Developer Guide

  • 2021.7.1
  • 09/08/2022
  • Public Content

Intel® oneAPI DPC++ Library Overview

Parallel API can be used with the C++ Standard Execution Policies to enable parallelism on the host.
The Intel® oneAPI DPC++ Library (oneDPL) is implemented in accordance with the oneDPL Specification.
To support heterogeneity, oneDPL works with the DPC++ API. More information can be found in the DPC++ Specification.

Before You Begin

Visit the oneDPL Release Notes page for:
  • Where to Find the Release
  • Overview
  • New Features
  • Fixed Issues
  • Known Issues and Limitations
Install the Intel® oneAPI Base Toolkit (Base Kit) to use oneDPL.
All oneDPL header files are in the
oneapi/dpl
directory. To use the oneDPL API, include the corresponding header in your source code with the
#include <oneapi/dpl/…>
directive. oneDPL introduces the namespace
oneapi::dpl
for most its classes and functions.
To use tested C++ standard APIs, you need to include the corresponding C++ standard header files and use the
std
namespace.

Prerequisites

C++17 is the minimal supported version of the C++ standard. That means, any use of oneDPL may require a C++17 compiler. While some APIs of the library may accidentally work with earlier versions of the C++ standard, it is no more guaranteed.
To call Parallel API with the C++ standard policies, you need to install the following software:
  • A C++ compiler with support for OpenMP* 4.0 (or higher) SIMD constructs
  • Depending on what parallel backend you want to use install either:
    • Intel® oneAPI Threading Building Blocks (oneTBB) or Intel® Threading Building Blocks (Intel® TBB) 2019 and later
    • A C++ compiler with support for OpenMP 4.5 (or higher)
For more information about parallel backends, see Execution Policies
To use Parallel API with the device execution policies, you need to install the following software:
  • A C++ compiler with support for SYCL 2020

Restrictions

When called with DPC++ execution policies, oneDPL algorithms apply the same restrictions as DPC++ does (see the DPC++ specification and the SYCL specification for details), such as:
  • Adding buffers to a lambda capture list is not allowed for lambdas passed to an algorithm.
  • Passing data types, which are not trivially copyable, is only allowed via USM, but not via buffers or host-allocated containers.
  • The definition of lambda functions used with parallel algorithms should not depend on preprocessor macros that makes it different for the host and the device. Otherwise, the behavior is undefined.
  • When used within SYCL kernels or transferred to/from a device, a container class can only hold objects whose type meets SYCL requirements for use in kernels and for data transfer, respectively.
  • Calling the API that throws exception is not allowed within callable objects passed to an algorithm.

Known Limitations

  • For
    transform_exclusive_scan
    ,
    transform_inclusive_scan
    algorithms, the result of the unary operation should be convertible to the type of the initial value if one is provided, otherwise it is convertible to the type of values in the processed data sequence:
    std::iterator_traits<IteratorType>::value_type
    .
  • exclusive_scan
    and
    transform_exclusive_scan
    algorithms may provide wrong results with vector execution policies when building a program with GCC 10 and using
    -O0
    option.
  • The use of oneDPL together with the GNU C++ standard library (libstdc++) version 9 or 10 may lead to compilation errors (caused by oneTBB API changes). Using libstdc++ version 9 requires TBB version 2020 for the header file. This may result in compilation errors when using C++17 or C++20 and TBB is not found in the environment, even if its use in oneDPL is switched off. To overcome these issues, include oneDPL header files before the standard C++ header files, or disable parallel algorithms support in the standard library. For more information, please see Intel® oneAPI Threading Building Blocks (oneTBB) Release Notes.
  • The
    using namespace oneapi;
    directive in a oneDPL program code may result in compilation errors with some compilers including GCC 7 and earlier. Instead of this directive, explicitly use
    oneapi::dpl
    namespace, or create a namespace alias.
  • std::array::at
    member function cannot be used in kernels because it may throw an exception; use
    std::array::operator[]
    instead.
  • Due to specifics of Microsoft* Visual C++, some standard floating-point math functions (including
    std::ldexp
    ,
    std::frexp
    ,
    std::sqrt(std::complex<float>)
    ) require device support for double precision.

Build Your Code with oneDPL

Follow the steps below to build your code with oneDPL:
  1. To build with the Intel® oneAPI DPC++/C++ Compiler, see the Get Started with the Intel® oneAPI DPC++/C++ Compiler for details.
  2. Set the environment variables for oneDPL and oneTBB.
  3. To avoid naming device policy objects explicitly, add the
    -fsycl-unnamed-lambda
    option.
Below is an example of a command line used to compile code that contains oneDPL parallel algorithms on Linux* (depending on the code, parameters within [] could be unnecessary):
dpcpp [-fsycl-unnamed-lambda] test.cpp [-ltbb|-fopenmp] -o test

Product and Performance Information

1

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