Developer Reference

Contents

Overview of Intel® oneMKL BLAS Routines for Data Parallel C++

The following pages describe the oneMKL BLAS routines for Data Parallel C++ (DPC++), all of which are declared in the header file
oneapi/mkl/blas.hpp
.
Several conventions are used throughout this document:
  • All oneMKL for DPC++ data types and non domain specific functions are inside the
    oneapi::mkl::
    namespace.
  • All oneMKL BLAS functions for DPC++ are inside the
    oneapi::mkl::blas
    namespace.
  • The routines are templated on precision. Each routine has a table detailing the supported precisions.

Device Support

DPC++ supports several types of devices:
  • Host device: Performs computations directly on the current CPU.
  • CPU device: Performs computations on a CPU using OpenCL™.
  • GPU device: Performs computations on a GPU.
In the current release of oneMKL BLAS for DPC++, all standard Level1, Level2, and Level3 BLAS routines and the BLAS extensions support host, CPU, and GPU devices.

Product and Performance Information

1

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