mirror of
https://github.com/RPCSX/llvm.git
synced 2024-11-25 04:39:44 +00:00
adea497673
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155153 91177308-0d34-0410-b5e6-96231b3b80d8
2068 lines
78 KiB
HTML
2068 lines
78 KiB
HTML
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
|
|
"http://www.w3.org/TR/html4/strict.dtd">
|
|
<html>
|
|
<head>
|
|
<title>LLVM's Analysis and Transform Passes</title>
|
|
<link rel="stylesheet" href="_static/llvm.css" type="text/css">
|
|
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
|
|
</head>
|
|
<body>
|
|
|
|
<!--
|
|
|
|
If Passes.html is up to date, the following "one-liner" should print
|
|
an empty diff.
|
|
|
|
egrep -e '^<tr><td><a href="#.*">-.*</a></td><td>.*</td></tr>$' \
|
|
-e '^ <a name=".*">.*</a>$' < Passes.html >html; \
|
|
perl >help <<'EOT' && diff -u help html; rm -f help html
|
|
open HTML, "<Passes.html" or die "open: Passes.html: $!\n";
|
|
while (<HTML>) {
|
|
m:^<tr><td><a href="#(.*)">-.*</a></td><td>.*</td></tr>$: or next;
|
|
$order{$1} = sprintf("%03d", 1 + int %order);
|
|
}
|
|
open HELP, "../Release/bin/opt -help|" or die "open: opt -help: $!\n";
|
|
while (<HELP>) {
|
|
m:^ -([^ ]+) +- (.*)$: or next;
|
|
my $o = $order{$1};
|
|
$o = "000" unless defined $o;
|
|
push @x, "$o<tr><td><a href=\"#$1\">-$1</a></td><td>$2</td></tr>\n";
|
|
push @y, "$o <a name=\"$1\">-$1: $2</a>\n";
|
|
}
|
|
@x = map { s/^\d\d\d//; $_ } sort @x;
|
|
@y = map { s/^\d\d\d//; $_ } sort @y;
|
|
print @x, @y;
|
|
EOT
|
|
|
|
This (real) one-liner can also be helpful when converting comments to HTML:
|
|
|
|
perl -e '$/ = undef; for (split(/\n/, <>)) { s:^ *///? ?::; print " <p>\n" if !$on && $_ =~ /\S/; print " </p>\n" if $on && $_ =~ /^\s*$/; print " $_\n"; $on = ($_ =~ /\S/); } print " </p>\n" if $on'
|
|
|
|
-->
|
|
|
|
<h1>LLVM's Analysis and Transform Passes</h1>
|
|
|
|
<ol>
|
|
<li><a href="#intro">Introduction</a></li>
|
|
<li><a href="#analyses">Analysis Passes</a>
|
|
<li><a href="#transforms">Transform Passes</a></li>
|
|
<li><a href="#utilities">Utility Passes</a></li>
|
|
</ol>
|
|
|
|
<div class="doc_author">
|
|
<p>Written by <a href="mailto:rspencer@x10sys.com">Reid Spencer</a>
|
|
and Gordon Henriksen</p>
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<h2><a name="intro">Introduction</a></h2>
|
|
<div>
|
|
<p>This document serves as a high level summary of the optimization features
|
|
that LLVM provides. Optimizations are implemented as Passes that traverse some
|
|
portion of a program to either collect information or transform the program.
|
|
The table below divides the passes that LLVM provides into three categories.
|
|
Analysis passes compute information that other passes can use or for debugging
|
|
or program visualization purposes. Transform passes can use (or invalidate)
|
|
the analysis passes. Transform passes all mutate the program in some way.
|
|
Utility passes provides some utility but don't otherwise fit categorization.
|
|
For example passes to extract functions to bitcode or write a module to
|
|
bitcode are neither analysis nor transform passes.
|
|
<p>The table below provides a quick summary of each pass and links to the more
|
|
complete pass description later in the document.</p>
|
|
|
|
<table>
|
|
<tr><th colspan="2"><b>ANALYSIS PASSES</b></th></tr>
|
|
<tr><th>Option</th><th>Name</th></tr>
|
|
<tr><td><a href="#aa-eval">-aa-eval</a></td><td>Exhaustive Alias Analysis Precision Evaluator</td></tr>
|
|
<tr><td><a href="#basicaa">-basicaa</a></td><td>Basic Alias Analysis (stateless AA impl)</td></tr>
|
|
<tr><td><a href="#basiccg">-basiccg</a></td><td>Basic CallGraph Construction</td></tr>
|
|
<tr><td><a href="#count-aa">-count-aa</a></td><td>Count Alias Analysis Query Responses</td></tr>
|
|
<tr><td><a href="#debug-aa">-debug-aa</a></td><td>AA use debugger</td></tr>
|
|
<tr><td><a href="#domfrontier">-domfrontier</a></td><td>Dominance Frontier Construction</td></tr>
|
|
<tr><td><a href="#domtree">-domtree</a></td><td>Dominator Tree Construction</td></tr>
|
|
<tr><td><a href="#dot-callgraph">-dot-callgraph</a></td><td>Print Call Graph to 'dot' file</td></tr>
|
|
<tr><td><a href="#dot-cfg">-dot-cfg</a></td><td>Print CFG of function to 'dot' file</td></tr>
|
|
<tr><td><a href="#dot-cfg-only">-dot-cfg-only</a></td><td>Print CFG of function to 'dot' file (with no function bodies)</td></tr>
|
|
<tr><td><a href="#dot-dom">-dot-dom</a></td><td>Print dominance tree of function to 'dot' file</td></tr>
|
|
<tr><td><a href="#dot-dom-only">-dot-dom-only</a></td><td>Print dominance tree of function to 'dot' file (with no function bodies)</td></tr>
|
|
<tr><td><a href="#dot-postdom">-dot-postdom</a></td><td>Print postdominance tree of function to 'dot' file</td></tr>
|
|
<tr><td><a href="#dot-postdom-only">-dot-postdom-only</a></td><td>Print postdominance tree of function to 'dot' file (with no function bodies)</td></tr>
|
|
<tr><td><a href="#globalsmodref-aa">-globalsmodref-aa</a></td><td>Simple mod/ref analysis for globals</td></tr>
|
|
<tr><td><a href="#instcount">-instcount</a></td><td>Counts the various types of Instructions</td></tr>
|
|
<tr><td><a href="#intervals">-intervals</a></td><td>Interval Partition Construction</td></tr>
|
|
<tr><td><a href="#iv-users">-iv-users</a></td><td>Induction Variable Users</td></tr>
|
|
<tr><td><a href="#lazy-value-info">-lazy-value-info</a></td><td>Lazy Value Information Analysis</td></tr>
|
|
<tr><td><a href="#lda">-lda</a></td><td>Loop Dependence Analysis</td></tr>
|
|
<tr><td><a href="#libcall-aa">-libcall-aa</a></td><td>LibCall Alias Analysis</td></tr>
|
|
<tr><td><a href="#lint">-lint</a></td><td>Statically lint-checks LLVM IR</td></tr>
|
|
<tr><td><a href="#loops">-loops</a></td><td>Natural Loop Information</td></tr>
|
|
<tr><td><a href="#memdep">-memdep</a></td><td>Memory Dependence Analysis</td></tr>
|
|
<tr><td><a href="#module-debuginfo">-module-debuginfo</a></td><td>Decodes module-level debug info</td></tr>
|
|
<tr><td><a href="#no-aa">-no-aa</a></td><td>No Alias Analysis (always returns 'may' alias)</td></tr>
|
|
<tr><td><a href="#no-profile">-no-profile</a></td><td>No Profile Information</td></tr>
|
|
<tr><td><a href="#postdomfrontier">-postdomfrontier</a></td><td>Post-Dominance Frontier Construction</td></tr>
|
|
<tr><td><a href="#postdomtree">-postdomtree</a></td><td>Post-Dominator Tree Construction</td></tr>
|
|
<tr><td><a href="#print-alias-sets">-print-alias-sets</a></td><td>Alias Set Printer</td></tr>
|
|
<tr><td><a href="#print-callgraph">-print-callgraph</a></td><td>Print a call graph</td></tr>
|
|
<tr><td><a href="#print-callgraph-sccs">-print-callgraph-sccs</a></td><td>Print SCCs of the Call Graph</td></tr>
|
|
<tr><td><a href="#print-cfg-sccs">-print-cfg-sccs</a></td><td>Print SCCs of each function CFG</td></tr>
|
|
<tr><td><a href="#print-dbginfo">-print-dbginfo</a></td><td>Print debug info in human readable form</td></tr>
|
|
<tr><td><a href="#print-dom-info">-print-dom-info</a></td><td>Dominator Info Printer</td></tr>
|
|
<tr><td><a href="#print-externalfnconstants">-print-externalfnconstants</a></td><td>Print external fn callsites passed constants</td></tr>
|
|
<tr><td><a href="#print-function">-print-function</a></td><td>Print function to stderr</td></tr>
|
|
<tr><td><a href="#print-module">-print-module</a></td><td>Print module to stderr</td></tr>
|
|
<tr><td><a href="#print-used-types">-print-used-types</a></td><td>Find Used Types</td></tr>
|
|
<tr><td><a href="#profile-estimator">-profile-estimator</a></td><td>Estimate profiling information</td></tr>
|
|
<tr><td><a href="#profile-loader">-profile-loader</a></td><td>Load profile information from llvmprof.out</td></tr>
|
|
<tr><td><a href="#profile-verifier">-profile-verifier</a></td><td>Verify profiling information</td></tr>
|
|
<tr><td><a href="#regions">-regions</a></td><td>Detect single entry single exit regions</td></tr>
|
|
<tr><td><a href="#scalar-evolution">-scalar-evolution</a></td><td>Scalar Evolution Analysis</td></tr>
|
|
<tr><td><a href="#scev-aa">-scev-aa</a></td><td>ScalarEvolution-based Alias Analysis</td></tr>
|
|
<tr><td><a href="#targetdata">-targetdata</a></td><td>Target Data Layout</td></tr>
|
|
|
|
|
|
<tr><th colspan="2"><b>TRANSFORM PASSES</b></th></tr>
|
|
<tr><th>Option</th><th>Name</th></tr>
|
|
<tr><td><a href="#adce">-adce</a></td><td>Aggressive Dead Code Elimination</td></tr>
|
|
<tr><td><a href="#always-inline">-always-inline</a></td><td>Inliner for always_inline functions</td></tr>
|
|
<tr><td><a href="#argpromotion">-argpromotion</a></td><td>Promote 'by reference' arguments to scalars</td></tr>
|
|
<tr><td><a href="#bb-vectorize">-bb-vectorize</a></td><td>Combine instructions to form vector instructions within basic blocks</td></tr>
|
|
<tr><td><a href="#block-placement">-block-placement</a></td><td>Profile Guided Basic Block Placement</td></tr>
|
|
<tr><td><a href="#break-crit-edges">-break-crit-edges</a></td><td>Break critical edges in CFG</td></tr>
|
|
<tr><td><a href="#codegenprepare">-codegenprepare</a></td><td>Optimize for code generation</td></tr>
|
|
<tr><td><a href="#constmerge">-constmerge</a></td><td>Merge Duplicate Global Constants</td></tr>
|
|
<tr><td><a href="#constprop">-constprop</a></td><td>Simple constant propagation</td></tr>
|
|
<tr><td><a href="#dce">-dce</a></td><td>Dead Code Elimination</td></tr>
|
|
<tr><td><a href="#deadargelim">-deadargelim</a></td><td>Dead Argument Elimination</td></tr>
|
|
<tr><td><a href="#deadtypeelim">-deadtypeelim</a></td><td>Dead Type Elimination</td></tr>
|
|
<tr><td><a href="#die">-die</a></td><td>Dead Instruction Elimination</td></tr>
|
|
<tr><td><a href="#dse">-dse</a></td><td>Dead Store Elimination</td></tr>
|
|
<tr><td><a href="#functionattrs">-functionattrs</a></td><td>Deduce function attributes</td></tr>
|
|
<tr><td><a href="#globaldce">-globaldce</a></td><td>Dead Global Elimination</td></tr>
|
|
<tr><td><a href="#globalopt">-globalopt</a></td><td>Global Variable Optimizer</td></tr>
|
|
<tr><td><a href="#gvn">-gvn</a></td><td>Global Value Numbering</td></tr>
|
|
<tr><td><a href="#indvars">-indvars</a></td><td>Canonicalize Induction Variables</td></tr>
|
|
<tr><td><a href="#inline">-inline</a></td><td>Function Integration/Inlining</td></tr>
|
|
<tr><td><a href="#insert-edge-profiling">-insert-edge-profiling</a></td><td>Insert instrumentation for edge profiling</td></tr>
|
|
<tr><td><a href="#insert-optimal-edge-profiling">-insert-optimal-edge-profiling</a></td><td>Insert optimal instrumentation for edge profiling</td></tr>
|
|
<tr><td><a href="#instcombine">-instcombine</a></td><td>Combine redundant instructions</td></tr>
|
|
<tr><td><a href="#internalize">-internalize</a></td><td>Internalize Global Symbols</td></tr>
|
|
<tr><td><a href="#ipconstprop">-ipconstprop</a></td><td>Interprocedural constant propagation</td></tr>
|
|
<tr><td><a href="#ipsccp">-ipsccp</a></td><td>Interprocedural Sparse Conditional Constant Propagation</td></tr>
|
|
<tr><td><a href="#jump-threading">-jump-threading</a></td><td>Jump Threading</td></tr>
|
|
<tr><td><a href="#lcssa">-lcssa</a></td><td>Loop-Closed SSA Form Pass</td></tr>
|
|
<tr><td><a href="#licm">-licm</a></td><td>Loop Invariant Code Motion</td></tr>
|
|
<tr><td><a href="#loop-deletion">-loop-deletion</a></td><td>Delete dead loops</td></tr>
|
|
<tr><td><a href="#loop-extract">-loop-extract</a></td><td>Extract loops into new functions</td></tr>
|
|
<tr><td><a href="#loop-extract-single">-loop-extract-single</a></td><td>Extract at most one loop into a new function</td></tr>
|
|
<tr><td><a href="#loop-reduce">-loop-reduce</a></td><td>Loop Strength Reduction</td></tr>
|
|
<tr><td><a href="#loop-rotate">-loop-rotate</a></td><td>Rotate Loops</td></tr>
|
|
<tr><td><a href="#loop-simplify">-loop-simplify</a></td><td>Canonicalize natural loops</td></tr>
|
|
<tr><td><a href="#loop-unroll">-loop-unroll</a></td><td>Unroll loops</td></tr>
|
|
<tr><td><a href="#loop-unswitch">-loop-unswitch</a></td><td>Unswitch loops</td></tr>
|
|
<tr><td><a href="#loweratomic">-loweratomic</a></td><td>Lower atomic intrinsics to non-atomic form</td></tr>
|
|
<tr><td><a href="#lowerinvoke">-lowerinvoke</a></td><td>Lower invoke and unwind, for unwindless code generators</td></tr>
|
|
<tr><td><a href="#lowerswitch">-lowerswitch</a></td><td>Lower SwitchInst's to branches</td></tr>
|
|
<tr><td><a href="#mem2reg">-mem2reg</a></td><td>Promote Memory to Register</td></tr>
|
|
<tr><td><a href="#memcpyopt">-memcpyopt</a></td><td>MemCpy Optimization</td></tr>
|
|
<tr><td><a href="#mergefunc">-mergefunc</a></td><td>Merge Functions</td></tr>
|
|
<tr><td><a href="#mergereturn">-mergereturn</a></td><td>Unify function exit nodes</td></tr>
|
|
<tr><td><a href="#partial-inliner">-partial-inliner</a></td><td>Partial Inliner</td></tr>
|
|
<tr><td><a href="#prune-eh">-prune-eh</a></td><td>Remove unused exception handling info</td></tr>
|
|
<tr><td><a href="#reassociate">-reassociate</a></td><td>Reassociate expressions</td></tr>
|
|
<tr><td><a href="#reg2mem">-reg2mem</a></td><td>Demote all values to stack slots</td></tr>
|
|
<tr><td><a href="#scalarrepl">-scalarrepl</a></td><td>Scalar Replacement of Aggregates (DT)</td></tr>
|
|
<tr><td><a href="#sccp">-sccp</a></td><td>Sparse Conditional Constant Propagation</td></tr>
|
|
<tr><td><a href="#simplify-libcalls">-simplify-libcalls</a></td><td>Simplify well-known library calls</td></tr>
|
|
<tr><td><a href="#simplifycfg">-simplifycfg</a></td><td>Simplify the CFG</td></tr>
|
|
<tr><td><a href="#sink">-sink</a></td><td>Code sinking</td></tr>
|
|
<tr><td><a href="#sretpromotion">-sretpromotion</a></td><td>Promote sret arguments to multiple ret values</td></tr>
|
|
<tr><td><a href="#strip">-strip</a></td><td>Strip all symbols from a module</td></tr>
|
|
<tr><td><a href="#strip-dead-debug-info">-strip-dead-debug-info</a></td><td>Strip debug info for unused symbols</td></tr>
|
|
<tr><td><a href="#strip-dead-prototypes">-strip-dead-prototypes</a></td><td>Strip Unused Function Prototypes</td></tr>
|
|
<tr><td><a href="#strip-debug-declare">-strip-debug-declare</a></td><td>Strip all llvm.dbg.declare intrinsics</td></tr>
|
|
<tr><td><a href="#strip-nondebug">-strip-nondebug</a></td><td>Strip all symbols, except dbg symbols, from a module</td></tr>
|
|
<tr><td><a href="#tailcallelim">-tailcallelim</a></td><td>Tail Call Elimination</td></tr>
|
|
<tr><td><a href="#tailduplicate">-tailduplicate</a></td><td>Tail Duplication</td></tr>
|
|
|
|
|
|
<tr><th colspan="2"><b>UTILITY PASSES</b></th></tr>
|
|
<tr><th>Option</th><th>Name</th></tr>
|
|
<tr><td><a href="#deadarghaX0r">-deadarghaX0r</a></td><td>Dead Argument Hacking (BUGPOINT USE ONLY; DO NOT USE)</td></tr>
|
|
<tr><td><a href="#extract-blocks">-extract-blocks</a></td><td>Extract Basic Blocks From Module (for bugpoint use)</td></tr>
|
|
<tr><td><a href="#instnamer">-instnamer</a></td><td>Assign names to anonymous instructions</td></tr>
|
|
<tr><td><a href="#preverify">-preverify</a></td><td>Preliminary module verification</td></tr>
|
|
<tr><td><a href="#verify">-verify</a></td><td>Module Verifier</td></tr>
|
|
<tr><td><a href="#view-cfg">-view-cfg</a></td><td>View CFG of function</td></tr>
|
|
<tr><td><a href="#view-cfg-only">-view-cfg-only</a></td><td>View CFG of function (with no function bodies)</td></tr>
|
|
<tr><td><a href="#view-dom">-view-dom</a></td><td>View dominance tree of function</td></tr>
|
|
<tr><td><a href="#view-dom-only">-view-dom-only</a></td><td>View dominance tree of function (with no function bodies)</td></tr>
|
|
<tr><td><a href="#view-postdom">-view-postdom</a></td><td>View postdominance tree of function</td></tr>
|
|
<tr><td><a href="#view-postdom-only">-view-postdom-only</a></td><td>View postdominance tree of function (with no function bodies)</td></tr>
|
|
</table>
|
|
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<h2><a name="analyses">Analysis Passes</a></h2>
|
|
<div>
|
|
<p>This section describes the LLVM Analysis Passes.</p>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="aa-eval">-aa-eval: Exhaustive Alias Analysis Precision Evaluator</a>
|
|
</h3>
|
|
<div>
|
|
<p>This is a simple N^2 alias analysis accuracy evaluator.
|
|
Basically, for each function in the program, it simply queries to see how the
|
|
alias analysis implementation answers alias queries between each pair of
|
|
pointers in the function.</p>
|
|
|
|
<p>This is inspired and adapted from code by: Naveen Neelakantam, Francesco
|
|
Spadini, and Wojciech Stryjewski.</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="basicaa">-basicaa: Basic Alias Analysis (stateless AA impl)</a>
|
|
</h3>
|
|
<div>
|
|
<p>A basic alias analysis pass that implements identities (two different
|
|
globals cannot alias, etc), but does no stateful analysis.</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="basiccg">-basiccg: Basic CallGraph Construction</a>
|
|
</h3>
|
|
<div>
|
|
<p>Yet to be written.</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="count-aa">-count-aa: Count Alias Analysis Query Responses</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
A pass which can be used to count how many alias queries
|
|
are being made and how the alias analysis implementation being used responds.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="debug-aa">-debug-aa: AA use debugger</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This simple pass checks alias analysis users to ensure that if they
|
|
create a new value, they do not query AA without informing it of the value.
|
|
It acts as a shim over any other AA pass you want.
|
|
</p>
|
|
|
|
<p>
|
|
Yes keeping track of every value in the program is expensive, but this is
|
|
a debugging pass.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="domfrontier">-domfrontier: Dominance Frontier Construction</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass is a simple dominator construction algorithm for finding forward
|
|
dominator frontiers.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="domtree">-domtree: Dominator Tree Construction</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass is a simple dominator construction algorithm for finding forward
|
|
dominators.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="dot-callgraph">-dot-callgraph: Print Call Graph to 'dot' file</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass, only available in <code>opt</code>, prints the call graph into a
|
|
<code>.dot</code> graph. This graph can then be processed with the "dot" tool
|
|
to convert it to postscript or some other suitable format.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="dot-cfg">-dot-cfg: Print CFG of function to 'dot' file</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass, only available in <code>opt</code>, prints the control flow graph
|
|
into a <code>.dot</code> graph. This graph can then be processed with the
|
|
"dot" tool to convert it to postscript or some other suitable format.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="dot-cfg-only">-dot-cfg-only: Print CFG of function to 'dot' file (with no function bodies)</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass, only available in <code>opt</code>, prints the control flow graph
|
|
into a <code>.dot</code> graph, omitting the function bodies. This graph can
|
|
then be processed with the "dot" tool to convert it to postscript or some
|
|
other suitable format.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="dot-dom">-dot-dom: Print dominance tree of function to 'dot' file</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass, only available in <code>opt</code>, prints the dominator tree
|
|
into a <code>.dot</code> graph. This graph can then be processed with the
|
|
"dot" tool to convert it to postscript or some other suitable format.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="dot-dom-only">-dot-dom-only: Print dominance tree of function to 'dot' file (with no function bodies)</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass, only available in <code>opt</code>, prints the dominator tree
|
|
into a <code>.dot</code> graph, omitting the function bodies. This graph can
|
|
then be processed with the "dot" tool to convert it to postscript or some
|
|
other suitable format.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="dot-postdom">-dot-postdom: Print postdominance tree of function to 'dot' file</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass, only available in <code>opt</code>, prints the post dominator tree
|
|
into a <code>.dot</code> graph. This graph can then be processed with the
|
|
"dot" tool to convert it to postscript or some other suitable format.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="dot-postdom-only">-dot-postdom-only: Print postdominance tree of function to 'dot' file (with no function bodies)</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass, only available in <code>opt</code>, prints the post dominator tree
|
|
into a <code>.dot</code> graph, omitting the function bodies. This graph can
|
|
then be processed with the "dot" tool to convert it to postscript or some
|
|
other suitable format.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="globalsmodref-aa">-globalsmodref-aa: Simple mod/ref analysis for globals</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This simple pass provides alias and mod/ref information for global values
|
|
that do not have their address taken, and keeps track of whether functions
|
|
read or write memory (are "pure"). For this simple (but very common) case,
|
|
we can provide pretty accurate and useful information.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="instcount">-instcount: Counts the various types of Instructions</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass collects the count of all instructions and reports them
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="intervals">-intervals: Interval Partition Construction</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This analysis calculates and represents the interval partition of a function,
|
|
or a preexisting interval partition.
|
|
</p>
|
|
|
|
<p>
|
|
In this way, the interval partition may be used to reduce a flow graph down
|
|
to its degenerate single node interval partition (unless it is irreducible).
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="iv-users">-iv-users: Induction Variable Users</a>
|
|
</h3>
|
|
<div>
|
|
<p>Bookkeeping for "interesting" users of expressions computed from
|
|
induction variables.</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="lazy-value-info">-lazy-value-info: Lazy Value Information Analysis</a>
|
|
</h3>
|
|
<div>
|
|
<p>Interface for lazy computation of value constraint information.</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="lda">-lda: Loop Dependence Analysis</a>
|
|
</h3>
|
|
<div>
|
|
<p>Loop dependence analysis framework, which is used to detect dependences in
|
|
memory accesses in loops.</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="libcall-aa">-libcall-aa: LibCall Alias Analysis</a>
|
|
</h3>
|
|
<div>
|
|
<p>LibCall Alias Analysis.</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="lint">-lint: Statically lint-checks LLVM IR</a>
|
|
</h3>
|
|
<div>
|
|
<p>This pass statically checks for common and easily-identified constructs
|
|
which produce undefined or likely unintended behavior in LLVM IR.</p>
|
|
|
|
<p>It is not a guarantee of correctness, in two ways. First, it isn't
|
|
comprehensive. There are checks which could be done statically which are
|
|
not yet implemented. Some of these are indicated by TODO comments, but
|
|
those aren't comprehensive either. Second, many conditions cannot be
|
|
checked statically. This pass does no dynamic instrumentation, so it
|
|
can't check for all possible problems.</p>
|
|
|
|
<p>Another limitation is that it assumes all code will be executed. A store
|
|
through a null pointer in a basic block which is never reached is harmless,
|
|
but this pass will warn about it anyway.</p>
|
|
|
|
<p>Optimization passes may make conditions that this pass checks for more or
|
|
less obvious. If an optimization pass appears to be introducing a warning,
|
|
it may be that the optimization pass is merely exposing an existing
|
|
condition in the code.</p>
|
|
|
|
<p>This code may be run before instcombine. In many cases, instcombine checks
|
|
for the same kinds of things and turns instructions with undefined behavior
|
|
into unreachable (or equivalent). Because of this, this pass makes some
|
|
effort to look through bitcasts and so on.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="loops">-loops: Natural Loop Information</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This analysis is used to identify natural loops and determine the loop depth
|
|
of various nodes of the CFG. Note that the loops identified may actually be
|
|
several natural loops that share the same header node... not just a single
|
|
natural loop.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="memdep">-memdep: Memory Dependence Analysis</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
An analysis that determines, for a given memory operation, what preceding
|
|
memory operations it depends on. It builds on alias analysis information, and
|
|
tries to provide a lazy, caching interface to a common kind of alias
|
|
information query.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="module-debuginfo">-module-debuginfo: Decodes module-level debug info</a>
|
|
</h3>
|
|
<div>
|
|
<p>This pass decodes the debug info metadata in a module and prints in a
|
|
(sufficiently-prepared-) human-readable form.
|
|
|
|
For example, run this pass from opt along with the -analyze option, and
|
|
it'll print to standard output.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="no-aa">-no-aa: No Alias Analysis (always returns 'may' alias)</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This is the default implementation of the Alias Analysis interface. It always
|
|
returns "I don't know" for alias queries. NoAA is unlike other alias analysis
|
|
implementations, in that it does not chain to a previous analysis. As such it
|
|
doesn't follow many of the rules that other alias analyses must.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="no-profile">-no-profile: No Profile Information</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
The default "no profile" implementation of the abstract
|
|
<code>ProfileInfo</code> interface.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="postdomfrontier">-postdomfrontier: Post-Dominance Frontier Construction</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass is a simple post-dominator construction algorithm for finding
|
|
post-dominator frontiers.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="postdomtree">-postdomtree: Post-Dominator Tree Construction</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass is a simple post-dominator construction algorithm for finding
|
|
post-dominators.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="print-alias-sets">-print-alias-sets: Alias Set Printer</a>
|
|
</h3>
|
|
<div>
|
|
<p>Yet to be written.</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="print-callgraph">-print-callgraph: Print a call graph</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass, only available in <code>opt</code>, prints the call graph to
|
|
standard error in a human-readable form.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="print-callgraph-sccs">-print-callgraph-sccs: Print SCCs of the Call Graph</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass, only available in <code>opt</code>, prints the SCCs of the call
|
|
graph to standard error in a human-readable form.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="print-cfg-sccs">-print-cfg-sccs: Print SCCs of each function CFG</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass, only available in <code>opt</code>, prints the SCCs of each
|
|
function CFG to standard error in a human-readable form.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="print-dbginfo">-print-dbginfo: Print debug info in human readable form</a>
|
|
</h3>
|
|
<div>
|
|
<p>Pass that prints instructions, and associated debug info:</p>
|
|
<ul>
|
|
|
|
<li>source/line/col information</li>
|
|
<li>original variable name</li>
|
|
<li>original type name</li>
|
|
</ul>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="print-dom-info">-print-dom-info: Dominator Info Printer</a>
|
|
</h3>
|
|
<div>
|
|
<p>Dominator Info Printer.</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="print-externalfnconstants">-print-externalfnconstants: Print external fn callsites passed constants</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass, only available in <code>opt</code>, prints out call sites to
|
|
external functions that are called with constant arguments. This can be
|
|
useful when looking for standard library functions we should constant fold
|
|
or handle in alias analyses.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="print-function">-print-function: Print function to stderr</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
The <code>PrintFunctionPass</code> class is designed to be pipelined with
|
|
other <code>FunctionPass</code>es, and prints out the functions of the module
|
|
as they are processed.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="print-module">-print-module: Print module to stderr</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass simply prints out the entire module when it is executed.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="print-used-types">-print-used-types: Find Used Types</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass is used to seek out all of the types in use by the program. Note
|
|
that this analysis explicitly does not include types only used by the symbol
|
|
table.
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="profile-estimator">-profile-estimator: Estimate profiling information</a>
|
|
</h3>
|
|
<div>
|
|
<p>Profiling information that estimates the profiling information
|
|
in a very crude and unimaginative way.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="profile-loader">-profile-loader: Load profile information from llvmprof.out</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
A concrete implementation of profiling information that loads the information
|
|
from a profile dump file.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="profile-verifier">-profile-verifier: Verify profiling information</a>
|
|
</h3>
|
|
<div>
|
|
<p>Pass that checks profiling information for plausibility.</p>
|
|
</div>
|
|
<h3>
|
|
<a name="regions">-regions: Detect single entry single exit regions</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
The <code>RegionInfo</code> pass detects single entry single exit regions in a
|
|
function, where a region is defined as any subgraph that is connected to the
|
|
remaining graph at only two spots. Furthermore, an hierarchical region tree is
|
|
built.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="scalar-evolution">-scalar-evolution: Scalar Evolution Analysis</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
The <code>ScalarEvolution</code> analysis can be used to analyze and
|
|
catagorize scalar expressions in loops. It specializes in recognizing general
|
|
induction variables, representing them with the abstract and opaque
|
|
<code>SCEV</code> class. Given this analysis, trip counts of loops and other
|
|
important properties can be obtained.
|
|
</p>
|
|
|
|
<p>
|
|
This analysis is primarily useful for induction variable substitution and
|
|
strength reduction.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="scev-aa">-scev-aa: ScalarEvolution-based Alias Analysis</a>
|
|
</h3>
|
|
<div>
|
|
<p>Simple alias analysis implemented in terms of ScalarEvolution queries.
|
|
|
|
This differs from traditional loop dependence analysis in that it tests
|
|
for dependencies within a single iteration of a loop, rather than
|
|
dependencies between different iterations.
|
|
|
|
ScalarEvolution has a more complete understanding of pointer arithmetic
|
|
than BasicAliasAnalysis' collection of ad-hoc analyses.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="targetdata">-targetdata: Target Data Layout</a>
|
|
</h3>
|
|
<div>
|
|
<p>Provides other passes access to information on how the size and alignment
|
|
required by the the target ABI for various data types.</p>
|
|
</div>
|
|
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<h2><a name="transforms">Transform Passes</a></h2>
|
|
<div>
|
|
<p>This section describes the LLVM Transform Passes.</p>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="adce">-adce: Aggressive Dead Code Elimination</a>
|
|
</h3>
|
|
<div>
|
|
<p>ADCE aggressively tries to eliminate code. This pass is similar to
|
|
<a href="#dce">DCE</a> but it assumes that values are dead until proven
|
|
otherwise. This is similar to <a href="#sccp">SCCP</a>, except applied to
|
|
the liveness of values.</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="always-inline">-always-inline: Inliner for always_inline functions</a>
|
|
</h3>
|
|
<div>
|
|
<p>A custom inliner that handles only functions that are marked as
|
|
"always inline".</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="argpromotion">-argpromotion: Promote 'by reference' arguments to scalars</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass promotes "by reference" arguments to be "by value" arguments. In
|
|
practice, this means looking for internal functions that have pointer
|
|
arguments. If it can prove, through the use of alias analysis, that an
|
|
argument is *only* loaded, then it can pass the value into the function
|
|
instead of the address of the value. This can cause recursive simplification
|
|
of code and lead to the elimination of allocas (especially in C++ template
|
|
code like the STL).
|
|
</p>
|
|
|
|
<p>
|
|
This pass also handles aggregate arguments that are passed into a function,
|
|
scalarizing them if the elements of the aggregate are only loaded. Note that
|
|
it refuses to scalarize aggregates which would require passing in more than
|
|
three operands to the function, because passing thousands of operands for a
|
|
large array or structure is unprofitable!
|
|
</p>
|
|
|
|
<p>
|
|
Note that this transformation could also be done for arguments that are only
|
|
stored to (returning the value instead), but does not currently. This case
|
|
would be best handled when and if LLVM starts supporting multiple return
|
|
values from functions.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="bb-vectorize">-bb-vectorize: Basic-Block Vectorization</a>
|
|
</h3>
|
|
<div>
|
|
<p>This pass combines instructions inside basic blocks to form vector
|
|
instructions. It iterates over each basic block, attempting to pair
|
|
compatible instructions, repeating this process until no additional
|
|
pairs are selected for vectorization. When the outputs of some pair
|
|
of compatible instructions are used as inputs by some other pair of
|
|
compatible instructions, those pairs are part of a potential
|
|
vectorization chain. Instruction pairs are only fused into vector
|
|
instructions when they are part of a chain longer than some
|
|
threshold length. Moreover, the pass attempts to find the best
|
|
possible chain for each pair of compatible instructions. These
|
|
heuristics are intended to prevent vectorization in cases where
|
|
it would not yield a performance increase of the resulting code.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="block-placement">-block-placement: Profile Guided Basic Block Placement</a>
|
|
</h3>
|
|
<div>
|
|
<p>This pass is a very simple profile guided basic block placement algorithm.
|
|
The idea is to put frequently executed blocks together at the start of the
|
|
function and hopefully increase the number of fall-through conditional
|
|
branches. If there is no profile information for a particular function, this
|
|
pass basically orders blocks in depth-first order.</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="break-crit-edges">-break-crit-edges: Break critical edges in CFG</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Break all of the critical edges in the CFG by inserting a dummy basic block.
|
|
It may be "required" by passes that cannot deal with critical edges. This
|
|
transformation obviously invalidates the CFG, but can update forward dominator
|
|
(set, immediate dominators, tree, and frontier) information.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="codegenprepare">-codegenprepare: Optimize for code generation</a>
|
|
</h3>
|
|
<div>
|
|
This pass munges the code in the input function to better prepare it for
|
|
SelectionDAG-based code generation. This works around limitations in it's
|
|
basic-block-at-a-time approach. It should eventually be removed.
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="constmerge">-constmerge: Merge Duplicate Global Constants</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Merges duplicate global constants together into a single constant that is
|
|
shared. This is useful because some passes (ie TraceValues) insert a lot of
|
|
string constants into the program, regardless of whether or not an existing
|
|
string is available.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="constprop">-constprop: Simple constant propagation</a>
|
|
</h3>
|
|
<div>
|
|
<p>This file implements constant propagation and merging. It looks for
|
|
instructions involving only constant operands and replaces them with a
|
|
constant value instead of an instruction. For example:</p>
|
|
<blockquote><pre>add i32 1, 2</pre></blockquote>
|
|
<p>becomes</p>
|
|
<blockquote><pre>i32 3</pre></blockquote>
|
|
<p>NOTE: this pass has a habit of making definitions be dead. It is a good
|
|
idea to to run a <a href="#die">DIE</a> (Dead Instruction Elimination) pass
|
|
sometime after running this pass.</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="dce">-dce: Dead Code Elimination</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Dead code elimination is similar to <a href="#die">dead instruction
|
|
elimination</a>, but it rechecks instructions that were used by removed
|
|
instructions to see if they are newly dead.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="deadargelim">-deadargelim: Dead Argument Elimination</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass deletes dead arguments from internal functions. Dead argument
|
|
elimination removes arguments which are directly dead, as well as arguments
|
|
only passed into function calls as dead arguments of other functions. This
|
|
pass also deletes dead arguments in a similar way.
|
|
</p>
|
|
|
|
<p>
|
|
This pass is often useful as a cleanup pass to run after aggressive
|
|
interprocedural passes, which add possibly-dead arguments.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="deadtypeelim">-deadtypeelim: Dead Type Elimination</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass is used to cleanup the output of GCC. It eliminate names for types
|
|
that are unused in the entire translation unit, using the <a
|
|
href="#findusedtypes">find used types</a> pass.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="die">-die: Dead Instruction Elimination</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Dead instruction elimination performs a single pass over the function,
|
|
removing instructions that are obviously dead.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="dse">-dse: Dead Store Elimination</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
A trivial dead store elimination that only considers basic-block local
|
|
redundant stores.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="functionattrs">-functionattrs: Deduce function attributes</a>
|
|
</h3>
|
|
<div>
|
|
<p>A simple interprocedural pass which walks the call-graph, looking for
|
|
functions which do not access or only read non-local memory, and marking them
|
|
readnone/readonly. In addition, it marks function arguments (of pointer type)
|
|
'nocapture' if a call to the function does not create any copies of the pointer
|
|
value that outlive the call. This more or less means that the pointer is only
|
|
dereferenced, and not returned from the function or stored in a global.
|
|
This pass is implemented as a bottom-up traversal of the call-graph.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="globaldce">-globaldce: Dead Global Elimination</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This transform is designed to eliminate unreachable internal globals from the
|
|
program. It uses an aggressive algorithm, searching out globals that are
|
|
known to be alive. After it finds all of the globals which are needed, it
|
|
deletes whatever is left over. This allows it to delete recursive chunks of
|
|
the program which are unreachable.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="globalopt">-globalopt: Global Variable Optimizer</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass transforms simple global variables that never have their address
|
|
taken. If obviously true, it marks read/write globals as constant, deletes
|
|
variables only stored to, etc.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="gvn">-gvn: Global Value Numbering</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass performs global value numbering to eliminate fully and partially
|
|
redundant instructions. It also performs redundant load elimination.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="indvars">-indvars: Canonicalize Induction Variables</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This transformation analyzes and transforms the induction variables (and
|
|
computations derived from them) into simpler forms suitable for subsequent
|
|
analysis and transformation.
|
|
</p>
|
|
|
|
<p>
|
|
This transformation makes the following changes to each loop with an
|
|
identifiable induction variable:
|
|
</p>
|
|
|
|
<ol>
|
|
<li>All loops are transformed to have a <em>single</em> canonical
|
|
induction variable which starts at zero and steps by one.</li>
|
|
<li>The canonical induction variable is guaranteed to be the first PHI node
|
|
in the loop header block.</li>
|
|
<li>Any pointer arithmetic recurrences are raised to use array
|
|
subscripts.</li>
|
|
</ol>
|
|
|
|
<p>
|
|
If the trip count of a loop is computable, this pass also makes the following
|
|
changes:
|
|
</p>
|
|
|
|
<ol>
|
|
<li>The exit condition for the loop is canonicalized to compare the
|
|
induction value against the exit value. This turns loops like:
|
|
<blockquote><pre>for (i = 7; i*i < 1000; ++i)</pre></blockquote>
|
|
into
|
|
<blockquote><pre>for (i = 0; i != 25; ++i)</pre></blockquote></li>
|
|
<li>Any use outside of the loop of an expression derived from the indvar
|
|
is changed to compute the derived value outside of the loop, eliminating
|
|
the dependence on the exit value of the induction variable. If the only
|
|
purpose of the loop is to compute the exit value of some derived
|
|
expression, this transformation will make the loop dead.</li>
|
|
</ol>
|
|
|
|
<p>
|
|
This transformation should be followed by strength reduction after all of the
|
|
desired loop transformations have been performed. Additionally, on targets
|
|
where it is profitable, the loop could be transformed to count down to zero
|
|
(the "do loop" optimization).
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="inline">-inline: Function Integration/Inlining</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Bottom-up inlining of functions into callees.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="insert-edge-profiling">-insert-edge-profiling: Insert instrumentation for edge profiling</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass instruments the specified program with counters for edge profiling.
|
|
Edge profiling can give a reasonable approximation of the hot paths through a
|
|
program, and is used for a wide variety of program transformations.
|
|
</p>
|
|
|
|
<p>
|
|
Note that this implementation is very naïve. It inserts a counter for
|
|
<em>every</em> edge in the program, instead of using control flow information
|
|
to prune the number of counters inserted.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="insert-optimal-edge-profiling">-insert-optimal-edge-profiling: Insert optimal instrumentation for edge profiling</a>
|
|
</h3>
|
|
<div>
|
|
<p>This pass instruments the specified program with counters for edge profiling.
|
|
Edge profiling can give a reasonable approximation of the hot paths through a
|
|
program, and is used for a wide variety of program transformations.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="instcombine">-instcombine: Combine redundant instructions</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Combine instructions to form fewer, simple
|
|
instructions. This pass does not modify the CFG This pass is where algebraic
|
|
simplification happens.
|
|
</p>
|
|
|
|
<p>
|
|
This pass combines things like:
|
|
</p>
|
|
|
|
<blockquote><pre
|
|
>%Y = add i32 %X, 1
|
|
%Z = add i32 %Y, 1</pre></blockquote>
|
|
|
|
<p>
|
|
into:
|
|
</p>
|
|
|
|
<blockquote><pre
|
|
>%Z = add i32 %X, 2</pre></blockquote>
|
|
|
|
<p>
|
|
This is a simple worklist driven algorithm.
|
|
</p>
|
|
|
|
<p>
|
|
This pass guarantees that the following canonicalizations are performed on
|
|
the program:
|
|
</p>
|
|
|
|
<ul>
|
|
<li>If a binary operator has a constant operand, it is moved to the right-
|
|
hand side.</li>
|
|
<li>Bitwise operators with constant operands are always grouped so that
|
|
shifts are performed first, then <code>or</code>s, then
|
|
<code>and</code>s, then <code>xor</code>s.</li>
|
|
<li>Compare instructions are converted from <code><</code>,
|
|
<code>></code>, <code>≤</code>, or <code>≥</code> to
|
|
<code>=</code> or <code>≠</code> if possible.</li>
|
|
<li>All <code>cmp</code> instructions on boolean values are replaced with
|
|
logical operations.</li>
|
|
<li><code>add <var>X</var>, <var>X</var></code> is represented as
|
|
<code>mul <var>X</var>, 2</code> ⇒ <code>shl <var>X</var>, 1</code></li>
|
|
<li>Multiplies with a constant power-of-two argument are transformed into
|
|
shifts.</li>
|
|
<li>… etc.</li>
|
|
</ul>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="internalize">-internalize: Internalize Global Symbols</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass loops over all of the functions in the input module, looking for a
|
|
main function. If a main function is found, all other functions and all
|
|
global variables with initializers are marked as internal.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="ipconstprop">-ipconstprop: Interprocedural constant propagation</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass implements an <em>extremely</em> simple interprocedural constant
|
|
propagation pass. It could certainly be improved in many different ways,
|
|
like using a worklist. This pass makes arguments dead, but does not remove
|
|
them. The existing dead argument elimination pass should be run after this
|
|
to clean up the mess.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="ipsccp">-ipsccp: Interprocedural Sparse Conditional Constant Propagation</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
An interprocedural variant of <a href="#sccp">Sparse Conditional Constant
|
|
Propagation</a>.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="jump-threading">-jump-threading: Jump Threading</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Jump threading tries to find distinct threads of control flow running through
|
|
a basic block. This pass looks at blocks that have multiple predecessors and
|
|
multiple successors. If one or more of the predecessors of the block can be
|
|
proven to always cause a jump to one of the successors, we forward the edge
|
|
from the predecessor to the successor by duplicating the contents of this
|
|
block.
|
|
</p>
|
|
<p>
|
|
An example of when this can occur is code like this:
|
|
</p>
|
|
|
|
<pre
|
|
>if () { ...
|
|
X = 4;
|
|
}
|
|
if (X < 3) {</pre>
|
|
|
|
<p>
|
|
In this case, the unconditional branch at the end of the first if can be
|
|
revectored to the false side of the second if.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="lcssa">-lcssa: Loop-Closed SSA Form Pass</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass transforms loops by placing phi nodes at the end of the loops for
|
|
all values that are live across the loop boundary. For example, it turns
|
|
the left into the right code:
|
|
</p>
|
|
|
|
<pre
|
|
>for (...) for (...)
|
|
if (c) if (c)
|
|
X1 = ... X1 = ...
|
|
else else
|
|
X2 = ... X2 = ...
|
|
X3 = phi(X1, X2) X3 = phi(X1, X2)
|
|
... = X3 + 4 X4 = phi(X3)
|
|
... = X4 + 4</pre>
|
|
|
|
<p>
|
|
This is still valid LLVM; the extra phi nodes are purely redundant, and will
|
|
be trivially eliminated by <code>InstCombine</code>. The major benefit of
|
|
this transformation is that it makes many other loop optimizations, such as
|
|
LoopUnswitching, simpler.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="licm">-licm: Loop Invariant Code Motion</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass performs loop invariant code motion, attempting to remove as much
|
|
code from the body of a loop as possible. It does this by either hoisting
|
|
code into the preheader block, or by sinking code to the exit blocks if it is
|
|
safe. This pass also promotes must-aliased memory locations in the loop to
|
|
live in registers, thus hoisting and sinking "invariant" loads and stores.
|
|
</p>
|
|
|
|
<p>
|
|
This pass uses alias analysis for two purposes:
|
|
</p>
|
|
|
|
<ul>
|
|
<li>Moving loop invariant loads and calls out of loops. If we can determine
|
|
that a load or call inside of a loop never aliases anything stored to,
|
|
we can hoist it or sink it like any other instruction.</li>
|
|
<li>Scalar Promotion of Memory - If there is a store instruction inside of
|
|
the loop, we try to move the store to happen AFTER the loop instead of
|
|
inside of the loop. This can only happen if a few conditions are true:
|
|
<ul>
|
|
<li>The pointer stored through is loop invariant.</li>
|
|
<li>There are no stores or loads in the loop which <em>may</em> alias
|
|
the pointer. There are no calls in the loop which mod/ref the
|
|
pointer.</li>
|
|
</ul>
|
|
If these conditions are true, we can promote the loads and stores in the
|
|
loop of the pointer to use a temporary alloca'd variable. We then use
|
|
the mem2reg functionality to construct the appropriate SSA form for the
|
|
variable.</li>
|
|
</ul>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="loop-deletion">-loop-deletion: Delete dead loops</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This file implements the Dead Loop Deletion Pass. This pass is responsible
|
|
for eliminating loops with non-infinite computable trip counts that have no
|
|
side effects or volatile instructions, and do not contribute to the
|
|
computation of the function's return value.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="loop-extract">-loop-extract: Extract loops into new functions</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
A pass wrapper around the <code>ExtractLoop()</code> scalar transformation to
|
|
extract each top-level loop into its own new function. If the loop is the
|
|
<em>only</em> loop in a given function, it is not touched. This is a pass most
|
|
useful for debugging via bugpoint.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="loop-extract-single">-loop-extract-single: Extract at most one loop into a new function</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Similar to <a href="#loop-extract">Extract loops into new functions</a>,
|
|
this pass extracts one natural loop from the program into a function if it
|
|
can. This is used by bugpoint.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="loop-reduce">-loop-reduce: Loop Strength Reduction</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass performs a strength reduction on array references inside loops that
|
|
have as one or more of their components the loop induction variable. This is
|
|
accomplished by creating a new value to hold the initial value of the array
|
|
access for the first iteration, and then creating a new GEP instruction in
|
|
the loop to increment the value by the appropriate amount.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="loop-rotate">-loop-rotate: Rotate Loops</a>
|
|
</h3>
|
|
<div>
|
|
<p>A simple loop rotation transformation.</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="loop-simplify">-loop-simplify: Canonicalize natural loops</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass performs several transformations to transform natural loops into a
|
|
simpler form, which makes subsequent analyses and transformations simpler and
|
|
more effective.
|
|
</p>
|
|
|
|
<p>
|
|
Loop pre-header insertion guarantees that there is a single, non-critical
|
|
entry edge from outside of the loop to the loop header. This simplifies a
|
|
number of analyses and transformations, such as LICM.
|
|
</p>
|
|
|
|
<p>
|
|
Loop exit-block insertion guarantees that all exit blocks from the loop
|
|
(blocks which are outside of the loop that have predecessors inside of the
|
|
loop) only have predecessors from inside of the loop (and are thus dominated
|
|
by the loop header). This simplifies transformations such as store-sinking
|
|
that are built into LICM.
|
|
</p>
|
|
|
|
<p>
|
|
This pass also guarantees that loops will have exactly one backedge.
|
|
</p>
|
|
|
|
<p>
|
|
Note that the simplifycfg pass will clean up blocks which are split out but
|
|
end up being unnecessary, so usage of this pass should not pessimize
|
|
generated code.
|
|
</p>
|
|
|
|
<p>
|
|
This pass obviously modifies the CFG, but updates loop information and
|
|
dominator information.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="loop-unroll">-loop-unroll: Unroll loops</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass implements a simple loop unroller. It works best when loops have
|
|
been canonicalized by the <a href="#indvars"><tt>-indvars</tt></a> pass,
|
|
allowing it to determine the trip counts of loops easily.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="loop-unswitch">-loop-unswitch: Unswitch loops</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass transforms loops that contain branches on loop-invariant conditions
|
|
to have multiple loops. For example, it turns the left into the right code:
|
|
</p>
|
|
|
|
<pre
|
|
>for (...) if (lic)
|
|
A for (...)
|
|
if (lic) A; B; C
|
|
B else
|
|
C for (...)
|
|
A; C</pre>
|
|
|
|
<p>
|
|
This can increase the size of the code exponentially (doubling it every time
|
|
a loop is unswitched) so we only unswitch if the resultant code will be
|
|
smaller than a threshold.
|
|
</p>
|
|
|
|
<p>
|
|
This pass expects LICM to be run before it to hoist invariant conditions out
|
|
of the loop, to make the unswitching opportunity obvious.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="loweratomic">-loweratomic: Lower atomic intrinsics to non-atomic form</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass lowers atomic intrinsics to non-atomic form for use in a known
|
|
non-preemptible environment.
|
|
</p>
|
|
|
|
<p>
|
|
The pass does not verify that the environment is non-preemptible (in
|
|
general this would require knowledge of the entire call graph of the
|
|
program including any libraries which may not be available in bitcode form);
|
|
it simply lowers every atomic intrinsic.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="lowerinvoke">-lowerinvoke: Lower invoke and unwind, for unwindless code generators</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This transformation is designed for use by code generators which do not yet
|
|
support stack unwinding. This pass supports two models of exception handling
|
|
lowering, the 'cheap' support and the 'expensive' support.
|
|
</p>
|
|
|
|
<p>
|
|
'Cheap' exception handling support gives the program the ability to execute
|
|
any program which does not "throw an exception", by turning 'invoke'
|
|
instructions into calls and by turning 'unwind' instructions into calls to
|
|
abort(). If the program does dynamically use the unwind instruction, the
|
|
program will print a message then abort.
|
|
</p>
|
|
|
|
<p>
|
|
'Expensive' exception handling support gives the full exception handling
|
|
support to the program at the cost of making the 'invoke' instruction
|
|
really expensive. It basically inserts setjmp/longjmp calls to emulate the
|
|
exception handling as necessary.
|
|
</p>
|
|
|
|
<p>
|
|
Because the 'expensive' support slows down programs a lot, and EH is only
|
|
used for a subset of the programs, it must be specifically enabled by the
|
|
<tt>-enable-correct-eh-support</tt> option.
|
|
</p>
|
|
|
|
<p>
|
|
Note that after this pass runs the CFG is not entirely accurate (exceptional
|
|
control flow edges are not correct anymore) so only very simple things should
|
|
be done after the lowerinvoke pass has run (like generation of native code).
|
|
This should not be used as a general purpose "my LLVM-to-LLVM pass doesn't
|
|
support the invoke instruction yet" lowering pass.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="lowerswitch">-lowerswitch: Lower SwitchInst's to branches</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Rewrites <tt>switch</tt> instructions with a sequence of branches, which
|
|
allows targets to get away with not implementing the switch instruction until
|
|
it is convenient.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="mem2reg">-mem2reg: Promote Memory to Register</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This file promotes memory references to be register references. It promotes
|
|
<tt>alloca</tt> instructions which only have <tt>load</tt>s and
|
|
<tt>store</tt>s as uses. An <tt>alloca</tt> is transformed by using dominator
|
|
frontiers to place <tt>phi</tt> nodes, then traversing the function in
|
|
depth-first order to rewrite <tt>load</tt>s and <tt>store</tt>s as
|
|
appropriate. This is just the standard SSA construction algorithm to construct
|
|
"pruned" SSA form.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="memcpyopt">-memcpyopt: MemCpy Optimization</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass performs various transformations related to eliminating memcpy
|
|
calls, or transforming sets of stores into memset's.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="mergefunc">-mergefunc: Merge Functions</a>
|
|
</h3>
|
|
<div>
|
|
<p>This pass looks for equivalent functions that are mergable and folds them.
|
|
|
|
A hash is computed from the function, based on its type and number of
|
|
basic blocks.
|
|
|
|
Once all hashes are computed, we perform an expensive equality comparison
|
|
on each function pair. This takes n^2/2 comparisons per bucket, so it's
|
|
important that the hash function be high quality. The equality comparison
|
|
iterates through each instruction in each basic block.
|
|
|
|
When a match is found the functions are folded. If both functions are
|
|
overridable, we move the functionality into a new internal function and
|
|
leave two overridable thunks to it.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="mergereturn">-mergereturn: Unify function exit nodes</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Ensure that functions have at most one <tt>ret</tt> instruction in them.
|
|
Additionally, it keeps track of which node is the new exit node of the CFG.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="partial-inliner">-partial-inliner: Partial Inliner</a>
|
|
</h3>
|
|
<div>
|
|
<p>This pass performs partial inlining, typically by inlining an if
|
|
statement that surrounds the body of the function.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="prune-eh">-prune-eh: Remove unused exception handling info</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This file implements a simple interprocedural pass which walks the call-graph,
|
|
turning <tt>invoke</tt> instructions into <tt>call</tt> instructions if and
|
|
only if the callee cannot throw an exception. It implements this as a
|
|
bottom-up traversal of the call-graph.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="reassociate">-reassociate: Reassociate expressions</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass reassociates commutative expressions in an order that is designed
|
|
to promote better constant propagation, GCSE, LICM, PRE, etc.
|
|
</p>
|
|
|
|
<p>
|
|
For example: 4 + (<var>x</var> + 5) ⇒ <var>x</var> + (4 + 5)
|
|
</p>
|
|
|
|
<p>
|
|
In the implementation of this algorithm, constants are assigned rank = 0,
|
|
function arguments are rank = 1, and other values are assigned ranks
|
|
corresponding to the reverse post order traversal of current function
|
|
(starting at 2), which effectively gives values in deep loops higher rank
|
|
than values not in loops.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="reg2mem">-reg2mem: Demote all values to stack slots</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This file demotes all registers to memory references. It is intented to be
|
|
the inverse of <a href="#mem2reg"><tt>-mem2reg</tt></a>. By converting to
|
|
<tt>load</tt> instructions, the only values live across basic blocks are
|
|
<tt>alloca</tt> instructions and <tt>load</tt> instructions before
|
|
<tt>phi</tt> nodes. It is intended that this should make CFG hacking much
|
|
easier. To make later hacking easier, the entry block is split into two, such
|
|
that all introduced <tt>alloca</tt> instructions (and nothing else) are in the
|
|
entry block.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="scalarrepl">-scalarrepl: Scalar Replacement of Aggregates (DT)</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
The well-known scalar replacement of aggregates transformation. This
|
|
transform breaks up <tt>alloca</tt> instructions of aggregate type (structure
|
|
or array) into individual <tt>alloca</tt> instructions for each member if
|
|
possible. Then, if possible, it transforms the individual <tt>alloca</tt>
|
|
instructions into nice clean scalar SSA form.
|
|
</p>
|
|
|
|
<p>
|
|
This combines a simple scalar replacement of aggregates algorithm with the <a
|
|
href="#mem2reg"><tt>mem2reg</tt></a> algorithm because often interact,
|
|
especially for C++ programs. As such, iterating between <tt>scalarrepl</tt>,
|
|
then <a href="#mem2reg"><tt>mem2reg</tt></a> until we run out of things to
|
|
promote works well.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="sccp">-sccp: Sparse Conditional Constant Propagation</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Sparse conditional constant propagation and merging, which can be summarized
|
|
as:
|
|
</p>
|
|
|
|
<ol>
|
|
<li>Assumes values are constant unless proven otherwise</li>
|
|
<li>Assumes BasicBlocks are dead unless proven otherwise</li>
|
|
<li>Proves values to be constant, and replaces them with constants</li>
|
|
<li>Proves conditional branches to be unconditional</li>
|
|
</ol>
|
|
|
|
<p>
|
|
Note that this pass has a habit of making definitions be dead. It is a good
|
|
idea to to run a DCE pass sometime after running this pass.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="simplify-libcalls">-simplify-libcalls: Simplify well-known library calls</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Applies a variety of small optimizations for calls to specific well-known
|
|
function calls (e.g. runtime library functions). For example, a call
|
|
<tt>exit(3)</tt> that occurs within the <tt>main()</tt> function can be
|
|
transformed into simply <tt>return 3</tt>.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="simplifycfg">-simplifycfg: Simplify the CFG</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Performs dead code elimination and basic block merging. Specifically:
|
|
</p>
|
|
|
|
<ol>
|
|
<li>Removes basic blocks with no predecessors.</li>
|
|
<li>Merges a basic block into its predecessor if there is only one and the
|
|
predecessor only has one successor.</li>
|
|
<li>Eliminates PHI nodes for basic blocks with a single predecessor.</li>
|
|
<li>Eliminates a basic block that only contains an unconditional
|
|
branch.</li>
|
|
</ol>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="sink">-sink: Code sinking</a>
|
|
</h3>
|
|
<div>
|
|
<p>This pass moves instructions into successor blocks, when possible, so that
|
|
they aren't executed on paths where their results aren't needed.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="sretpromotion">-sretpromotion: Promote sret arguments to multiple ret values</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass finds functions that return a struct (using a pointer to the struct
|
|
as the first argument of the function, marked with the '<tt>sret</tt>' attribute) and
|
|
replaces them with a new function that simply returns each of the elements of
|
|
that struct (using multiple return values).
|
|
</p>
|
|
|
|
<p>
|
|
This pass works under a number of conditions:
|
|
</p>
|
|
|
|
<ul>
|
|
<li>The returned struct must not contain other structs</li>
|
|
<li>The returned struct must only be used to load values from</li>
|
|
<li>The placeholder struct passed in is the result of an <tt>alloca</tt></li>
|
|
</ul>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="strip">-strip: Strip all symbols from a module</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
performs code stripping. this transformation can delete:
|
|
</p>
|
|
|
|
<ol>
|
|
<li>names for virtual registers</li>
|
|
<li>symbols for internal globals and functions</li>
|
|
<li>debug information</li>
|
|
</ol>
|
|
|
|
<p>
|
|
note that this transformation makes code much less readable, so it should
|
|
only be used in situations where the <tt>strip</tt> utility would be used,
|
|
such as reducing code size or making it harder to reverse engineer code.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="strip-dead-debug-info">-strip-dead-debug-info: Strip debug info for unused symbols</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
performs code stripping. this transformation can delete:
|
|
</p>
|
|
|
|
<ol>
|
|
<li>names for virtual registers</li>
|
|
<li>symbols for internal globals and functions</li>
|
|
<li>debug information</li>
|
|
</ol>
|
|
|
|
<p>
|
|
note that this transformation makes code much less readable, so it should
|
|
only be used in situations where the <tt>strip</tt> utility would be used,
|
|
such as reducing code size or making it harder to reverse engineer code.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="strip-dead-prototypes">-strip-dead-prototypes: Strip Unused Function Prototypes</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass loops over all of the functions in the input module, looking for
|
|
dead declarations and removes them. Dead declarations are declarations of
|
|
functions for which no implementation is available (i.e., declarations for
|
|
unused library functions).
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="strip-debug-declare">-strip-debug-declare: Strip all llvm.dbg.declare intrinsics</a>
|
|
</h3>
|
|
<div>
|
|
<p>This pass implements code stripping. Specifically, it can delete:</p>
|
|
<ul>
|
|
<li>names for virtual registers</li>
|
|
<li>symbols for internal globals and functions</li>
|
|
<li>debug information</li>
|
|
</ul>
|
|
<p>
|
|
Note that this transformation makes code much less readable, so it should
|
|
only be used in situations where the 'strip' utility would be used, such as
|
|
reducing code size or making it harder to reverse engineer code.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="strip-nondebug">-strip-nondebug: Strip all symbols, except dbg symbols, from a module</a>
|
|
</h3>
|
|
<div>
|
|
<p>This pass implements code stripping. Specifically, it can delete:</p>
|
|
<ul>
|
|
<li>names for virtual registers</li>
|
|
<li>symbols for internal globals and functions</li>
|
|
<li>debug information</li>
|
|
</ul>
|
|
<p>
|
|
Note that this transformation makes code much less readable, so it should
|
|
only be used in situations where the 'strip' utility would be used, such as
|
|
reducing code size or making it harder to reverse engineer code.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="tailcallelim">-tailcallelim: Tail Call Elimination</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This file transforms calls of the current function (self recursion) followed
|
|
by a return instruction with a branch to the entry of the function, creating
|
|
a loop. This pass also implements the following extensions to the basic
|
|
algorithm:
|
|
</p>
|
|
|
|
<ul>
|
|
<li>Trivial instructions between the call and return do not prevent the
|
|
transformation from taking place, though currently the analysis cannot
|
|
support moving any really useful instructions (only dead ones).
|
|
<li>This pass transforms functions that are prevented from being tail
|
|
recursive by an associative expression to use an accumulator variable,
|
|
thus compiling the typical naive factorial or <tt>fib</tt> implementation
|
|
into efficient code.
|
|
<li>TRE is performed if the function returns void, if the return
|
|
returns the result returned by the call, or if the function returns a
|
|
run-time constant on all exits from the function. It is possible, though
|
|
unlikely, that the return returns something else (like constant 0), and
|
|
can still be TRE'd. It can be TRE'd if <em>all other</em> return
|
|
instructions in the function return the exact same value.
|
|
<li>If it can prove that callees do not access theier caller stack frame,
|
|
they are marked as eligible for tail call elimination (by the code
|
|
generator).
|
|
</ul>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="tailduplicate">-tailduplicate: Tail Duplication</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass performs a limited form of tail duplication, intended to simplify
|
|
CFGs by removing some unconditional branches. This pass is necessary to
|
|
straighten out loops created by the C front-end, but also is capable of
|
|
making other code nicer. After this pass is run, the CFG simplify pass
|
|
should be run to clean up the mess.
|
|
</p>
|
|
</div>
|
|
|
|
</div>
|
|
|
|
<!-- ======================================================================= -->
|
|
<h2><a name="utilities">Utility Passes</a></h2>
|
|
<div>
|
|
<p>This section describes the LLVM Utility Passes.</p>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="deadarghaX0r">-deadarghaX0r: Dead Argument Hacking (BUGPOINT USE ONLY; DO NOT USE)</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Same as dead argument elimination, but deletes arguments to functions which
|
|
are external. This is only for use by <a
|
|
href="Bugpoint.html">bugpoint</a>.</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="extract-blocks">-extract-blocks: Extract Basic Blocks From Module (for bugpoint use)</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
This pass is used by bugpoint to extract all blocks from the module into their
|
|
own functions.</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="instnamer">-instnamer: Assign names to anonymous instructions</a>
|
|
</h3>
|
|
<div>
|
|
<p>This is a little utility pass that gives instructions names, this is mostly
|
|
useful when diffing the effect of an optimization because deleting an
|
|
unnamed instruction can change all other instruction numbering, making the
|
|
diff very noisy.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="preverify">-preverify: Preliminary module verification</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Ensures that the module is in the form required by the <a
|
|
href="#verifier">Module Verifier</a> pass.
|
|
</p>
|
|
|
|
<p>
|
|
Running the verifier runs this pass automatically, so there should be no need
|
|
to use it directly.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="verify">-verify: Module Verifier</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Verifies an LLVM IR code. This is useful to run after an optimization which is
|
|
undergoing testing. Note that <tt>llvm-as</tt> verifies its input before
|
|
emitting bitcode, and also that malformed bitcode is likely to make LLVM
|
|
crash. All language front-ends are therefore encouraged to verify their output
|
|
before performing optimizing transformations.
|
|
</p>
|
|
|
|
<ul>
|
|
<li>Both of a binary operator's parameters are of the same type.</li>
|
|
<li>Verify that the indices of mem access instructions match other
|
|
operands.</li>
|
|
<li>Verify that arithmetic and other things are only performed on
|
|
first-class types. Verify that shifts and logicals only happen on
|
|
integrals f.e.</li>
|
|
<li>All of the constants in a switch statement are of the correct type.</li>
|
|
<li>The code is in valid SSA form.</li>
|
|
<li>It is illegal to put a label into any other type (like a structure) or
|
|
to return one.</li>
|
|
<li>Only phi nodes can be self referential: <tt>%x = add i32 %x, %x</tt> is
|
|
invalid.</li>
|
|
<li>PHI nodes must have an entry for each predecessor, with no extras.</li>
|
|
<li>PHI nodes must be the first thing in a basic block, all grouped
|
|
together.</li>
|
|
<li>PHI nodes must have at least one entry.</li>
|
|
<li>All basic blocks should only end with terminator insts, not contain
|
|
them.</li>
|
|
<li>The entry node to a function must not have predecessors.</li>
|
|
<li>All Instructions must be embedded into a basic block.</li>
|
|
<li>Functions cannot take a void-typed parameter.</li>
|
|
<li>Verify that a function's argument list agrees with its declared
|
|
type.</li>
|
|
<li>It is illegal to specify a name for a void value.</li>
|
|
<li>It is illegal to have a internal global value with no initializer.</li>
|
|
<li>It is illegal to have a ret instruction that returns a value that does
|
|
not agree with the function return value type.</li>
|
|
<li>Function call argument types match the function prototype.</li>
|
|
<li>All other things that are tested by asserts spread about the code.</li>
|
|
</ul>
|
|
|
|
<p>
|
|
Note that this does not provide full security verification (like Java), but
|
|
instead just tries to ensure that code is well-formed.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="view-cfg">-view-cfg: View CFG of function</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Displays the control flow graph using the GraphViz tool.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="view-cfg-only">-view-cfg-only: View CFG of function (with no function bodies)</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Displays the control flow graph using the GraphViz tool, but omitting function
|
|
bodies.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="view-dom">-view-dom: View dominance tree of function</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Displays the dominator tree using the GraphViz tool.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="view-dom-only">-view-dom-only: View dominance tree of function (with no function bodies)</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Displays the dominator tree using the GraphViz tool, but omitting function
|
|
bodies.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="view-postdom">-view-postdom: View postdominance tree of function</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Displays the post dominator tree using the GraphViz tool.
|
|
</p>
|
|
</div>
|
|
|
|
<!-------------------------------------------------------------------------- -->
|
|
<h3>
|
|
<a name="view-postdom-only">-view-postdom-only: View postdominance tree of function (with no function bodies)</a>
|
|
</h3>
|
|
<div>
|
|
<p>
|
|
Displays the post dominator tree using the GraphViz tool, but omitting
|
|
function bodies.
|
|
</p>
|
|
</div>
|
|
|
|
</div>
|
|
|
|
<!-- *********************************************************************** -->
|
|
|
|
<hr>
|
|
<address>
|
|
<a href="http://jigsaw.w3.org/css-validator/check/referer"><img
|
|
src="http://jigsaw.w3.org/css-validator/images/vcss-blue" alt="Valid CSS"></a>
|
|
<a href="http://validator.w3.org/check/referer"><img
|
|
src="http://www.w3.org/Icons/valid-html401-blue" alt="Valid HTML 4.01"></a>
|
|
|
|
<a href="mailto:rspencer@x10sys.com">Reid Spencer</a><br>
|
|
<a href="http://llvm.org/">LLVM Compiler Infrastructure</a><br>
|
|
Last modified: $Date$
|
|
</address>
|
|
|
|
</body>
|
|
</html>
|