From fb879247e5d61ef19800995e03f834b76f4bb44e Mon Sep 17 00:00:00 2001
From: lkcl <lkcl@web>
Date: Sat, 4 Jun 2022 17:26:33 +0100
Subject: [PATCH]

---
 openpower/sv/remap.mdwn | 84 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 83 insertions(+), 1 deletion(-)

diff --git a/openpower/sv/remap.mdwn b/openpower/sv/remap.mdwn
index 6b6a02179..07d6c57ae 100644
--- a/openpower/sv/remap.mdwn
+++ b/openpower/sv/remap.mdwn
@@ -218,10 +218,92 @@ Fields:
 
 * **SVxd** - SV REMAP "xdim"
 * **SVyd** - SV REMAP "ydim"
-* **SVMM** - SV REMAP Mode (0b00000 for Matrix, 0b00001 for FFT)
+* **SVRM** - SV REMAP Mode (0b00000 for Matrix, 0b00001 for FFT)
 * **vf** - sets "Vertical-First" mode
 * **XO** - standard 5-bit XO field
 
+```
+# set schedule up for multiply
+if (SVRM = 0b0000) then
+    # VL in Matrix Multiply is xd*yd*zd
+    n <- (0b00 || SVxd) * (0b00 || SVyd) * (0b00 || SVzd)
+    vlen[0:6] <- n[14:20]
+    # set up template in SVSHAPE0, then copy to 1-3
+    SVSHAPE0[0:5] <- (0b0 || SVxd)   # xdim
+    SVSHAPE0[6:11] <- (0b0 || SVyd)   # ydim
+    SVSHAPE0[12:17] <- (0b0 || SVzd)   # zdim
+    SVSHAPE0[28:29] <- 0b11           # skip z
+    # copy
+    SVSHAPE1[0:31] <- SVSHAPE0[0:31]
+    SVSHAPE2[0:31] <- SVSHAPE0[0:31]
+    SVSHAPE3[0:31] <- SVSHAPE0[0:31]
+    # set up FRA
+    SVSHAPE1[18:20] <- 0b001          # permute x,z,y
+    SVSHAPE1[28:29] <- 0b01           # skip z
+    # FRC
+    SVSHAPE2[18:20] <- 0b001          # permute x,z,y
+    SVSHAPE2[28:29] <- 0b11           # skip y
+# set schedule up for FFT butterfly
+if (SVRM = 0b0001) then
+    # calculate O(N log2 N)
+    n <- [0] * 3
+    do while n < 5
+       if SVxd[4-n] = 0 then
+           leave
+       n <- n + 1
+    n <- ((0b0 || SVxd) + 1) * n
+    vlen[0:6] <- n[1:7]
+    # set up template in SVSHAPE0, then copy to 1-3
+    # for FRA and FRT
+    SVSHAPE0[0:5] <- (0b0 || SVxd)   # xdim
+    SVSHAPE0[30:31] <- 0b01          # Butterfly mode
+    # copy
+    SVSHAPE1[0:31] <- SVSHAPE0[0:31]
+    SVSHAPE2[0:31] <- SVSHAPE0[0:31]
+    # set up FRB and FRS
+    SVSHAPE1[28:29] <- 0b01           # j+halfstep schedule
+    # FRC (coefficients)
+    SVSHAPE2[28:29] <- 0b10           # k schedule
+# set schedule up for (i)DCT Inner butterfly
+if ((SVRM = 0b0010) | (SVRM = 0b0100) |
+    (SVRM = 0b1010) | (SVRM = 0b1100)) then
+    # calculate O(N log2 N)
+    n <- [0] * 3
+    do while n < 5
+       if SVxd[4-n] = 0 then
+           leave
+       n <- n + 1
+    n <- ((0b0 || SVxd) + 1) * n
+    vlen[0:6] <- n[1:7]
+    # set up template in SVSHAPE0, then copy to 1-3
+    # set up FRB and FRS
+    SVSHAPE0[0:5] <- (0b0 || SVxd)   # xdim
+    if (SVRM = 0b1010) | (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
+    if (SVRM = 0b1100) | (SVRM = 0b0100) then
+        SVSHAPE0[6:11] <- 0b000011       # (i)DCT Inner Butterfly mode 4
+    else
+        SVSHAPE0[6:11] <- 0b000001       # (i)DCT Inner Butterfly mode 2
+# set schedule up for iDCT / DCT inverse of half-swapped ordering
+if (SVRM = 0b0110) | (SVRM = 0b1110) | (SVRM = 0b1111) then
+    vlen[0:6] <- (0b00 || SVxd) + 0b0000001
+```
+
+    | 0b0010 | DCT Inner butterfly, pre-calculated coefficients |
+    | 0b0110 | iDCT Inner butterfly, pre-calculated coefficients |
+    | 0b0100 | DCT Inner butterfly, on-the-fly (Vertical-First Mode) |
+    | 0b1100 | iDCT Inner butterfly, on-the-fly (Vertical-First Mode) |
+    | 0b0011 |  DCT Outer butterfly  |
+    | 0b1011 |  (i)DCT Outer butterfly  |
+    | 0b0101 | iDCT COS table generation |
+    | 0b1101 | DCT COS table generation |
+
+
 # 4x4 Matrix to vec4 Multiply Example
 
 The following settings will allow a 4x4 matrix (starting at f8), expressed
-- 
2.30.2