Script.atomic.shared_max

Script.atomic.shared_max(dst, values, *, sem='relaxed', scope='cta', output=None)

Element-wise dst[i] = max(dst[i], values[i]) atomically, on shared memory.

See shared_add() for the full parameter description.

Notes

• Thread group: Can be executed by any sized thread group.

• Hardware: Requires compute capability 7.0+ (sm_70).

• PTX: atom.{sem}.{scope}.shared.max.s32.

Parameters:

• dst (SharedTensor)

• values (RegisterTensor)

• sem (str)

• scope (str)

• output (RegisterTensor | None)

Return type:

RegisterTensor | None