SVM-Form
-* svshape SVxd,SVyd,SVzd,SVRM,vf
+* svshape SVxd,SVyd,SVzd,SVrm,vf
Pseudo-code:
SVSHAPE2[0:31] <- [0] * 32
SVSHAPE3[0:31] <- [0] * 32
# set schedule up for multiply
- if (SVRM = 0b0000) then
+ 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]
SVSHAPE2[18:20] <- 0b001 # permute x,z,y
SVSHAPE2[28:29] <- 0b11 # skip y
# set schedule up for FFT butterfly
- if (SVRM = 0b0001) then
+ if (SVrm = 0b0001) then
# calculate O(N log2 N)
n <- [0] * 3
do while n < 5
# FRC (coefficients)
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
+ # 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
# 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
+ 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
+ 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
# copy
SVSHAPE1[0:31] <- SVSHAPE0[0:31]
SVSHAPE2[0:31] <- SVSHAPE0[0:31]
- if (SVRM != 0b0100) & (SVRM != 0b1100) 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) & (SVRM != 0b1100) then
+ 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
+ if (SVrm = 0b0011) | (SVrm = 0b1011) then
# calculate O(N log2 N) number of outer butterfly overlapping adds
vlen[0:6] <- [0] * 7
n <- 0b000
# set up template in SVSHAPE0, then copy to 1-3
# set up FRB and FRS
SVSHAPE0[0:5] <- (0b0 || SVxd) # xdim
- if (SVRM = 0b1011) then
+ 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
# for FRA and FRT
SVSHAPE1[28:29] <- 0b01 # j+halfstep schedule
# set schedule up for DCT COS table generation
- if (SVRM = 0b0101) | (SVRM = 0b1101) then
+ if (SVrm = 0b0101) | (SVrm = 0b1101) then
# calculate O(N log2 N)
vlen[0:6] <- [0] * 7
itercount[0:6] <- (0b00 || SVxd) + 0b0000001
SVSHAPE0[0:5] <- (0b0 || SVxd) # xdim
SVSHAPE0[30:31] <- 0b01 # DCT/FFT mode
SVSHAPE0[6:11] <- 0b000100 # DCT Inner Butterfly COS-gen mode
- if (SVRM = 0b0101) then
+ if (SVrm = 0b0101) then
SVSHAPE0[21:23] <- 0b001 # "inverse" on outer loop for DCT
# copy
SVSHAPE1[0:31] <- SVSHAPE0[0:31]
SVSHAPE1[28:29] <- 0b10 # ci schedule
SVSHAPE2[28:29] <- 0b11 # size schedule
# set schedule up for iDCT / DCT inverse of half-swapped ordering
- if (SVRM = 0b0110) | (SVRM = 0b1110) | (SVRM = 0b1111) then
+ 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
- if (SVRM = 0b1110) then
+ if (SVrm = 0b1110) then
SVSHAPE0[18:20] <- 0b001 # DCT opposite half-swap
- if (SVRM = 0b1111) then
+ if (SVrm = 0b1111) then
SVSHAPE0[30:31] <- 0b01 # FFT mode
else
SVSHAPE0[30:31] <- 0b11 # DCT mode