AMDGPU API Reference

workitemIdx()::ROCDim3

Returns the work item index within the work group. See also: threadIdx

workgroupIdx()::ROCDim3

Returns the work group index. See also: blockIdx

workgroupDim()::ROCDim3

Returns the size of each workgroup in workitems. See also: blockDim

gridItemDim()::ROCDim3

Returns the size of the grid in workitems. This behaviour is different from CUDA where gridDim gives the size of the grid in blocks.

gridGroupDim()::ROCDim3

Returns the size of the grid in workgroups. This is equivalent to CUDA's gridDim.

threadIdx()::ROCDim3

Returns the thread index within the block. See also: workitemIdx

blockIdx()::ROCDim3

Returns the block index within the grid. See also: workgroupIdx

blockDim()::ROCDim3

Returns the dimensions of the block. See also: workgroupDim

sync_workgroup()

Waits until all wavefronts in a workgroup have reached this call.

sync_workgroup_count(predicate::Cint)::Cint

Identical to sync_workgroup, with the additional feature that it evaluates the predicate for all workitems in the workgroup and returns the number of workitems for which predicate evaluates to non-zero.

sync_workgroup_and(predicate::Cint)::Cint

Identical to sync_workgroup, with the additional feature that it evaluates the predicate for all workitems in the workgroup and returns non-zero if and only if predicate evaluates to non-zero for all of them.

sync_workgroup_or(predicate::Cint)::Cint

Identical to sync_workgroup, with the additional feature that it evaluates the predicate for all workitems in the workgroup and returns non-zero if and only if predicate evaluates to non-zero for any of them.