offset_pair-members.html delete mode 100644 docs/html/structcub_1_1_numeric_traits.html delete mode 100644 docs/html/structcub_1_1_numeric_traits.png rename docs/html/{structcub_1_1_base_traits-members.html => structcub_1_1_reduce_by_key_op-members.html} (78%) rename docs/html/{classcub_1_1_reduce_by_segment_op.html => structcub_1_1_reduce_by_key_op.html} (64%) create mode 100644 docs/html/structcub_1_1_reduce_by_segment_op-members.html rename docs/html/{structcub_1_1_item_offset_pair.html => structcub_1_1_reduce_by_segment_op.html} (51%) rename docs/html/{structcub_1_1_numeric_traits-members.html => structcub_1_1_remove_qualifiers-members.html} (81%) rename docs/html/{structcub_1_1_base_traits.html => structcub_1_1_remove_qualifiers.html} (76%) delete mode 100644 docs/html/structcub_1_1_traits.html delete mode 100644 docs/html/structcub_1_1_traits.png diff --git a/CHANGE_LOG.TXT b/CHANGE_LOG.TXT index b2695c0e42..202ec6f160 100644 --- a/CHANGE_LOG.TXT +++ b/CHANGE_LOG.TXT @@ -1,5 +1,19 @@ //----------------------------------------------------------------------------- +1.4.1 04/13/2015 + - Bug fixes: + - Fixes for CUDA 7.0 issues with SHFL-based warp-scan and warp-reduction + on non-primitive data types (e.g., user-defined structs) + - Fixes for minor CUDA 7.0 performance regressions in cub::DeviceScan, + DeviceReduceByKey + - Fixes to allow cub::DeviceRadixSort and cub::BlockRadixSort on bool types + - Remove requirement for callers to define the CUB_CDP macro + when invoking CUB device-wide rountines using CUDA dynamic parallelism + - Fix for headers not being included in the proper order (or missing includes) + for some block-wide functions + +//----------------------------------------------------------------------------- + 1.4.0 03/18/2015 - New Features: - Support and performance tuning for new Maxwell GPU architectures diff --git a/README.md b/README.md index 98c5f72ecb..6cbd133f26 100644 --- a/README.md +++ b/README.md @@ -1,7 +1,7 @@

About CUB

-Current release: v1.4.0 (03/18/2015) +Current release: v1.4.1 (04/13/2015) We recommend the [CUB Project Website](http://nvlabs.github.com/cub) and the [cub-users discussion forum](http://groups.google.com/group/cub-users) for further information and examples. @@ -89,16 +89,6 @@ feature set. At the moment, we do not publicly provide non-stable releases such as development snapshots, beta releases or rolling releases. (Feel free to contact us if you would like such things.) See the [CUB Project Website](http://nvlabs.github.com/cub) for more information. - -| Date | Version | -| ---- | ------- | -| 03/18/2015 | [CUB v1.4.0](https://github.com/NVlabs/cub/archive/1.4.0.zip) | -| 05/23/2014 | [CUB v1.3.2](https://github.com/NVlabs/cub/archive/1.3.2.zip) | -| 04/01/2014 | [CUB v1.2.3](https://github.com/NVlabs/cub/archive/1.2.3.zip) | -| 12/10/2013 | [CUB v1.1.1](https://github.com/NVlabs/cub/archive/1.1.1.zip) | -| 08/08/2013 | [CUB v1.0.1](https://github.com/NVlabs/cub/archive/1.0.1.zip) | -| 03/07/2013 | [CUB v0.9.0](https://github.com/NVlabs/cub/archive/0.9.zip) | -

Contributors

diff --git a/cub/device/device_spmv.cuh b/cub/device/device_spmv.cuh index e80228dcf1..64ce7cfec0 100644 --- a/cub/device/device_spmv.cuh +++ b/cub/device/device_spmv.cuh @@ -94,8 +94,8 @@ struct DeviceSpmv * float beta = 0.0; * * float* d_values; // e.g., [1, 1, 1, 1, 1, 1, 1, 1, - * // 1, 1, 1, 1, 1, 1, 1, 1, - * // 1, 1, 1, 1, 1, 1, 1, 1] + * // 1, 1, 1, 1, 1, 1, 1, 1, + * // 1, 1, 1, 1, 1, 1, 1, 1] * * int* d_column_indices; // e.g., [1, 3, 0, 2, 4, 1, 5, 0, * // 4, 6, 1, 3, 5, 7, 2, 4, diff --git a/docs/download_cub.html b/docs/download_cub.html index 70d40bb0b7..f2d78ad3e0 100644 --- a/docs/download_cub.html +++ b/docs/download_cub.html @@ -37,14 +37,14 @@
If your download doesn't start in 3s:

- -Download CUB! + +Download CUB!
diff --git a/docs/html/CHANGE_LOG.TXT b/docs/html/CHANGE_LOG.TXT index 019de0c78e..202ec6f160 100644 --- a/docs/html/CHANGE_LOG.TXT +++ b/docs/html/CHANGE_LOG.TXT @@ -1,5 +1,19 @@ //----------------------------------------------------------------------------- +1.4.1 04/13/2015 + - Bug fixes: + - Fixes for CUDA 7.0 issues with SHFL-based warp-scan and warp-reduction + on non-primitive data types (e.g., user-defined structs) + - Fixes for minor CUDA 7.0 performance regressions in cub::DeviceScan, + DeviceReduceByKey + - Fixes to allow cub::DeviceRadixSort and cub::BlockRadixSort on bool types + - Remove requirement for callers to define the CUB_CDP macro + when invoking CUB device-wide rountines using CUDA dynamic parallelism + - Fix for headers not being included in the proper order (or missing includes) + for some block-wide functions + +//----------------------------------------------------------------------------- + 1.4.0 03/18/2015 - New Features: - Support and performance tuning for new Maxwell GPU architectures @@ -118,7 +132,7 @@ - Added min, max, arg-min, and arg-max to DeviceReduce - Added DeviceSelect (select-unique, select-if, and select-flagged) - Added DevicePartition (partition-if, partition-flagged) - - Added generic cub::ShuffleUp(), cub::ShuffleDown(), and cub::ShuffleBroadcast() for warp-wide communication of arbitrary data types (SM3x+) + - Added generic cub::ShuffleUp(), cub::ShuffleDown(), and cub::ShuffleIndex() for warp-wide communication of arbitrary data types (SM3x+) - Added cub::MaxSmOccupancy() for accurately determining SM occupancy for any given kernel function pointer - Performance - Improved DeviceScan and DeviceRadixSort performance for older architectures (SM10-SM30) diff --git a/docs/html/annotated.html b/docs/html/annotated.html index 790a6923df..f96d2a777a 100644 --- a/docs/html/annotated.html +++ b/docs/html/annotated.html @@ -107,33 +107,33 @@  oCInt2TypeAllows for the treatment of an integral constant as a type at compile-time (e.g., to achieve static call dispatch based on constant integral values)  oCCubVectorExposes a member typedef Type that names the corresponding CUDA vector type if one exists. Otherwise Type refers to the CubVector structure itself, which will wrap the corresponding x, y, etc. vector fields  oCUninitializedA storage-backing wrapper that allows types with non-trivial constructors to be aliased in unions - oCItemOffsetPairAn item value paired with a corresponding offset - oCKeyValuePairA key identifier paired with a corresponding value - oCDoubleBufferDouble-buffer storage wrapper for multi-pass stream transformations that require more than one storage array for streaming intermediate results back and forth - oCLog2Statically determine log2(N), rounded up - oCPowerOfTwoStatically determine if N is a power-of-two - oCBaseTraitsBasic type traits - oCNumericTraitsNumeric type traits - oCTraitsType traits - oCArgIndexInputIteratorA random-access input wrapper for pairing dereferenced values with their corresponding indices (forming ItemOffsetPair tuples) - oCCacheModifiedInputIteratorA random-access input wrapper for dereferencing array values using a PTX cache load modifier - oCCacheModifiedOutputIteratorA random-access output wrapper for storing array values using a PTX cache-modifier - oCConstantInputIteratorA random-access input generator for dereferencing a sequence of homogeneous values - oCCountingInputIteratorA random-access input generator for dereferencing a sequence of incrementing integer values - oCTexObjInputIteratorA random-access input wrapper for dereferencing array values through texture cache. Uses newer Kepler-style texture objects - oCTexRefInputIteratorA random-access input wrapper for dereferencing array values through texture cache. Uses older Tesla/Fermi-style texture references - oCTransformInputIteratorA random-access input wrapper for transforming dereferenced values - oCEqualityDefault equality functor - oCInequalityDefault inequality functor - oCInequalityWrapperInequality functor (wraps equality functor) - oCSumDefault sum functor - oCMaxDefault max functor - oCArgMaxArg max functor (keeps the value and offset of the first occurrence of the larger item) - oCMinDefault min functor - oCArgMinArg min functor (keeps the value and offset of the first occurrence of the smallest item) - oCCastDefault cast functor - oCSwizzleScanOpBinary operator wrapper for switching non-commutative scan arguments - oCReduceBySegmentOpReduce-by-segment functor + oCKeyValuePairA key identifier paired with a corresponding value + oCDoubleBufferDouble-buffer storage wrapper for multi-pass stream transformations that require more than one storage array for streaming intermediate results back and forth + oCLog2Statically determine log2(N), rounded up + oCPowerOfTwoStatically determine if N is a power-of-two + oCIsPointerPointer vs. iterator + oCIsVolatileVolatile modifier test + oCRemoveQualifiersRemoves const and volatile qualifiers from type Tp + oCArgIndexInputIteratorA random-access input wrapper for pairing dereferenced values with their corresponding indices (forming KeyValuePair tuples) + oCCacheModifiedInputIteratorA random-access input wrapper for dereferencing array values using a PTX cache load modifier + oCCacheModifiedOutputIteratorA random-access output wrapper for storing array values using a PTX cache-modifier + oCConstantInputIteratorA random-access input generator for dereferencing a sequence of homogeneous values + oCCountingInputIteratorA random-access input generator for dereferencing a sequence of incrementing integer values + oCTexObjInputIteratorA random-access input wrapper for dereferencing array values through texture cache. Uses newer Kepler-style texture objects + oCTexRefInputIteratorA random-access input wrapper for dereferencing array values through texture cache. Uses older Tesla/Fermi-style texture references + oCTransformInputIteratorA random-access input wrapper for transforming dereferenced values + oCEqualityDefault equality functor + oCInequalityDefault inequality functor + oCInequalityWrapperInequality functor (wraps equality functor) + oCSumDefault sum functor + oCMaxDefault max functor + oCArgMaxArg max functor (keeps the value and offset of the first occurrence of the larger item) + oCMinDefault min functor + oCArgMinArg min functor (keeps the value and offset of the first occurrence of the smallest item) + oCCastDefault cast functor + oCSwizzleScanOpBinary operator wrapper for switching non-commutative scan arguments + oCReduceBySegmentOpReduce-by-segment functor + oCReduceByKeyOp< Binary reduction operator to apply to values  oCBlockDiscontinuityThe BlockDiscontinuity class provides collective methods for flagging discontinuities within an ordered set of items partitioned across a CUDA thread block.

discont_logo.png @@ -236,7 +236,7 @@