Data Parallel C++ : Programming Accelerated Systems Using C++ and SYCL

Learn how to accelerate C++ programs using data parallelism and SYCL. This book enables C++ programmers to be at the forefront of this exciting and important development that is helping to push computing to new levels. This updated second edition is full of practical advice, detailed explanations, and code examples to illustrate key topics. SYCL enables access to parallel resources in modern accelerated heterogeneous systems. Now, a single C++ application can use any combination of devices–including GPUs, CPUs, FPGAs, and ASICs–that are suitable to the problems at hand. This book teaches data-parallel programming using C++ with SYCL and walks through everything needed to program accelerated systems. The book begins by introducing data parallelism and foundational topics for effective use of SYCL. Later chapters cover advanced topics, including error handling, hardware-specific programming, communication and synchronization, and memory model considerations. Computer hardware development is driven by our needs to solve larger and more complex problems, but those hardware advances are largely useless unless programmers like you and me have languages that allow us to implement our ideas and exploit the power available with reasonable effort. There are numerous examples of amazing hardware, and the first solutions to use them have often been proprietary since it saves time not having to bother with committees agreeing on standards. However, in the history of computing, they have eventually always ended up as vendor lock-in—unable to compete with open standards that allow developers to target any hardware and share code—because ultimately the resources of the worldwide community and ecosystem are far greater than any individual vendor, not to mention how open software standards drive hardware competition. If you are new to parallel programming that is okay. If you have never heard of SYCL or the DPC++ compilerthat is also okay. Compared with programming in CUDA, C++ with SYCL offers portability beyond NVIDIA, and portability beyond GPUs, plus a tight alignment to enhance modern C++ as it evolves too. C++ with SYCL offers these advantages without sacrificing performance. C++ with SYCL allows us to accelerate our applications by harnessing the combined capabilities of CPUs, GPUs, FPGAs, and processing devices of the future without being tied to any one vendor. SYCL is an industry-driven Khronos Group standard adding advanced support for data parallelism with C++ to exploit accelerated (heterogeneous) systems. SYCL provides mechanisms for C++ compilers that are highly synergistic with C++ and C++ build systems. DPC++ is an open source compiler project based on LLVM that adds SYCL support. All examples in this book should work with any C++ compiler supporting SYCL 2020 including the DPC++ compiler. If you are a C programmer who is not well versed in C++, you are in good company. Several of the authors of this book happily share that they picked up much of C++ by reading books that utilized C++ like this one. With a little patience, this book should also be approachable by C programmers with a desire to write modern C++ programs. All source code for the examples used in this book is freely available on GitHub. The examples are written in modern SYCL and are regularly updated to ensure compatibility with multiple compilers. What You Will Learn: Accelerate C++ programs using data-parallel programming Use SYCL and C++ compilers that support SYCL Write portable code for accelerators that is vendor and device agnostic Optimize code to improve performance for specific accelerators Be poised to benefit as new accelerators appear from many vendors Who This Book Is For: New data-parallel programming and computer programmers interested in data-parallel programming using C++. "This book, now in is second edition, is the premier resource to learn SYCL 2020 and is the ONLY book you need to become part of this community." Erik Lindahl, GROMACS and Stockholm University "This book, now in is second edition, is the premier resource to learn SYCL 2020 and is the ONLY book you need to become part of this community." Erik Lindahl, GROMACS and Stockholm University Learn how to accelerate C++ programs using data parallelism and SYCL. This open access book enables C++ programmers to be at the forefront of this exciting and important development that is helping to push computing to new levels. This updated second edition is full of practical advice, detailed explanations, and code examples to illustrate key topics. SYCL enables access to parallel resources in modern accelerated heterogeneous systems. Now, a single C++ application can use any combination of devices–including GPUs, CPUs, FPGAs, and ASICs–that are suitable to the problems at hand. This book teaches data-parallel programming using C++ with SYCL and walks through everything needed to program accelerated systems. The book begins by introducing data parallelism and foundational topics for effective use of SYCL. Later chapters cover advanced topics, including error handling, hardware-specific programming, communication and synchronization, and memory model considerations. All source code for the examples used in this book is freely available on GitHub. The examples are written in modern SYCL and are regularly updated to ensure compatibility with multiple compilers. What You Will Learn Accelerate C++ programs using data-parallel programming Use SYCL and C++ compilers that support SYCL Write portable code for accelerators that is vendor and device agnostic Optimize code to improve performance for specific accelerators Be poised to benefit as new accelerators appear from many vendors Who This Book Is For New data-parallel programming and computer programmers interested in data-parallel programming using C++ This is an open access book. Learn how to accelerate C++ programs using data parallelism. This open access book enables C++ programmers to be at the forefront of this exciting and important new development that is helping to push computing to new levels. It is full of practical advice, detailed explanations, and code examples to illustrate key topics. Data parallelism in C++ enables access to parallel resources in a modern heterogeneous system, freeing you from being locked into any particular computing device. Now a single C++ application can use any combination of devices—including GPUs, CPUs, FPGAs and AI ASICs—that are suitable to the problems at hand. This book begins by introducing data parallelism and foundational topics for effective use of the SYCL standard from the Khronos Group and Data Parallel C++ (DPC++), the open source compiler used in this book. Later chapters cover advanced topics including error handling, hardware-specific programming, communication and synchronization, and memory model considerations. Data Parallel C++ provides you with everything needed to use SYCL for programming heterogeneous systems. What You'll Learn Accelerate C++ programs using data-parallel programming Target multiple device types (e.g. CPU, GPU, FPGA) Use SYCL and SYCL compilers Connect with computing’s heterogeneous future via Intel’s oneAPI initiative Who This Book Is For Those new data-parallel programming and computer programmers interested in data-parallel programming using C++. Cover Front Matter 1. Introduction 2. Where Code Executes 3. Data Management 4. Expressing Parallelism 5. Error Handling 6. Unified Shared Memory 7. Buffers 8. Scheduling Kernels and Data Movement 9. Communication and Synchronization 10. Defining Kernels 11. Vectors and Math Arrays 12. Device Information and Kernel Specialization 13. Practical Tips 14. Common Parallel Patterns 15. Programming for GPUs 16. Programming for CPUs 17. Programming for FPGAs 18. Libraries 19. Memory Model and Atomics 20. Backend Interoperability 21. Migrating CUDA Code Back Matter