From: lkcl <lkcl@web>
Date: Fri, 29 Oct 2021 11:16:47 +0000 (+0100)
Subject: (no commit message)
X-Git-Tag: opf_rfc_ls005_v1~3491
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=4e27458bd665856619881d673d3dc1160b7575d8;p=libreriscv.git

---

diff --git a/3d_gpu/architecture/dynamic_simd/shape.mdwn b/3d_gpu/architecture/dynamic_simd/shape.mdwn
index 86a33b6db..1497a4d50 100644
--- a/3d_gpu/architecture/dynamic_simd/shape.mdwn
+++ b/3d_gpu/architecture/dynamic_simd/shape.mdwn
@@ -457,6 +457,11 @@ used on both LHS and RHS, it is effectively an identical case to
 when the RHS is an integer, because the fixed_width of the RHS is
 itself an integer.
 
+A special case of this also occurs in instances where all elwidths
+in all partitions on either LHS or RHS are identical: element widths {3,3,3,3} for
+example.  Under such special circumstances, multiply would
+function correctly even for dual-priority, due to uniform scaling.
+
 Summary:
 
 * **Both LHS and RHS Fixed-width Priority**