diff --git a/am/src/riscv/npc/libgcc/ashldi3.c b/am/src/riscv/npc/libgcc/ashldi3.c new file mode 100644 index 0000000..63bb3b6 --- /dev/null +++ b/am/src/riscv/npc/libgcc/ashldi3.c @@ -0,0 +1,27 @@ +#define LIBGCC2_UNITS_PER_WORD (__riscv_xlen / 8) +#include "libgcc2.h" + +DWtype __ashldi3 (DWtype u, shift_count_type b) +{ + if (b == 0) + return u; + + const DWunion uu = {.ll = u}; + const shift_count_type bm = W_TYPE_SIZE - b; + DWunion w; + + if (bm <= 0) + { + w.s.low = 0; + w.s.high = (UWtype) uu.s.low << -bm; + } + else + { + const UWtype carries = (UWtype) uu.s.low >> bm; + + w.s.low = (UWtype) uu.s.low << b; + w.s.high = ((UWtype) uu.s.high << b) | carries; + } + + return w.ll; +} diff --git a/am/src/riscv/npc/libgcc/div.S b/am/src/riscv/npc/libgcc/div.S new file mode 100644 index 0000000..d941a90 --- /dev/null +++ b/am/src/riscv/npc/libgcc/div.S @@ -0,0 +1,150 @@ +/* Integer division routines for RISC-V. + + Copyright (C) 2016-2022 Free Software Foundation, Inc. + +This file is part of GCC. + +GCC is free software; 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, or (at your option) any later +version. + +GCC 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 General Public License +for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +. */ + +#include "riscv-asm.h" + + .text + .align 2 + +#if __riscv_xlen == 32 +/* Our RV64 64-bit routines are equivalent to our RV32 32-bit routines. */ +# define __udivdi3 __udivsi3 +# define __umoddi3 __umodsi3 +# define __divdi3 __divsi3 +# define __moddi3 __modsi3 +#else +FUNC_BEGIN (__udivsi3) + /* Compute __udivdi3(a0 << 32, a1 << 32); cast result to uint32_t. */ + sll a0, a0, 32 + sll a1, a1, 32 + move t0, ra + jal HIDDEN_JUMPTARGET(__udivdi3) + sext.w a0, a0 + jr t0 +FUNC_END (__udivsi3) + +FUNC_BEGIN (__umodsi3) + /* Compute __udivdi3((uint32_t)a0, (uint32_t)a1); cast a1 to uint32_t. */ + sll a0, a0, 32 + sll a1, a1, 32 + srl a0, a0, 32 + srl a1, a1, 32 + move t0, ra + jal HIDDEN_JUMPTARGET(__udivdi3) + sext.w a0, a1 + jr t0 +FUNC_END (__umodsi3) + +FUNC_ALIAS (__modsi3, __moddi3) + +FUNC_BEGIN( __divsi3) + /* Check for special case of INT_MIN/-1. Otherwise, fall into __divdi3. */ + li t0, -1 + beq a1, t0, .L20 +#endif + +FUNC_BEGIN (__divdi3) + bltz a0, .L10 + bltz a1, .L11 + /* Since the quotient is positive, fall into __udivdi3. */ + +FUNC_BEGIN (__udivdi3) + mv a2, a1 + mv a1, a0 + li a0, -1 + beqz a2, .L5 + li a3, 1 + bgeu a2, a1, .L2 +.L1: + blez a2, .L2 + slli a2, a2, 1 + slli a3, a3, 1 + bgtu a1, a2, .L1 +.L2: + li a0, 0 +.L3: + bltu a1, a2, .L4 + sub a1, a1, a2 + or a0, a0, a3 +.L4: + srli a3, a3, 1 + srli a2, a2, 1 + bnez a3, .L3 +.L5: + ret +FUNC_END (__udivdi3) +HIDDEN_DEF (__udivdi3) + +FUNC_BEGIN (__umoddi3) + /* Call __udivdi3(a0, a1), then return the remainder, which is in a1. */ + move t0, ra + jal HIDDEN_JUMPTARGET(__udivdi3) + move a0, a1 + jr t0 +FUNC_END (__umoddi3) + + /* Handle negative arguments to __divdi3. */ +.L10: + neg a0, a0 + /* Zero is handled as a negative so that the result will not be inverted. */ + bgtz a1, .L12 /* Compute __udivdi3(-a0, a1), then negate the result. */ + + neg a1, a1 + j HIDDEN_JUMPTARGET(__udivdi3) /* Compute __udivdi3(-a0, -a1). */ +.L11: /* Compute __udivdi3(a0, -a1), then negate the result. */ + neg a1, a1 +.L12: + move t0, ra + jal HIDDEN_JUMPTARGET(__udivdi3) + neg a0, a0 + jr t0 +FUNC_END (__divdi3) + +FUNC_BEGIN (__moddi3) + move t0, ra + bltz a1, .L31 + bltz a0, .L32 +.L30: + jal HIDDEN_JUMPTARGET(__udivdi3) /* The dividend is not negative. */ + move a0, a1 + jr t0 +.L31: + neg a1, a1 + bgez a0, .L30 +.L32: + neg a0, a0 + jal HIDDEN_JUMPTARGET(__udivdi3) /* The dividend is hella negative. */ + neg a0, a1 + jr t0 +FUNC_END (__moddi3) + +#if __riscv_xlen == 64 + /* continuation of __divsi3 */ +.L20: + sll t0, t0, 31 + bne a0, t0, __divdi3 + ret +FUNC_END (__divsi3) +#endif diff --git a/am/src/riscv/npc/libgcc/libgcc2.h b/am/src/riscv/npc/libgcc/libgcc2.h new file mode 100644 index 0000000..f0724ee --- /dev/null +++ b/am/src/riscv/npc/libgcc/libgcc2.h @@ -0,0 +1,543 @@ +/* Header file for libgcc2.c. */ +/* Copyright (C) 2000-2022 Free Software Foundation, Inc. + +This file is part of GCC. + +GCC is free software; 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, or (at your option) any later +version. + +GCC 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 General Public License +for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +. */ + +#ifndef GCC_LIBGCC2_H +#define GCC_LIBGCC2_H + +#include + +#define MIN_UNITS_PER_WORD (__riscv_xlen / 8) + +#ifndef HIDE_EXPORTS +#pragma GCC visibility push(default) +#endif + +extern int __gcc_bcmp (const unsigned char *, const unsigned char *, size_t); +extern void __clear_cache (void *, void *); +extern void __eprintf (const char *, const char *, unsigned int, const char *) + __attribute__ ((__noreturn__)); + +#ifdef __LIBGCC_HAS_HF_MODE__ +#define LIBGCC2_HAS_HF_MODE 1 +#else +#define LIBGCC2_HAS_HF_MODE 0 +#endif + +#ifdef __LIBGCC_HAS_SF_MODE__ +#define LIBGCC2_HAS_SF_MODE 1 +#else +#define LIBGCC2_HAS_SF_MODE 0 +#endif + +#ifdef __LIBGCC_HAS_DF_MODE__ +#define LIBGCC2_HAS_DF_MODE 1 +#else +#define LIBGCC2_HAS_DF_MODE 0 +#endif + +#ifdef __LIBGCC_HAS_XF_MODE__ +#define LIBGCC2_HAS_XF_MODE 1 +#else +#define LIBGCC2_HAS_XF_MODE 0 +#endif + +#ifdef __LIBGCC_HAS_TF_MODE__ +#define LIBGCC2_HAS_TF_MODE 1 +#else +#define LIBGCC2_HAS_TF_MODE 0 +#endif + +#ifndef __LIBGCC_SF_MANT_DIG__ +#if LIBGCC2_HAS_SF_MODE +#error __LIBGCC_SF_MANT_DIG__ not defined +#else +#define __LIBGCC_SF_MANT_DIG__ 0 +#endif +#endif + +#ifndef __LIBGCC_DF_MANT_DIG__ +#if LIBGCC2_HAS_DF_MODE +#error __LIBGCC_DF_MANT_DIG__ not defined +#else +#define __LIBGCC_DF_MANT_DIG__ 0 +#endif +#endif + +#ifndef __LIBGCC_XF_MANT_DIG__ +#if LIBGCC2_HAS_XF_MODE +#error __LIBGCC_XF_MANT_DIG__ not defined +#else +#define __LIBGCC_XF_MANT_DIG__ 0 +#endif +#endif + +#ifndef __LIBGCC_TF_MANT_DIG__ +#if LIBGCC2_HAS_TF_MODE +#error __LIBGCC_TF_MANT_DIG__ not defined +#else +#define __LIBGCC_TF_MANT_DIG__ 0 +#endif +#endif + +/* FIXME: This #ifdef probably should be removed, ie. enable the test + for mips too. */ +/* Don't use IBM Extended Double TFmode for TI->SF calculations. + The conversion from long double to float suffers from double + rounding, because we convert via double. In other cases, going + through the software fp routines is much slower than the fallback. */ +#ifdef __powerpc__ +#define AVOID_FP_TYPE_CONVERSION(SIZE) (SIZE == 106) +#elif defined(WIDEST_HARDWARE_FP_SIZE) +#define AVOID_FP_TYPE_CONVERSION(SIZE) (SIZE > WIDEST_HARDWARE_FP_SIZE) +#else +#define AVOID_FP_TYPE_CONVERSION(SIZE) 0 +#endif + +/* In the first part of this file, we are interfacing to calls generated + by the compiler itself. These calls pass values into these routines + which have very specific modes (rather than very specific types), and + these compiler-generated calls also expect any return values to have + very specific modes (rather than very specific types). Thus, we need + to avoid using regular C language type names in this part of the file + because the sizes for those types can be configured to be anything. + Instead we use the following special type names. */ + +typedef int QItype __attribute__ ((mode (QI))); +typedef unsigned int UQItype __attribute__ ((mode (QI))); +typedef int HItype __attribute__ ((mode (HI))); +typedef unsigned int UHItype __attribute__ ((mode (HI))); +#if MIN_UNITS_PER_WORD > 1 +/* These typedefs are usually forbidden on dsp's with UNITS_PER_WORD 1. */ +typedef int SItype __attribute__ ((mode (SI))); +typedef unsigned int USItype __attribute__ ((mode (SI))); +#if __SIZEOF_LONG_LONG__ > 4 +/* These typedefs are usually forbidden on archs with UNITS_PER_WORD 2. */ +typedef int DItype __attribute__ ((mode (DI))); +typedef unsigned int UDItype __attribute__ ((mode (DI))); +#if MIN_UNITS_PER_WORD > 4 +/* These typedefs are usually forbidden on archs with UNITS_PER_WORD 4. */ +typedef int TItype __attribute__ ((mode (TI))); +typedef unsigned int UTItype __attribute__ ((mode (TI))); +#endif +#endif +#endif + +#if LIBGCC2_HAS_HF_MODE +typedef float HFtype __attribute__ ((mode (HF))); +typedef _Complex float HCtype __attribute__ ((mode (HC))); +#endif +#if LIBGCC2_HAS_SF_MODE +typedef float SFtype __attribute__ ((mode (SF))); +typedef _Complex float SCtype __attribute__ ((mode (SC))); +#endif +#if LIBGCC2_HAS_DF_MODE +typedef float DFtype __attribute__ ((mode (DF))); +typedef _Complex float DCtype __attribute__ ((mode (DC))); +#endif +#if LIBGCC2_HAS_XF_MODE +typedef float XFtype __attribute__ ((mode (XF))); +typedef _Complex float XCtype __attribute__ ((mode (XC))); +#endif +#if LIBGCC2_HAS_TF_MODE +typedef float TFtype __attribute__ ((mode (TF))); +typedef _Complex float TCtype __attribute__ ((mode (TC))); +#endif + +typedef int cmp_return_type __attribute__((mode (__libgcc_cmp_return__))); +typedef int shift_count_type __attribute__((mode (__libgcc_shift_count__))); + +/* Make sure that we don't accidentally use any normal C language built-in + type names in the first part of this file. Instead we want to use *only* + the type names defined above. The following macro definitions insure + that if we *do* accidentally use some normal C language built-in type name, + we will get a syntax error. */ + +#define char bogus_type +#define short bogus_type +#define int bogus_type +#define long bogus_type +#define unsigned bogus_type +#define float bogus_type +#define double bogus_type + +/* Versions prior to 3.4.4 were not taking into account the word size for + the 5 trapping arithmetic functions absv, addv, subv, mulv and negv. As + a consequence, the si and di variants were always and the only ones emitted. + To maintain backward compatibility, COMPAT_SIMODE_TRAPPING_ARITHMETIC is + defined on platforms where it makes sense to still have the si variants + emitted. As a bonus, their implementation is now correct. Note that the + same mechanism should have been implemented for the di variants, but it + turns out that no platform would define COMPAT_DIMODE_TRAPPING_ARITHMETIC + if it existed. */ + +#if LIBGCC2_UNITS_PER_WORD == 8 +#define W_TYPE_SIZE (8 * __CHAR_BIT__) +#define Wtype DItype +#define UWtype UDItype +#define HWtype DItype +#define UHWtype UDItype +#define DWtype TItype +#define UDWtype UTItype +#ifdef LIBGCC2_GNU_PREFIX +#define __NW(a,b) __gnu_ ## a ## di ## b +#define __NDW(a,b) __gnu_ ## a ## ti ## b +#else +#define __NW(a,b) __ ## a ## di ## b +#define __NDW(a,b) __ ## a ## ti ## b +#endif +#define COMPAT_SIMODE_TRAPPING_ARITHMETIC +#elif LIBGCC2_UNITS_PER_WORD == 4 +#define W_TYPE_SIZE (4 * __CHAR_BIT__) +#define Wtype SItype +#define UWtype USItype +#define HWtype SItype +#define UHWtype USItype +#define DWtype DItype +#define UDWtype UDItype +#ifdef LIBGCC2_GNU_PREFIX +#define __NW(a,b) __gnu_ ## a ## si ## b +#define __NDW(a,b) __gnu_ ## a ## di ## b +#else +#define __NW(a,b) __ ## a ## si ## b +#define __NDW(a,b) __ ## a ## di ## b +#endif +#elif LIBGCC2_UNITS_PER_WORD == 2 +#define W_TYPE_SIZE (2 * __CHAR_BIT__) +#define Wtype HItype +#define UWtype UHItype +#define HWtype HItype +#define UHWtype UHItype +#define DWtype SItype +#define UDWtype USItype +#ifdef LIBGCC2_GNU_PREFIX +#define __NW(a,b) __gnu_ ## a ## hi ## b +#define __NDW(a,b) __gnu_ ## a ## si ## b +#else +#define __NW(a,b) __ ## a ## hi ## b +#define __NDW(a,b) __ ## a ## si ## b +#endif +#else +#define W_TYPE_SIZE __CHAR_BIT__ +#define Wtype QItype +#define UWtype UQItype +#define HWtype QItype +#define UHWtype UQItype +#define DWtype HItype +#define UDWtype UHItype +#ifdef LIBGCC2_GNU_PREFIX +#define __NW(a,b) __gnu_ ## a ## qi ## b +#define __NDW(a,b) __gnu_ ## a ## hi ## b +#else +#define __NW(a,b) __ ## a ## qi ## b +#define __NDW(a,b) __ ## a ## hi ## b +#endif +#endif + +#ifdef LIBGCC2_GNU_PREFIX +#define __N(a) __gnu_ ## a +#else +#define __N(a) __ ## a +#endif +#define Wtype_MAX ((Wtype)(((UWtype)1 << (W_TYPE_SIZE - 1)) - 1)) +#define Wtype_MIN (- Wtype_MAX - 1) + +#if W_TYPE_SIZE == 8 +# define Wtype_MAXp1_F 0x1p8f +#elif W_TYPE_SIZE == 16 +# define Wtype_MAXp1_F 0x1p16f +#elif W_TYPE_SIZE == 32 +# define Wtype_MAXp1_F 0x1p32f +#elif W_TYPE_SIZE == 64 +# define Wtype_MAXp1_F 0x1p64f +#else +# error "expand the table" +#endif + +#define __muldi3 __NDW(mul,3) +#define __divdi3 __NDW(div,3) +#define __udivdi3 __NDW(udiv,3) +#define __moddi3 __NDW(mod,3) +#define __umoddi3 __NDW(umod,3) +#define __negdi2 __NDW(neg,2) +#define __lshrdi3 __NDW(lshr,3) +#define __ashldi3 __NDW(ashl,3) +#define __ashrdi3 __NDW(ashr,3) +#define __cmpdi2 __NDW(cmp,2) +#define __ucmpdi2 __NDW(ucmp,2) +#define __divmoddi4 __NDW(divmod,4) +#define __udivmoddi4 __NDW(udivmod,4) +#define __fixunstfDI __NDW(fixunstf,) +#define __fixtfdi __NDW(fixtf,) +#define __fixunsxfDI __NDW(fixunsxf,) +#define __fixxfdi __NDW(fixxf,) +#define __fixunsdfDI __NDW(fixunsdf,) +#define __fixdfdi __NDW(fixdf,) +#define __fixunssfDI __NDW(fixunssf,) +#define __fixsfdi __NDW(fixsf,) +#define __floatdixf __NDW(float,xf) +#define __floatditf __NDW(float,tf) +#define __floatdidf __NDW(float,df) +#define __floatdisf __NDW(float,sf) +#define __floatundixf __NDW(floatun,xf) +#define __floatunditf __NDW(floatun,tf) +#define __floatundidf __NDW(floatun,df) +#define __floatundisf __NDW(floatun,sf) +#define __fixunsxfSI __NW(fixunsxf,) +#define __fixunstfSI __NW(fixunstf,) +#define __fixunsdfSI __NW(fixunsdf,) +#define __fixunssfSI __NW(fixunssf,) + +#define __absvSI2 __NW(absv,2) +#define __addvSI3 __NW(addv,3) +#define __subvSI3 __NW(subv,3) +#define __mulvSI3 __NW(mulv,3) +#define __negvSI2 __NW(negv,2) +#define __absvDI2 __NDW(absv,2) +#define __addvDI3 __NDW(addv,3) +#define __subvDI3 __NDW(subv,3) +#define __mulvDI3 __NDW(mulv,3) +#define __negvDI2 __NDW(negv,2) + +#define __ffsSI2 __NW(ffs,2) +#define __clzSI2 __NW(clz,2) +#define __ctzSI2 __NW(ctz,2) +#define __clrsbSI2 __NW(clrsb,2) +#define __popcountSI2 __NW(popcount,2) +#define __paritySI2 __NW(parity,2) +#define __ffsDI2 __NDW(ffs,2) +#define __clzDI2 __NDW(clz,2) +#define __ctzDI2 __NDW(ctz,2) +#define __clrsbDI2 __NDW(clrsb,2) +#define __popcountDI2 __NDW(popcount,2) +#define __parityDI2 __NDW(parity,2) + +#define __clz_tab __N(clz_tab) +#define __bswapsi2 __N(bswapsi2) +#define __bswapdi2 __N(bswapdi2) +#define __udiv_w_sdiv __N(udiv_w_sdiv) +#define __clear_cache __N(clear_cache) +#define __enable_execute_stack __N(enable_execute_stack) + +#ifndef __powisf2 +#define __powisf2 __N(powisf2) +#endif +#ifndef __powidf2 +#define __powidf2 __N(powidf2) +#endif +#ifndef __powitf2 +#define __powitf2 __N(powitf2) +#endif +#ifndef __powixf2 +#define __powixf2 __N(powixf2) +#endif +#ifndef __mulsc3 +#define __mulsc3 __N(mulsc3) +#endif +#ifndef __muldc3 +#define __muldc3 __N(muldc3) +#endif +#ifndef __mulxc3 +#define __mulxc3 __N(mulxc3) +#endif +#ifndef __multc3 +#define __multc3 __N(multc3) +#endif +#ifndef __divsc3 +#define __divsc3 __N(divsc3) +#endif +#ifndef __divdc3 +#define __divdc3 __N(divdc3) +#endif +#ifndef __divxc3 +#define __divxc3 __N(divxc3) +#endif +#ifndef __divtc3 +#define __divtc3 __N(divtc3) +#endif + +extern DWtype __muldi3 (DWtype, DWtype); +extern DWtype __divdi3 (DWtype, DWtype); +extern UDWtype __udivdi3 (UDWtype, UDWtype); +extern UDWtype __umoddi3 (UDWtype, UDWtype); +extern DWtype __moddi3 (DWtype, DWtype); +extern DWtype __divmoddi4 (DWtype, DWtype, DWtype *); + +/* __udivmoddi4 is static inline when building other libgcc2 portions. */ +#if (!defined (L_udivdi3) && !defined (L_divdi3) && \ + !defined (L_umoddi3) && !defined (L_moddi3) && \ + !defined (L_divmoddi4)) +extern UDWtype __udivmoddi4 (UDWtype, UDWtype, UDWtype *); +#endif + +/* __negdi2 is static inline when building other libgcc2 portions. */ +#if !defined(L_divdi3) && !defined(L_moddi3) +extern DWtype __negdi2 (DWtype); +#endif + +extern DWtype __lshrdi3 (DWtype, shift_count_type); +extern DWtype __ashldi3 (DWtype, shift_count_type); +extern DWtype __ashrdi3 (DWtype, shift_count_type); + +/* __udiv_w_sdiv is static inline when building other libgcc2 portions. */ +#if (!defined(L_udivdi3) && !defined(L_divdi3) && \ + !defined(L_umoddi3) && !defined(L_moddi3)) +extern UWtype __udiv_w_sdiv (UWtype *, UWtype, UWtype, UWtype); +#endif + +extern cmp_return_type __cmpdi2 (DWtype, DWtype); +extern cmp_return_type __ucmpdi2 (UDWtype, UDWtype); + +#if MIN_UNITS_PER_WORD > 1 +extern SItype __bswapsi2 (SItype); +#endif +#if __SIZEOF_LONG_LONG__ > 4 +extern DItype __bswapdi2 (DItype); +#endif + +extern Wtype __absvSI2 (Wtype); +extern Wtype __addvSI3 (Wtype, Wtype); +extern Wtype __subvSI3 (Wtype, Wtype); +extern Wtype __mulvSI3 (Wtype, Wtype); +extern Wtype __negvSI2 (Wtype); +extern DWtype __absvDI2 (DWtype); +extern DWtype __addvDI3 (DWtype, DWtype); +extern DWtype __subvDI3 (DWtype, DWtype); +extern DWtype __mulvDI3 (DWtype, DWtype); +extern DWtype __negvDI2 (DWtype); + +#ifdef COMPAT_SIMODE_TRAPPING_ARITHMETIC +#define __absvsi2 __N(absvsi2) +#define __negvsi2 __N(negvsi2) +#define __addvsi3 __N(addvsi3) +#define __subvsi3 __N(subvsi3) +#define __mulvsi3 __N(mulvsi3) + +extern SItype __absvsi2 (SItype); +extern SItype __addvsi3 (SItype, SItype); +extern SItype __subvsi3 (SItype, SItype); +extern SItype __mulvsi3 (SItype, SItype); +extern SItype __negvsi2 (SItype); +#endif /* COMPAT_SIMODE_TRAPPING_ARITHMETIC */ + +#undef int +#if LIBGCC2_HAS_HF_MODE +extern HCtype __divhc3 (HFtype, HFtype, HFtype, HFtype); +extern HCtype __mulhc3 (HFtype, HFtype, HFtype, HFtype); +#endif +#if LIBGCC2_HAS_SF_MODE +extern DWtype __fixsfdi (SFtype); +extern SFtype __floatdisf (DWtype); +extern SFtype __floatundisf (UDWtype); +extern UWtype __fixunssfSI (SFtype); +extern UDWtype __fixunssfDI (SFtype); +extern SFtype __powisf2 (SFtype, int); +extern SCtype __divsc3 (SFtype, SFtype, SFtype, SFtype); +extern SCtype __mulsc3 (SFtype, SFtype, SFtype, SFtype); +#endif +#if LIBGCC2_HAS_DF_MODE +extern DWtype __fixdfdi (DFtype); +extern DFtype __floatdidf (DWtype); +extern DFtype __floatundidf (UDWtype); +extern UWtype __fixunsdfSI (DFtype); +extern UDWtype __fixunsdfDI (DFtype); +extern DFtype __powidf2 (DFtype, int); +extern DCtype __divdc3 (DFtype, DFtype, DFtype, DFtype); +extern DCtype __muldc3 (DFtype, DFtype, DFtype, DFtype); +#endif + +#if LIBGCC2_HAS_XF_MODE +extern DWtype __fixxfdi (XFtype); +extern UDWtype __fixunsxfDI (XFtype); +extern XFtype __floatdixf (DWtype); +extern XFtype __floatundixf (UDWtype); +extern UWtype __fixunsxfSI (XFtype); +extern XFtype __powixf2 (XFtype, int); +extern XCtype __divxc3 (XFtype, XFtype, XFtype, XFtype); +extern XCtype __mulxc3 (XFtype, XFtype, XFtype, XFtype); +#endif + +#if LIBGCC2_HAS_TF_MODE +extern UDWtype __fixunstfDI (TFtype); +extern DWtype __fixtfdi (TFtype); +extern TFtype __floatditf (DWtype); +extern TFtype __floatunditf (UDWtype); +extern TFtype __powitf2 (TFtype, int); +extern TCtype __divtc3 (TFtype, TFtype, TFtype, TFtype); +extern TCtype __multc3 (TFtype, TFtype, TFtype, TFtype); +#endif +#define int bogus_type + +/* DWstructs are pairs of Wtype values in the order determined by + __BYTE_ORDER__. */ + +#if __BYTE_ORDER__ != __ORDER_LITTLE_ENDIAN__ + struct DWstruct {Wtype high, low;}; +#else + struct DWstruct {Wtype low, high;}; +#endif + +/* We need this union to unpack/pack DImode values, since we don't have + any arithmetic yet. Incoming DImode parameters are stored into the + `ll' field, and the unpacked result is read from the struct `s'. */ + +typedef union +{ + struct DWstruct s; + DWtype ll; +} DWunion; + +/* Defined for L_popcount_tab. Exported here because some targets may + want to use it for their own versions of the __popcount builtins. */ +extern const UQItype __popcount_tab[256]; + +/* Defined for L_clz. Exported here because some targets may want to use + it for their own versions of the __clz builtins. It contains the bit + position of the first set bit for the numbers 0 - 255. This avoids the + need for a separate table for the __ctz builtins. */ +extern const UQItype __clz_tab[256]; + +#include "longlong.h" + +#undef int +extern int __clzDI2 (UDWtype); +extern int __clzSI2 (UWtype); +extern int __ctzSI2 (UWtype); +extern int __ctzDI2 (UDWtype); +extern int __clrsbSI2 (Wtype); +extern int __clrsbDI2 (DWtype); +extern int __ffsSI2 (UWtype); +extern int __ffsDI2 (DWtype); +extern int __popcountSI2 (UWtype); +extern int __popcountDI2 (UDWtype); +extern int __paritySI2 (UWtype); +extern int __parityDI2 (UDWtype); +#define int bogus_type + +extern void __enable_execute_stack (void *); + +#ifndef HIDE_EXPORTS +#pragma GCC visibility pop +#endif + +#endif /* ! GCC_LIBGCC2_H */ diff --git a/am/src/riscv/npc/libgcc/longlong.h b/am/src/riscv/npc/libgcc/longlong.h new file mode 100644 index 0000000..64a7b10 --- /dev/null +++ b/am/src/riscv/npc/libgcc/longlong.h @@ -0,0 +1,1774 @@ +/* longlong.h -- definitions for mixed size 32/64 bit arithmetic. + Copyright (C) 1991-2022 Free Software Foundation, Inc. + + This file is part of the GNU C Library. + + The GNU C 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 version. + + In addition to the permissions in the GNU Lesser General Public + License, the Free Software Foundation gives you unlimited + permission to link the compiled version of this file into + combinations with other programs, and to distribute those + combinations without any restriction coming from the use of this + file. (The Lesser General Public License restrictions do apply in + other respects; for example, they cover modification of the file, + and distribution when not linked into a combine executable.) + + The GNU C 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 GNU C Library; if not, see + . */ + +/* You have to define the following before including this file: + + UWtype -- An unsigned type, default type for operations (typically a "word") + UHWtype -- An unsigned type, at least half the size of UWtype. + UDWtype -- An unsigned type, at least twice as large a UWtype + W_TYPE_SIZE -- size in bits of UWtype + + UQItype -- Unsigned 8 bit type. + SItype, USItype -- Signed and unsigned 32 bit types. + DItype, UDItype -- Signed and unsigned 64 bit types. + + On a 32 bit machine UWtype should typically be USItype; + on a 64 bit machine, UWtype should typically be UDItype. */ + +#define __BITS4 (W_TYPE_SIZE / 4) +#define __ll_B ((UWtype) 1 << (W_TYPE_SIZE / 2)) +#define __ll_lowpart(t) ((UWtype) (t) & (__ll_B - 1)) +#define __ll_highpart(t) ((UWtype) (t) >> (W_TYPE_SIZE / 2)) + +#ifndef W_TYPE_SIZE +#define W_TYPE_SIZE 32 +#define UWtype USItype +#define UHWtype USItype +#define UDWtype UDItype +#endif + +/* Used in glibc only. */ +#ifndef attribute_hidden +#define attribute_hidden +#endif + +extern const UQItype __clz_tab[256] attribute_hidden; + +/* Define auxiliary asm macros. + + 1) umul_ppmm(high_prod, low_prod, multiplier, multiplicand) multiplies two + UWtype integers MULTIPLIER and MULTIPLICAND, and generates a two UWtype + word product in HIGH_PROD and LOW_PROD. + + 2) __umulsidi3(a,b) multiplies two UWtype integers A and B, and returns a + UDWtype product. This is just a variant of umul_ppmm. + + 3) udiv_qrnnd(quotient, remainder, high_numerator, low_numerator, + denominator) divides a UDWtype, composed by the UWtype integers + HIGH_NUMERATOR and LOW_NUMERATOR, by DENOMINATOR and places the quotient + in QUOTIENT and the remainder in REMAINDER. HIGH_NUMERATOR must be less + than DENOMINATOR for correct operation. If, in addition, the most + significant bit of DENOMINATOR must be 1, then the pre-processor symbol + UDIV_NEEDS_NORMALIZATION is defined to 1. + + 4) sdiv_qrnnd(quotient, remainder, high_numerator, low_numerator, + denominator). Like udiv_qrnnd but the numbers are signed. The quotient + is rounded towards 0. + + 5) count_leading_zeros(count, x) counts the number of zero-bits from the + msb to the first nonzero bit in the UWtype X. This is the number of + steps X needs to be shifted left to set the msb. Undefined for X == 0, + unless the symbol COUNT_LEADING_ZEROS_0 is defined to some value. + + 6) count_trailing_zeros(count, x) like count_leading_zeros, but counts + from the least significant end. + + 7) add_ssaaaa(high_sum, low_sum, high_addend_1, low_addend_1, + high_addend_2, low_addend_2) adds two UWtype integers, composed by + HIGH_ADDEND_1 and LOW_ADDEND_1, and HIGH_ADDEND_2 and LOW_ADDEND_2 + respectively. The result is placed in HIGH_SUM and LOW_SUM. Overflow + (i.e. carry out) is not stored anywhere, and is lost. + + 8) sub_ddmmss(high_difference, low_difference, high_minuend, low_minuend, + high_subtrahend, low_subtrahend) subtracts two two-word UWtype integers, + composed by HIGH_MINUEND_1 and LOW_MINUEND_1, and HIGH_SUBTRAHEND_2 and + LOW_SUBTRAHEND_2 respectively. The result is placed in HIGH_DIFFERENCE + and LOW_DIFFERENCE. Overflow (i.e. carry out) is not stored anywhere, + and is lost. + + If any of these macros are left undefined for a particular CPU, + C macros are used. */ + +/* The CPUs come in alphabetical order below. + + Please add support for more CPUs here, or improve the current support + for the CPUs below! + (E.g. WE32100, IBM360.) */ + +#if defined (__GNUC__) && !defined (NO_ASM) + +/* We sometimes need to clobber "cc" with gcc2, but that would not be + understood by gcc1. Use cpp to avoid major code duplication. */ +#if __GNUC__ < 2 +#define __CLOBBER_CC +#define __AND_CLOBBER_CC +#else /* __GNUC__ >= 2 */ +#define __CLOBBER_CC : "cc" +#define __AND_CLOBBER_CC , "cc" +#endif /* __GNUC__ < 2 */ + +#if defined (__aarch64__) + +#if W_TYPE_SIZE == 32 +#define count_leading_zeros(COUNT, X) ((COUNT) = __builtin_clz (X)) +#define count_trailing_zeros(COUNT, X) ((COUNT) = __builtin_ctz (X)) +#define COUNT_LEADING_ZEROS_0 32 +#endif /* W_TYPE_SIZE == 32 */ + +#if W_TYPE_SIZE == 64 +#define count_leading_zeros(COUNT, X) ((COUNT) = __builtin_clzll (X)) +#define count_trailing_zeros(COUNT, X) ((COUNT) = __builtin_ctzll (X)) +#define COUNT_LEADING_ZEROS_0 64 +#endif /* W_TYPE_SIZE == 64 */ + +#endif /* __aarch64__ */ + +#if defined (__alpha) && W_TYPE_SIZE == 64 +/* There is a bug in g++ before version 5 that + errors on __builtin_alpha_umulh. */ +#if !defined(__cplusplus) || __GNUC__ >= 5 +#define umul_ppmm(ph, pl, m0, m1) \ + do { \ + UDItype __m0 = (m0), __m1 = (m1); \ + (ph) = __builtin_alpha_umulh (__m0, __m1); \ + (pl) = __m0 * __m1; \ + } while (0) +#define UMUL_TIME 46 +#endif /* !c++ */ +#ifndef LONGLONG_STANDALONE +#define udiv_qrnnd(q, r, n1, n0, d) \ + do { UDItype __r; \ + (q) = __udiv_qrnnd (&__r, (n1), (n0), (d)); \ + (r) = __r; \ + } while (0) +extern UDItype __udiv_qrnnd (UDItype *, UDItype, UDItype, UDItype); +#define UDIV_TIME 220 +#endif /* LONGLONG_STANDALONE */ +#ifdef __alpha_cix__ +#define count_leading_zeros(COUNT,X) ((COUNT) = __builtin_clzl (X)) +#define count_trailing_zeros(COUNT,X) ((COUNT) = __builtin_ctzl (X)) +#define COUNT_LEADING_ZEROS_0 64 +#else +#define count_leading_zeros(COUNT,X) \ + do { \ + UDItype __xr = (X), __t, __a; \ + __t = __builtin_alpha_cmpbge (0, __xr); \ + __a = __clz_tab[__t ^ 0xff] - 1; \ + __t = __builtin_alpha_extbl (__xr, __a); \ + (COUNT) = 64 - (__clz_tab[__t] + __a*8); \ + } while (0) +#define count_trailing_zeros(COUNT,X) \ + do { \ + UDItype __xr = (X), __t, __a; \ + __t = __builtin_alpha_cmpbge (0, __xr); \ + __t = ~__t & -~__t; \ + __a = ((__t & 0xCC) != 0) * 2; \ + __a += ((__t & 0xF0) != 0) * 4; \ + __a += ((__t & 0xAA) != 0); \ + __t = __builtin_alpha_extbl (__xr, __a); \ + __a <<= 3; \ + __t &= -__t; \ + __a += ((__t & 0xCC) != 0) * 2; \ + __a += ((__t & 0xF0) != 0) * 4; \ + __a += ((__t & 0xAA) != 0); \ + (COUNT) = __a; \ + } while (0) +#endif /* __alpha_cix__ */ +#endif /* __alpha */ + +#if defined (__arc__) && W_TYPE_SIZE == 32 +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + __asm__ ("add.f %1, %4, %5\n\tadc %0, %2, %3" \ + : "=r" ((USItype) (sh)), \ + "=&r" ((USItype) (sl)) \ + : "%r" ((USItype) (ah)), \ + "rICal" ((USItype) (bh)), \ + "%r" ((USItype) (al)), \ + "rICal" ((USItype) (bl)) \ + : "cc") +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + __asm__ ("sub.f %1, %4, %5\n\tsbc %0, %2, %3" \ + : "=r" ((USItype) (sh)), \ + "=&r" ((USItype) (sl)) \ + : "r" ((USItype) (ah)), \ + "rICal" ((USItype) (bh)), \ + "r" ((USItype) (al)), \ + "rICal" ((USItype) (bl)) \ + : "cc") + +#define __umulsidi3(u,v) ((UDItype)(USItype)u*(USItype)v) +#ifdef __ARC_NORM__ +#define count_leading_zeros(count, x) \ + do \ + { \ + SItype c_; \ + \ + __asm__ ("norm.f\t%0,%1\n\tmov.mi\t%0,-1" : "=r" (c_) : "r" (x) : "cc");\ + (count) = c_ + 1; \ + } \ + while (0) +#define COUNT_LEADING_ZEROS_0 32 +#endif /* __ARC_NORM__ */ +#endif /* __arc__ */ + +#if defined (__arm__) && (defined (__thumb2__) || !defined (__thumb__)) \ + && W_TYPE_SIZE == 32 +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + __asm__ ("adds %1, %4, %5\n\tadc %0, %2, %3" \ + : "=r" ((USItype) (sh)), \ + "=&r" ((USItype) (sl)) \ + : "%r" ((USItype) (ah)), \ + "rI" ((USItype) (bh)), \ + "%r" ((USItype) (al)), \ + "rI" ((USItype) (bl)) __CLOBBER_CC) +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + __asm__ ("subs %1, %4, %5\n\tsbc %0, %2, %3" \ + : "=r" ((USItype) (sh)), \ + "=&r" ((USItype) (sl)) \ + : "r" ((USItype) (ah)), \ + "rI" ((USItype) (bh)), \ + "r" ((USItype) (al)), \ + "rI" ((USItype) (bl)) __CLOBBER_CC) +# if defined(__ARM_ARCH_2__) || defined(__ARM_ARCH_2A__) \ + || defined(__ARM_ARCH_3__) +# define umul_ppmm(xh, xl, a, b) \ + do { \ + register USItype __t0, __t1, __t2; \ + __asm__ ("%@ Inlined umul_ppmm\n" \ + " mov %2, %5, lsr #16\n" \ + " mov %0, %6, lsr #16\n" \ + " bic %3, %5, %2, lsl #16\n" \ + " bic %4, %6, %0, lsl #16\n" \ + " mul %1, %3, %4\n" \ + " mul %4, %2, %4\n" \ + " mul %3, %0, %3\n" \ + " mul %0, %2, %0\n" \ + " adds %3, %4, %3\n" \ + " addcs %0, %0, #65536\n" \ + " adds %1, %1, %3, lsl #16\n" \ + " adc %0, %0, %3, lsr #16" \ + : "=&r" ((USItype) (xh)), \ + "=r" ((USItype) (xl)), \ + "=&r" (__t0), "=&r" (__t1), "=r" (__t2) \ + : "r" ((USItype) (a)), \ + "r" ((USItype) (b)) __CLOBBER_CC ); \ + } while (0) +# define UMUL_TIME 20 +# else +# define umul_ppmm(xh, xl, a, b) \ + do { \ + /* Generate umull, under compiler control. */ \ + register UDItype __t0 = (UDItype)(USItype)(a) * (USItype)(b); \ + (xl) = (USItype)__t0; \ + (xh) = (USItype)(__t0 >> 32); \ + } while (0) +# define UMUL_TIME 3 +# endif +# define UDIV_TIME 100 +#endif /* __arm__ */ + +#if defined(__arm__) +/* Let gcc decide how best to implement count_leading_zeros. */ +#define count_leading_zeros(COUNT,X) ((COUNT) = __builtin_clz (X)) +#define count_trailing_zeros(COUNT,X) ((COUNT) = __builtin_ctz (X)) +#define COUNT_LEADING_ZEROS_0 32 +#endif + +#if defined (__AVR__) + +#if W_TYPE_SIZE == 16 +#define count_leading_zeros(COUNT,X) ((COUNT) = __builtin_clz (X)) +#define count_trailing_zeros(COUNT,X) ((COUNT) = __builtin_ctz (X)) +#define COUNT_LEADING_ZEROS_0 16 +#endif /* W_TYPE_SIZE == 16 */ + +#if W_TYPE_SIZE == 32 +#define count_leading_zeros(COUNT,X) ((COUNT) = __builtin_clzl (X)) +#define count_trailing_zeros(COUNT,X) ((COUNT) = __builtin_ctzl (X)) +#define COUNT_LEADING_ZEROS_0 32 +#endif /* W_TYPE_SIZE == 32 */ + +#if W_TYPE_SIZE == 64 +#define count_leading_zeros(COUNT,X) ((COUNT) = __builtin_clzll (X)) +#define count_trailing_zeros(COUNT,X) ((COUNT) = __builtin_ctzll (X)) +#define COUNT_LEADING_ZEROS_0 64 +#endif /* W_TYPE_SIZE == 64 */ + +#endif /* defined (__AVR__) */ + +#if defined (__CRIS__) + +#if __CRIS_arch_version >= 3 +#define count_leading_zeros(COUNT, X) ((COUNT) = __builtin_clz (X)) +#define COUNT_LEADING_ZEROS_0 32 +#endif /* __CRIS_arch_version >= 3 */ + +#if __CRIS_arch_version >= 8 +#define count_trailing_zeros(COUNT, X) ((COUNT) = __builtin_ctz (X)) +#endif /* __CRIS_arch_version >= 8 */ + +#if __CRIS_arch_version >= 10 +#define __umulsidi3(u,v) ((UDItype)(USItype) (u) * (UDItype)(USItype) (v)) +#else +#define __umulsidi3 __umulsidi3 +extern UDItype __umulsidi3 (USItype, USItype); +#endif /* __CRIS_arch_version >= 10 */ + +#define umul_ppmm(w1, w0, u, v) \ + do { \ + UDItype __x = __umulsidi3 (u, v); \ + (w0) = (USItype) (__x); \ + (w1) = (USItype) (__x >> 32); \ + } while (0) + +/* FIXME: defining add_ssaaaa and sub_ddmmss should be advantageous for + DFmode ("double" intrinsics, avoiding two of the three insns handling + carry), but defining them as open-code C composing and doing the + operation in DImode (UDImode) shows that the DImode needs work: + register pressure from requiring neighboring registers and the + traffic to and from them come to dominate, in the 4.7 series. */ + +#endif /* defined (__CRIS__) */ + +#if defined (__hppa) && W_TYPE_SIZE == 32 +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + __asm__ ("add %4,%5,%1\n\taddc %2,%3,%0" \ + : "=r" ((USItype) (sh)), \ + "=&r" ((USItype) (sl)) \ + : "%rM" ((USItype) (ah)), \ + "rM" ((USItype) (bh)), \ + "%rM" ((USItype) (al)), \ + "rM" ((USItype) (bl))) +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + __asm__ ("sub %4,%5,%1\n\tsubb %2,%3,%0" \ + : "=r" ((USItype) (sh)), \ + "=&r" ((USItype) (sl)) \ + : "rM" ((USItype) (ah)), \ + "rM" ((USItype) (bh)), \ + "rM" ((USItype) (al)), \ + "rM" ((USItype) (bl))) +#if defined (_PA_RISC1_1) +#define umul_ppmm(w1, w0, u, v) \ + do { \ + union \ + { \ + UDItype __f; \ + struct {USItype __w1, __w0;} __w1w0; \ + } __t; \ + __asm__ ("xmpyu %1,%2,%0" \ + : "=x" (__t.__f) \ + : "x" ((USItype) (u)), \ + "x" ((USItype) (v))); \ + (w1) = __t.__w1w0.__w1; \ + (w0) = __t.__w1w0.__w0; \ + } while (0) +#define UMUL_TIME 8 +#else +#define UMUL_TIME 30 +#endif +#define UDIV_TIME 40 +#define count_leading_zeros(count, x) \ + do { \ + USItype __tmp; \ + __asm__ ( \ + "ldi 1,%0\n" \ +" extru,= %1,15,16,%%r0 ; Bits 31..16 zero?\n" \ +" extru,tr %1,15,16,%1 ; No. Shift down, skip add.\n"\ +" ldo 16(%0),%0 ; Yes. Perform add.\n" \ +" extru,= %1,23,8,%%r0 ; Bits 15..8 zero?\n" \ +" extru,tr %1,23,8,%1 ; No. Shift down, skip add.\n"\ +" ldo 8(%0),%0 ; Yes. Perform add.\n" \ +" extru,= %1,27,4,%%r0 ; Bits 7..4 zero?\n" \ +" extru,tr %1,27,4,%1 ; No. Shift down, skip add.\n"\ +" ldo 4(%0),%0 ; Yes. Perform add.\n" \ +" extru,= %1,29,2,%%r0 ; Bits 3..2 zero?\n" \ +" extru,tr %1,29,2,%1 ; No. Shift down, skip add.\n"\ +" ldo 2(%0),%0 ; Yes. Perform add.\n" \ +" extru %1,30,1,%1 ; Extract bit 1.\n" \ +" sub %0,%1,%0 ; Subtract it.\n" \ + : "=r" (count), "=r" (__tmp) : "1" (x)); \ + } while (0) +#endif + +#if (defined (__i370__) || defined (__s390__) || defined (__mvs__)) && W_TYPE_SIZE == 32 +#if !defined (__zarch__) +#define smul_ppmm(xh, xl, m0, m1) \ + do { \ + union {DItype __ll; \ + struct {USItype __h, __l;} __i; \ + } __x; \ + __asm__ ("lr %N0,%1\n\tmr %0,%2" \ + : "=&r" (__x.__ll) \ + : "r" (m0), "r" (m1)); \ + (xh) = __x.__i.__h; (xl) = __x.__i.__l; \ + } while (0) +#define sdiv_qrnnd(q, r, n1, n0, d) \ + do { \ + union {DItype __ll; \ + struct {USItype __h, __l;} __i; \ + } __x; \ + __x.__i.__h = n1; __x.__i.__l = n0; \ + __asm__ ("dr %0,%2" \ + : "=r" (__x.__ll) \ + : "0" (__x.__ll), "r" (d)); \ + (q) = __x.__i.__l; (r) = __x.__i.__h; \ + } while (0) +#else +#define smul_ppmm(xh, xl, m0, m1) \ + do { \ + register SItype __r0 __asm__ ("0"); \ + register SItype __r1 __asm__ ("1") = (m0); \ + \ + __asm__ ("mr\t%%r0,%3" \ + : "=r" (__r0), "=r" (__r1) \ + : "r" (__r1), "r" (m1)); \ + (xh) = __r0; (xl) = __r1; \ + } while (0) + +#define sdiv_qrnnd(q, r, n1, n0, d) \ + do { \ + register SItype __r0 __asm__ ("0") = (n1); \ + register SItype __r1 __asm__ ("1") = (n0); \ + \ + __asm__ ("dr\t%%r0,%4" \ + : "=r" (__r0), "=r" (__r1) \ + : "r" (__r0), "r" (__r1), "r" (d)); \ + (q) = __r1; (r) = __r0; \ + } while (0) +#endif /* __zarch__ */ +#endif + +#if (defined (__i386__) || defined (__i486__)) && W_TYPE_SIZE == 32 +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + __asm__ ("add{l} {%5,%1|%1,%5}\n\tadc{l} {%3,%0|%0,%3}" \ + : "=r" ((USItype) (sh)), \ + "=&r" ((USItype) (sl)) \ + : "%0" ((USItype) (ah)), \ + "g" ((USItype) (bh)), \ + "%1" ((USItype) (al)), \ + "g" ((USItype) (bl))) +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + __asm__ ("sub{l} {%5,%1|%1,%5}\n\tsbb{l} {%3,%0|%0,%3}" \ + : "=r" ((USItype) (sh)), \ + "=&r" ((USItype) (sl)) \ + : "0" ((USItype) (ah)), \ + "g" ((USItype) (bh)), \ + "1" ((USItype) (al)), \ + "g" ((USItype) (bl))) +#define umul_ppmm(w1, w0, u, v) \ + __asm__ ("mul{l} %3" \ + : "=a" ((USItype) (w0)), \ + "=d" ((USItype) (w1)) \ + : "%0" ((USItype) (u)), \ + "rm" ((USItype) (v))) +#define udiv_qrnnd(q, r, n1, n0, dv) \ + __asm__ ("div{l} %4" \ + : "=a" ((USItype) (q)), \ + "=d" ((USItype) (r)) \ + : "0" ((USItype) (n0)), \ + "1" ((USItype) (n1)), \ + "rm" ((USItype) (dv))) +#define count_leading_zeros(count, x) ((count) = __builtin_clz (x)) +#define count_trailing_zeros(count, x) ((count) = __builtin_ctz (x)) +#define UMUL_TIME 40 +#define UDIV_TIME 40 +#endif /* 80x86 */ + +#if defined (__x86_64__) && W_TYPE_SIZE == 64 +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + __asm__ ("add{q} {%5,%1|%1,%5}\n\tadc{q} {%3,%0|%0,%3}" \ + : "=r" ((UDItype) (sh)), \ + "=&r" ((UDItype) (sl)) \ + : "%0" ((UDItype) (ah)), \ + "rme" ((UDItype) (bh)), \ + "%1" ((UDItype) (al)), \ + "rme" ((UDItype) (bl))) +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + __asm__ ("sub{q} {%5,%1|%1,%5}\n\tsbb{q} {%3,%0|%0,%3}" \ + : "=r" ((UDItype) (sh)), \ + "=&r" ((UDItype) (sl)) \ + : "0" ((UDItype) (ah)), \ + "rme" ((UDItype) (bh)), \ + "1" ((UDItype) (al)), \ + "rme" ((UDItype) (bl))) +#define umul_ppmm(w1, w0, u, v) \ + __asm__ ("mul{q} %3" \ + : "=a" ((UDItype) (w0)), \ + "=d" ((UDItype) (w1)) \ + : "%0" ((UDItype) (u)), \ + "rm" ((UDItype) (v))) +#define udiv_qrnnd(q, r, n1, n0, dv) \ + __asm__ ("div{q} %4" \ + : "=a" ((UDItype) (q)), \ + "=d" ((UDItype) (r)) \ + : "0" ((UDItype) (n0)), \ + "1" ((UDItype) (n1)), \ + "rm" ((UDItype) (dv))) +#define count_leading_zeros(count, x) ((count) = __builtin_clzll (x)) +#define count_trailing_zeros(count, x) ((count) = __builtin_ctzll (x)) +#define UMUL_TIME 40 +#define UDIV_TIME 40 +#endif /* x86_64 */ + +#if defined (__i960__) && W_TYPE_SIZE == 32 +#define umul_ppmm(w1, w0, u, v) \ + ({union {UDItype __ll; \ + struct {USItype __l, __h;} __i; \ + } __xx; \ + __asm__ ("emul %2,%1,%0" \ + : "=d" (__xx.__ll) \ + : "%dI" ((USItype) (u)), \ + "dI" ((USItype) (v))); \ + (w1) = __xx.__i.__h; (w0) = __xx.__i.__l;}) +#define __umulsidi3(u, v) \ + ({UDItype __w; \ + __asm__ ("emul %2,%1,%0" \ + : "=d" (__w) \ + : "%dI" ((USItype) (u)), \ + "dI" ((USItype) (v))); \ + __w; }) +#endif /* __i960__ */ + +#if defined (__ia64) && W_TYPE_SIZE == 64 +/* This form encourages gcc (pre-release 3.4 at least) to emit predicated + "sub r=r,r" and "sub r=r,r,1", giving a 2 cycle latency. The generic + code using "al>= _c; \ + if (_x >= 1 << 4) \ + _x >>= 4, _c += 4; \ + if (_x >= 1 << 2) \ + _x >>= 2, _c += 2; \ + _c += _x >> 1; \ + (count) = W_TYPE_SIZE - 1 - _c; \ + } while (0) +/* similar to what gcc does for __builtin_ffs, but 0 based rather than 1 + based, and we don't need a special case for x==0 here */ +#define count_trailing_zeros(count, x) \ + do { \ + UWtype __ctz_x = (x); \ + __asm__ ("popcnt %0 = %1" \ + : "=r" (count) \ + : "r" ((__ctz_x-1) & ~__ctz_x)); \ + } while (0) +#define UMUL_TIME 14 +#endif + +#if defined (__M32R__) && W_TYPE_SIZE == 32 +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + /* The cmp clears the condition bit. */ \ + __asm__ ("cmp %0,%0\n\taddx %1,%5\n\taddx %0,%3" \ + : "=r" ((USItype) (sh)), \ + "=&r" ((USItype) (sl)) \ + : "0" ((USItype) (ah)), \ + "r" ((USItype) (bh)), \ + "1" ((USItype) (al)), \ + "r" ((USItype) (bl)) \ + : "cbit") +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + /* The cmp clears the condition bit. */ \ + __asm__ ("cmp %0,%0\n\tsubx %1,%5\n\tsubx %0,%3" \ + : "=r" ((USItype) (sh)), \ + "=&r" ((USItype) (sl)) \ + : "0" ((USItype) (ah)), \ + "r" ((USItype) (bh)), \ + "1" ((USItype) (al)), \ + "r" ((USItype) (bl)) \ + : "cbit") +#endif /* __M32R__ */ + +#if defined (__mc68000__) && W_TYPE_SIZE == 32 +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + __asm__ ("add%.l %5,%1\n\taddx%.l %3,%0" \ + : "=d" ((USItype) (sh)), \ + "=&d" ((USItype) (sl)) \ + : "%0" ((USItype) (ah)), \ + "d" ((USItype) (bh)), \ + "%1" ((USItype) (al)), \ + "g" ((USItype) (bl))) +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + __asm__ ("sub%.l %5,%1\n\tsubx%.l %3,%0" \ + : "=d" ((USItype) (sh)), \ + "=&d" ((USItype) (sl)) \ + : "0" ((USItype) (ah)), \ + "d" ((USItype) (bh)), \ + "1" ((USItype) (al)), \ + "g" ((USItype) (bl))) + +/* The '020, '030, '040, '060 and CPU32 have 32x32->64 and 64/32->32q-32r. */ +#if (defined (__mc68020__) && !defined (__mc68060__)) +#define umul_ppmm(w1, w0, u, v) \ + __asm__ ("mulu%.l %3,%1:%0" \ + : "=d" ((USItype) (w0)), \ + "=d" ((USItype) (w1)) \ + : "%0" ((USItype) (u)), \ + "dmi" ((USItype) (v))) +#define UMUL_TIME 45 +#define udiv_qrnnd(q, r, n1, n0, d) \ + __asm__ ("divu%.l %4,%1:%0" \ + : "=d" ((USItype) (q)), \ + "=d" ((USItype) (r)) \ + : "0" ((USItype) (n0)), \ + "1" ((USItype) (n1)), \ + "dmi" ((USItype) (d))) +#define UDIV_TIME 90 +#define sdiv_qrnnd(q, r, n1, n0, d) \ + __asm__ ("divs%.l %4,%1:%0" \ + : "=d" ((USItype) (q)), \ + "=d" ((USItype) (r)) \ + : "0" ((USItype) (n0)), \ + "1" ((USItype) (n1)), \ + "dmi" ((USItype) (d))) + +#elif defined (__mcoldfire__) /* not mc68020 */ + +#define umul_ppmm(xh, xl, a, b) \ + __asm__ ("| Inlined umul_ppmm\n" \ + " move%.l %2,%/d0\n" \ + " move%.l %3,%/d1\n" \ + " move%.l %/d0,%/d2\n" \ + " swap %/d0\n" \ + " move%.l %/d1,%/d3\n" \ + " swap %/d1\n" \ + " move%.w %/d2,%/d4\n" \ + " mulu %/d3,%/d4\n" \ + " mulu %/d1,%/d2\n" \ + " mulu %/d0,%/d3\n" \ + " mulu %/d0,%/d1\n" \ + " move%.l %/d4,%/d0\n" \ + " clr%.w %/d0\n" \ + " swap %/d0\n" \ + " add%.l %/d0,%/d2\n" \ + " add%.l %/d3,%/d2\n" \ + " jcc 1f\n" \ + " add%.l %#65536,%/d1\n" \ + "1: swap %/d2\n" \ + " moveq %#0,%/d0\n" \ + " move%.w %/d2,%/d0\n" \ + " move%.w %/d4,%/d2\n" \ + " move%.l %/d2,%1\n" \ + " add%.l %/d1,%/d0\n" \ + " move%.l %/d0,%0" \ + : "=g" ((USItype) (xh)), \ + "=g" ((USItype) (xl)) \ + : "g" ((USItype) (a)), \ + "g" ((USItype) (b)) \ + : "d0", "d1", "d2", "d3", "d4") +#define UMUL_TIME 100 +#define UDIV_TIME 400 +#else /* not ColdFire */ +/* %/ inserts REGISTER_PREFIX, %# inserts IMMEDIATE_PREFIX. */ +#define umul_ppmm(xh, xl, a, b) \ + __asm__ ("| Inlined umul_ppmm\n" \ + " move%.l %2,%/d0\n" \ + " move%.l %3,%/d1\n" \ + " move%.l %/d0,%/d2\n" \ + " swap %/d0\n" \ + " move%.l %/d1,%/d3\n" \ + " swap %/d1\n" \ + " move%.w %/d2,%/d4\n" \ + " mulu %/d3,%/d4\n" \ + " mulu %/d1,%/d2\n" \ + " mulu %/d0,%/d3\n" \ + " mulu %/d0,%/d1\n" \ + " move%.l %/d4,%/d0\n" \ + " eor%.w %/d0,%/d0\n" \ + " swap %/d0\n" \ + " add%.l %/d0,%/d2\n" \ + " add%.l %/d3,%/d2\n" \ + " jcc 1f\n" \ + " add%.l %#65536,%/d1\n" \ + "1: swap %/d2\n" \ + " moveq %#0,%/d0\n" \ + " move%.w %/d2,%/d0\n" \ + " move%.w %/d4,%/d2\n" \ + " move%.l %/d2,%1\n" \ + " add%.l %/d1,%/d0\n" \ + " move%.l %/d0,%0" \ + : "=g" ((USItype) (xh)), \ + "=g" ((USItype) (xl)) \ + : "g" ((USItype) (a)), \ + "g" ((USItype) (b)) \ + : "d0", "d1", "d2", "d3", "d4") +#define UMUL_TIME 100 +#define UDIV_TIME 400 + +#endif /* not mc68020 */ + +/* The '020, '030, '040 and '060 have bitfield insns. + cpu32 disguises as a 68020, but lacks them. */ +#if defined (__mc68020__) && !defined (__mcpu32__) +#define count_leading_zeros(count, x) \ + __asm__ ("bfffo %1{%b2:%b2},%0" \ + : "=d" ((USItype) (count)) \ + : "od" ((USItype) (x)), "n" (0)) +/* Some ColdFire architectures have a ff1 instruction supported via + __builtin_clz. */ +#elif defined (__mcfisaaplus__) || defined (__mcfisac__) +#define count_leading_zeros(count,x) ((count) = __builtin_clz (x)) +#define COUNT_LEADING_ZEROS_0 32 +#endif +#endif /* mc68000 */ + +#if defined (__m88000__) && W_TYPE_SIZE == 32 +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + __asm__ ("addu.co %1,%r4,%r5\n\taddu.ci %0,%r2,%r3" \ + : "=r" ((USItype) (sh)), \ + "=&r" ((USItype) (sl)) \ + : "%rJ" ((USItype) (ah)), \ + "rJ" ((USItype) (bh)), \ + "%rJ" ((USItype) (al)), \ + "rJ" ((USItype) (bl))) +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + __asm__ ("subu.co %1,%r4,%r5\n\tsubu.ci %0,%r2,%r3" \ + : "=r" ((USItype) (sh)), \ + "=&r" ((USItype) (sl)) \ + : "rJ" ((USItype) (ah)), \ + "rJ" ((USItype) (bh)), \ + "rJ" ((USItype) (al)), \ + "rJ" ((USItype) (bl))) +#define count_leading_zeros(count, x) \ + do { \ + USItype __cbtmp; \ + __asm__ ("ff1 %0,%1" \ + : "=r" (__cbtmp) \ + : "r" ((USItype) (x))); \ + (count) = __cbtmp ^ 31; \ + } while (0) +#define COUNT_LEADING_ZEROS_0 63 /* sic */ +#if defined (__mc88110__) +#define umul_ppmm(wh, wl, u, v) \ + do { \ + union {UDItype __ll; \ + struct {USItype __h, __l;} __i; \ + } __xx; \ + __asm__ ("mulu.d %0,%1,%2" \ + : "=r" (__xx.__ll) \ + : "r" ((USItype) (u)), \ + "r" ((USItype) (v))); \ + (wh) = __xx.__i.__h; \ + (wl) = __xx.__i.__l; \ + } while (0) +#define udiv_qrnnd(q, r, n1, n0, d) \ + ({union {UDItype __ll; \ + struct {USItype __h, __l;} __i; \ + } __xx; \ + USItype __q; \ + __xx.__i.__h = (n1); __xx.__i.__l = (n0); \ + __asm__ ("divu.d %0,%1,%2" \ + : "=r" (__q) \ + : "r" (__xx.__ll), \ + "r" ((USItype) (d))); \ + (r) = (n0) - __q * (d); (q) = __q; }) +#define UMUL_TIME 5 +#define UDIV_TIME 25 +#else +#define UMUL_TIME 17 +#define UDIV_TIME 150 +#endif /* __mc88110__ */ +#endif /* __m88000__ */ + +#if defined (__mn10300__) +# if defined (__AM33__) +# define count_leading_zeros(COUNT,X) ((COUNT) = __builtin_clz (X)) +# define umul_ppmm(w1, w0, u, v) \ + asm("mulu %3,%2,%1,%0" : "=r"(w0), "=r"(w1) : "r"(u), "r"(v)) +# define smul_ppmm(w1, w0, u, v) \ + asm("mul %3,%2,%1,%0" : "=r"(w0), "=r"(w1) : "r"(u), "r"(v)) +# else +# define umul_ppmm(w1, w0, u, v) \ + asm("nop; nop; mulu %3,%0" : "=d"(w0), "=z"(w1) : "%0"(u), "d"(v)) +# define smul_ppmm(w1, w0, u, v) \ + asm("nop; nop; mul %3,%0" : "=d"(w0), "=z"(w1) : "%0"(u), "d"(v)) +# endif +# define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + do { \ + DWunion __s, __a, __b; \ + __a.s.low = (al); __a.s.high = (ah); \ + __b.s.low = (bl); __b.s.high = (bh); \ + __s.ll = __a.ll + __b.ll; \ + (sl) = __s.s.low; (sh) = __s.s.high; \ + } while (0) +# define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + do { \ + DWunion __s, __a, __b; \ + __a.s.low = (al); __a.s.high = (ah); \ + __b.s.low = (bl); __b.s.high = (bh); \ + __s.ll = __a.ll - __b.ll; \ + (sl) = __s.s.low; (sh) = __s.s.high; \ + } while (0) +# define udiv_qrnnd(q, r, nh, nl, d) \ + asm("divu %2,%0" : "=D"(q), "=z"(r) : "D"(d), "0"(nl), "1"(nh)) +# define sdiv_qrnnd(q, r, nh, nl, d) \ + asm("div %2,%0" : "=D"(q), "=z"(r) : "D"(d), "0"(nl), "1"(nh)) +# define UMUL_TIME 3 +# define UDIV_TIME 38 +#endif + +#if defined (__mips__) && W_TYPE_SIZE == 32 +#define umul_ppmm(w1, w0, u, v) \ + do { \ + UDItype __x = (UDItype) (USItype) (u) * (USItype) (v); \ + (w1) = (USItype) (__x >> 32); \ + (w0) = (USItype) (__x); \ + } while (0) +#define UMUL_TIME 10 +#define UDIV_TIME 100 + +#if (__mips == 32 || __mips == 64) && ! defined (__mips16) +#define count_leading_zeros(COUNT,X) ((COUNT) = __builtin_clz (X)) +#define COUNT_LEADING_ZEROS_0 32 +#endif +#endif /* __mips__ */ + +/* FIXME: We should test _IBMR2 here when we add assembly support for the + system vendor compilers. + FIXME: What's needed for gcc PowerPC VxWorks? __vxworks__ is not good + enough, since that hits ARM and m68k too. */ +#if (defined (_ARCH_PPC) /* AIX */ \ + || defined (__powerpc__) /* gcc */ \ + || defined (__POWERPC__) /* BEOS */ \ + || defined (__ppc__) /* Darwin */ \ + || (defined (PPC) && ! defined (CPU_FAMILY)) /* gcc 2.7.x GNU&SysV */ \ + || (defined (PPC) && defined (CPU_FAMILY) /* VxWorks */ \ + && CPU_FAMILY == PPC) \ + ) && W_TYPE_SIZE == 32 +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + do { \ + if (__builtin_constant_p (bh) && (bh) == 0) \ + __asm__ ("add%I4c %1,%3,%4\n\taddze %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\ + else if (__builtin_constant_p (bh) && (bh) == ~(USItype) 0) \ + __asm__ ("add%I4c %1,%3,%4\n\taddme %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\ + else \ + __asm__ ("add%I5c %1,%4,%5\n\tadde %0,%2,%3" \ + : "=r" (sh), "=&r" (sl) \ + : "%r" (ah), "r" (bh), "%r" (al), "rI" (bl)); \ + } while (0) +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + do { \ + if (__builtin_constant_p (ah) && (ah) == 0) \ + __asm__ ("subf%I3c %1,%4,%3\n\tsubfze %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\ + else if (__builtin_constant_p (ah) && (ah) == ~(USItype) 0) \ + __asm__ ("subf%I3c %1,%4,%3\n\tsubfme %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\ + else if (__builtin_constant_p (bh) && (bh) == 0) \ + __asm__ ("subf%I3c %1,%4,%3\n\taddme %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\ + else if (__builtin_constant_p (bh) && (bh) == ~(USItype) 0) \ + __asm__ ("subf%I3c %1,%4,%3\n\taddze %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\ + else \ + __asm__ ("subf%I4c %1,%5,%4\n\tsubfe %0,%3,%2" \ + : "=r" (sh), "=&r" (sl) \ + : "r" (ah), "r" (bh), "rI" (al), "r" (bl)); \ + } while (0) +#define count_leading_zeros(count, x) \ + __asm__ ("cntlzw %0,%1" : "=r" (count) : "r" (x)) +#define COUNT_LEADING_ZEROS_0 32 +#if defined (_ARCH_PPC) || defined (__powerpc__) || defined (__POWERPC__) \ + || defined (__ppc__) \ + || (defined (PPC) && ! defined (CPU_FAMILY)) /* gcc 2.7.x GNU&SysV */ \ + || (defined (PPC) && defined (CPU_FAMILY) /* VxWorks */ \ + && CPU_FAMILY == PPC) +#define umul_ppmm(ph, pl, m0, m1) \ + do { \ + USItype __m0 = (m0), __m1 = (m1); \ + __asm__ ("mulhwu %0,%1,%2" : "=r" (ph) : "%r" (m0), "r" (m1)); \ + (pl) = __m0 * __m1; \ + } while (0) +#define UMUL_TIME 15 +#define smul_ppmm(ph, pl, m0, m1) \ + do { \ + SItype __m0 = (m0), __m1 = (m1); \ + __asm__ ("mulhw %0,%1,%2" : "=r" (ph) : "%r" (m0), "r" (m1)); \ + (pl) = __m0 * __m1; \ + } while (0) +#define SMUL_TIME 14 +#define UDIV_TIME 120 +#endif +#endif /* 32-bit POWER architecture variants. */ + +/* We should test _IBMR2 here when we add assembly support for the system + vendor compilers. */ +#if (defined (_ARCH_PPC64) || defined (__powerpc64__)) && W_TYPE_SIZE == 64 +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + do { \ + if (__builtin_constant_p (bh) && (bh) == 0) \ + __asm__ ("add%I4c %1,%3,%4\n\taddze %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\ + else if (__builtin_constant_p (bh) && (bh) == ~(UDItype) 0) \ + __asm__ ("add%I4c %1,%3,%4\n\taddme %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\ + else \ + __asm__ ("add%I5c %1,%4,%5\n\tadde %0,%2,%3" \ + : "=r" (sh), "=&r" (sl) \ + : "%r" (ah), "r" (bh), "%r" (al), "rI" (bl)); \ + } while (0) +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + do { \ + if (__builtin_constant_p (ah) && (ah) == 0) \ + __asm__ ("subf%I3c %1,%4,%3\n\tsubfze %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\ + else if (__builtin_constant_p (ah) && (ah) == ~(UDItype) 0) \ + __asm__ ("subf%I3c %1,%4,%3\n\tsubfme %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\ + else if (__builtin_constant_p (bh) && (bh) == 0) \ + __asm__ ("subf%I3c %1,%4,%3\n\taddme %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\ + else if (__builtin_constant_p (bh) && (bh) == ~(UDItype) 0) \ + __asm__ ("subf%I3c %1,%4,%3\n\taddze %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\ + else \ + __asm__ ("subf%I4c %1,%5,%4\n\tsubfe %0,%3,%2" \ + : "=r" (sh), "=&r" (sl) \ + : "r" (ah), "r" (bh), "rI" (al), "r" (bl)); \ + } while (0) +#define count_leading_zeros(count, x) \ + __asm__ ("cntlzd %0,%1" : "=r" (count) : "r" (x)) +#define COUNT_LEADING_ZEROS_0 64 +#define umul_ppmm(ph, pl, m0, m1) \ + do { \ + UDItype __m0 = (m0), __m1 = (m1); \ + __asm__ ("mulhdu %0,%1,%2" : "=r" (ph) : "%r" (m0), "r" (m1)); \ + (pl) = __m0 * __m1; \ + } while (0) +#define UMUL_TIME 15 +#define smul_ppmm(ph, pl, m0, m1) \ + do { \ + DItype __m0 = (m0), __m1 = (m1); \ + __asm__ ("mulhd %0,%1,%2" : "=r" (ph) : "%r" (m0), "r" (m1)); \ + (pl) = __m0 * __m1; \ + } while (0) +#define SMUL_TIME 14 /* ??? */ +#define UDIV_TIME 120 /* ??? */ +#endif /* 64-bit PowerPC. */ + +#if defined (__ibm032__) /* RT/ROMP */ && W_TYPE_SIZE == 32 +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + __asm__ ("a %1,%5\n\tae %0,%3" \ + : "=r" ((USItype) (sh)), \ + "=&r" ((USItype) (sl)) \ + : "%0" ((USItype) (ah)), \ + "r" ((USItype) (bh)), \ + "%1" ((USItype) (al)), \ + "r" ((USItype) (bl))) +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + __asm__ ("s %1,%5\n\tse %0,%3" \ + : "=r" ((USItype) (sh)), \ + "=&r" ((USItype) (sl)) \ + : "0" ((USItype) (ah)), \ + "r" ((USItype) (bh)), \ + "1" ((USItype) (al)), \ + "r" ((USItype) (bl))) +#define umul_ppmm(ph, pl, m0, m1) \ + do { \ + USItype __m0 = (m0), __m1 = (m1); \ + __asm__ ( \ + "s r2,r2\n" \ +" mts r10,%2\n" \ +" m r2,%3\n" \ +" m r2,%3\n" \ +" m r2,%3\n" \ +" m r2,%3\n" \ +" m r2,%3\n" \ +" m r2,%3\n" \ +" m r2,%3\n" \ +" m r2,%3\n" \ +" m r2,%3\n" \ +" m r2,%3\n" \ +" m r2,%3\n" \ +" m r2,%3\n" \ +" m r2,%3\n" \ +" m r2,%3\n" \ +" m r2,%3\n" \ +" m r2,%3\n" \ +" cas %0,r2,r0\n" \ +" mfs r10,%1" \ + : "=r" ((USItype) (ph)), \ + "=r" ((USItype) (pl)) \ + : "%r" (__m0), \ + "r" (__m1) \ + : "r2"); \ + (ph) += ((((SItype) __m0 >> 31) & __m1) \ + + (((SItype) __m1 >> 31) & __m0)); \ + } while (0) +#define UMUL_TIME 20 +#define UDIV_TIME 200 +#define count_leading_zeros(count, x) \ + do { \ + if ((x) >= 0x10000) \ + __asm__ ("clz %0,%1" \ + : "=r" ((USItype) (count)) \ + : "r" ((USItype) (x) >> 16)); \ + else \ + { \ + __asm__ ("clz %0,%1" \ + : "=r" ((USItype) (count)) \ + : "r" ((USItype) (x))); \ + (count) += 16; \ + } \ + } while (0) +#endif + +#if defined(__riscv) +#ifdef __riscv_mul +#define __umulsidi3(u,v) ((UDWtype)(UWtype)(u) * (UWtype)(v)) +#define __muluw3(a, b) ((UWtype)(a) * (UWtype)(b)) +#else +#if __riscv_xlen == 32 + #define MULUW3 "call __mulsi3" +#elif __riscv_xlen == 64 + #define MULUW3 "call __muldi3" +#else +#error unsupport xlen +#endif /* __riscv_xlen */ +/* We rely on the fact that MULUW3 doesn't clobber the t-registers. + It can get better register allocation result. */ +#define __muluw3(a, b) \ + ({ \ + register UWtype __op0 asm ("a0") = a; \ + register UWtype __op1 asm ("a1") = b; \ + asm volatile (MULUW3 \ + : "+r" (__op0), "+r" (__op1) \ + : \ + : "ra", "a2", "a3"); \ + __op0; \ + }) +#endif /* __riscv_mul */ +#define umul_ppmm(w1, w0, u, v) \ + do { \ + UWtype __x0, __x1, __x2, __x3; \ + UHWtype __ul, __vl, __uh, __vh; \ + \ + __ul = __ll_lowpart (u); \ + __uh = __ll_highpart (u); \ + __vl = __ll_lowpart (v); \ + __vh = __ll_highpart (v); \ + \ + __x0 = __muluw3 (__ul, __vl); \ + __x1 = __muluw3 (__ul, __vh); \ + __x2 = __muluw3 (__uh, __vl); \ + __x3 = __muluw3 (__uh, __vh); \ + \ + __x1 += __ll_highpart (__x0);/* this can't give carry */ \ + __x1 += __x2; /* but this indeed can */ \ + if (__x1 < __x2) /* did we get it? */ \ + __x3 += __ll_B; /* yes, add it in the proper pos. */ \ + \ + (w1) = __x3 + __ll_highpart (__x1); \ + (w0) = __ll_lowpart (__x1) * __ll_B + __ll_lowpart (__x0); \ + } while (0) +#endif /* __riscv */ + +#if defined(__sh__) && W_TYPE_SIZE == 32 +#ifndef __sh1__ +#define umul_ppmm(w1, w0, u, v) \ + __asm__ ( \ + "dmulu.l %2,%3\n\tsts%M1 macl,%1\n\tsts%M0 mach,%0" \ + : "=r<" ((USItype)(w1)), \ + "=r<" ((USItype)(w0)) \ + : "r" ((USItype)(u)), \ + "r" ((USItype)(v)) \ + : "macl", "mach") +#define UMUL_TIME 5 +#endif + +/* This is the same algorithm as __udiv_qrnnd_c. */ +#define UDIV_NEEDS_NORMALIZATION 1 + +#ifdef __FDPIC__ +/* FDPIC needs a special version of the asm fragment to extract the + code address from the function descriptor. __udiv_qrnnd_16 is + assumed to be local and not to use the GOT, so loading r12 is + not needed. */ +#define udiv_qrnnd(q, r, n1, n0, d) \ + do { \ + extern UWtype __udiv_qrnnd_16 (UWtype, UWtype) \ + __attribute__ ((visibility ("hidden"))); \ + /* r0: rn r1: qn */ /* r0: n1 r4: n0 r5: d r6: d1 */ /* r2: __m */ \ + __asm__ ( \ + "mov%M4 %4,r5\n" \ +" swap.w %3,r4\n" \ +" swap.w r5,r6\n" \ +" mov.l @%5,r2\n" \ +" jsr @r2\n" \ +" shll16 r6\n" \ +" swap.w r4,r4\n" \ +" mov.l @%5,r2\n" \ +" jsr @r2\n" \ +" swap.w r1,%0\n" \ +" or r1,%0" \ + : "=r" (q), "=&z" (r) \ + : "1" (n1), "r" (n0), "rm" (d), "r" (&__udiv_qrnnd_16) \ + : "r1", "r2", "r4", "r5", "r6", "pr", "t"); \ + } while (0) +#else +#define udiv_qrnnd(q, r, n1, n0, d) \ + do { \ + extern UWtype __udiv_qrnnd_16 (UWtype, UWtype) \ + __attribute__ ((visibility ("hidden"))); \ + /* r0: rn r1: qn */ /* r0: n1 r4: n0 r5: d r6: d1 */ /* r2: __m */ \ + __asm__ ( \ + "mov%M4 %4,r5\n" \ +" swap.w %3,r4\n" \ +" swap.w r5,r6\n" \ +" jsr @%5\n" \ +" shll16 r6\n" \ +" swap.w r4,r4\n" \ +" jsr @%5\n" \ +" swap.w r1,%0\n" \ +" or r1,%0" \ + : "=r" (q), "=&z" (r) \ + : "1" (n1), "r" (n0), "rm" (d), "r" (&__udiv_qrnnd_16) \ + : "r1", "r2", "r4", "r5", "r6", "pr", "t"); \ + } while (0) +#endif /* __FDPIC__ */ + +#define UDIV_TIME 80 + +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + __asm__ ("clrt;subc %5,%1; subc %4,%0" \ + : "=r" (sh), "=r" (sl) \ + : "0" (ah), "1" (al), "r" (bh), "r" (bl) : "t") + +#endif /* __sh__ */ + +#if defined (__sparc__) && !defined (__arch64__) && !defined (__sparcv9) \ + && W_TYPE_SIZE == 32 +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + __asm__ ("addcc %r4,%5,%1\n\taddx %r2,%3,%0" \ + : "=r" ((USItype) (sh)), \ + "=&r" ((USItype) (sl)) \ + : "%rJ" ((USItype) (ah)), \ + "rI" ((USItype) (bh)), \ + "%rJ" ((USItype) (al)), \ + "rI" ((USItype) (bl)) \ + __CLOBBER_CC) +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + __asm__ ("subcc %r4,%5,%1\n\tsubx %r2,%3,%0" \ + : "=r" ((USItype) (sh)), \ + "=&r" ((USItype) (sl)) \ + : "rJ" ((USItype) (ah)), \ + "rI" ((USItype) (bh)), \ + "rJ" ((USItype) (al)), \ + "rI" ((USItype) (bl)) \ + __CLOBBER_CC) +#if defined (__sparc_v9__) +#define umul_ppmm(w1, w0, u, v) \ + do { \ + register USItype __g1 asm ("g1"); \ + __asm__ ("umul\t%2,%3,%1\n\t" \ + "srlx\t%1, 32, %0" \ + : "=r" ((USItype) (w1)), \ + "=r" (__g1) \ + : "r" ((USItype) (u)), \ + "r" ((USItype) (v))); \ + (w0) = __g1; \ + } while (0) +#define udiv_qrnnd(__q, __r, __n1, __n0, __d) \ + __asm__ ("mov\t%2,%%y\n\t" \ + "udiv\t%3,%4,%0\n\t" \ + "umul\t%0,%4,%1\n\t" \ + "sub\t%3,%1,%1" \ + : "=&r" ((USItype) (__q)), \ + "=&r" ((USItype) (__r)) \ + : "r" ((USItype) (__n1)), \ + "r" ((USItype) (__n0)), \ + "r" ((USItype) (__d))) +#else +#if defined (__sparc_v8__) +#define umul_ppmm(w1, w0, u, v) \ + __asm__ ("umul %2,%3,%1;rd %%y,%0" \ + : "=r" ((USItype) (w1)), \ + "=r" ((USItype) (w0)) \ + : "r" ((USItype) (u)), \ + "r" ((USItype) (v))) +#define udiv_qrnnd(__q, __r, __n1, __n0, __d) \ + __asm__ ("mov %2,%%y;nop;nop;nop;udiv %3,%4,%0;umul %0,%4,%1;sub %3,%1,%1"\ + : "=&r" ((USItype) (__q)), \ + "=&r" ((USItype) (__r)) \ + : "r" ((USItype) (__n1)), \ + "r" ((USItype) (__n0)), \ + "r" ((USItype) (__d))) +#else +#if defined (__sparclite__) +/* This has hardware multiply but not divide. It also has two additional + instructions scan (ffs from high bit) and divscc. */ +#define umul_ppmm(w1, w0, u, v) \ + __asm__ ("umul %2,%3,%1;rd %%y,%0" \ + : "=r" ((USItype) (w1)), \ + "=r" ((USItype) (w0)) \ + : "r" ((USItype) (u)), \ + "r" ((USItype) (v))) +#define udiv_qrnnd(q, r, n1, n0, d) \ + __asm__ ("! Inlined udiv_qrnnd\n" \ +" wr %%g0,%2,%%y ! Not a delayed write for sparclite\n" \ +" tst %%g0\n" \ +" divscc %3,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%%g1\n" \ +" divscc %%g1,%4,%0\n" \ +" rd %%y,%1\n" \ +" bl,a 1f\n" \ +" add %1,%4,%1\n" \ +"1: ! End of inline udiv_qrnnd" \ + : "=r" ((USItype) (q)), \ + "=r" ((USItype) (r)) \ + : "r" ((USItype) (n1)), \ + "r" ((USItype) (n0)), \ + "rI" ((USItype) (d)) \ + : "g1" __AND_CLOBBER_CC) +#define UDIV_TIME 37 +#define count_leading_zeros(count, x) \ + do { \ + __asm__ ("scan %1,1,%0" \ + : "=r" ((USItype) (count)) \ + : "r" ((USItype) (x))); \ + } while (0) +/* Early sparclites return 63 for an argument of 0, but they warn that future + implementations might change this. Therefore, leave COUNT_LEADING_ZEROS_0 + undefined. */ +#else +/* SPARC without integer multiplication and divide instructions. + (i.e. at least Sun4/20,40,60,65,75,110,260,280,330,360,380,470,490) */ +#define umul_ppmm(w1, w0, u, v) \ + __asm__ ("! Inlined umul_ppmm\n" \ +" wr %%g0,%2,%%y ! SPARC has 0-3 delay insn after a wr\n"\ +" sra %3,31,%%o5 ! Don't move this insn\n" \ +" and %2,%%o5,%%o5 ! Don't move this insn\n" \ +" andcc %%g0,0,%%g1 ! Don't move this insn\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,%3,%%g1\n" \ +" mulscc %%g1,0,%%g1\n" \ +" add %%g1,%%o5,%0\n" \ +" rd %%y,%1" \ + : "=r" ((USItype) (w1)), \ + "=r" ((USItype) (w0)) \ + : "%rI" ((USItype) (u)), \ + "r" ((USItype) (v)) \ + : "g1", "o5" __AND_CLOBBER_CC) +#define UMUL_TIME 39 /* 39 instructions */ +/* It's quite necessary to add this much assembler for the sparc. + The default udiv_qrnnd (in C) is more than 10 times slower! */ +#define udiv_qrnnd(__q, __r, __n1, __n0, __d) \ + __asm__ ("! Inlined udiv_qrnnd\n" \ +" mov 32,%%g1\n" \ +" subcc %1,%2,%%g0\n" \ +"1: bcs 5f\n" \ +" addxcc %0,%0,%0 ! shift n1n0 and a q-bit in lsb\n" \ +" sub %1,%2,%1 ! this kills msb of n\n" \ +" addx %1,%1,%1 ! so this can't give carry\n" \ +" subcc %%g1,1,%%g1\n" \ +"2: bne 1b\n" \ +" subcc %1,%2,%%g0\n" \ +" bcs 3f\n" \ +" addxcc %0,%0,%0 ! shift n1n0 and a q-bit in lsb\n" \ +" b 3f\n" \ +" sub %1,%2,%1 ! this kills msb of n\n" \ +"4: sub %1,%2,%1\n" \ +"5: addxcc %1,%1,%1\n" \ +" bcc 2b\n" \ +" subcc %%g1,1,%%g1\n" \ +"! Got carry from n. Subtract next step to cancel this carry.\n" \ +" bne 4b\n" \ +" addcc %0,%0,%0 ! shift n1n0 and a 0-bit in lsb\n" \ +" sub %1,%2,%1\n" \ +"3: xnor %0,0,%0\n" \ +" ! End of inline udiv_qrnnd" \ + : "=&r" ((USItype) (__q)), \ + "=&r" ((USItype) (__r)) \ + : "r" ((USItype) (__d)), \ + "1" ((USItype) (__n1)), \ + "0" ((USItype) (__n0)) : "g1" __AND_CLOBBER_CC) +#define UDIV_TIME (3+7*32) /* 7 instructions/iteration. 32 iterations. */ +#endif /* __sparclite__ */ +#endif /* __sparc_v8__ */ +#endif /* __sparc_v9__ */ +#endif /* sparc32 */ + +#if ((defined (__sparc__) && defined (__arch64__)) || defined (__sparcv9)) \ + && W_TYPE_SIZE == 64 +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + do { \ + UDItype __carry = 0; \ + __asm__ ("addcc\t%r5,%6,%1\n\t" \ + "add\t%r3,%4,%0\n\t" \ + "movcs\t%%xcc, 1, %2\n\t" \ + "add\t%0, %2, %0" \ + : "=r" ((UDItype)(sh)), \ + "=&r" ((UDItype)(sl)), \ + "+r" (__carry) \ + : "%rJ" ((UDItype)(ah)), \ + "rI" ((UDItype)(bh)), \ + "%rJ" ((UDItype)(al)), \ + "rI" ((UDItype)(bl)) \ + __CLOBBER_CC); \ + } while (0) + +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + do { \ + UDItype __carry = 0; \ + __asm__ ("subcc\t%r5,%6,%1\n\t" \ + "sub\t%r3,%4,%0\n\t" \ + "movcs\t%%xcc, 1, %2\n\t" \ + "sub\t%0, %2, %0" \ + : "=r" ((UDItype)(sh)), \ + "=&r" ((UDItype)(sl)), \ + "+r" (__carry) \ + : "%rJ" ((UDItype)(ah)), \ + "rI" ((UDItype)(bh)), \ + "%rJ" ((UDItype)(al)), \ + "rI" ((UDItype)(bl)) \ + __CLOBBER_CC); \ + } while (0) + +#define umul_ppmm(wh, wl, u, v) \ + do { \ + UDItype tmp1, tmp2, tmp3, tmp4; \ + __asm__ __volatile__ ( \ + "srl %7,0,%3\n\t" \ + "mulx %3,%6,%1\n\t" \ + "srlx %6,32,%2\n\t" \ + "mulx %2,%3,%4\n\t" \ + "sllx %4,32,%5\n\t" \ + "srl %6,0,%3\n\t" \ + "sub %1,%5,%5\n\t" \ + "srlx %5,32,%5\n\t" \ + "addcc %4,%5,%4\n\t" \ + "srlx %7,32,%5\n\t" \ + "mulx %3,%5,%3\n\t" \ + "mulx %2,%5,%5\n\t" \ + "sethi %%hi(0x80000000),%2\n\t" \ + "addcc %4,%3,%4\n\t" \ + "srlx %4,32,%4\n\t" \ + "add %2,%2,%2\n\t" \ + "movcc %%xcc,%%g0,%2\n\t" \ + "addcc %5,%4,%5\n\t" \ + "sllx %3,32,%3\n\t" \ + "add %1,%3,%1\n\t" \ + "add %5,%2,%0" \ + : "=r" ((UDItype)(wh)), \ + "=&r" ((UDItype)(wl)), \ + "=&r" (tmp1), "=&r" (tmp2), "=&r" (tmp3), "=&r" (tmp4) \ + : "r" ((UDItype)(u)), \ + "r" ((UDItype)(v)) \ + __CLOBBER_CC); \ + } while (0) +#define UMUL_TIME 96 +#define UDIV_TIME 230 +#endif /* sparc64 */ + +#if defined (__vax__) && W_TYPE_SIZE == 32 +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + __asm__ ("addl2 %5,%1\n\tadwc %3,%0" \ + : "=g" ((USItype) (sh)), \ + "=&g" ((USItype) (sl)) \ + : "%0" ((USItype) (ah)), \ + "g" ((USItype) (bh)), \ + "%1" ((USItype) (al)), \ + "g" ((USItype) (bl))) +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + __asm__ ("subl2 %5,%1\n\tsbwc %3,%0" \ + : "=g" ((USItype) (sh)), \ + "=&g" ((USItype) (sl)) \ + : "0" ((USItype) (ah)), \ + "g" ((USItype) (bh)), \ + "1" ((USItype) (al)), \ + "g" ((USItype) (bl))) +#define umul_ppmm(xh, xl, m0, m1) \ + do { \ + union { \ + UDItype __ll; \ + struct {USItype __l, __h;} __i; \ + } __xx; \ + USItype __m0 = (m0), __m1 = (m1); \ + __asm__ ("emul %1,%2,$0,%0" \ + : "=r" (__xx.__ll) \ + : "g" (__m0), \ + "g" (__m1)); \ + (xh) = __xx.__i.__h; \ + (xl) = __xx.__i.__l; \ + (xh) += ((((SItype) __m0 >> 31) & __m1) \ + + (((SItype) __m1 >> 31) & __m0)); \ + } while (0) +#define sdiv_qrnnd(q, r, n1, n0, d) \ + do { \ + union {DItype __ll; \ + struct {SItype __l, __h;} __i; \ + } __xx; \ + __xx.__i.__h = n1; __xx.__i.__l = n0; \ + __asm__ ("ediv %3,%2,%0,%1" \ + : "=g" (q), "=g" (r) \ + : "g" (__xx.__ll), "g" (d)); \ + } while (0) +#endif /* __vax__ */ + +#ifdef _TMS320C6X +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + do \ + { \ + UDItype __ll; \ + __asm__ ("addu .l1 %1, %2, %0" \ + : "=a" (__ll) : "a" (al), "a" (bl)); \ + (sl) = (USItype)__ll; \ + (sh) = ((USItype)(__ll >> 32)) + (ah) + (bh); \ + } \ + while (0) + +#ifdef _TMS320C6400_PLUS +#define __umulsidi3(u,v) ((UDItype)(USItype)u*(USItype)v) +#define umul_ppmm(w1, w0, u, v) \ + do { \ + UDItype __x = (UDItype) (USItype) (u) * (USItype) (v); \ + (w1) = (USItype) (__x >> 32); \ + (w0) = (USItype) (__x); \ + } while (0) +#endif /* _TMS320C6400_PLUS */ + +#define count_leading_zeros(count, x) ((count) = __builtin_clz (x)) +#ifdef _TMS320C6400 +#define count_trailing_zeros(count, x) ((count) = __builtin_ctz (x)) +#endif +#define UMUL_TIME 4 +#define UDIV_TIME 40 +#endif /* _TMS320C6X */ + +#if defined (__xtensa__) && W_TYPE_SIZE == 32 +/* This code is not Xtensa-configuration-specific, so rely on the compiler + to expand builtin functions depending on what configuration features + are available. This avoids library calls when the operation can be + performed in-line. */ +#define umul_ppmm(w1, w0, u, v) \ + do { \ + DWunion __w; \ + __w.ll = __builtin_umulsidi3 (u, v); \ + w1 = __w.s.high; \ + w0 = __w.s.low; \ + } while (0) +#define __umulsidi3(u, v) __builtin_umulsidi3 (u, v) +#define count_leading_zeros(COUNT, X) ((COUNT) = __builtin_clz (X)) +#define count_trailing_zeros(COUNT, X) ((COUNT) = __builtin_ctz (X)) +#endif /* __xtensa__ */ + +#if defined xstormy16 +extern UHItype __stormy16_count_leading_zeros (UHItype); +#define count_leading_zeros(count, x) \ + do \ + { \ + UHItype size; \ + \ + /* We assume that W_TYPE_SIZE is a multiple of 16... */ \ + for ((count) = 0, size = W_TYPE_SIZE; size; size -= 16) \ + { \ + UHItype c; \ + \ + c = __clzhi2 ((x) >> (size - 16)); \ + (count) += c; \ + if (c != 16) \ + break; \ + } \ + } \ + while (0) +#define COUNT_LEADING_ZEROS_0 W_TYPE_SIZE +#endif + +#if defined (__z8000__) && W_TYPE_SIZE == 16 +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + __asm__ ("add %H1,%H5\n\tadc %H0,%H3" \ + : "=r" ((unsigned int)(sh)), \ + "=&r" ((unsigned int)(sl)) \ + : "%0" ((unsigned int)(ah)), \ + "r" ((unsigned int)(bh)), \ + "%1" ((unsigned int)(al)), \ + "rQR" ((unsigned int)(bl))) +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + __asm__ ("sub %H1,%H5\n\tsbc %H0,%H3" \ + : "=r" ((unsigned int)(sh)), \ + "=&r" ((unsigned int)(sl)) \ + : "0" ((unsigned int)(ah)), \ + "r" ((unsigned int)(bh)), \ + "1" ((unsigned int)(al)), \ + "rQR" ((unsigned int)(bl))) +#define umul_ppmm(xh, xl, m0, m1) \ + do { \ + union {long int __ll; \ + struct {unsigned int __h, __l;} __i; \ + } __xx; \ + unsigned int __m0 = (m0), __m1 = (m1); \ + __asm__ ("mult %S0,%H3" \ + : "=r" (__xx.__i.__h), \ + "=r" (__xx.__i.__l) \ + : "%1" (__m0), \ + "rQR" (__m1)); \ + (xh) = __xx.__i.__h; (xl) = __xx.__i.__l; \ + (xh) += ((((signed int) __m0 >> 15) & __m1) \ + + (((signed int) __m1 >> 15) & __m0)); \ + } while (0) +#endif /* __z8000__ */ + +#endif /* __GNUC__ */ + +/* If this machine has no inline assembler, use C macros. */ + +#if !defined (add_ssaaaa) +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + do { \ + UWtype __x; \ + __x = (al) + (bl); \ + (sh) = (ah) + (bh) + (__x < (al)); \ + (sl) = __x; \ + } while (0) +#endif + +#if !defined (sub_ddmmss) +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + do { \ + UWtype __x; \ + __x = (al) - (bl); \ + (sh) = (ah) - (bh) - (__x > (al)); \ + (sl) = __x; \ + } while (0) +#endif + +/* If we lack umul_ppmm but have smul_ppmm, define umul_ppmm in terms of + smul_ppmm. */ +#if !defined (umul_ppmm) && defined (smul_ppmm) +#define umul_ppmm(w1, w0, u, v) \ + do { \ + UWtype __w1; \ + UWtype __xm0 = (u), __xm1 = (v); \ + smul_ppmm (__w1, w0, __xm0, __xm1); \ + (w1) = __w1 + (-(__xm0 >> (W_TYPE_SIZE - 1)) & __xm1) \ + + (-(__xm1 >> (W_TYPE_SIZE - 1)) & __xm0); \ + } while (0) +#endif + +/* If we still don't have umul_ppmm, define it using plain C. */ +#if !defined (umul_ppmm) +#define umul_ppmm(w1, w0, u, v) \ + do { \ + UWtype __x0, __x1, __x2, __x3; \ + UHWtype __ul, __vl, __uh, __vh; \ + \ + __ul = __ll_lowpart (u); \ + __uh = __ll_highpart (u); \ + __vl = __ll_lowpart (v); \ + __vh = __ll_highpart (v); \ + \ + __x0 = (UWtype) __ul * __vl; \ + __x1 = (UWtype) __ul * __vh; \ + __x2 = (UWtype) __uh * __vl; \ + __x3 = (UWtype) __uh * __vh; \ + \ + __x1 += __ll_highpart (__x0);/* this can't give carry */ \ + __x1 += __x2; /* but this indeed can */ \ + if (__x1 < __x2) /* did we get it? */ \ + __x3 += __ll_B; /* yes, add it in the proper pos. */ \ + \ + (w1) = __x3 + __ll_highpart (__x1); \ + (w0) = __ll_lowpart (__x1) * __ll_B + __ll_lowpart (__x0); \ + } while (0) +#endif + +#if !defined (__umulsidi3) +#define __umulsidi3(u, v) \ + ({DWunion __w; \ + umul_ppmm (__w.s.high, __w.s.low, u, v); \ + __w.ll; }) +#endif + +/* Define this unconditionally, so it can be used for debugging. */ +#define __udiv_qrnnd_c(q, r, n1, n0, d) \ + do { \ + UWtype __d1, __d0, __q1, __q0; \ + UWtype __r1, __r0, __m; \ + __d1 = __ll_highpart (d); \ + __d0 = __ll_lowpart (d); \ + \ + __r1 = (n1) % __d1; \ + __q1 = (n1) / __d1; \ + __m = (UWtype) __q1 * __d0; \ + __r1 = __r1 * __ll_B | __ll_highpart (n0); \ + if (__r1 < __m) \ + { \ + __q1--, __r1 += (d); \ + if (__r1 >= (d)) /* i.e. we didn't get carry when adding to __r1 */\ + if (__r1 < __m) \ + __q1--, __r1 += (d); \ + } \ + __r1 -= __m; \ + \ + __r0 = __r1 % __d1; \ + __q0 = __r1 / __d1; \ + __m = (UWtype) __q0 * __d0; \ + __r0 = __r0 * __ll_B | __ll_lowpart (n0); \ + if (__r0 < __m) \ + { \ + __q0--, __r0 += (d); \ + if (__r0 >= (d)) \ + if (__r0 < __m) \ + __q0--, __r0 += (d); \ + } \ + __r0 -= __m; \ + \ + (q) = (UWtype) __q1 * __ll_B | __q0; \ + (r) = __r0; \ + } while (0) + +/* If the processor has no udiv_qrnnd but sdiv_qrnnd, go through + __udiv_w_sdiv (defined in libgcc or elsewhere). */ +#if !defined (udiv_qrnnd) && defined (sdiv_qrnnd) +#define udiv_qrnnd(q, r, nh, nl, d) \ + do { \ + extern UWtype __udiv_w_sdiv (UWtype *, UWtype, UWtype, UWtype); \ + UWtype __r; \ + (q) = __udiv_w_sdiv (&__r, nh, nl, d); \ + (r) = __r; \ + } while (0) +#endif + +/* If udiv_qrnnd was not defined for this processor, use __udiv_qrnnd_c. */ +#if !defined (udiv_qrnnd) +#define UDIV_NEEDS_NORMALIZATION 1 +#define udiv_qrnnd __udiv_qrnnd_c +#endif + +#if !defined (count_leading_zeros) +#define count_leading_zeros(count, x) \ + do { \ + UWtype __xr = (x); \ + UWtype __a; \ + \ + if (W_TYPE_SIZE <= 32) \ + { \ + __a = __xr < ((UWtype)1<<2*__BITS4) \ + ? (__xr < ((UWtype)1<<__BITS4) ? 0 : __BITS4) \ + : (__xr < ((UWtype)1<<3*__BITS4) ? 2*__BITS4 : 3*__BITS4); \ + } \ + else \ + { \ + for (__a = W_TYPE_SIZE - 8; __a > 0; __a -= 8) \ + if (((__xr >> __a) & 0xff) != 0) \ + break; \ + } \ + \ + (count) = W_TYPE_SIZE - (__clz_tab[__xr >> __a] + __a); \ + } while (0) +#define COUNT_LEADING_ZEROS_0 W_TYPE_SIZE +#endif + +#if !defined (count_trailing_zeros) +/* Define count_trailing_zeros using count_leading_zeros. The latter might be + defined in asm, but if it is not, the C version above is good enough. */ +#define count_trailing_zeros(count, x) \ + do { \ + UWtype __ctz_x = (x); \ + UWtype __ctz_c; \ + count_leading_zeros (__ctz_c, __ctz_x & -__ctz_x); \ + (count) = W_TYPE_SIZE - 1 - __ctz_c; \ + } while (0) +#endif + +#ifndef UDIV_NEEDS_NORMALIZATION +#define UDIV_NEEDS_NORMALIZATION 0 +#endif diff --git a/am/src/riscv/npc/libgcc/muldi3.S b/am/src/riscv/npc/libgcc/muldi3.S new file mode 100644 index 0000000..16166d0 --- /dev/null +++ b/am/src/riscv/npc/libgcc/muldi3.S @@ -0,0 +1,48 @@ +/* Integer multiplication routines for RISC-V. + + Copyright (C) 2016-2022 Free Software Foundation, Inc. + +This file is part of GCC. + +GCC is free software; 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, or (at your option) any later +version. + +GCC 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 General Public License +for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +. */ + +#include "riscv-asm.h" + + .text + .align 2 + +#if __riscv_xlen == 32 +/* Our RV64 64-bit routine is equivalent to our RV32 32-bit routine. */ +# define __muldi3 __mulsi3 +#endif + +FUNC_BEGIN (__muldi3) + mv a2, a0 + li a0, 0 +.L1: + andi a3, a1, 1 + beqz a3, .L2 + add a0, a0, a2 +.L2: + srli a1, a1, 1 + slli a2, a2, 1 + bnez a1, .L1 + ret +FUNC_END (__muldi3) diff --git a/am/src/riscv/npc/libgcc/multi3.c b/am/src/riscv/npc/libgcc/multi3.c new file mode 100644 index 0000000..ce357ed --- /dev/null +++ b/am/src/riscv/npc/libgcc/multi3.c @@ -0,0 +1,86 @@ +/* Multiplication two double word integers for RISC-V. + + Copyright (C) 2016-2022 Free Software Foundation, Inc. + +This file is part of GCC. + +GCC is free software; 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, or (at your option) any later +version. + +GCC 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 General Public License +for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +. */ + +//#include "tconfig.h" +//#include "tsystem.h" +//#include "coretypes.h" +//#include "tm.h" +//#include "libgcc_tm.h" +#define LIBGCC2_UNITS_PER_WORD (__riscv_xlen / 8) + +#include "libgcc2.h" + +#if __riscv_xlen == 32 +/* Our RV64 64-bit routines are equivalent to our RV32 32-bit routines. */ +# define __multi3 __muldi3 +#endif + +DWtype +__multi3 (DWtype u, DWtype v) +{ + const DWunion uu = {.ll = u}; + const DWunion vv = {.ll = v}; + DWunion w; + UWtype u_low = uu.s.low; + UWtype v_low = vv.s.low; + UWtype u_low_msb; + UWtype w_low = 0; + UWtype new_w_low; + UWtype w_high = 0; + UWtype w_high_tmp = 0; + UWtype w_high_tmp2x; + UWtype carry; + + /* Calculate low half part of u and v, and get a UDWtype result just like + what __umulsidi3 do. */ + do + { + new_w_low = w_low + u_low; + w_high_tmp2x = w_high_tmp << 1; + w_high_tmp += w_high; + if (v_low & 1) + { + carry = new_w_low < w_low; + w_low = new_w_low; + w_high = carry + w_high_tmp; + } + u_low_msb = (u_low >> ((sizeof (UWtype) * 8) - 1)); + v_low >>= 1; + u_low <<= 1; + w_high_tmp = u_low_msb | w_high_tmp2x; + } + while (v_low); + + w.s.low = w_low; + w.s.high = w_high; + + if (uu.s.high) + w.s.high = w.s.high + __muluw3(vv.s.low, uu.s.high); + + if (vv.s.high) + w.s.high += __muluw3(uu.s.low, vv.s.high); + + return w.ll; +} diff --git a/am/src/riscv/npc/libgcc/riscv-asm.h b/am/src/riscv/npc/libgcc/riscv-asm.h new file mode 100644 index 0000000..b70930e --- /dev/null +++ b/am/src/riscv/npc/libgcc/riscv-asm.h @@ -0,0 +1,41 @@ +/* Copyright (C) 2017-2022 Free Software Foundation, Inc. + +This file is free software; 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, or (at your option) any +later version. + +This file 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 +General Public License for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +. */ + +#define FUNC_TYPE(X) .type X,@function +#define FUNC_SIZE(X) .size X,.-X + +#define FUNC_BEGIN(X) \ + .globl X; \ + FUNC_TYPE (X); \ +X: + +#define FUNC_END(X) \ + FUNC_SIZE(X) + +#define FUNC_ALIAS(X,Y) \ + .globl X; \ + X = Y + +#define CONCAT1(a, b) CONCAT2(a, b) +#define CONCAT2(a, b) a ## b +#define HIDDEN_JUMPTARGET(X) CONCAT1(__hidden_, X) +#define HIDDEN_DEF(X) FUNC_ALIAS(HIDDEN_JUMPTARGET(X), X); \ + .hidden HIDDEN_JUMPTARGET(X) diff --git a/am/src/riscv/npc/libgcc/unused.c b/am/src/riscv/npc/libgcc/unused.c new file mode 100644 index 0000000..bf95515 --- /dev/null +++ b/am/src/riscv/npc/libgcc/unused.c @@ -0,0 +1,5 @@ +#include +#include + +double __muldf3 (double a, double b) { panic("Not implement"); } +long __fixdfdi (double a) { panic("Not implement"); } diff --git a/scripts/riscv32e-npc.mk b/scripts/riscv32e-npc.mk index c7d0a2b..b2b6fec 100644 --- a/scripts/riscv32e-npc.mk +++ b/scripts/riscv32e-npc.mk @@ -2,3 +2,9 @@ include $(AM_HOME)/scripts/isa/riscv.mk include $(AM_HOME)/scripts/platform/npc.mk COMMON_CFLAGS += -march=rv32e_zicsr -mabi=ilp32e # overwrite LDFLAGS += -melf32lriscv # overwrite + +AM_SRCS += riscv/npc/libgcc/div.S \ + riscv/npc/libgcc/muldi3.S \ + riscv/npc/libgcc/multi3.c \ + riscv/npc/libgcc/ashldi3.c \ + riscv/npc/libgcc/unused.c