workspace_compute_gate_split_sizes#

cuquantum.bindings.cutensornet.workspace_compute_gate_split_sizes( intptr_t handle, intptr_t desc_tensor_in_a, intptr_t desc_tensor_in_b, intptr_t desc_tensor_in_g, intptr_t desc_tensor_u, intptr_t desc_tensor_v, int gate_algo, intptr_t svd_config, int compute_type, intptr_t work_desc, )[source]#

Computes the workspace size needed to perform the gating operation.

Parameters:

handle (intptr_t) – Opaque handle holding cuTensorNet’s library context.
desc_tensor_in_a (intptr_t) – Describes the modes, extents, and other metadata information of the input tensor A.
desc_tensor_in_b (intptr_t) – Describes the modes, extents, and other metadata information of the input tensor B.
desc_tensor_in_g (intptr_t) – Describes the modes, extents, and other metadata information of the input gate tensor.
desc_tensor_u (intptr_t) – Describes the modes, extents, and other metadata information of the output U tensor. The extents of uncontracted modes are expected to be consistent with desc_tensor_in_a and desc_tensor_in_g.
desc_tensor_v (intptr_t) – Describes the modes, extents, and other metadata information of the output V tensor. The extents of uncontracted modes are expected to be consistent with desc_tensor_in_b and desc_tensor_in_g.
gate_algo (int) – The algorithm to use for splitting the gate tensor onto tensor A and B.
svd_config (intptr_t) – Opaque structure holding the user-requested SVD parameters.
compute_type (ComputeType) – Denotes the compute type used throughout the computation.
work_desc (intptr_t) – Opaque structure describing the workspace.