Get the App
SLTechnology News&Howtos  ›  Development  › 

What is the use of Intel's LLVM architecture CumberCutter + compiler

Shulou Source: shulou.com Published: 2022-06-03 16:54:32 10月19日 Update

Xiaobian to share with you what is the use of Intel's LLVM architecture CumberCraft + compiler, I believe most people do not know much about it, so share this article for your reference, I hope you can learn a lot after reading this article, let's learn about it!

A few days ago, Intel officially announced that it will launch the next generation of C _ swap compiler based on LLVM architecture, which will replace the previous classic Intel C++ compiler. LLVM, the abbreviation of underlying virtual machine (Low Level Virtual Machine), is an open source compiler architecture. LLVM core library provides compiler-related support and can be used as a background for multi-language compilers.

In this regard, Intel expert James R Reinders explained in an article: "Why Intel uses LLVM for the latest Cpicket + compiler. It also emphasizes that LLVM can help Intel achieve its goal of achieving the best Cmax + compiler, and believes that using the latest LLVM-based Cmax + compiler can get faster compilation time, better optimization, more support for technical standards, and uninstall GPU and FPGA.

Benefits of adopting LLVM

According to Intel engineers, the build time of their latest LLVM-based Cumberbatch + compiler is 14% lower than that of the classic C++ compiler, and although their classic C++ compiler has an 18% performance advantage over the native LLVM and GCC, the latest LLVM-based C++ + compiler 2021.3 based on LLVM provides 41% faster performance than GCC 11.1. Intel announced in the report that it will add optimization support for GPU and FPGA to the latest compiler and continue to work to provide industry-leading CPU optimization.

Future plans for the latest compiler

Intel recommends that all new projects use the LLVM-based Intel CumberCandler + compiler, and plans to migrate all projects to the new compiler this year. At the same time, the classic CumberCutter + compiler is about to enter "traditional product support" mode, indicating that once the regular updates of classic compilers are over, they may not continue to appear in the oneAPI toolkit. James R Reinders (James R. Redes) added on his blog that "the new LLVM-based Cmax Candle + editor is on a par with the classic version, and the LLVM-based Cwispy + provides the best optimization technology we have. We recommend that all users try the new Cwispy + compiler now and provide feedback."

James R Reinders (James R Redes) finally hinted in his blog that there are guidelines for users to convert from the classic Cmax Clipper + compiler to a LLVM-based compiler, and users only need to note that the compiler has a different name (icx). The LLVM-based Intel Fortran compiler is under development and testing, and the LLVM-based Fortran compiler beta provides extensive support for Fortran. Users can view the status of specific functions: find the status of each version of each function in the Fortran and OpenMP function status tables.

The above is all the content of the article "what is the use of Intel's LLVM architecture Cumberbatch + compiler". Thank you for reading! I believe we all have a certain understanding, hope to share the content to help you, if you want to learn more knowledge, welcome to follow the industry information channel!

Tags: Compilers compilers Intel Intel Classics Architecture support users articles Features status Clippers content blogs suggestions performance Technology reports time more Apple Docker Huawei Linux macOS MariaDB Microsoft MySQL NVidia OPPO Reno MariaDB Linux NVidia Shulou Technology Apple