#[non_exhaustive]pub enum Status {
Show 13 variants
Success,
NotInitialized,
AllocFailed,
InvalidValue,
ArchitectureMismatch,
MappingError,
ExecutionFailed,
InternalError,
MatrixTypeNotSupported,
ZeroPivot,
NotSupported,
InsufficientResources,
Unknown(u32),
}Expand description
Status is the cuSPARSE status code returned by cuSPARSE operations.
Variants (Non-exhaustive)§
This enum is marked as non-exhaustive
Success
The operation completed successfully.
NotInitialized
The cuSPARSE library was not initialized.
Common causes include a missing Context::create call, a CUDA runtime error reported by cuSPARSE, or an error in the hardware setup.
The error also applies when a matrix or vector descriptor is not initialized.
AllocFailed
Resource allocation failed inside the cuSPARSE library.
Usually caused by a device memory allocation (cudaMalloc()) or host memory allocation failure.
InvalidValue
An unsupported value or parameter was passed to the operation, such as a negative vector size.
ArchitectureMismatch
The operation requires a feature absent from the device architecture.
MappingError
An access to GPU memory space failed, which is usually caused by a failure to bind a texture or an invalid device pointer. To correct: check that all device pointers are valid and that no texture is bound that could interfere with the operation.
ExecutionFailed
The GPU program failed to execute. A kernel launch failure on the GPU is a common cause.
InternalError
An internal cuSPARSE operation failed. Also check that memory passed to the operation is not released before the operation completes.
MatrixTypeNotSupported
The matrix type is not supported by this operation.
Usually caused by passing an invalid matrix descriptor to the operation.
Check that the fields in MatrixDescriptor were set correctly.
ZeroPivot
A zero pivot was encountered during the factorization. The operation cannot proceed because a diagonal element is zero. To correct: ensure the input matrix is non-singular.
NotSupported
The operation or data type combination is currently not supported.
InsufficientResources
The resources for the computation, such as GPU global or shared memory, are not sufficient to complete the operation. The error can also indicate that the current computation mode, such as sparse matrix index bit size, cannot handle the given input.
Unknown(u32)
A status code not known to this version of Singe.