From: lkcl <lkcl@web>
Date: Mon, 13 Jun 2022 14:33:51 +0000 (+0100)
Subject: (no commit message)
X-Git-Tag: opf_rfc_ls005_v1~1814
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=0879c186340c65b1b0e6391698ba5aa7551bf040;p=libreriscv.git

---

diff --git a/openpower/sv/mv.vec.mdwn b/openpower/sv/mv.vec.mdwn
index d0b1e1263..40a31c954 100644
--- a/openpower/sv/mv.vec.mdwn
+++ b/openpower/sv/mv.vec.mdwn
@@ -100,31 +100,29 @@ Illustrating a
 
 For a separate source/dest SUBVL (again, no elwidth overrides):
 
+    # only one of these will be >1 at any given time
+    subvl = MAX(SUBVL,SRC_SUBVL)
     # yield an outer-SUBVL, inner VL loop with SRC SUBVL
     def index_src(outer):
         if outer:
-            # outer on *dest* subvl, to match inner dest
-            for j in range(SUBVL):
+            for j in range(subvl):
                 for i in range(VL):
                     yield i+VL*j
         else:
-            # inner on *src* subvl, to match *outer* src
             for i in range(VL):
-                for j in range(SRC_SUBVL):
-                    yield i*SRC_SUBVL+j
+                for j in range(subvl):
+                    yield i*subvl+j
 
     # yield an outer-SUBVL, inner VL loop with DEST SUBVL
     def index_dest(outer):
         if outer:
-            # outer on *src* subvl, to match inner src
-            for j in range(SRC_SUBVL):
+            for j in range(subvl):
                 for i in range(VL):
                     yield i+VL*j
         else:
-            # inner on *dest* subvl, to match *outer* dest
             for i in range(VL):
-                for j in range(SUBVL):
-                    yield i*SUBVL+j
+                for j in range(subvl):
+                    yield i*subvl+j
 
     # inner looping when SUBVLs are equal
     if SRC_SUBVL == SUBVL:
@@ -132,7 +130,8 @@ For a separate source/dest SUBVL (again, no elwidth overrides):
             move_operation(RT+idx, RA+idx)
     else:
         # walk through both source and dest indices simultaneously
-        for src_idx, dst_idx in zip(index_src(), index_dst()):
+        so, do = SRC_SUBVL>SUBVL, SUBVL>SRC_SUBVL
+        for src_idx, dst_idx in zip(index_src(so), index_dst(do)):
             move_operation(RT+dst_idx, RA+src_idx)
 
 "yield" from python is used here for simplicity and clarity.
@@ -140,9 +139,8 @@ The two Finite State Machines for the generation of the source
 and destination element offsets progress incrementally in
 lock-step.
 
-Normal uaage, `SRC_SUBVL=1, SUBVL=2/3/4` gives
-a "pack" effect, and `SUBVL=1, SRC_SUBVL=2/3/4` gives an
-"unpack".  Setting both SUBVL and SRC_SUBVL to greater than
-1 will, unlike [[sv/mv.swizzle]], produce defined deterministic results,
-even if a little hard to understand.  Loops run through
-`MIN(SUBVL, SRC_SUBVL) * VL` elements.
+* Normal usage, `SUBVL=SRC_SUBVL`, gives straight subvector copy.
+* `SRC_SUBVL=1, SUBVL=2/3/4` gives a "pack" effect
+* `SUBVL=1, SRC_SUBVL=2/3/4` gives an "unpack".
+* Setting both SUBVL and SRC_SUBVL to unequal values greater than
+  1 will, like [[sv/mv.swizzle]], produce `UNDEFINED` results.