diff options
Diffstat (limited to 'libc/sysdeps/linux/sparc64/soft-fp/longlong.h')
| -rw-r--r-- | libc/sysdeps/linux/sparc64/soft-fp/longlong.h | 1773 |
1 files changed, 1773 insertions, 0 deletions
diff --git a/libc/sysdeps/linux/sparc64/soft-fp/longlong.h b/libc/sysdeps/linux/sparc64/soft-fp/longlong.h new file mode 100644 index 000000000..0ec11c505 --- /dev/null +++ b/libc/sysdeps/linux/sparc64/soft-fp/longlong.h @@ -0,0 +1,1773 @@ +/* longlong.h -- definitions for mixed size 32/64 bit arithmetic. + Copyright (C) 1991-2017 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 + <http://www.gnu.org/licenses/>. */ + +/* 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)), \ + "rIJ" ((USItype) (bh)), \ + "%r" ((USItype) (al)), \ + "rIJ" ((USItype) (bl))) +#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)), \ + "rIJ" ((USItype) (bh)), \ + "r" ((USItype) (al)), \ + "rIJ" ((USItype) (bl))) + +#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 +#endif + +#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<bl" arithmetically comes out making an actual 0 or 1 in a + register, which takes an extra cycle. */ +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + do { \ + UWtype __x; \ + __x = (al) - (bl); \ + if ((al) < (bl)) \ + (sh) = (ah) - (bh) - 1; \ + else \ + (sh) = (ah) - (bh); \ + (sl) = __x; \ + } while (0) + +/* Do both product parts in assembly, since that gives better code with + all gcc versions. Some callers will just use the upper part, and in + that situation we waste an instruction, but not any cycles. */ +#define umul_ppmm(ph, pl, m0, m1) \ + __asm__ ("xma.hu %0 = %2, %3, f0\n\txma.l %1 = %2, %3, f0" \ + : "=&f" (ph), "=f" (pl) \ + : "f" (m0), "f" (m1)) +#define count_leading_zeros(count, x) \ + do { \ + UWtype _x = (x), _y, _a, _c; \ + __asm__ ("mux1 %0 = %1, @rev" : "=r" (_y) : "r" (_x)); \ + __asm__ ("czx1.l %0 = %1" : "=r" (_a) : "r" (-_y | _y)); \ + _c = (_a - 1) << 3; \ + _x >>= _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__ */ + +#if defined (__ns32000__) && W_TYPE_SIZE == 32 +#define umul_ppmm(w1, w0, u, v) \ + ({union {UDItype __ll; \ + struct {USItype __l, __h;} __i; \ + } __xx; \ + __asm__ ("meid %2,%0" \ + : "=g" (__xx.__ll) \ + : "%0" ((USItype) (u)), \ + "g" ((USItype) (v))); \ + (w1) = __xx.__i.__h; (w0) = __xx.__i.__l;}) +#define __umulsidi3(u, v) \ + ({UDItype __w; \ + __asm__ ("meid %2,%0" \ + : "=g" (__w) \ + : "%0" ((USItype) (u)), \ + "g" ((USItype) (v))); \ + __w; }) +#define udiv_qrnnd(q, r, n1, n0, d) \ + ({union {UDItype __ll; \ + struct {USItype __l, __h;} __i; \ + } __xx; \ + __xx.__i.__h = (n1); __xx.__i.__l = (n0); \ + __asm__ ("deid %2,%0" \ + : "=g" (__xx.__ll) \ + : "0" (__xx.__ll), \ + "g" ((USItype) (d))); \ + (r) = __xx.__i.__l; (q) = __xx.__i.__h; }) +#define count_trailing_zeros(count,x) \ + do { \ + __asm__ ("ffsd %2,%0" \ + : "=r" ((USItype) (count)) \ + : "0" ((USItype) 0), \ + "r" ((USItype) (x))); \ + } while (0) +#endif /* __ns32000__ */ + +/* 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), |