Function cusparseSpVV 

pub unsafe extern "C" fn cusparseSpVV(
    handle: cusparseHandle_t,
    opX: cusparseOperation_t,
    vecX: cusparseConstSpVecDescr_t,
    vecY: cusparseConstDnVecDescr_t,
    result: *mut c_void,
    computeType: cudaDataType,
    externalBuffer: *mut c_void,
) -> cusparseStatus_t

👎Deprecated

The function computes the inner dot product of a sparse vector vecX and a dense vector vecY

In other words,

The function cusparseSpVV_bufferSize returns the size of the workspace needed by cusparseSpVV

cusparseSpVV 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)

The data types combinations currently supported for cusparseSpVV are listed below:

Uniform-precision computation:

X/Y/computeType
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	computeType/result	Notes
cudaDataType_t::CUDA_R_8I	cudaDataType_t::CUDA_R_32I
cudaDataType_t::CUDA_R_8I	cudaDataType_t::CUDA_R_32F
cudaDataType_t::CUDA_R_16F	cudaDataType_t::CUDA_R_32F
cudaDataType_t::CUDA_R_16BF	cudaDataType_t::CUDA_R_32F
cudaDataType_t::CUDA_C_16F	cudaDataType_t::CUDA_C_32F	[DEPRECATED]
cudaDataType_t::CUDA_C_16BF	cudaDataType_t::CUDA_C_32F	[DEPRECATED]

cusparseSpVV has the following constraints:

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

cusparseSpVV 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
• The routine allows indices of vecX to be unsorted

cusparseSpVV supports the following optimizations:

• CUDA graph capture
• Hardware Memory Compression

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

Parameters

• handle: Handle to the cuSPARSE library context.
• opX: Operation op(X) that is non-transpose or conjugate transpose.
• vecX: Sparse vector X.
• vecY: Dense vector Y.
• result: The resulting dot product.
• computeType: Datatype in which the computation is executed.
• externalBuffer: Pointer to a workspace buffer of at least bufferSize bytes.