From: lkcl <lkcl@web>
Date: Fri, 22 Oct 2021 15:57:00 +0000 (+0100)
Subject: (no commit message)
X-Git-Tag: opf_rfc_ls005_v1~3553
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=652dcbfd3cc9682d1b2297f925e13eed4b0cd3f4;p=libreriscv.git

---

diff --git a/3d_gpu/architecture/dynamic_simd/simdscope.mdwn b/3d_gpu/architecture/dynamic_simd/simdscope.mdwn
index 5f2d654b0..191afb9c6 100644
--- a/3d_gpu/architecture/dynamic_simd/simdscope.mdwn
+++ b/3d_gpu/architecture/dynamic_simd/simdscope.mdwn
@@ -61,4 +61,11 @@ because SimdShape works out that its maximum scalar size is
 scalar mode.  When scalar=False, full SIMD is activated and
 the resultant HDL combines vec_el_counts with expshape to create
 1xFP64, 2xFP32, 4xFP16, 4xBF16 where the exponents are 11, 8, 5, 8
-respectively.0
+respectively.
+
+Behind the scenes, when calling SimdShape.Signal in SIMD mode,
+the elwid and vec_el_counts parameters from the context are combined
+with the SimdShape as inputs to create a layout that is "Element-width
+aware" (ElwidPartType).  With the full information being passed in to
+SimdSignals, the actual use of the SimdSignals need not be inside
+the Context Manager.