oneMKL Developer Guides:

• oneMKL Developer Guide for Linux*

• oneMKL Developer Guide for Windows*

The Developer Guide contains detailed information on several topics including:

• Compiling and linking applications

• Building custom DLLs

• Threading

• Memory Management

oneMKL Developer References for Supported Languages:

• oneMKL Developer Reference - C

• oneMKL Developer Reference - Fortran

• oneMKL Developer Reference - SYCL

The Developer Reference (in C, Fortran, and SYCL formats) contains detailed descriptions of the functions and interfaces for all library domains.

For SYCL interfaces with dynamic linking on Linux

icpx -fsycl <typical user includes and linking flags and other libs> -L${MKLROOT}/lib -lmkl_sycl_<domain> -lmkl_intel_<lp64|ilp64> -lmkl_<threading> -lmkl_core <thread runtime> -lpthread -ldl -lm

Here is an example of building / dynamically linking main.cpp with ilp64 interfaces and Intel OpenMP threading including all SYCL domains:

icpx -fsycl -DMKL_ILP64 -I${MKLROOT}/include main.cpp -L${MKLROOT}/lib \
-lmkl_sycl -lmkl_intel_ilp64 -lmkl_intel_thread -lmkl_core \
-liomp5 -lpthread -ldl -lm

Here is the same configuration with the BLAS SYCL domain only (note that libraries specific to the SYCL domain are aligned with oneMKL domain namespaces):

icpx -fsycl -DMKL_ILP64 -I${MKLROOT}/include main.cpp -L${MKLROOT}/lib \
-lmkl_sycl_blas -lmkl_intel_ilp64 -lmkl_intel_thread -lmkl_core \
-liomp5 -lpthread -ldl -lm

For SYCL interfaces with dynamic linking on Windows

icx -fsycl <typical user includes and linking flags and other libs> mkl_sycl_<domain>_dll.lib mkl_intel_<lp64|ilp64>_dll.lib mkl_<thread>_dll.lib mkl_core_dll.lib <thread runtime>

Here is an example of building / dynamically linking main.cpp with lp64 interfaces and oneTBB threading including all SYCL domains:

icx -fsycl -I"%MKLROOT%\include" main.cpp mkl_sycl_dll.lib^
mkl_intel_lp64_dll.lib mkl_tbb_thread_dll.lib mkl_core_dll.lib^
tbb.lib

Here is the same configuration with the BLAS SYCL domain only (note that libraries specific to the SYCL domain are aligned with oneMKL domain namespaces):

icx -fsycl -I"%MKLROOT%\include" main.cpp mkl_sycl_blas_dll.lib^
mkl_intel_lp64_dll.lib mkl_tbb_thread_dll.lib mkl_core_dll.lib^
tbb.lib

For C/Fortran Interfaces with OpenMP Offload Support

Use the C/Fortran Intel® oneAPI Math Kernel Library interfaces with the OpenMP offload feature for GPU. Add the following changes to the C/Fortran oneMKL compile/link lines to enable the OpenMP offload feature for GPU:

• Additional compile/link options: -fiopenmp -fopenmp-targets=spir64 -fsycl

• Additional oneMKL library: oneMKL SYCL library (in case of dynamic link only, not needed in case of linking with single dynamic library)

Here is an example of building / dynamically linking main.cpp on Linux with oneMKL Single Dynamic Library:

icx -fiopenmp -fopenmp-targets=spir64 -fsycl -I$(MKLROOT)/include main.cpp \
-L${MKLROOT}/lib -lmkl_rt \
-liomp5 -lsycl -lstdc++ -lpthread -lm -ldl

For all other supported configurations, see Intel® oneAPI Math Kernel Library Link Line Advisor.

oneMKL SYCL Samples in GitHub

These samples were designed to help you develop, offload, and optimize multi-architecture applications targeting CPUs and GPUs.

Tutorial: Using Intel® oneAPI Math Kernel Library for Matrix Multiplication:

• Tutorial - C Language

• Tutorial - Fortran Language

This tutorial demonstrates how you can use oneMKL to multiply matrices, measure the performance of matrix multiplication, and control threading.

Intel® oneAPI Math Kernel Library (oneMKL) Release Notes

The release notes contain information specific to the latest release of oneMKL including new and changed features. The release notes include links to principal online information resources related to the release. You can also find information on:

• What’s new in the release

• Product contents

• Obtaining technical support

• License definitions

Intel® oneAPI Math Kernel Library

For support and online documentation, refer to this Intel® oneAPI Math Kernel Library (oneMKL) product page.

Intel® oneAPI Math Kernel Library Cookbook

The Intel® oneAPI Math Kernel Library contains many routines to help you solve various numerical problems, such as multiplying matrices, solving a system of equations, and performing a Fourier transform.

Notes for Intel® oneAPI Math Kernel Library Vector Statistics

This document includes an overview, a usage model, and testing results of random number generators included in VS.

Intel® oneAPI Math Kernel Library Vector Statistics Random Number Generator Performance Data

Refer to this document for performance data obtained using VS (vector statistics), RNG (random number generators) including CPE (clocks per element), BRNG (basic random number generators), generated distribution generators, and length of generated vectors.

Intel® oneAPI Math Kernel Library Vector Mathematics Performance and Accuracy Data

Vector Mathematics (VM) computes elementary functions on vector arguments. VM includes a set of highly optimized implementations of computationally expensive core mathematical functions (power, trigonometric, exponential, hyperbolic, and others) that operate on vectors.

Application Notes for Intel® oneAPI Math Kernel Library Summary Statistics

Summary Statistics is a subcomponent of the Vector Statistics domain of Intel® oneAPI Math Kernel Library. Summary Statistics provides you with functions for initial statistical analysis and offers solutions for parallel processing of multi-dimensional datasets.

LAPACK Examples

This document provides code examples for oneMKL LAPACK (Linear Algebra PACKage) routines.

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex. Notice revision #20201201