| 1 | ; $Id: remainder.asm 96218 2022-08-15 12:33:57Z vboxsync $
|
|---|
| 2 | ;; @file
|
|---|
| 3 | ; IPRT - No-CRT remainder - AMD64 & X86.
|
|---|
| 4 | ;
|
|---|
| 5 |
|
|---|
| 6 | ;
|
|---|
| 7 | ; Copyright (C) 2006-2022 Oracle Corporation
|
|---|
| 8 | ;
|
|---|
| 9 | ; This file is part of VirtualBox Open Source Edition (OSE), as
|
|---|
| 10 | ; available from http://www.virtualbox.org. This file is free software;
|
|---|
| 11 | ; you can redistribute it and/or modify it under the terms of the GNU
|
|---|
| 12 | ; General Public License (GPL) as published by the Free Software
|
|---|
| 13 | ; Foundation, in version 2 as it comes in the "COPYING" file of the
|
|---|
| 14 | ; VirtualBox OSE distribution. VirtualBox OSE is distributed in the
|
|---|
| 15 | ; hope that it will be useful, but WITHOUT ANY WARRANTY of any kind.
|
|---|
| 16 | ;
|
|---|
| 17 | ; The contents of this file may alternatively be used under the terms
|
|---|
| 18 | ; of the Common Development and Distribution License Version 1.0
|
|---|
| 19 | ; (CDDL) only, as it comes in the "COPYING.CDDL" file of the
|
|---|
| 20 | ; VirtualBox OSE distribution, in which case the provisions of the
|
|---|
| 21 | ; CDDL are applicable instead of those of the GPL.
|
|---|
| 22 | ;
|
|---|
| 23 | ; You may elect to license modified versions of this file under the
|
|---|
| 24 | ; terms and conditions of either the GPL or the CDDL or both.
|
|---|
| 25 | ;
|
|---|
| 26 |
|
|---|
| 27 |
|
|---|
| 28 | %define RT_ASM_WITH_SEH64
|
|---|
| 29 | %include "iprt/asmdefs.mac"
|
|---|
| 30 | %include "iprt/x86.mac"
|
|---|
| 31 |
|
|---|
| 32 |
|
|---|
| 33 | BEGINCODE
|
|---|
| 34 |
|
|---|
| 35 | ;;
|
|---|
| 36 | ; See SUS.
|
|---|
| 37 | ; @returns st(0) / xmm0
|
|---|
| 38 | ; @param rd1 [ebp + 8h] xmm0 Dividend.
|
|---|
| 39 | ; @param rd2 [ebp + 10h] xmm1 Divisor.
|
|---|
| 40 | RT_NOCRT_BEGINPROC remainder
|
|---|
| 41 | push xBP
|
|---|
| 42 | SEH64_PUSH_xBP
|
|---|
| 43 | mov xBP, xSP
|
|---|
| 44 | SEH64_SET_FRAME_xBP 0
|
|---|
| 45 | %ifdef RT_ARCH_AMD64
|
|---|
| 46 | sub xSP, 20h
|
|---|
| 47 | SEH64_ALLOCATE_STACK 20h
|
|---|
| 48 | %endif
|
|---|
| 49 | SEH64_END_PROLOGUE
|
|---|
| 50 |
|
|---|
| 51 | ;
|
|---|
| 52 | ; Load the dividend into st0 and divisor into st1.
|
|---|
| 53 | ;
|
|---|
| 54 | %ifdef RT_ARCH_AMD64
|
|---|
| 55 | movsd [xBP - 20h], xmm1
|
|---|
| 56 | movsd [xBP - 10h], xmm0
|
|---|
| 57 | fld qword [xBP - 20h]
|
|---|
| 58 | fld qword [xBP - 10h]
|
|---|
| 59 | %else
|
|---|
| 60 | fld qword [ebp + 10h]
|
|---|
| 61 | fld qword [ebp + 08h]
|
|---|
| 62 | %endif
|
|---|
| 63 |
|
|---|
| 64 | ;
|
|---|
| 65 | ; The fprem1 only does between 32 and 64 rounds, so we have to loop
|
|---|
| 66 | ; here till we've got a final result. We count down in ECX to
|
|---|
| 67 | ; avoid getting stuck here...
|
|---|
| 68 | ;
|
|---|
| 69 | mov ecx, 2048 / 32 + 4
|
|---|
| 70 | .again:
|
|---|
| 71 | fprem1
|
|---|
| 72 | fstsw ax
|
|---|
| 73 | test ah, (X86_FSW_C2 >> 8)
|
|---|
| 74 | jz .done
|
|---|
| 75 | dec cx
|
|---|
| 76 | jnz .again
|
|---|
| 77 | %ifdef RT_STRICT
|
|---|
| 78 | int3
|
|---|
| 79 | %endif
|
|---|
| 80 |
|
|---|
| 81 | ;
|
|---|
| 82 | ; Return the result.
|
|---|
| 83 | ;
|
|---|
| 84 | .done:
|
|---|
| 85 | fstp st1
|
|---|
| 86 | %ifdef RT_ARCH_AMD64
|
|---|
| 87 | fstp qword [rsp]
|
|---|
| 88 | movsd xmm0, [rsp]
|
|---|
| 89 | %endif
|
|---|
| 90 |
|
|---|
| 91 | leave
|
|---|
| 92 | ret
|
|---|
| 93 | ENDPROC RT_NOCRT(remainder)
|
|---|
| 94 |
|
|---|
