From 48d2b0af37fe6e126029ff48cf7fd2e6aef62879 Mon Sep 17 00:00:00 2001
From: Chris Lattner <sabre@nondot.org>
Date: Fri, 10 Nov 2006 00:23:26 +0000
Subject: [PATCH] add a note about viterbi

llvm-svn: 31612
---
 lib/Target/README.txt | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/lib/Target/README.txt b/lib/Target/README.txt
index 19bd9d137d5..3e5dbf6172d 100644
--- a/lib/Target/README.txt
+++ b/lib/Target/README.txt
@@ -354,3 +354,9 @@ Instcombine misses several of these cases (see the testcase in the patch):
 http://gcc.gnu.org/ml/gcc-patches/2006-10/msg01519.html
 
 //===---------------------------------------------------------------------===//
+
+viterbi speeds up *significantly* if the various "history" related copy loops
+are turned into memcpy calls at the source level.  We need a "loops to memcpy"
+pass.
+
+//===---------------------------------------------------------------------===//