add a note about viterbi

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@31612 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/README.txt b/lib/Target/README.txt
index 19bd9d137d57b98f1c8b1bad77c857cb796a0118..3e5dbf6172dc749261ed075d15e1a2852907c280 100644 (file)
--- 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.
+
+//===---------------------------------------------------------------------===//