(no commit message)

diff --git a/3d_gpu/architecture/dynamic_simd.mdwn b/3d_gpu/architecture/dynamic_simd.mdwn
index 1e2cf1abed1cb6fc6de18d0434e458da13411919..a7bc929ee0621678c2da0b403a6242e56290663c 100644 (file)
--- a/3d_gpu/architecture/dynamic_simd.mdwn
+++ b/3d_gpu/architecture/dynamic_simd.mdwn
@@ -2,8 +2,9 @@
 
 Links:
 
-* <https://bugs.libre-soc.org/show_bug.cgi?id=458>
-* <https://bugs.libre-soc.org/show_bug.cgi?id=594>
+* <https://bugs.libre-soc.org/show_bug.cgi?id=458> 
+* <https://bugs.libre-soc.org/show_bug.cgi?id=594> RFC
+* <https://bugs.libre-soc.org/show_bug.cgi?id=565> Formal proof
 
 To save hugely on gate count the normal practice of having separate scalar ALUs and separate SIMD ALUs is not followed.