; stMarshalIigs.s - Space Taxi's stSimMarshal for the Apple IIgs.
;
; GAS syntax for the llvm-mos w65816 toolchain (see src/iigs/peislam.s
; for the conventions). The C version copies eight sprites' shadow
; registers into the displayed frame through far pointers, which the
; w65816 backend turns into ~5000 cycles of pointer re-materialisation
; per tick (5% of a ride frame). This is the same copy as straight-line
; [dp],y moves: ~700 cycles.
;
; void stSimMarshalIigs(const StMarshalArgsT *args)
;   args (A = low word, X = bank) points at { spr, frame, multi }:
;     +0  const StSpriteT *spr    (32-bit: low word, bank word)
;     +4  StFrameT        *frame
;     +8  uint8_t          multi
;   StSpriteT (6 bytes): col, msb, row, enable, ptr, color.
;   StFrameT: x[8] (u16, +0), y[8] (+16), ptr[8] (+24), color[8] (+32),
;             enableMask (+40), multiMask (+41).
;   stSim.c checks these layouts at compile time.
;
; Every store runs with M=16 and writes two bytes: the byte after each
; single-byte field gets a junk high byte that the NEXT store repairs,
; so the blocks run in order x, y, ptr, color and finish with the
; enable/multi word. The last colour store's junk lands on enableMask,
; which the final word overwrites.
;
; Direct-page $E0-$EF are the compiler's own per-function scratch
; (re-set before every use, never live across a call); $C0 is left alone.
	.section .text.stSimMarshalIigs,"ax"
	.globl stSimMarshalIigs
stSimMarshalIigs:
	php
	rep #0x30
	.a16
	.i16
	sta 0xe0            ; args low
	txa
	sta 0xe2            ; args bank
	ldy #0
	lda [0xe0],y
	sta 0xe4            ; spr low
	ldy #2
	lda [0xe0],y
	sta 0xe6            ; spr bank
	ldy #4
	lda [0xe0],y
	sta 0xe8            ; frame low
	ldy #6
	lda [0xe0],y
	sta 0xea            ; frame bank
	ldy #8
	lda [0xe0],y
	and #0xff
	sta 0xec            ; multi
	stz 0xee            ; enable mask accumulator
; sprite 0: x = (msb ? 0x100 : 0) | col; enable bit
	ldy #0
	lda [0xe4],y        ; col | msb<<8
	sta 0xf0
	and #0xff00
	beq mX0clr
	lda 0xf0
	and #0x00ff
	ora #0x0100
	bra mX0st
mX0clr:
	lda 0xf0
	and #0x00ff
mX0st:
	ldy #0
	sta [0xe8],y
	ldy #3
	lda [0xe4],y        ; enable | ptr<<8
	and #0xff
	beq mE0off
	lda 0xee
	ora #1
	sta 0xee
mE0off:
; sprite 1: x = (msb ? 0x100 : 0) | col; enable bit
	ldy #6
	lda [0xe4],y        ; col | msb<<8
	sta 0xf0
	and #0xff00
	beq mX1clr
	lda 0xf0
	and #0x00ff
	ora #0x0100
	bra mX1st
mX1clr:
	lda 0xf0
	and #0x00ff
mX1st:
	ldy #2
	sta [0xe8],y
	ldy #9
	lda [0xe4],y        ; enable | ptr<<8
	and #0xff
	beq mE1off
	lda 0xee
	ora #2
	sta 0xee
mE1off:
; sprite 2: x = (msb ? 0x100 : 0) | col; enable bit
	ldy #12
	lda [0xe4],y        ; col | msb<<8
	sta 0xf0
	and #0xff00
	beq mX2clr
	lda 0xf0
	and #0x00ff
	ora #0x0100
	bra mX2st
mX2clr:
	lda 0xf0
	and #0x00ff
mX2st:
	ldy #4
	sta [0xe8],y
	ldy #15
	lda [0xe4],y        ; enable | ptr<<8
	and #0xff
	beq mE2off
	lda 0xee
	ora #4
	sta 0xee
mE2off:
; sprite 3: x = (msb ? 0x100 : 0) | col; enable bit
	ldy #18
	lda [0xe4],y        ; col | msb<<8
	sta 0xf0
	and #0xff00
	beq mX3clr
	lda 0xf0
	and #0x00ff
	ora #0x0100
	bra mX3st
mX3clr:
	lda 0xf0
	and #0x00ff
mX3st:
	ldy #6
	sta [0xe8],y
	ldy #21
	lda [0xe4],y        ; enable | ptr<<8
	and #0xff
	beq mE3off
	lda 0xee
	ora #8
	sta 0xee
mE3off:
; sprite 4: x = (msb ? 0x100 : 0) | col; enable bit
	ldy #24
	lda [0xe4],y        ; col | msb<<8
	sta 0xf0
	and #0xff00
	beq mX4clr
	lda 0xf0
	and #0x00ff
	ora #0x0100
	bra mX4st
mX4clr:
	lda 0xf0
	and #0x00ff
mX4st:
	ldy #8
	sta [0xe8],y
	ldy #27
	lda [0xe4],y        ; enable | ptr<<8
	and #0xff
	beq mE4off
	lda 0xee
	ora #16
	sta 0xee
mE4off:
; sprite 5: x = (msb ? 0x100 : 0) | col; enable bit
	ldy #30
	lda [0xe4],y        ; col | msb<<8
	sta 0xf0
	and #0xff00
	beq mX5clr
	lda 0xf0
	and #0x00ff
	ora #0x0100
	bra mX5st
mX5clr:
	lda 0xf0
	and #0x00ff
mX5st:
	ldy #10
	sta [0xe8],y
	ldy #33
	lda [0xe4],y        ; enable | ptr<<8
	and #0xff
	beq mE5off
	lda 0xee
	ora #32
	sta 0xee
mE5off:
; sprite 6: x = (msb ? 0x100 : 0) | col; enable bit
	ldy #36
	lda [0xe4],y        ; col | msb<<8
	sta 0xf0
	and #0xff00
	beq mX6clr
	lda 0xf0
	and #0x00ff
	ora #0x0100
	bra mX6st
mX6clr:
	lda 0xf0
	and #0x00ff
mX6st:
	ldy #12
	sta [0xe8],y
	ldy #39
	lda [0xe4],y        ; enable | ptr<<8
	and #0xff
	beq mE6off
	lda 0xee
	ora #64
	sta 0xee
mE6off:
; sprite 7: x = (msb ? 0x100 : 0) | col; enable bit
	ldy #42
	lda [0xe4],y        ; col | msb<<8
	sta 0xf0
	and #0xff00
	beq mX7clr
	lda 0xf0
	and #0x00ff
	ora #0x0100
	bra mX7st
mX7clr:
	lda 0xf0
	and #0x00ff
mX7st:
	ldy #14
	sta [0xe8],y
	ldy #45
	lda [0xe4],y        ; enable | ptr<<8
	and #0xff
	beq mE7off
	lda 0xee
	ora #128
	sta 0xee
mE7off:
; y[] block (16-bit stores; the junk high byte is repaired by the next store)
	ldy #2
	lda [0xe4],y
	ldy #16
	sta [0xe8],y
	ldy #8
	lda [0xe4],y
	ldy #17
	sta [0xe8],y
	ldy #14
	lda [0xe4],y
	ldy #18
	sta [0xe8],y
	ldy #20
	lda [0xe4],y
	ldy #19
	sta [0xe8],y
	ldy #26
	lda [0xe4],y
	ldy #20
	sta [0xe8],y
	ldy #32
	lda [0xe4],y
	ldy #21
	sta [0xe8],y
	ldy #38
	lda [0xe4],y
	ldy #22
	sta [0xe8],y
	ldy #44
	lda [0xe4],y
	ldy #23
	sta [0xe8],y
; ptr[] block (16-bit stores; the junk high byte is repaired by the next store)
	ldy #4
	lda [0xe4],y
	ldy #24
	sta [0xe8],y
	ldy #10
	lda [0xe4],y
	ldy #25
	sta [0xe8],y
	ldy #16
	lda [0xe4],y
	ldy #26
	sta [0xe8],y
	ldy #22
	lda [0xe4],y
	ldy #27
	sta [0xe8],y
	ldy #28
	lda [0xe4],y
	ldy #28
	sta [0xe8],y
	ldy #34
	lda [0xe4],y
	ldy #29
	sta [0xe8],y
	ldy #40
	lda [0xe4],y
	ldy #30
	sta [0xe8],y
	ldy #46
	lda [0xe4],y
	ldy #31
	sta [0xe8],y
; color[] block (16-bit stores; the junk high byte is repaired by the next store)
	ldy #5
	lda [0xe4],y
	ldy #32
	sta [0xe8],y
	ldy #11
	lda [0xe4],y
	ldy #33
	sta [0xe8],y
	ldy #17
	lda [0xe4],y
	ldy #34
	sta [0xe8],y
	ldy #23
	lda [0xe4],y
	ldy #35
	sta [0xe8],y
	ldy #29
	lda [0xe4],y
	ldy #36
	sta [0xe8],y
	ldy #35
	lda [0xe4],y
	ldy #37
	sta [0xe8],y
	ldy #41
	lda [0xe4],y
	ldy #38
	sta [0xe8],y
	ldy #47
	lda [0xe4],y
	ldy #39
	sta [0xe8],y
; enableMask | multiMask<<8
	lda 0xec
	xba
	and #0xff00
	ora 0xee
	ldy #40
	sta [0xe8],y
	plp
	rtl