; program: flanger-16b-sine.asm
; UID = 000045 - unique id to eliminate conflicts between variables
; 16b address space
; mono data in on left channel, mono data out on both channels
; pot (MOD1) controls lfo frequency
; rotary encoder (MOD2) controls lfo depth and offset delay
; pushbutton (on MOD2) controls wether depth or offset is being modded
; offset delay variable from 90us to 23ms

; program overview
;
; data is read in from the codec and stored to sram.  data is read out of
; sram at a variable delay set by an lfo and an offset.  the lfo is
; generated from a 16b/512s half sinewave lookup table.  this is incremented
; with a 24b number to get very low frequencies.  the lfo rate is set via
; the adc, which is oversampled 256 times and deadbanded to get rid of
; glitches.  the lfo depth is created by multiplying the lfo signal with
; an 8b depth value, which is set via the rotary encoder.  the offset delay
; is an 8b value, which is also set with the rotary encoder, with the
; pushbutton selecting which function is currently active.

; register usage - may be redefined in other sections
;
; r0  multiply result lsb
; r1  multiply result msb
; r2  accumulation lsb
; r3  accumulation mlb
; r4  right/left lsb out/accumulation mhb
; r5  right/left msb out/accumulation msb
; r6  pushbutton state register
; r7  
; r8  adc accumulator fractional byte
; r9  adc accumulator lsb
; r10 adc accumulator msb
; r11 rotary encoder counter
; r12 lfo rate lsb
; r13 lfo rate msb
; r14 null register
; r15 switch sample counter
; r16 temporary swap register
; r17 temporary swap register
; r18 sine wave buffer/multiply msb
; r19 sine wave buffer/multiply msb
; r20 multiply swap register
; r21 multiply swap register
; r22 sinetable lookup address lsb
; r23 sinetable lookup address mlb
; r24 write address lsb
; r25 write address msb
; r26 sinetable lookup address mhb
; r27 sinetable lookup address msb
; r28 delay offset
; r29 lfo depth
; r30 jump location for interrupt lsb
; r31 jump location for interrupt msb
; t   rotary encoder edge detect indicator

; program starts here first time
; intialize registers
ldi r30,$05 ; increment z pointer to new jump location
clr r14 ; clear null register
ldi r28,$09 ; initialize delay offset
ldi r29,$06 ; intiialize lfo depth
reti ; finish with initialization and wait for next interrupt

; program starts here every time but first
; initiate data transfer to codec
sbi portb,portb0 ; toggle slave select pin
out spdr,r5 ; send out left channel msb
cbi portb,portb0

adiw r25:r24,$01 ; increment write address

wait1_000045: ; check if byte has been sent

in r17,spsr
sbrs r17,spif
rjmp wait1_000045
in r19,spdr ; recieve in left channel msb
out spdr,r4 ; send out left channel lsb

wait2_000045: ; check if byte has been sent

in r17,spsr
sbrs r17,spif
rjmp wait2_000045
in r18,spdr ; recieve in left channel lsb
out spdr,r5 ; send out right channel msb

;write left channel data to sram
out portd,r24 ; set address
sts porth,r25
out portg,r14 ; pull ce low,we low,and set high bits of address
ldi r17,$ff
out ddra,r17 ; set porta as output for data write
out ddrc,r17 ; set portc as output for data write
out porta,r18 ; set data
out portc,r19
sbi portg,portg2 ; pull we high to write
out ddra,r14 ; set porta as input for data lines
out ddrc,r14 ; set portc as input for data lines

wait3_000045: ; check if byte has been sent

in r17,spsr
sbrs r17,spif
rjmp wait3_000045
in r17,spdr ; recieve in right channel msb
out spdr,r4 ; send out right channel lsb

wait4_000045: ; check if byte has been sent

in r17,spsr
sbrs r17,spif
rjmp wait4_000045
in r17,spdr ; recieve in right channel lsb

; vco generation
movw r17:r16,r31:r30 ; store z register
;get sample 1
add r22,r12 ; increment sinetable address
adc r23,r13
adc r26,r14 ; r14 is cleared above
adc r27,r14
movw r31:r30,r27:r26 ; move to z register for data fetch
lsl r30 ; adjust pointer for 16b fetch
rol r31
andi r31,$03 ; limit value to 10b (512 samples x 2 bytes)
ori r31,$48 ; set to memory address location where table is stored
lpm r18,z+ ; get sine value lsb, increment z register
lpm r19,z ; get sine value msb
sbrc r27,$01 ; flip sign for half of the values
rjmp interpolate_000045
neg r18
adc r19,r14 ; r14 is cleared above
neg r19

interpolate_000045: ; multiply sample 1 by distance

movw r21:r20,r23:r22 ; get distance from sample 1
com r20 ; invert distance
com r21
mulsu r19,r21 ; (signed)Ah * (unsigned)Bh - multiply high bytes
movw r5:r4,r1:r0 ; store high bytes result for later
mul	r18,r20	; (unsigned)Al * (unsigned)Bl ; multiply low bytes
movw r3:r2,r1:r0 ; store low byets for later
mulsu r19,r20 ; (signed)Ah * (unsigned)Bl - multiply middle bytes
sbc	r5,r14 ; r14 is cleared above - subtract sign bit
add	r3,r0 ; accumulate result
adc	r4,r1
adc	r5,r14 ; r14 is cleared above
mul r21,r18 ; (unsigned)Bh * (unsigned)Al - multiply middle bytes
add	r3,r0 ; accumulate result
adc	r4,r1
adc	r5,r14 ; r14 is cleared above

;get sample 2
adiw r27:r26,$01 ; set to next sample
movw r31:r30,r27:r26 ; move to z register for data fetch
lsl r30 ; adjust pointer for 16b fetch
rol r31
andi r31,$03 ; limit value to 10b (512 samples x 2 bytes)
ori r31,$48 ; set to memory address location where table is stored
lpm r18,z+ ; get sine value lsb, increment z register
lpm r19,z ; get sine value msb
sbrc r27,$01 ; flip sign for half of the values
rjmp interpolate1_000045
neg r18
adc r19,r14 ; r14 is cleared above
neg r19

interpolate1_000045: ; multiply sample 2 by distance

sbiw r27:r26,$01 ; reset address
movw r31:r30,r17:r16 ; restore z register
mulsu r19,r23 ; (signed)Ah * (unsigned)Bh - multiply high bytes
add r4,r0 ; accumulate result
adc r5,r1
mul	r18,r22	; (unsigned)Al * (unsigned)Bl ; multiply low bytes
add r2,r0 ; accumulate result
adc r3,r1
adc r4,r14 ; r14 is cleared above
adc r5,r14
mulsu r19,r22 ; (signed)Ah * (unsigned)Bl - multiply middle bytes
sbc	r5,r14 ; r14 is cleared above - subtract sign bit
add	r3,r0 ; accumulate result
adc	r4,r1
adc	r5,r14 ; r14 is cleared above
mul r23,r18 ; (unsigned)Bh * (unsigned)Al - multiply middle bytes
add	r3,r0 ; accumulate result
adc	r4,r1
adc	r5,r14 ; r14 is cleared above

;set lfo depth - 8b value
ldi r16,$80 ; convert lfo to unsigned number
add r5,r16
movw r19:r18,r5:r4 ; move lfo signal to multiply register
mov r21,r29 ; move lfo depth to multiply register
mul r19,r21 ; (unsigned)ah * (unsigned)b
movw r5:r4,r1:r0
mul r21,r18 ; (unsigned)b * (unsigned)al
add	r4,r1
adc	r5,r14 ; r14 is cleared above

;add lfo to delay
movw r17:r16,r25:r24 ; move current location to read address
mov r20,r28 ; move delay offset to temporary register
clr r21 ; clear temporary high byte
lsl r20 ; multiply delay time by 4
rol r21
lsl r20
rol r21
sub r16,r20 ; remove delay offset
sbc r17,r21
sec ; set the carry bit so all values are reduced by 1 lsb
sbc r16,r5 ; remove lfo time
sbc r17,r14 ; r14 is cleared above

;get left channel sample 1 from sram
out portd,r16 ; set address
sts porth,r17
nop ; wait setup period of two cycles
nop
in r18,pina ; get data
in r19,pinc ; get data

;multiply sample 1 by distance
mov r20,r4 ; get distance from sample 1
mulsu r19,r20 ; (signed)ah * b
movw r5:r4,r1:r0
mul r18,r20 ; al * b
add r4,r1
adc r5,r14 ; r14 is cleared above
mov r3,r0

;get left channel sample 2 from sram
subi r16,$ff ; set to next sample
sbci r17,$ff ; done this way because there is no addi or adci
out portd,r16 ; set address
sts porth,r17
nop ; wait setup period of two cycles
nop
in r18,pina ; get data
in r19,pinc ; get data

;multiply sample 2 by distance
com r20 ; get distance to sample 2
mulsu r19,r20 ; (signed)ah * b
add r4,r0 ; accumulate result
adc r5,r1
mul r18,r20 ; al * b
add r3,r0 ; accumulate result
add r4,r1
adc r5,r14 ; r14 is cleared above

;check rotary encoder and adjust lfo depth
; although rotary encoder is externally debounced, it is done here again.
; pin1 is sampled on a transition from high to low on pin0.  if pin1 is
; high, a left turn occured, if pin1 is low, a right turn occured.
dec r11 ; check if time to sample rotary encoder
brne adcsample_000045 ; continue if not
ldi r17,$40 ; adjust sample frequency to catch all rising edges (1.5ms)
mov r11,r17
lds r17,pinj ; get encoder/pushbutton data
mov r16,r17 ; store pushbutton data to temporary register
eor r16,r6 ; check if pushbutton changed value
and r16,r17 ; check if rising edge
sbrc r16,$02 ; continue if not
rjmp pushbutton_000045 ; go to pushbutton routine if pressed
ldi r20,$80 ; mask off the high bit of the pushbutton state register
and r6,r20 ; pinj7 should be 0, as there is no i/o attached to it
or r6,r17 ; store pushbutton data for next sample comparison
sbrs r17,$02 ; check if pushbutton pressed
rjmp adcsample_000045 ; do not allow any parameter change while button pressed
sbrs r17,$00 ; check if pin0 is low
rjmp edge_000045 ; check if pin0 was low on previous sample
clt ;  clear state register if back high
rjmp adcsample_000045 ; finish off

edge_000045: ; check for falling edge

brts adcsample_000045 ; do nothing if edge was already detected
set ; set t register to indicate edge detected
ldi r21,$01 ; prepare for addition or subtraction
sbrs r6,$07 ; check which function is being modded
rjmp lfo_000045 ; do lfo function
sbrs r17,$01 ; check if pin1 is high
rjmp increment_000045 ; increment desired delay if right rotation
dec r28 ; decrement delay register else
cp r28,r21 ; r21 set to $01 above
brsh adcsample_000045 ; continue if not
mov r28,r16 ; set delay to min
rjmp adcsample_000045 ; finish off

increment_000045: ; increment desired delay register

add r28,r21 ; increment delay register
brcc adcsample_000045 ; check if overflow occured
ser r28 ; set delay to max

adcsample_000045: ; sample adc for lfo rate

lds r17,adcsra ; get adc control register
sbrs r17,adif ; check if adc conversion is complete
rjmp done_000045 ; skip adc sampling
lds r16,adcl ; get low byte adc value
lds r17,adch ; get high byte adc value
add r8,r16 ; accumulate adc samples
adc r9,r17
adc r10,r14 ; r14 is cleared above
ldi r17,$f7
sts adcsra,r17 ; clear interrupt flag
dec r15 ; countdown adc sample clock
brne done_000045 ; get delay time if its been long enough

deadband_000045: ; set the low value of the delay

lsr r10 ; divide adc value by 16
ror r9
ror r8
lsr r10
ror r9
ror r8
lsr r9 ; r10 is now empty
ror r8
lsr r9
ror r8
movw r17:r16,r9:r8 ; move adc sample to temporary register
ldi r21,$80 ; add in offset of min lfo rate ($0080)
add r16,r21
adc r17,r14 ; r14 is cleared above
sub r16,r12 ; find difference between adc sample and current lfo rate
sbc r17,r13
brsh check_000045 ; check for deadband if positive
neg r16 ; invert if negative
adc r17,r14 ; r14 is cleared above
neg r17

check_000045: ; check if difference is greater than deadband

cpi r16,$10 ; check if difference is less than 1 adc lsb
cpc r17,r14 ; r14 cleared above
brlo empty_000045 ; do nothing if less than 1 adc lsb
movw r13:r12,r9:r8 ; move adc sample to lfo rate register
add r12,r21 ; add in offset of min lfo rate ($0080)
adc r13,r14 ; r14 is cleared above

empty_000045: ; empty accumulation registers and finish off

clr r8 ; empty accumulation registers
clr r9
clr r10

switchsample_000045: ; check rotary switch

lds r16,pinj ; get switch data
andi r16,$78 ; mask off rotary switch
lsr r16 ; adjust switch position to program memory location
lsr r16
ldi r17,$02
add r16,r17
cpse r16,r31 ; check if location has changed
clr r30 ; reset jump register to intial state
mov r31,r16

done_000045:

reti ; return to waiting

lfo_000045: ; modify lfo depth parameter

sbrs r17,$01 ; check if pin1 is high
rjmp increment1_000045 ; increment desired delay if right rotation
sub r29,r21 ; decrement lfo depth register else
brcc adcsample_000045 ; check if underflow
clr r29 ; set depth to min
rjmp adcsample_000045 ; finish off

increment1_000045: ; increment desired delay register

add r29,r21 ; increment lfo depth register
brcc adcsample_000045 ; check if overflow occured
ser r29 ; set depth to max
rjmp adcsample_000045 ; finish off

pushbutton_000045: ; edge detect

ldi r20,$80 ; toggle msb to inidicate function change
eor r6,r20
and r6,r20 ; mask off the high bit
or r6,r17 ; store pushbutton data for next sample comparison
rjmp adcsample_000045 ; finish off

