cuSPARSE

E213160

cuSPARSE is NVIDIA’s GPU-accelerated library providing high-performance sparse linear algebra routines for CUDA applications.

All labels observed (1)

Label Occurrences
cuSPARSE canonical 4

How this entity was disambiguated

Statements (48)

Predicate Object
instanceOf CUDA library
GPU-accelerated sparse linear algebra library
software library
developer NVIDIA Corporation
surface form: NVIDIA
documentationURL https://docs.nvidia.com/cuda/cusparse
domain sparse linear algebra
includedIn CUDA Toolkit installation
integratesWith NVIDIA HPC SDK
Thrust
cuBLAS
cuSOLVER
license proprietary
optimizedFor high-performance sparse computations on GPUs
partOf CUDA toolkit
surface form: NVIDIA CUDA Toolkit
programmingModel NVIDIA CUDA
surface form: CUDA
providesAPI C API
requires CUDA Runtime API
surface form: CUDA runtime

CUDA-capable NVIDIA GPU
supportsDataType complex double-precision (for some routines)
complex single-precision (for some routines)
double-precision floating point
half-precision floating point (for some routines)
single-precision floating point
supportsExecution asynchronous GPU execution (via CUDA streams)
supportsFeature batched sparse operations (for some routines)
descriptor-based matrix and vector objects
mixed-precision computation (for some routines)
supportsLanguage C
C++
Fortran (via wrappers)
supportsMatrixFormat BSR (Block Sparse Row)
COO (Coordinate)
SparseMatrixCSC
surface form: CSC (Compressed Sparse Column)

CSR (Compressed Sparse Row)
ELL (ELLPACK)
HYB (Hybrid ELL/COO)
supportsOperation sparse matrix factorization (limited routines)
sparse matrix format conversion
sparse matrix reordering
sparse matrix-matrix multiplication
sparse matrix-vector multiplication
sparse triangular solve
targetPlatform GPU
surface form: NVIDIA GPU
useCase engineering simulation
graph analytics (via sparse matrices)
machine learning with sparse data
scientific computing
vendor NVIDIA Corporation

How these facts were elicited

Referenced by (4)

Full triples — surface form annotated when it differs from this entity's canonical label.

NVIDIA CUDA includes cuSPARSE
CUDA Fortran supports cuSPARSE
cuBLAS relatedLibrary cuSPARSE
Compute Unified Device Architecture includesLibrary cuSPARSE
subject surface form: CUDA