LLVM's BOLT Flipped On By Default For Linux x86/AArch64 Test Releases
BOLT as the Facebook/Meta-developed tech for optimizing binaries in the name of greater performance by optimizing the code layout was merged to mainline LLVM at the start of the year. Now as we approach the end of the year BOLT is getting a bit of a promotion with being flipped on by default for Linux x86_64 and AArch64 test releases.
LLVM's test-release script that is used for generating the LLVM assets for testing of new compiler release candidates has been updated to build BOLT by default. This BOLT-by-default for LLVM test releases currently only applies for Linux and on AArch64 and x86_64 architectures.
The default change was merged yesterday for future test-release consumption.
Those wanting to learn more about this post-link optimizer developed by Facebook can find the in-tree code here. Generating an optimized binary does work for large applications with Facebook/Meta even having worked on optimized Linux kernel images, but in any event does require first profiling the application/software with Linux perf so that BOLT can make appropriate optimizations to the code layout. The linked GitHub page outlines more of the BOLT optimization steps and other details for those wanting to play with this LLVM tool.
LLVM's test-release script that is used for generating the LLVM assets for testing of new compiler release candidates has been updated to build BOLT by default. This BOLT-by-default for LLVM test releases currently only applies for Linux and on AArch64 and x86_64 architectures.
The default change was merged yesterday for future test-release consumption.
Those wanting to learn more about this post-link optimizer developed by Facebook can find the in-tree code here. Generating an optimized binary does work for large applications with Facebook/Meta even having worked on optimized Linux kernel images, but in any event does require first profiling the application/software with Linux perf so that BOLT can make appropriate optimizations to the code layout. The linked GitHub page outlines more of the BOLT optimization steps and other details for those wanting to play with this LLVM tool.
8 Comments