From 3eaaa8de42fc7703e537267de7bae972635583cb Mon Sep 17 00:00:00 2001
From: Luke Kenneth Casson Leighton <lkcl@lkcl.net>
Date: Wed, 29 Mar 2023 10:14:13 +0100
Subject: [PATCH] corrections in ls009 svshape pseudocode, add missing modes
 not properly cut/paste (sigh)

---
 openpower/sv/rfc/ls009.mdwn | 47 ++++++++++++++++++++++++++++++++++---
 1 file changed, 44 insertions(+), 3 deletions(-)

diff --git a/openpower/sv/rfc/ls009.mdwn b/openpower/sv/rfc/ls009.mdwn
index b0ba78458..0ec5ba28c 100644
--- a/openpower/sv/rfc/ls009.mdwn
+++ b/openpower/sv/rfc/ls009.mdwn
@@ -894,10 +894,9 @@ Form: SVM-Form SV "Matrix" Form (see [[isatables/fields.text]])
         SVSHAPE2[28:29] <- 0b10           # k schedule
 
     # set schedule up for (i)DCT Inner butterfly
-    # SVrm Mode 2 (Mode 6 for iDCT) is for pre-calculated coefficients,
     # SVrm Mode 4 (Mode 12 for iDCT) is for on-the-fly (Vertical-First Mode)
-    if ((SVrm = 0b0010) | (SVrm = 0b0100) |
-        (SVrm = 0b1010) | (SVrm = 0b1100)) then
+    if ((SVrm = 0b0100) |
+        (SVrm = 0b1100)) then
         # calculate O(N log2 N)
         n <- [0] * 3
         do while n < 5
@@ -911,6 +910,48 @@ Form: SVM-Form SV "Matrix" Form (see [[isatables/fields.text]])
         SVSHAPE0[0:5] <- (0b0 || SVxd)   # xdim
         SVSHAPE0[12:17] <- (0b0 || SVzd)   # zdim - "striding" (2D DCT)
         mscale <- (0b0 || SVzd) + 1
+        if (SVrm = 0b1100) then
+            SVSHAPE0[30:31] <- 0b11          # iDCT mode
+            SVSHAPE0[18:20] <- 0b011         # iDCT Inner Butterfly sub-mode
+        else
+            SVSHAPE0[30:31] <- 0b01          # DCT mode
+            SVSHAPE0[18:20] <- 0b001         # DCT Inner Butterfly sub-mode
+            SVSHAPE0[21:23] <- 0b001         # "inverse" on outer loop
+        SVSHAPE0[6:11] <- 0b000011       # (i)DCT Inner Butterfly mode 4
+        # copy
+        SVSHAPE1[0:31] <- SVSHAPE0[0:31]
+        SVSHAPE2[0:31] <- SVSHAPE0[0:31]
+        if (SVrm != 0b0100) & (SVrm != 0b1100) then
+            SVSHAPE3[0:31] <- SVSHAPE0[0:31]
+        # for FRA and FRT
+        SVSHAPE0[28:29] <- 0b01           # j+halfstep schedule
+        # for cos coefficient
+        SVSHAPE2[28:29] <- 0b10           # ci (k for mode 4) schedule
+        SVSHAPE2[12:17] <- 0b000000       # reset costable "striding" to 1
+        if (SVrm != 0b0100) & (SVrm != 0b1100) then
+            SVSHAPE3[28:29] <- 0b11           # size schedule
+
+    # set schedule up for (i)DCT Outer butterfly
+    if (SVrm = 0b0011) | (SVrm = 0b1011) then
+        # calculate O(N log2 N) number of outer butterfly overlapping adds
+        vlen[0:6] <- [0] * 7
+        n <- 0b000
+        size <- 0b0000001
+        itercount[0:6] <- (0b00 || SVxd) + 0b0000001
+        itercount[0:6] <- (0b0 || itercount[0:5])
+        do while n < 5
+           if SVxd[4-n] = 0 then
+               leave
+           n <- n + 1
+           count <- (itercount - 0b0000001) * size
+           vlen[0:6] <- vlen + count[7:13]
+           size[0:6] <- (size[1:6] || 0b0)
+           itercount[0:6] <- (0b0 || itercount[0:5])
+        # set up template in SVSHAPE0, then copy to 1-3
+        # set up FRB and FRS
+        SVSHAPE0[0:5] <- (0b0 || SVxd)   # xdim
+        SVSHAPE0[12:17] <- (0b0 || SVzd)   # zdim - "striding" (2D DCT)
+        mscale <- (0b0 || SVzd) + 1
         if (SVrm = 0b1011) then
             SVSHAPE0[30:31] <- 0b11      # iDCT mode
             SVSHAPE0[18:20] <- 0b011     # iDCT Outer Butterfly sub-mode
-- 
2.30.2