From: lkcl <lkcl@web>
Date: Sun, 14 Aug 2022 00:18:38 +0000 (+0100)
Subject: (no commit message)
X-Git-Tag: opf_rfc_ls005_v1~865
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=fa5351c50ae9d305512c68da79b91a4f72d6af85;p=libreriscv.git

---

diff --git a/openpower/sv/svp64/appendix.mdwn b/openpower/sv/svp64/appendix.mdwn
index 3e4699da7..c51e85d0d 100644
--- a/openpower/sv/svp64/appendix.mdwn
+++ b/openpower/sv/svp64/appendix.mdwn
@@ -601,39 +601,24 @@ Thus logically there is nothing special or unanticipated about
 Sub-Vector rules.
 
 By contrast, when SVM is set and SUBVL!=1, a Horizontal
-Subvector mode is enabled, which behaves very much more
-like a traditional Vector Processor Reduction instruction.
+Subvector mode is enabled, applying the Parallel Reduction
+Algorithm to the Subvector Elements. The Parallel Reduction
+is independently applied VL times, to each group of Subvector
+elements. Bear in mind that predication is never applied down
+into individual Subvector elements, but will be applied
+to select whether the *entire* Parallel Reduction on each
+group is performed or not.
 
-Example for a vec2:
-
-    for i in range(VL):
-        iregs[RT+i] = op(iregs[RA+i].x, iregs[RB+i].y)
-
-Example for a vec3:
-
-    for i in range(VL):
-        iregs[RT+i] = op(iregs[RA+i].x, iregs[RB+i].y)
-        iregs[RT+i] = op(iregs[RT+i]  , iregs[RB+i].z)
+      for (i = 0; i < VL; i++)
+        if (predval & 1<<i) # predication
+           subvecparallelreduction(...)
 
-Example for a vec4:
+Note that as this is a Parallel Reduction, for best results
+it should be an overwrite operation, where the result for
+the Horizontal Reduction of each Subvector will be in the
+first Subvector element.
 
-    for i in range(VL):
-        iregs[RT+i] = op(iregs[RA+i].x, iregs[RB+i].y)
-        iregs[RT+i] = op(iregs[RT+i]  , iregs[RB+i].z)
-        iregs[RT+i] = op(iregs[RT+i]  , iregs[RB+i].w)
-
-In this mode, when Rc=1 the Vector of CRs is as normal: each result
-element creates a corresponding CR element (for the final, reduced, result).
-
-Note:
-
-1. that the destination (RT) is inherently used as an "Accumulator"
-   register, and consequently the Sub-Vector Loop is interruptible.
-   If RT is a Scalar then as usual the main VL Loop terminates at the
-   first predicated element (or the first element if unpredicated).
-2. that the Sub-Vector designation applies to RA and RB *but not RT*.
-3. that the number of operations executed is one less than the Sub-vector
-   length
+Also note that use of Rc=1 is `UNDEFINED` behaviour.
 
 # Fail-on-first <a name="fail-first"> </a>