Function cusparseRot 

pub unsafe extern "C" fn cusparseRot(
    handle: cusparseHandle_t,
    c_coeff: *const c_void,
    s_coeff: *const c_void,
    vecX: cusparseSpVecDescr_t,
    vecY: cusparseDnVecDescr_t,
) -> cusparseStatus_t

👎Deprecated

The function computes the Givens rotation matrix

to a sparse vecX and a dense vector vecY

In other words,

for i=0 to nnz-1
Y[X_indices[i]] = c * Y[X_indices[i]] - s * X_values[i]
X_values[i]     = c * X_values[i]     + s * Y[X_indices[i]]

cusparseRot supports the following index type for representing the sparse vector vecX:

• 32-bit indices (cusparseIndexType_t::CUSPARSE_INDEX_32I)
• 64-bit indices (cusparseIndexType_t::CUSPARSE_INDEX_64I)

cusparseRot supports the following data types:

Uniform-precision computation:

X/Y/compute
cudaDataType_t::CUDA_R_32F
cudaDataType_t::CUDA_R_64F
cudaDataType_t::CUDA_C_32F
cudaDataType_t::CUDA_C_64F

Mixed-precision computation:

X/Y	compute
cudaDataType_t::CUDA_R_16F	cudaDataType_t::CUDA_R_32F
cudaDataType_t::CUDA_R_16BF
cudaDataType_t::CUDA_C_16F	cudaDataType_t::CUDA_C_32F	[DEPRECATED]
cudaDataType_t::CUDA_C_16BF	[DEPRECATED]

cusparseRot has the following constraints:

• The arrays representing the sparse vector vecX must be aligned to 16 bytes

cusparseRot has the following properties:

• The routine requires no extra storage
• The routine supports asynchronous execution
• Provides deterministic (bit-wise) results for each run if the the sparse vector vecX indices are distinct

cusparseRot supports the following optimizations:

• CUDA graph capture
• Hardware Memory Compression

Please visit cuSPARSE Library Samples - cusparseRot for a code example.

Parameters

• handle: Handle to the cuSPARSE library context.
• c_coeff: cosine element of the rotation matrix.
• s_coeff: sine element of the rotation matrix.
• vecX: Sparse vector X.
• vecY: Dense vector Y.