/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-hip/checkouts/clr/hipamd/include/hip/amd_detail/amd_hip_cooperative_groups.h File Reference#
amd_hip_cooperative_groups.h File Reference
Device side implementation of Cooperative Group
feature.
More...
#include <hip/amd_detail/hip_cooperative_groups_helper.h>
Include dependency graph for amd_hip_cooperative_groups.h:
Go to the source code of this file.
Namespaces | |
namespace | cooperative_groups |
namespace | cooperative_groups::impl |
Functions | |
multi_grid_group | cooperative_groups::this_multi_grid () |
User-exposed API interface to construct grid cooperative group type object - multi_grid_group . | |
grid_group | cooperative_groups::this_grid () |
User-exposed API interface to construct grid cooperative group type object - grid_group . | |
thread_block | cooperative_groups::this_thread_block () |
User-exposed API interface to construct workgroup cooperative group type object - thread_block . | |
coalesced_group | cooperative_groups::coalesced_threads () |
User-exposed API to create coalesced groups. | |
template<class CGTy > | |
uint32_t | cooperative_groups::group_size (CGTy const &g) |
Returns the size of the group. | |
template<class CGTy > | |
uint32_t | cooperative_groups::thread_rank (CGTy const &g) |
Returns the rank of thread of the group. | |
template<class CGTy > | |
bool | cooperative_groups::is_valid (CGTy const &g) |
Returns true if the group has not violated any API constraints. | |
template<class CGTy > | |
void | cooperative_groups::sync (CGTy const &g) |
Synchronizes the threads in the group. | |
thread_group | cooperative_groups::this_thread () |
thread_group | cooperative_groups::tiled_partition (const thread_group &parent, unsigned int tile_size) |
User-exposed API to partition groups. | |
thread_group | cooperative_groups::tiled_partition (const thread_block &parent, unsigned int tile_size) |
tiled_group | cooperative_groups::tiled_partition (const tiled_group &parent, unsigned int tile_size) |
coalesced_group | cooperative_groups::tiled_partition (const coalesced_group &parent, unsigned int tile_size) |
template<unsigned int size, class ParentCGTy > | |
thread_block_tile< size, ParentCGTy > | cooperative_groups::tiled_partition (const ParentCGTy &g) |
Create a partition. | |
coalesced_group | cooperative_groups::binary_partition (const coalesced_group &cgrp, bool pred) |
Binary partition. | |
template<unsigned int size, class parent > | |
coalesced_group | cooperative_groups::binary_partition (const thread_block_tile< size, parent > &tgrp, bool pred) |
Binary partition. | |
Detailed Description
Device side implementation of Cooperative Group
feature.
Defines new types and device API wrappers related to Cooperative Group
feature, which the programmer can directly use in his kernel(s) in order to make use of this feature.