Sparse BLAS SYCL Functionality

oneMKL - Data Parallel C++ Developer Reference

Download PDF

ID 772045

Date 6/24/2024

Version

Public

A newer version of this document is available. Customers should click here to go to the newest version.

Visible to Intel only — GUID: GUID-A8580A9B-F681-4E3F-B926-7FC3EEA99354

View Details

Sparse BLAS SYCL Functionality

The following tables summarize the current support of SYCL Sparse BLAS APIs in Intel oneAPI Math Kernel Library (oneMKL).

In the tables, we use these symbols for the sparse and dense objects in the operation descriptions:

scalar values = , , ,
dense vectors = , ,
sparse vectors = , ,
dense matrices = , and
sparse matrices = , , ,
identity matrix = .

Some operations involve the upper/lower decomposition of a sparse matrix into with strictly lower (), diagonal (), and strictly upper () parts of the sparse matrix, . The choice of which part of the data to use in the operation is controlled by the input parameters:

for selecting or for the operation
for selecting or for the operation

Some of the triangular operations permit you to ignore the main diagonal data in the sparse matrix and replace it, in the operation, with ones on the diagonal:

uses as provided in the data and
ignores and instead uses the identity, .

Finally, the operation represents one of three “transpose” operations:

when using
when using
when using .

Typically all are intended to be supported, but the actual support list and limitations are provided in each API’s individual description page.

Level 1

Sparse BLAS operations involving a sparse vector and other vectors.

There are currently no SYCL Sparse BLAS APIs in oneMKL supporting sparse vectors or Sparse Level 1 operations.

Level 2

Sparse BLAS operations involving a sparse matrix and vectors.

Common Name	SYCL API name with oneapi::mkl:: namespace	Operation	CSR support	COO support
SpMV	sparse::gemv()		CPU/GPU	CPU/GPU
	sparse::symv() + uplo::lower		CPU/GPU	None
	sparse::symv() + uplo::upper		CPU/GPU	None
	sparse::trmv() + uplo::lower + diag::nonunit		CPU/GPU	CPU
	sparse::trmv() + uplo::lower + diag::unit		CPU/GPU	CPU
	sparse::trmv() + uplo::upper + diag::nonunit		CPU/GPU	CPU
	sparse::trmv() + uplo::upper + diag::unit		CPU/GPU	CPU
SpMV + dot fusion	sparse::gemvdot()		CPU/GPU	CPU
SpSV or SpTRSV	sparse::trsv() + uplo::lower + diag::nonunit	Solve for :	CPU/GPU	CPU
	sparse::trsv() + uplo::lower + diag::unit	Solve for :	CPU/GPU	CPU
	sparse::trsv() + uplo::upper + diag::nonunit	Solve for :	CPU/GPU	CPU
	sparse::trsv() + uplo::upper + diag::unit	Solve for :	CPU/GPU	CPU

Level 3

Sparse BLAS operations involving one or more sparse/dense matrices.

Common Name	SYCL API name with oneapi::mkl:: namespace	Operation	CSR support	COO support
SpMM (Dn <- Sp * Dn)	sparse::gemm()		CPU/GPU	CPU
SpSM or SpTRSM	sparse::trsm() + uplo::lower + diag::nonunit	Solve for :	CPU/GPU	CPU
	sparse::trsm() + uplo::lower + diag::unit	Solve for :	CPU/GPU	CPU
	sparse::trsm() + uplo::upper + diag::nonunit	Solve for :	CPU/GPU	CPU
	sparse::trsm() + uplo::upper + diag::unit	Solve for :	CPU/GPU	CPU
SpGEAM (Sp <- Sp + Sp)	sparse::omatadd()		CPU/GPU	None
SpGEMM (Sp <- Sp * Sp)	sparse::matmat()		CPU/GPU	None
SpGEMMD (Dn <- Sp * Sp)	sparse::matmatd()		GPU	None

Auxiliary Functions

Operations that can manipulate the sparse matrix handle.

Common Name	SYCL API name with oneapi::mkl:: namespace	Operation	CSR support	COO support
Sparse Copy or Sparse Matrix Transpose	sparse::omatcopy()		CPU/GPU	CPU/GPU
Sparse Matrix Conversion	sparse::omatconvert()	, where and are represented using different sparse matrix formats	CPU/GPU	CPU/GPU
Sparse Matrix Sort	sparse::sort_matrix()	by natural ordering for the sparse matrix format	CPU/GPU	None (see note below)
Update Matrix Main Diagonal	sparse::update_diagonal_data()	update in-place with new provided diagonal values,	GPU	None

NOTE:

COO format does not have a natural sparse ordering. It could be SortInRows, which is the natural ordering for the CSR format with column index sorted within each row, or it could be SortInColumns, which is the natural ordering for the CSC format with row index sorted within each column. A new API or overload for specifying which ordering to use for COO format will be provided in the future.

Select Your Language

Using Intel.com Search

Quick Links

Recent Searches

Advanced Search

Only search in

oneMKL - Data Parallel C++ Developer Reference

Sparse BLAS SYCL Functionality

Level 1

Level 2

Level 3

Auxiliary Functions