1/* SPDX-License-Identifier: GPL-2.0 */ 2/*---------------------------------------------------------------------------+ 3 | poly.h | 4 | | 5 | Header file for the FPU-emu poly*.c source files. | 6 | | 7 | Copyright (C) 1994,1999 | 8 | W. Metzenthen, 22 Parker St, Ormond, Vic 3163, | 9 | Australia. E-mail billm@melbpc.org.au | 10 | | 11 | Declarations and definitions for functions operating on Xsig (12-byte | 12 | extended-significand) quantities. | 13 | | 14 +---------------------------------------------------------------------------*/ 15 16#ifndef _POLY_H 17#define _POLY_H 18 19/* This 12-byte structure is used to improve the accuracy of computation 20 of transcendental functions. 21 Intended to be used to get results better than 8-byte computation 22 allows. 9-byte would probably be sufficient. 23 */ 24typedef struct { 25 unsigned long lsw; 26 unsigned long midw; 27 unsigned long msw; 28} Xsig; 29 30asmlinkage void mul64(unsigned long long const *a, unsigned long long const *b, 31 unsigned long long *result); 32asmlinkage void polynomial_Xsig(Xsig *, const unsigned long long *x, 33 const unsigned long long terms[], const int n); 34 35asmlinkage void mul32_Xsig(Xsig *, const unsigned long mult); 36asmlinkage void mul64_Xsig(Xsig *, const unsigned long long *mult); 37asmlinkage void mul_Xsig_Xsig(Xsig *dest, const Xsig *mult); 38 39asmlinkage void shr_Xsig(Xsig *, const int n); 40asmlinkage int round_Xsig(Xsig *); 41asmlinkage int norm_Xsig(Xsig *); 42asmlinkage void div_Xsig(Xsig *x1, const Xsig *x2, const Xsig *dest); 43 44/* Macro to extract the most significant 32 bits from a long long */ 45#define LL_MSW(x) (((unsigned long *)&x)[1]) 46 47/* Macro to initialize an Xsig struct */ 48#define MK_XSIG(a,b,c) { c, b, a } 49 50/* Macro to access the 8 ms bytes of an Xsig as a long long */ 51#define XSIG_LL(x) (*(unsigned long long *)&x.midw) 52 53/* 54 Need to run gcc with optimizations on to get these to 55 actually be in-line. 56 */ 57 58/* Multiply two fixed-point 32 bit numbers, producing a 32 bit result. 59 The answer is the ms word of the product. */ 60/* Some versions of gcc make it difficult to stop eax from being clobbered. 61 Merely specifying that it is used doesn't work... 62 */ 63static inline unsigned long mul_32_32(const unsigned long arg1, 64 const unsigned long arg2) 65{ 66 int retval; 67 asm volatile ("mull %2; movl %%edx,%%eax":"=a" (retval) 68 :"0"(arg1), "g"(arg2) 69 :"dx"); 70 return retval; 71} 72 73/* Add the 12 byte Xsig x2 to Xsig dest, with no checks for overflow. */ 74static inline void add_Xsig_Xsig(Xsig *dest, const Xsig *x2) 75{ 76 asm volatile ("movl %1,%%edi; movl %2,%%esi;\n" 77 "movl (%%esi),%%eax; addl %%eax,(%%edi);\n" 78 "movl 4(%%esi),%%eax; adcl %%eax,4(%%edi);\n" 79 "movl 8(%%esi),%%eax; adcl %%eax,8(%%edi);\n":"=g" 80 (*dest):"g"(dest), "g"(x2) 81 :"ax", "si", "di"); 82} 83 84/* Add the 12 byte Xsig x2 to Xsig dest, adjust exp if overflow occurs. */ 85/* Note: the constraints in the asm statement didn't always work properly 86 with gcc 2.5.8. Changing from using edi to using ecx got around the 87 problem, but keep fingers crossed! */ 88static inline void add_two_Xsig(Xsig *dest, const Xsig *x2, long int *exp) 89{ 90 asm volatile ("movl %2,%%ecx; movl %3,%%esi;\n" 91 "movl (%%esi),%%eax; addl %%eax,(%%ecx);\n" 92 "movl 4(%%esi),%%eax; adcl %%eax,4(%%ecx);\n" 93 "movl 8(%%esi),%%eax; adcl %%eax,8(%%ecx);\n" 94 "jnc 0f;\n" 95 "rcrl 8(%%ecx); rcrl 4(%%ecx); rcrl (%%ecx)\n" 96 "movl %4,%%ecx; incl (%%ecx)\n" 97 "movl $1,%%eax; jmp 1f;\n" 98 "0: xorl %%eax,%%eax;\n" "1:\n":"=g" (*exp), "=g"(*dest) 99 :"g"(dest), "g"(x2), "g"(exp) 100 :"cx", "si", "ax"); 101} 102 103/* Negate (subtract from 1.0) the 12 byte Xsig */ 104/* This is faster in a loop on my 386 than using the "neg" instruction. */ 105static inline void negate_Xsig(Xsig *x) 106{ 107 asm volatile ("movl %1,%%esi;\n" 108 "xorl %%ecx,%%ecx;\n" 109 "movl %%ecx,%%eax; subl (%%esi),%%eax; movl %%eax,(%%esi);\n" 110 "movl %%ecx,%%eax; sbbl 4(%%esi),%%eax; movl %%eax,4(%%esi);\n" 111 "movl %%ecx,%%eax; sbbl 8(%%esi),%%eax; movl %%eax,8(%%esi);\n":"=g" 112 (*x):"g"(x):"si", "ax", "cx"); 113} 114 115#endif /* _POLY_H */ 116