Intel® oneAPI Math Kernel Library (oneMKL) - Data Parallel C++ Developer Reference

Developer Reference

Contents

Data Types

BLAS and LAPACK Data Types

Intel® oneAPI Math Kernel Library (oneMKL) BLAS and LAPACK for Data Parallel C++ (DPC++) introduces several new enumeration data types, which are type-safe versions of the traditional Fortran characters in BLAS and LAPACK. They are declared in
oneapi/mkl/types.hpp
, which is included automatically when you include
oneapi/mkl/blas.hpp
 or
oneapi/mkl/lapack.hpp
. Like all oneMKL DPC++ functionality, they belong to the namespace
oneapi::mkl::
.
Each enumeration value comes with two names: A single-character name (the traditional BLAS/LAPACK character) and a longer, descriptive name. The two names are exactly equivalent and may be used interchangeably.
Transpose
The
transpose
 type specifies whether an input matrix should be transposed and/or conjugated. It can take the following values:
Short Name
Long Name
Description
transpose::N
transpose::nontrans
Do not transpose or conjugate the matrix.
transpose::T
transpose::trans
Transpose the matrix.
transpose::C
transpose::conjtrans
Perform Hermitian transpose (transpose and conjugate). Only applicable to complex matrices.
Uplo
The
uplo
 type specifies whether the lower or upper triangle of a triangular, symmetric, or Hermitian matrix should be accessed. It can take the following values:
Short Name
Long Name
Description
uplo::U
uplo::upper
Access the upper triangle of the matrix.
uplo::L
uplo::lower
Access the lower triangle of the matrix.
In both cases, elements that are not in the selected triangle are not accessed or updated.
Diag
The
diag
 type specifies the values on the diagonal of a triangular matrix. It can take the following values:
Short Name
Long Name
Description
diag::N
diag::nonunit
The matrix is not unit triangular. The diagonal entries are stored with the matrix data.
diag::U
diag::unit
The matrix is unit triangular (the diagonal entries are all 1s). The diagonal entries in the matrix data are not accessed.
Side
The
side
 type specifies the order of matrix multiplication when one matrix has a special form (triangular, symmetric, or Hermitian):
Short Name
Long Name
Description
side::L
side::left
The special form matrix is on the left in the multiplication.
side::R
side::right
The special form matrix is on the right in the multiplication.
Offset
The
offset
 type specifies whether the offset to apply to an output matrix is a fix offset, column offset or row offset. It can take the following values
Short Name
Long Name
Description
offset::F
offset::fix
The offset to apply to the output matrix is fix, all the inputs in the
C_offset
 matrix has the same value given by the first element in the
co
 array.
offset::C
offset::column
The offset to apply to the output matrix is a column offset, that is to say all the columns in the
C_offset
 matrix are the same and given by the elements in the
co
 array.
offset::R
offset::row
The offset to apply to the output matrix is a row offset, that is to say all the rows in the
C_offset
 matrix are the same and given by the elements in the
co
 array.

Vector Math Data Types

oneMKL VM for Data Parallel C++ (DPC++) introduces a slice type, available in the
oneapi::mkl
 namespace. Slices are used in the DPC++ VM Strided APIs. oneMKL slices accept positive, zero, and negative strides, for forward, static, and backward traversals of a vector, respectively.
Constructors
Description
slice()
Default constructor equivalent to slice(0, 0, 0).
slice(
std::size_t
start
,
std::size_t
size
,
std::int64_t
stride
)
Slice defining the start index, the number of values to select, and the stride between two elements.
slice(
const
slice
& other
)
Copy constructor.
For example:
  • slice(1, 5, 2) defines a selector of elements at indices 1, 3, 5, 7, 9 in a buffer or array;
  • slice(0, 5, 0) defines a selector of a single element at index 0, repeated five times;
  • slice(9, 4, -3) defines a selector of elements at indices 9, 6, 3, 0.
A slice is considered invalid if it produces negative indices. A slice of size 0 selects no element. If a slice may cause out-of-bounds memory accesses, the behavior is undefined.
The behavior of VM Strided APIs used with invalid or non-equal slices is configurable with several oneMKL VM mode values. See the set_mode function for possible values and their descriptions.
In the
slice_cyclic
 mode, zero-sized slices are invalid.

Product and Performance Information

1

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.