(no commit message)

diff --git a/3d_gpu/architecture/dynamic_simd/mul.mdwn b/3d_gpu/architecture/dynamic_simd/mul.mdwn
new file mode 100644 (file)
index 0000000..a8e4f4e
--- /dev/null
+++ b/3d_gpu/architecture/dynamic_simd/mul.mdwn
@@ -0,0 +1,3 @@
+# Dynamic Partitioned Multiply
+
+This is complicated!  It is necessary to compute a full NxN matrix of partial multiplication results, then perform a cascade of adds, using PartitionedAdd to "automatically" break them down into segments.  The Wallace Tree algorithm is presently deployed, here: we need to use the (more efficient) Dadda algorithm.