Browse Library
Sign In Start Free Trial
Close icon Search icon
Account
Browse Library Sign In Start Free Trial

Add to playlist

Create a Playlist

Modal Close icon
You need to login to use this feature.
  • Book Overview & Buying LLVM Cookbook
  • Table Of Contents Toc
LLVM Cookbook

LLVM Cookbook

By : Mayur Pandey, Suyog Sarda
2 (9)
Buy this Book
close
close
LLVM Cookbook

LLVM Cookbook

2 (9)
By: Mayur Pandey, Suyog Sarda
Buy this Book

Overview of this book

The book is for compiler programmers who are familiar with concepts of compilers and want to indulge in understanding, exploring, and using LLVM infrastructure in a meaningful way in their work. This book is also for programmers who are not directly involved in compiler projects but are often involved in development phases where they write thousands of lines of code. With knowledge of how compilers work, they will be able to code in an optimal way and improve performance with clean code.
Table of Contents (11 chapters)
close
close
close
Preface
Icon
Preface
Icon
What this book covers
Icon
What you need for this book
Icon
Who this book is for
Icon
Sections
Icon
Conventions
Icon
Reader feedback
Icon
Customer support
Lock Free Chapter
1
1. LLVM Design and Use
chevron up
Icon
1. LLVM Design and Use
Icon
Introduction
Icon
Understanding modular design
Icon
Cross-compiling Clang/LLVM
Icon
Converting a C source code to LLVM assembly
Icon
Converting IR to LLVM bitcode
Icon
Converting LLVM bitcode to target machine assembly
Icon
Converting LLVM bitcode back to LLVM assembly
Icon
Transforming LLVM IR
Icon
Linking LLVM bitcode
Icon
Executing LLVM bitcode
Icon
Using the C frontend Clang
Icon
Using the GO frontend
Icon
Using DragonEgg
2
2. Steps in Writing a Frontend
Icon
2. Steps in Writing a Frontend
Icon
Introduction
Icon
Defining a TOY language
Icon
Implementing a lexer
Icon
Defining Abstract Syntax Tree
Icon
Implementing a parser
Icon
Parsing simple expressions
Icon
Parsing binary expressions
Icon
Invoking a driver for parsing
Icon
Running lexer and parser on our TOY language
Icon
Defining IR code generation methods for each AST class
Icon
Generating IR code for expressions
Icon
Generating IR code for functions
Icon
Adding IR optimization support
3
3. Extending the Frontend and Adding JIT Support
Icon
3. Extending the Frontend and Adding JIT Support
Icon
Introduction
Icon
Handling decision making paradigms – if/then/else constructs
Icon
Generating code for loops
Icon
Handling user-defined operators – binary operators
Icon
Handling user-defined operators – unary operators
Icon
Adding JIT support
4
4. Preparing Optimizations
Icon
4. Preparing Optimizations
Icon
Introduction
Icon
Various levels of optimization
Icon
Writing your own LLVM pass
Icon
Running your own pass with the opt tool
Icon
Using another pass in a new pass
Icon
Registering a pass with pass manager
Icon
Writing an analysis pass
Icon
Writing an alias analysis pass
Icon
Using other analysis passes
5
5. Implementing Optimizations
Icon
5. Implementing Optimizations
Icon
Introduction
Icon
Writing a dead code elimination pass
Icon
Writing an inlining transformation pass
Icon
Writing a pass for memory optimization
Icon
Combining LLVM IR
Icon
Transforming and optimizing loops
Icon
Reassociating expressions
Icon
Vectorizing IR
Icon
Other optimization passes
6
6. Target-independent Code Generator
Icon
6. Target-independent Code Generator
Icon
Introduction
Icon
The life of an LLVM IR instruction
Icon
Visualizing LLVM IR CFG using GraphViz
Icon
Describing targets using TableGen
Icon
Defining an instruction set
Icon
Adding a machine code descriptor
Icon
Implementing the MachineInstrBuilder class
Icon
Implementing the MachineBasicBlock class
Icon
Implementing the MachineFunction class
Icon
Writing an instruction selector
Icon
Legalizing SelectionDAG
Icon
Optimizing SelectionDAG
Icon
Selecting instruction from the DAG
Icon
Scheduling instructions in SelectionDAG
7
7. Optimizing the Machine Code
Icon
7. Optimizing the Machine Code
Icon
Introduction
Icon
Eliminating common subexpression from machine code
Icon
Analyzing live intervals
Icon
Allocating registers
Icon
Inserting the prologue-epilogue code
Icon
Code emission
Icon
Tail call optimization
Icon
Sibling call optimisation
8
8. Writing an LLVM Backend
Icon
8. Writing an LLVM Backend
Icon
Introduction
Icon
Defining registers and registers sets
Icon
Defining the calling convention
Icon
Defining the instruction set
Icon
Implementing frame lowering
Icon
Printing an instruction
Icon
Selecting an instruction
Icon
Adding instruction encoding
Icon
Supporting a subtarget
Icon
Lowering to multiple instructions
Icon
Registering a target
9
9. Using LLVM for Various Useful Projects
Icon
9. Using LLVM for Various Useful Projects
Icon
Introduction
Icon
Exception handling in LLVM
Icon
Using sanitizers
Icon
Writing the garbage collector with LLVM
Icon
Converting LLVM IR to JavaScript
Icon
Using the Clang Static Analyzer
Icon
Using bugpoint
Icon
Using LLDB
Icon
Using LLVM utility passes
10
Index
Icon
Index

Transforming LLVM IR

In this recipe, we will see how we can transform the IR from one form to another using the opt tool. We will see different optimizations being applied to IR code.

Getting ready

You need to have the opt tool installed.

How to do it...

The opt tool runs the transformation pass as in the following command:

$opt –passname input.ll –o output.ll
  1. Let's take an actual example now. We create the LLVM IR equivalent to the C code used in the recipe Converting a C source code to LLVM assembly:
    $ cat multiply.c
int mult() {
int a =5;
int b = 3;
int c = a * b;
return c;
}
  2. Converting and outputting it, we get the unoptimized output:
    $ clang -emit-llvm -S multiply.c -o multiply.ll
$ cat multiply.ll
; ModuleID = 'multiply.c'
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

; Function Attrs: nounwind uwtable
define i32 @mult() #0 {
  %a = alloca i32, align 4
  %b = alloca i32, align 4
  %c = alloca i32, align 4
  store i32 5, i32* %a, align 4
  store i32 3, i32* %b, align 4
  %1 = load i32* %a, align 4
  %2 = load i32* %b, align 4
  %3 = mul nsw i32 %1, %2
  store i32 %3, i32* %c, align 4
  %4 = load i32* %c, align 4
  ret i32 %4
}
  3. Now use the opt tool to transform it to a form where memory is promoted to register:
    $ opt -mem2reg -S multiply.ll -o multiply1.ll
$ cat multiply1.ll
; ModuleID = 'multiply.ll'
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

; Function Attrs: nounwind uwtable
define i32 @mult(i32 %a, i32 %b) #0 {
  %1 = mul nsw i32 %a, %b
  ret i32 %1
}

How it works...

The opt, LLVM optimizer, and analyzer tools take the input.ll file as the input and run the pass passname on it. The output after running the pass is obtained in the output.ll file that contains the IR code after the transformation. There can be more than one pass passed to the opt tool.

There's more...

When the –analyze option is passed to opt, it performs various analyses of the input source and prints results usually on the standard output or standard error. Also, the output can be redirected to a file when it is meant to be fed to another program.

When the –analyze option is not passed to opt, it runs the transformation passes meant to optimize the input file.

Some of the important transformations are listed as follows, which can be passed as a flag to the opt tool:

  • adce: Aggressive Dead Code Elimination
  • bb-vectorize: Basic-Block Vectorization
  • constprop: Simple constant propagation
  • dce: Dead Code Elimination
  • deadargelim: Dead Argument Elimination
  • globaldce: Dead Global Elimination
  • globalopt: Global Variable Optimizer
  • gvn: Global Value Numbering
  • inline: Function Integration/Inlining
  • instcombine: Combine redundant instructions
  • licm: Loop Invariant Code Motion
  • loop: unswitch: Unswitch loops
  • loweratomic: Lower atomic intrinsics to non-atomic form
  • lowerinvoke: Lower invokes to calls, for unwindless code generators
  • lowerswitch: Lower SwitchInsts to branches
  • mem2reg: Promote Memory to Register
  • memcpyopt: MemCpy Optimization
  • simplifycfg: Simplify the CFG
  • sink: Code sinking
  • tailcallelim: Tail Call Elimination

Run at least some of the preceding passes to get an understanding of how they work. To get to the appropriate source code on which these passes might be applicable, go to the llvm/test/Transforms directory. For each of the above mentioned passes, you can see the test codes. Apply the relevant pass and see how the test code is getting modified.

Note

To see the mapping of how C code is converted to IR, after converting the C code to IR, as discussed in an earlier recipe Converting a C source code to LLVM assembly, run the mem2reg pass. It will then help you understand how a C instruction is getting mapped into IR instructions.

CONTINUE READING
83
Tech Concepts
36
Programming languages
73
Tech Tools
Icon Unlimited access to the largest independent learning library in tech of over 8,000 expert-authored tech books and videos.
Icon Innovative learning tools, including AI book assistants, code context explainers, and text-to-speech.
Icon 50+ new titles added per month and exclusive early access to books as they are being written.
LLVM Cookbook
End of Section 1
Next Section
notes
bookmark Notes and Bookmarks search Search in title playlist Add to playlist font-size Font size

Change the font size

margin-width Margin width

Change margin width

day-mode Day/Sepia/Night Modes

Change background colour

Close icon Search
Country selected
Close icon Your notes and bookmarks

Confirmation

Modal Close icon
claim successful
Order Page Read Now

Buy this book with your credits?

Modal Close icon
Are you sure you want to buy this book with one of your credits?
Close
YES, BUY

Submit Your Feedback

Modal Close icon
Modal Close icon
Modal Close icon