BLAS-like Extensions

oneMKL - Data Parallel C++ Developer Reference

Download PDF

ID 772045

Date 6/30/2025

Version

Public

BLAS-like Extensions

Intel® oneAPI Math Kernel Library (oneMKL) DPC++ provides additional routines to extend the functionality of the BLAS routines. These include routines to compute many independent vector-vector, vector-matrix, matrix-matrix operations.

The following table lists these routines.

Routine	Data Types	Description
axpby	`float`, `double`, `std::complex<float>`, `std::complex<double>`	Computes a vector-scalar product added to a scaled-vector.
axpy_batch	`float`, `double`, `std::complex<float>`, `std::complex<double>`	Computes groups of vector-scalar product added to a vector.
copy_batch	`float`, `double`, `std::complex<float>`, `std::complex<double>`	Computes groups of vector copies.
dgmm_batch	`float`, `double`, `std::complex<float>`, `std::complex<double>`	Computes a group of diagonal matrix-matrix product.
gemm_batch	`std::int8_t`, `oneapi::mkl::bfloat16`, `sycl::half`, `float`, `double`, `std::complex<float>`, `std::complex<double>`, mixed	Computes groups of matrix-matrix product with general matrices.
gemm_bias	mixed `std::int8_t`, `std::uint8_t`, and `std::int32_t`	Computes a matrix-matrix product with general matrices and mixed precision.
gemmt	`float`, `double`, `std::complex<float>`, `std::complex<double>`	Computes a matrix-matrix product with general matrices, but updates only the upper/lower triangular part of the output matrix.
gemv_batch	`float`, `double`, `std::complex<float>`, `std::complex<double>`	Computes a group of matrix-vector product using general matrices.
syrk_batch	`float`, `double`, `std::complex<float>`, `std::complex<double>`	Computes rank-k updates on a group of symmetric matrices by a group of general matrices.
trsm_batch	`float`, `double`, `std::complex<float>`, `std::complex<double>`	Solves a triangular matrix equation for a group of matrices.
omatcopy	`float`, `double`, `std::complex<float>`, `std::complex<double>`	Computes an out-of-place matrix copy or transposition.
imatcopy	`float`, `double`, `std::complex<float>`, `std::complex<double>`	Computes an in-place matrix copy or transposition.
omatadd	`float`, `double`, `std::complex<float>`, `std::complex<double>`	Computes a sum of two general matrices, with optional transposes.
omatcopy_batch	`float`, `double`, `std::complex<float>`, `std::complex<double>`	Computes groups of out-of-place matrix copies or transpositions.
imatcopy_batch	`float`, `double`, `std::complex<float>`, `std::complex<double>`	Computes groups of in-place matrix copies or transpositions.
omatadd_batch	`float`, `double`, `std::complex<float>`, `std::complex<double>`	Computes groups of matrix additions.

Select Your Language

Using Intel.com Search

Quick Links

Recent Searches

Advanced Search

Only search in

oneMKL - Data Parallel C++ Developer Reference

BLAS-like Extensions