Book Image

LLVM Essentials

By : Mayur Pandey, Suyog Sarda, David Farago
Book Image

LLVM Essentials

By: Mayur Pandey, Suyog Sarda, David Farago

Overview of this book

LLVM is currently the point of interest for many firms, and has a very active open source community. It provides us with a compiler infrastructure that can be used to write a compiler for a language. It provides us with a set of reusable libraries that can be used to optimize code, and a target-independent code generator to generate code for different backends. It also provides us with a lot of other utility tools that can be easily integrated into compiler projects. This book details how you can use the LLVM compiler infrastructure libraries effectively, and will enable you to design your own custom compiler with LLVM in a snap. We start with the basics, where you’ll get to know all about LLVM. We then cover how you can use LLVM library calls to emit intermediate representation (IR) of simple and complex high-level language paradigms. Moving on, we show you how to implement optimizations at different levels, write an optimization pass, generate code that is independent of a target, and then map the code generated to a backend. The book also walks you through CLANG, IR to IR transformations, advanced IR block transformations, and target machines. By the end of this book, you’ll be able to easily utilize the LLVM libraries in your own projects.
Table of Contents (14 chapters)
LLVM Essentials
About the Authors
About the Reviewer


Vectorization is an important optimization for compilers where we can vectorize code to execute an instruction on multiple datasets in one go. Advance target architecture typically have vector registers set and vector instructions—where broad range of data type (typically 128/246 bit) can be loaded into the vector registers and operations can be performed on those register set, performing two, four, and sometimes eight operations at the same time, with the cost of one scalar operation.

There are two types of vectorization in LLVM—Superword-Level Parallelism (SLP) and loop vectorization. Loop vectorization deals with vectorization opportunities in a loop, while SLP vectorization deals with vectorizing straight-line code in a basic block.

A vector instruction performs Single-instruction multiple-data (SIMD) operations; the same operation on multiple data lanes (in parallel).

Let's look at how SLP Vectorization is implemented in LLVM infrastructure.

As the code itself attributes...