Subversion Repositories zipcpu

;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;
; Filename:     divu.S
;
; Project:      Zip CPU -- a small, lightweight, RISC CPU soft core
;
; Purpose:      Zip assembly file for running doing an unsigned divide.
;               This routine is also called by the signed divide.
;
; Creator:      Dan Gisselquist, Ph.D.
;               Gisselquist Technology, LLC
;
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;
; Copyright (C) 2015, Gisselquist Technology, LLC
;
; This program is free software (firmware): you can redistribute it and/or
; modify it under the terms of  the GNU General Public License as published
; by the Free Software Foundation, either version 3 of the License, or (at
; your option) any later version.
;
; This program is distributed in the hope that it will be useful, but WITHOUT
; ANY WARRANTY; without even the implied warranty of MERCHANTIBILITY or
; FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
; for more details.
;
; License:      GPL, v3, as defined and found on www.gnu.org,
;               http://www.gnu.org/licenses/gpl.html
;
;
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;
;
;
lib_divu:       ; Given R0,R1, computer R0 = R0/R1 and R1 = R0%R1
        TST     -1,R1
        ; BNZ   divu_valid_divide
        CLR.Z   R0              ; Should be a divide by zero error / trap
        JMP.Z   R2
divu_valid_divide:
        SUB     2,SP
        STO     R2,(SP)
        STO     R3,1(SP)
        ;
        LDI     1,R2    ; Here's where we record the bit we are working on
        CLR     R3      ; Here's where we build our result
; Our original loop rejoin point, before a touch of unrolling
        CMP     R1,R0
        BRC     divu_prep_next_bit
        TST     -1,R1
        BLT     divu_top_bit_set
divu_rotate_up_r1:
        LSL     1,R2
        LSL     1,R1
/*
        CMP     R1,R0
        BRC     divu_prep_next_bit
        TST     -1,R1
        BGT     divu_rotate_up_r1
*/
        BLT     divu_top_bit_set
        CMP     R1,R0
        BRC     divu_prep_next_bit
        ;
        LSL     1,R2
        LSL     1,R1
        BLT     divu_top_bit_set
        CMP     R1,R0
        BRC     divu_prep_next_bit
        ;
        LSL     1,R2
        LSL     1,R1
        BLT     divu_top_bit_set
        CMP     R1,R0
        BRC     divu_prep_next_bit
        ;
        LSL     1,R2
        LSL     1,R1
        BLT     divu_top_bit_set
        CMP     R1,R0
        BRC     divu_prep_next_bit
        BRA     divu_rotate_up_r1

divu_top_bit_set:
        CMP     R1,R0
        BRC     divu_prep_next_bit
        SUB     R1,R0
        OR      R2,R3
divu_prep_next_bit:
        LSR     1,R1
        LSR     1,R2
        BZ      divu_record_result
        ;
divu_next_loop:
        CMP     R1,R0           ;
        SUB.GE  R1,R0           ; We also switch to signed arithmetic, since
        OR.GE   R2,R3           ; after the first bit, we are signed
        LSR     1,R1
        LSR     1,R2
        BZ      divu_record_result
        ;
        CMP     R1,R0
        SUB.GE  R1,R0
        OR.GE   R2,R3
        LSR     1,R1
        LSR     1,R2
        BZ      divu_record_result
        ;
        CMP     R1,R0
        SUB.GE  R1,R0
        OR.GE   R2,R3
        LSR     1,R1
        LSR     1,R2
        BZ      divu_record_result
        ;
        CMP     R1,R0
        SUB.GE  R1,R0
        OR.GE   R2,R3
        LSR     1,R1
        LSR     1,R2
        BNZ     divu_next_loop

divu_record_result:
        MOV     R0,R1
        MOV     R3,R0
        LOD     (SP),R2
        LOD     1(SP),R3
        ADD     2,SP
        JMP     R2