Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/ROCm/rocPRIM
/ functions
Functions
2,472 in github.com/ROCm/rocPRIM
⨍
Functions
2,472
◇
Types & classes
7,856
Method
__init__
(self, fallback_entries)
scripts/autotune/create_optimization.py:682
Method
__init__
(self, fallback_config_file: str)
scripts/autotune/create_optimization.py:776
Method
_allocate_device_memory
Allocates device memory for merge operation. Args: key_type: Type of the keys value_type: Optional type of t
tuning/tuning_scripts/tuning_device_merge.py:110
Method
_create
benchmark/benchmark_device_segmented_radix_sort_keys.parallel.hpp:254
Method
_create
benchmark/benchmark_device_segmented_radix_sort_pairs.parallel.hpp:269
Method
_get_grid_div_x
Return the grid_div_x parameter for kernel_tuner.tune_kernel()
tuning/tuning_scripts/tuning_device_merge.py:106
Method
_get_restrictions
Constraints for what parameter combinations are valid during tuning
tuning/tuning_scripts/tuning_device_merge.py:69
Method
_get_tune_params
Returns tuning parameters and their possible values as an OrderedDict. Each parameter maps to a list of valid values to explore during tuning.
tuning/tuning_scripts/tuning_device_merge.py:61
Method
a
common/utils_data_generation.hpp:67
Function
add_benchmarks
benchmark/benchmark_warp_scan.cpp:191
Function
add_benchmarks
benchmark/benchmark_device_segmented_radix_sort_pairs.cpp:56
Function
add_benchmarks
benchmark/benchmark_block_adjacent_difference.cpp:347
Function
add_benchmarks
benchmark/benchmark_device_segmented_radix_sort_keys.cpp:50
Function
add_benchmarks
benchmark/benchmark_device_reduce_by_key.parallel.hpp:255
Method
add_context
benchmark/benchmark_utils.hpp:2065
Method
add_measurement
Adds a single tuning run.
tuning/configs_header_generation.py:214
Method
add_measurement
Adds a single benchmark run.
scripts/autotune/create_optimization.py:172
Method
adjacent_difference_config
rocprim/include/rocprim/device/detail/device_config_helper.hpp:898
Function
adjacent_difference_impl
rocprim/include/rocprim/device/device_adjacent_difference.hpp:66
Function
adjacent_difference_inplace
rocprim/include/rocprim/device/device_adjacent_difference.hpp:345
Function
adjacent_difference_kernel_impl
rocprim/include/rocprim/device/detail/device_adjacent_difference.hpp:174
Function
adjacent_difference_right
rocprim/include/rocprim/device/device_adjacent_difference.hpp:504
Function
adjacent_difference_right_inplace
rocprim/include/rocprim/device/device_adjacent_difference.hpp:562
Method
adjacent_find_config
rocprim/include/rocprim/device/detail/device_config_helper.hpp:1386
Method
advance_iterator
rocprim/include/rocprim/iterator/zip_iterator.hpp:81
Method
algo_sort
rocprim/include/rocprim/device/device_partial_sort.hpp:80
Method
algo_sort
rocprim/include/rocprim/device/device_partial_sort.hpp:126
Method
allocate
test/hip/test_hip_async_copy.cpp:49
Function
alternate
\brief Returns a pointer to the alternate buffer.
rocprim/include/rocprim/types/double_buffer.hpp:75
Method
amdsmi
benchmark/benchmark_utils.hpp:1023
Function
apply
rocprim/include/rocprim/types/tuple.hpp:1102
Function
apply
test/rocprim/test_block_adjacent_difference.kernels.hpp:39
Method
apply_init
rocprim/include/rocprim/block/detail/block_scan_warp_scan.hpp:812
Method
apply_init
rocprim/include/rocprim/block/detail/block_scan_reduce_then_scan.hpp:736
Method
apply_left
rocprim/include/rocprim/block/detail/block_adjacent_difference_impl.hpp:110
Method
apply_left_partial
rocprim/include/rocprim/block/detail/block_adjacent_difference_impl.hpp:174
Method
apply_right
rocprim/include/rocprim/block/detail/block_adjacent_difference_impl.hpp:241
Method
apply_right_partial
rocprim/include/rocprim/block/detail/block_adjacent_difference_impl.hpp:304
Method
apply_settings
benchmark/benchmark_utils.hpp:2191
Function
arg_index_iterator operator+
rocprim/include/rocprim/iterator/arg_index_iterator.hpp:129
Function
arg_index_iterator operator++
rocprim/include/rocprim/iterator/arg_index_iterator.hpp:107
Function
arg_index_iterator operator-
rocprim/include/rocprim/iterator/arg_index_iterator.hpp:143
Function
arg_index_iterator<InputIterator, Difference, InputValueType> make_arg_index_iterator
rocprim/include/rocprim/iterator/arg_index_iterator.hpp:251
Function
arg_index_iterator<InputIterator, Difference, InputValueType> operator+
rocprim/include/rocprim/iterator/arg_index_iterator.hpp:224
Function
asm_thread_load
rocprim/include/rocprim/thread/thread_load.hpp:71
Function
atomicIncrement
test/hipgraph/test_hipgraph_basic.cpp:48
Function
atomic_cas
rocprim/include/rocprim/intrinsics/atomic.hpp:108
Function
atomic_exch
rocprim/include/rocprim/intrinsics/atomic.hpp:128
Function
atomic_max
rocprim/include/rocprim/intrinsics/atomic.hpp:72
Function
atomic_wrapinc
rocprim/include/rocprim/intrinsics/atomic.hpp:66
Method
b
common/utils_data_generation.hpp:72
Function
ballot_kernel
test/rocprim/test_intrinsics.cpp:1013
Method
base
rocprim/include/rocprim/iterator/reverse_iterator.hpp:83
Function
batch_copy
benchmark/benchmark_device_batch_memcpy.cpp:59
Function
batch_copy
test/rocprim/test_device_batch_memcpy.cpp:140
Method
batch_memcpy_config
rocprim/include/rocprim/device/detail/device_config_helper.hpp:977
Method
best_config_by_selection_types
Returns a dictionary containing each instantion of the selection configuration as a key and the single best performing tuning run as
tuning/configs_header_generation.py:237
Method
best_config_by_selection_types
Returns a dictionary containing each instantion of the selection configuration as a key and the single best performing benchmark run
scripts/autotune/create_optimization.py:195
Method
bfloat16 native_to_bfloat16
test/rocprim/test_utils_bfloat16.hpp:37
Method
bfloat16>
test/rocprim/test_utils_assertions.hpp:178
Function
binary_search_config_name
benchmark/benchmark_device_binary_search.parallel.hpp:117
Function
bit_cast
rocprim/include/rocprim/detail/various.hpp:380
Method
bit_cast
rocprim/include/rocprim/type_traits.hpp:449
Method
bit_key_type encode
rocprim/include/rocprim/type_traits.hpp:678
Method
bit_key_type encode
rocprim/include/rocprim/type_traits.hpp:794
Method
bit_key_type encode
rocprim/include/rocprim/type_traits.hpp:879
Method
bitonic_sort
rocprim/include/rocprim/warp/detail/warp_sort_shuffle.hpp:240
Function
bitwise_equal
test/rocprim/test_utils_assertions.hpp:424
Method
blev_memcpy_kernel_impl
rocprim/include/rocprim/device/detail/device_batch_memcpy.hpp:995
Function
block_id
rocprim/include/rocprim/intrinsics/thread.hpp:242
Function
block_id_kernel
test/rocprim/test_thread.cpp:141
Method
block_merge_kernel
rocprim/include/rocprim/device/device_merge_inplace.hpp:558
Function
block_merge_oddeven_kernel
rocprim/include/rocprim/device/detail/device_merge_sort.hpp:546
Method
block_reduce_kernel
rocprim/include/rocprim/device/detail/device_adjacent_find.hpp:55
Function
block_reduce_kernel_impl
rocprim/include/rocprim/device/detail/device_reduce.hpp:76
Function
block_run_length_decode_kernel
benchmark/benchmark_block_run_length_decode.cpp:47
Function
block_run_length_decode_kernel
test/rocprim/test_block_run_length_decode.cpp:110
Function
block_size
rocprim/include/rocprim/intrinsics/thread.hpp:252
Function
block_sort_config_get_best
(input: Dict)
tuning/configs_header_generation.py:439
Function
block_sort_config_get_best
(input: Dict)
scripts/autotune/create_optimization.py:330
Function
block_sort_kernel_impl
rocprim/include/rocprim/device/detail/device_nth_element.hpp:125
Function
block_store_direct_blocked_cast
rocprim/include/rocprim/block/block_store_func.hpp:535
Function
block_store_direct_striped
rocprim/include/rocprim/block/block_store_func.hpp:214
Function
block_thread_id
rocprim/include/rocprim/intrinsics/thread.hpp:232
Function
blocked_to_striped
rocprim/include/rocprim/block/block_exchange.hpp:157
Function
blocked_to_striped
rocprim/include/rocprim/warp/warp_exchange.hpp:787
Function
blocked_to_striped_kernel
test/rocprim/test_block_exchange.kernels.hpp:56
Function
blocked_to_striped_shuffle
rocprim/include/rocprim/warp/warp_exchange.hpp:843
Function
blocked_to_warp_striped
rocprim/include/rocprim/block/block_exchange.hpp:291
Function
blocked_to_warp_striped_kernel
test/rocprim/test_block_exchange.kernels.hpp:104
Method
bounds_checking_iterator
test/rocprim/bounds_checking_iterator.hpp:47
Function
broadcast
rocprim/include/rocprim/warp/warp_scan.hpp:954
Function
broadcast
Broadcast
rocprim/include/rocprim/warp/detail/warp_scan_crosslane.hpp:244
Function
broadcast
rocprim/include/rocprim/warp/detail/warp_scan_dpp.hpp:316
Method
broadcast
rocprim/include/rocprim/warp/detail/warp_scan_shared_mem.hpp:210
Function
cast_align_down
rocprim/include/rocprim/detail/various.hpp:364
Function
cast_align_up
rocprim/include/rocprim/detail/various.hpp:341
Method
check_output_iterator
test/rocprim/test_device_adjacent_difference.cpp:422
Function
check_result
test/rocprim/test_device_batch_memcpy.cpp:191
Function
check_virtual_wave_size
rocprim/include/rocprim/intrinsics/arch.hpp:272
← previous
next →
801–900 of 2,472, ranked by callers