mult1.a

; mult1.a
; from codebase64: https://www.codebase64.org/doku.php?id=base:16bit_multiplication_32-bit_product
; also from '6502 Software Design' by Leo J Scanlon (1980): https://archive.org/details/6502softwaredesi0000scan/page/124/mode/1up
;
; 16 bit x 16 bit unsigned multiply, 32 bit result
; Average cycles: 751
; 38 bytes


multiplier      = $02               ; 2 bytes
multiplicand    = $04               ; 2 bytes
product         = $06               ; 4 bytes

* = $0200

; product = multiplier * multiplicand
mult
    lda #0
    sta product+2           ; clear upper bits of product
    sta product+3
    ldx #16                 ; set binary count to 16
shift_r
    lsr multiplier+1        ; divide multiplier by 2
    ror multiplier
    bcc rotate_r
    lda product+2           ; get upper half of product and add multiplicand
    clc
    adc multiplicand
    sta product+2
    lda product+3
    adc multiplicand+1
rotate_r
    ror                     ; rotate partial product
    sta product+3
    ror product+2
    ror product+1
    ror product
    dex
    bne shift_r
    rts