bit of a mess being sorted out

[openpower-isa.git] / openpower / isa / simplev.mdwn

diff --git a/openpower/isa/simplev.mdwn b/openpower/isa/simplev.mdwn
index a48c405ecce47435c9f0143de18043db87fe901e..8a21f038075e94668fcb344cff1260db8cc1162b 100644 (file)
--- a/openpower/isa/simplev.mdwn
+++ b/openpower/isa/simplev.mdwn
@@ -148,10 +148,11 @@ Pseudo-code:
         SVSHAPE1[28:29] <- 0b01           # j+halfstep schedule
         # FRC (coefficients)
         SVSHAPE2[28:29] <- 0b10           # k schedule
-    # set schedule up for DCT Inner butterfly
-    # SVRM Mode 2 is for pre-calculated coefficients,
-    # SVRM Mode 4 is for on-the-fly (Vertical-First Mode)
-    if (SVRM = 0b0010) | (SVRM = 0b0100) then
+    # 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
         # calculate O(N log2 N)
         n <- [0] * 3
         do while n < 5
@@ -163,26 +164,30 @@ Pseudo-code:
         # set up template in SVSHAPE0, then copy to 1-3
         # set up FRB and FRS
         SVSHAPE0[0:5] <- (0b0 || SVxd)   # xdim
-        SVSHAPE0[30:31] <- 0b01          # DCT/FFT mode
-        if (SVRM = 0b0100) then
-            SVSHAPE0[6:11] <- 0b000011       # DCT Inner Butterfly mode 4
+        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       # DCT Inner Butterfly mode 2
-        SVSHAPE0[18:20] <- 0b001         # DCT Inner Butterfly sub-mode
-        SVSHAPE0[21:23] <- 0b001         # "inverse" on outer loop
+            SVSHAPE0[6:11] <- 0b000001       # (i)DCT Inner Butterfly mode 2
         # copy
         SVSHAPE1[0:31] <- SVSHAPE0[0:31]
         SVSHAPE2[0:31] <- SVSHAPE0[0:31]
-        if (SVRM != 0b0100) then
+        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
-        if (SVRM != 0b0100) then
+        if (SVRM != 0b0100) & (SVRM != 0b1100) then
             SVSHAPE3[28:29] <- 0b11           # size schedule
-    # set schedule up for DCT Outer butterfly
-    if (SVRM = 0b0011) then
+    # 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
@@ -200,16 +205,21 @@ Pseudo-code:
         # set up template in SVSHAPE0, then copy to 1-3
         # set up FRB and FRS
         SVSHAPE0[0:5] <- (0b0 || SVxd)   # xdim
-        SVSHAPE0[30:31] <- 0b01          # DCT/FFT mode
+        if (SVRM = 0b1011) then
+            SVSHAPE0[30:31] <- 0b11      # iDCT mode
+            SVSHAPE0[18:20] <- 0b011     # iDCT Outer Butterfly sub-mode
+            SVSHAPE0[21:23] <- 0b101     # "inverse" on outer and inner loop
+        else
+            SVSHAPE0[30:31] <- 0b01      # DCT mode
+            SVSHAPE0[18:20] <- 0b100     # DCT Outer Butterfly sub-mode
         SVSHAPE0[6:11] <- 0b000010       # DCT Butterfly mode
-        SVSHAPE0[18:20] <- 0b100         # DCT Outer Butterfly sub-mode
         # copy
         SVSHAPE1[0:31] <- SVSHAPE0[0:31]
         SVSHAPE2[0:31] <- SVSHAPE0[0:31]
         # for FRA and FRT
         SVSHAPE1[28:29] <- 0b01           # j+halfstep schedule
     # set schedule up for DCT COS table generation
-    if (SVRM = 0b0101) then
+    if (SVRM = 0b0101) | (SVRM = 0b1101) then
         # calculate O(N log2 N)
         vlen[0:6] <- [0] * 7
         itercount[0:6] <- (0b00 || SVxd) + 0b0000001
@@ -226,19 +236,25 @@ Pseudo-code:
         SVSHAPE0[0:5] <- (0b0 || SVxd)   # xdim
         SVSHAPE0[30:31] <- 0b01          # DCT/FFT mode
         SVSHAPE0[6:11] <- 0b000100       # DCT Inner Butterfly COS-gen mode
-        SVSHAPE0[21:23] <- 0b001         # "inverse" on outer loop
+        if (SVRM = 0b0101) then
+            SVSHAPE0[21:23] <- 0b001     # "inverse" on outer loop for DCT
         # copy
         SVSHAPE1[0:31] <- SVSHAPE0[0:31]
         SVSHAPE2[0:31] <- SVSHAPE0[0:31]
         # for cos coefficient
         SVSHAPE1[28:29] <- 0b10           # ci schedule
         SVSHAPE2[28:29] <- 0b11           # size schedule
-    # set schedule up for DCT inverse of half-swapped ordering
-    if (SVRM = 0b0110) then
+    # 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
         # set up template in SVSHAPE0
         SVSHAPE0[0:5] <- (0b0 || SVxd)   # xdim
-        SVSHAPE0[30:31] <- 0b01          # DCT/FFT mode
+        if (SVRM = 0b1110) then
+            SVSHAPE0[18:20] <- 0b001     # DCT opposite half-swap
+        if (SVRM = 0b1111) then
+            SVSHAPE0[30:31] <- 0b01          # FFT mode
+        else
+            SVSHAPE0[30:31] <- 0b11          # DCT mode
         SVSHAPE0[6:11] <- 0b000101       # DCT "half-swap" mode
     # set VL, MVL and Vertical-First
     SVSTATE[0:6] <- vlen