; ---------------------------------------------------------------- one block
; \1 = right-shift needed to bring this block's 2 mode bits to bits 1-0.
BLOCK   macro
        move.b  (a1),d0
        ifne    \1
        lsr.b   #\1,d0
        endc
        and.w   #3,d0
        beq     .sk\@                   ; 00 SKIP -- the median block
        subq.w  #1,d0
        beq     .v1\@                   ; 01 V1
        subq.w  #1,d0
        bne     .rw\@                   ; 11 RAW, else 10 V4

; -- V4: four 2x2 codewords, sub-block order TL TR BL BR (vq_hybrid.paint)
        moveq   #0,d0
        move.b  (a0)+,d0
        lsl.w   #3,d0
        movem.l (a3,d0.w),d0-d1
        move.l  d0,(a4)
        move.l  d1,1024(a4)
        moveq   #0,d0
        move.b  (a0)+,d0
        lsl.w   #3,d0
        movem.l (a3,d0.w),d0-d1
        move.l  d0,4(a4)
        move.l  d1,1028(a4)
        moveq   #0,d0
        move.b  (a0)+,d0
        lsl.w   #3,d0
        movem.l (a3,d0.w),d0-d1
        move.l  d0,2048(a4)
        move.l  d1,3072(a4)
        moveq   #0,d0
        move.b  (a0)+,d0
        lsl.w   #3,d0
        movem.l (a3,d0.w),d0-d1
        move.l  d0,2052(a4)
        move.l  d1,3076(a4)
        bra     .sk\@

; -- V1: one 4x4 codeword, 32 bytes, straight out of the expanded codebook
.v1\@:
        moveq   #0,d0
        move.b  (a0)+,d0
        lsl.w   #5,d0
        movem.l (a2,d0.w),d0-d7         ; EA is resolved before the load
        movem.l d0-d1,(a4)
        movem.l d2-d3,1024(a4)
        movem.l d4-d5,2048(a4)
        movem.l d6-d7,3072(a4)
        bra     .sk\@

; -- RAW: 16 literal palette indices.  Two indices are assembled into one long
;    via swap, so each pair of pixels costs one write instead of two; the high
;    byte of each word is left as zero because the hardware discards it anyway.
.rw\@:
        RAWPAIR 0
        RAWPAIR 4
        RAWPAIR 1024
        RAWPAIR 1028
        RAWPAIR 2048
        RAWPAIR 2052
        RAWPAIR 3072
        RAWPAIR 3076
.sk\@:
        addq.l  #8,a4
        endm

RAWPAIR macro
        moveq   #0,d0
        move.b  (a0)+,d0
        swap    d0
        move.b  (a0)+,d0
        move.l  d0,\1(a4)
        endm

; ------------------------------------------------------- the span section
; in:  a0 = span section, a1 = mode header (preserved across the call)
; out: a0 = one past the section, i.e. the block payload
;
; This is tools/bench/blit.s v7 verbatim, and deliberately so: the 66.0 clocks
; per span + 9.143 per coarse pixel + 9.978 per fine pixel of FINDINGS 40 were
; measured on exactly this instruction sequence, over thirteen span lengths, and
; a "tidier" rewrite here would silently invalidate every span figure in
; FINDINGS 39/40 and in tools/analysis/14_dmac_chain.py.
;
; The fine chain is entered by FALLING OUT of the coarse one, so a span with no
; coarse units enters at v7cx with d0 already reloaded -- which is why the
; coarse displacement for c=0 is SPCN*SPCU, one past the last coarse unit,
; rather than a special case.
paint_spans:
        move.w  (a0)+,d7                ; spans in this frame
        subq.w  #1,d7
        bmi     spnone                  ; a frame may legitimately have none (the
                                        ; chain is far past a short branch)
        move.l  a1,-(sp)                ; a1 is a payload register below
spspan: move.l  (a0)+,a2                ; absolute GVRAM destination
        move.w  (a0)+,d0                ; (SPCN - coarse) * SPCU
        jmp     spch(pc,d0.w)
spch:
        movem.l (a0)+,d0-d6/a1/a3-a6
        movem.l d0-d6/a1/a3-a6,(a2)
        lea     48(a2),a2
        movem.l (a0)+,d0-d6/a1/a3-a6
        movem.l d0-d6/a1/a3-a6,(a2)
        lea     48(a2),a2
        movem.l (a0)+,d0-d6/a1/a3-a6
        movem.l d0-d6/a1/a3-a6,(a2)
        lea     48(a2),a2
        movem.l (a0)+,d0-d6/a1/a3-a6
        movem.l d0-d6/a1/a3-a6,(a2)
        lea     48(a2),a2
        movem.l (a0)+,d0-d6/a1/a3-a6
        movem.l d0-d6/a1/a3-a6,(a2)
        lea     48(a2),a2
        movem.l (a0)+,d0-d6/a1/a3-a6
        movem.l d0-d6/a1/a3-a6,(a2)
        lea     48(a2),a2
        movem.l (a0)+,d0-d6/a1/a3-a6
        movem.l d0-d6/a1/a3-a6,(a2)
        lea     48(a2),a2
        movem.l (a0)+,d0-d6/a1/a3-a6
        movem.l d0-d6/a1/a3-a6,(a2)
        lea     48(a2),a2
        movem.l (a0)+,d0-d6/a1/a3-a6
        movem.l d0-d6/a1/a3-a6,(a2)
        lea     48(a2),a2
        movem.l (a0)+,d0-d6/a1/a3-a6
        movem.l d0-d6/a1/a3-a6,(a2)
        lea     48(a2),a2
        movem.l (a0)+,d0-d6/a1/a3-a6
        movem.l d0-d6/a1/a3-a6,(a2)
        lea     48(a2),a2
spcx:   move.w  (a0)+,d0                ; (SPFN - fine) * SPFU, from mid-stream
        jmp     spfh(pc,d0.w)
spfh:
        move.l  (a0)+,(a2)+
        move.l  (a0)+,(a2)+
        move.l  (a0)+,(a2)+
        move.l  (a0)+,(a2)+
        move.l  (a0)+,(a2)+
        move.l  (a0)+,(a2)+
        move.l  (a0)+,(a2)+
        move.l  (a0)+,(a2)+
        move.l  (a0)+,(a2)+
        move.l  (a0)+,(a2)+
        move.l  (a0)+,(a2)+
        dbra    d7,spspan
        move.l  (sp)+,a1
spnone: rts

; ------------------------------------------------------------- one frame
; in:  a0 = payload, a1 = packed mode header
; out: a0 = one past the last payload byte consumed
decode_frame:
        lea     CB1,a2
        lea     CB4,a3
        lea     DST0,a6
rowloop:
        move.l  a6,a4
        lea     ROWLEN(a6),a5
byteloop:
        tst.b   (a1)                    ; four SKIPs in one test
        beq     allskip
        BLOCK   6
        BLOCK   4
        BLOCK   2
        BLOCK   0
        addq.l  #1,a1
        cmpa.l  a5,a4
        bne     byteloop
        bra     rowdone
allskip:
        addq.l  #1,a1
        lea     32(a4),a4
        cmpa.l  a5,a4
        bne     byteloop
rowdone:
        lea     BROW(a6),a6
        cmpa.l  #DSTE,a6
        bne     rowloop
        rts