summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--docs/AliasAnalysis.html19
1 files changed, 19 insertions, 0 deletions
diff --git a/docs/AliasAnalysis.html b/docs/AliasAnalysis.html
index 748b3cb..7c3fa81 100644
--- a/docs/AliasAnalysis.html
+++ b/docs/AliasAnalysis.html
@@ -50,6 +50,7 @@
implementations</a></li>
</ul>
</li>
+ <li><a hread="#memdep">Memory Dependence Analysis</a></li>
</ol>
<div class="doc_author">
@@ -948,6 +949,24 @@ algorithm will have a lower number of may aliases).</p>
</div>
<!-- *********************************************************************** -->
+<div class="doc_section">
+ <a name="memdep">Memory Dependence Analysis</a>
+</div>
+<!-- *********************************************************************** -->
+
+<div class="doc_text">
+
+<p>If you're just looking to be a client of alias analysis information, consider
+using the Memory Dependence Analysis interface instead. MemDep is a lazy,
+caching layer on top of alias analysis that is able to answer the question of
+what preceding memory operations a given instruction depends on, either at an
+intra- or inter-block level. Because of its laziness and caching
+policy, using MemDep can be a significant performance win over accessing alias
+analysis directly.</p>
+
+</div>
+
+<!-- *********************************************************************** -->
<hr>
<address>