; X86_64 mpn_diveby (B-1)/f
;
;  Copyright 2008 Jason Moxham and Brian Gladman
;
;  This file is part of the MPIR Library.
;  The MPIR Library is free software; you can redistribute it and/or modify
;  it under the terms of the GNU Lesser General Public License as published
;  by the Free Software Foundation; either version 2.1 of the License, or (at
;  your option) any later veSRCon.
;  The MPIR Library is distributed in the hope that it will be useful, but
;  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
;  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public
;  License for more details.
;  You should have received a copy of the GNU Lesser General Public License
;  along with the MPIR Library; see the file COPYING.LIB.  If not, write
;  to the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
;  Boston, MA 02110-1301, USA.
;
;  Calling interface:
;
; mp_limb_t mpn_divexact_byBm1of (
;     mp_ptr dst,                rcx
;     mp_srcptr src,             rdx
;     mp_size_t len,              r8
;     mp_limb_t f                 r9
;     mp_limb_t bm1of    [rsp+ 0x28] = (B - 1) / f
; )
;
;     dst[] = src[] / ((B - 1) / f)
;
; This is an SEH leaf function

%include "yasm_mac.inc"

%define CARRY_OUT

    BITS 64

    LEAF_PROC mpn_divexact_byBm1of
    movsxd  rax, r8d
    mov     r8, [rsp+0x28]
%ifdef CARRY_OUT
    mov     [rsp+0x20], r9  ; this needs changing if there is a carry in
%endif
    lea     r10, [rdx+rax*8-24]
    lea     r11, [rcx+rax*8-24]
    mov     ecx, 3

%ifdef CARRY_IN             ; r9 is the carry in
    imul    r9, r8          ; this is needed if we have non-zero carry in
%else
    mov     r9, 0
%endif

    sub     rcx, rax
    jnc     .2

    xalign  16
.1: mov     rax, [r10+rcx*8]
    mul     r8
    sub     r9, rax
    mov     [r11+rcx*8], r9
    sbb     r9, rdx
    mov     rax, [r10+rcx*8+8]
    mul     r8
    sub     r9, rax
    mov     [r11+rcx*8+8], r9
    sbb     r9, rdx
    mov     rax, [r10+rcx*8+16]
    mul     r8
    sub     r9, rax
    mov     [r11+rcx*8+16], r9
    sbb     r9, rdx
    mov     rax, [r10+rcx*8+24]
    mul     r8
    sub     r9, rax
    mov     [r11+rcx*8+24], r9
    sbb     r9, rdx
    add     rcx, 4
    jnc     .1
.2: test    rcx, 2
    jnz     .3
    mov     rax, [r10+rcx*8]
    mul     r8
    sub     r9, rax
    mov     [r11+rcx*8], r9
    sbb     r9, rdx
    mov     rax, [r10+rcx*8+8]
    mul     r8
    sub     r9, rax
    mov     [r11+rcx*8+8], r9
    sbb     r9, rdx
    add     rcx, 2
.3: test    rcx, 1
    jnz     .4
    mov     rax, [r10+rcx*8]
    mul     r8
    sub     r9, rax
    mov     [r11+rcx*8], r9
    sbb     r9, rdx
.4: 
%ifdef CARRY_OUT
    imul    r9, [rsp+0x20]
%endif
    mov     rax, r9
    neg     rax
    ret

    end