| 1 | ; $Id: bs3-wc32-U8M.asm 93115 2022-01-01 11:31:46Z vboxsync $
|
|---|
| 2 | ;; @file
|
|---|
| 3 | ; BS3Kit - 32-bit Watcom C/C++, 64-bit integer multiplication.
|
|---|
| 4 | ;
|
|---|
| 5 |
|
|---|
| 6 | ;
|
|---|
| 7 | ; Copyright (C) 2007-2022 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 | %include "bs3kit-template-header.mac"
|
|---|
| 28 |
|
|---|
| 29 |
|
|---|
| 30 | ;;
|
|---|
| 31 | ; 64-bit unsigned & signed integer multiplication.
|
|---|
| 32 | ;
|
|---|
| 33 | ; @returns EDX:EAX as the product.
|
|---|
| 34 | ; @param EDX:EAX Factor 1 - edx=F1H, eax=F1L.
|
|---|
| 35 | ; @param ECX:EBX Factor 2 - ecx=F2H, ebx=F2L.
|
|---|
| 36 | ;
|
|---|
| 37 | global $??I8M
|
|---|
| 38 | $??I8M:
|
|---|
| 39 | global $??U8M
|
|---|
| 40 | $??U8M:
|
|---|
| 41 | ;
|
|---|
| 42 | ; If both the high dwords are zero, we can get away with
|
|---|
| 43 | ; a simple 32-bit multiplication.
|
|---|
| 44 | ;
|
|---|
| 45 | test ecx, ecx
|
|---|
| 46 | jnz .big
|
|---|
| 47 | test edx, edx
|
|---|
| 48 | jnz .big
|
|---|
| 49 | mul ebx
|
|---|
| 50 | ret
|
|---|
| 51 |
|
|---|
| 52 | .big:
|
|---|
| 53 | ;
|
|---|
| 54 | ; Imagine we use 4294967296-base (2^32), so each factor has two
|
|---|
| 55 | ; digits H and L, thus we have: F1H:F1L * F2H:F1L which we can
|
|---|
| 56 | ; multipy like we learned in primary school. Since the result
|
|---|
| 57 | ; is limited to 64-bit, we can skip F1H*F2H and discard the
|
|---|
| 58 | ; high 32-bit in F1L*F2H and F1H*F2L.
|
|---|
| 59 | ; result = ((F1L*F2H) << 32)
|
|---|
| 60 | ; + ((F1H*F2L) << 32)
|
|---|
| 61 | ; + (F1L*F2L);
|
|---|
| 62 | ;
|
|---|
| 63 | push ecx ; Preserve ECX just to be nice.
|
|---|
| 64 | push eax ; Stash F1L for later.
|
|---|
| 65 | push edx ; Stash F1H for later.
|
|---|
| 66 |
|
|---|
| 67 | ; ECX = F1L*F2H
|
|---|
| 68 | mul ecx
|
|---|
| 69 | mov ecx, eax
|
|---|
| 70 |
|
|---|
| 71 | ; ECX += F1H * F2L
|
|---|
| 72 | pop eax
|
|---|
| 73 | mul ebx
|
|---|
| 74 | add ecx, eax
|
|---|
| 75 |
|
|---|
| 76 | ; EDX:EAX = F1L * F2L
|
|---|
| 77 | pop eax
|
|---|
| 78 | mul ebx
|
|---|
| 79 | add edx, ecx
|
|---|
| 80 |
|
|---|
| 81 | pop ecx
|
|---|
| 82 | ret
|
|---|
| 83 |
|
|---|
