Add a note about the MUL -> FMADD vector bug.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@26874 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/PowerPC/README.txt b/lib/Target/PowerPC/README.txt
index 42a644c1f33cf2df19a3e9c28d8c9892f4198df4..0a9c5bdc27def721b6a3041f3ec4fd68da569050 100644 (file)
--- a/lib/Target/PowerPC/README.txt
+++ b/lib/Target/PowerPC/README.txt
@@ -536,3 +536,13 @@ void foo(void) {
   bar (x);
 }
 
+===-------------------------------------------------------------------------===
+
+Altivec: Codegen'ing MUL with vector FMADD should add -0.0, not 0.0:
+http://gcc.gnu.org/bugzilla/show_bug.cgi?id=8763
+
+We need to codegen -0.0 vector efficiently (no constant pool load).
+
+When -ffast-math is on, we can use 0.0.
+
+===-------------------------------------------------------------------------===