/* longlong.h -- definitions for mixed size 32/64 bit arithmetic.
- Copyright (C) 1991,92,94,95,96,97,98,99, 2000 Free Software Foundation, Inc.
+ Copyright (C) 1991, 1992, 1994, 1995, 1996, 1997, 1998, 1999, 2000,
+ 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011
+ Free Software Foundation, Inc.
- This definition 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 2, or (at your option) any later version.
-
- This definition 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.
+ This file is part of the GNU C Library.
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 59 Temple Place - Suite 330,
- Boston, MA 02111-1307, USA. */
+ 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, write to the Free
+ Software Foundation, 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301, USA. */
/* You have to define the following before including this file:
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.
-*/
+ 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 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, multipler, multiplicand) multiplies two
- UWtype integers MULTIPLER and MULTIPLICAND, and generates a two UWtype
+ 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
is rounded towards 0.
5) count_leading_zeros(count, x) counts the number of zero-bits from the
- msb to the first non-zero bit in the UWtype X. This is the number of
+ 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.
#define __AND_CLOBBER_CC , "cc"
#endif /* __GNUC__ < 2 */
-#if (defined (__a29k__) || defined (_AM29K)) && W_TYPE_SIZE == 32
-#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
- __asm__ ("add %1,%4,%5\n\taddc %0,%2,%3" \
- : "=r" ((USItype) (sh)), \
- "=&r" ((USItype) (sl)) \
- : "%r" ((USItype) (ah)), \
- "rI" ((USItype) (bh)), \
- "%r" ((USItype) (al)), \
- "rI" ((USItype) (bl)))
-#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
- __asm__ ("sub %1,%4,%5\n\tsubc %0,%2,%3" \
- : "=r" ((USItype) (sh)), \
- "=&r" ((USItype) (sl)) \
- : "r" ((USItype) (ah)), \
- "rI" ((USItype) (bh)), \
- "r" ((USItype) (al)), \
- "rI" ((USItype) (bl)))
-#define umul_ppmm(xh, xl, m0, m1) \
- do { \
- USItype __m0 = (m0), __m1 = (m1); \
- __asm__ ("multiplu %0,%1,%2" \
- : "=r" ((USItype) (xl)) \
- : "r" (__m0), \
- "r" (__m1)); \
- __asm__ ("multmu %0,%1,%2" \
- : "=r" ((USItype) (xh)) \
- : "r" (__m0), \
- "r" (__m1)); \
- } while (0)
-#define udiv_qrnnd(q, r, n1, n0, d) \
- __asm__ ("dividu %0,%3,%4" \
- : "=r" ((USItype) (q)), \
- "=q" ((USItype) (r)) \
- : "1" ((USItype) (n1)), \
- "r" ((USItype) (n0)), \
- "r" ((USItype) (d)))
-#define count_leading_zeros(count, x) \
- __asm__ ("clz %0,%1" \
- : "=r" ((USItype) (count)) \
- : "r" ((USItype) (x)))
-#define COUNT_LEADING_ZEROS_0 32
-#endif /* __a29k__ */
-
#if defined (__alpha) && W_TYPE_SIZE == 64
#define umul_ppmm(ph, pl, m0, m1) \
do { \
UDItype __m0 = (m0), __m1 = (m1); \
- __asm__ ("umulh %r1,%2,%0" \
- : "=r" ((UDItype) ph) \
- : "%rJ" (__m0), \
- "rI" (__m1)); \
+ (ph) = __builtin_alpha_umulh (__m0, __m1); \
(pl) = __m0 * __m1; \
} while (0)
#define UMUL_TIME 46
(q) = __udiv_qrnnd (&__r, (n1), (n0), (d)); \
(r) = __r; \
} while (0)
-extern UDItype __udiv_qrnnd PARAMS ((UDItype *, UDItype, UDItype, UDItype));
+extern UDItype __udiv_qrnnd (UDItype *, UDItype, UDItype, UDItype);
#define UDIV_TIME 220
#endif /* LONGLONG_STANDALONE */
#ifdef __alpha_cix__
-#define count_leading_zeros(COUNT,X) \
- __asm__("ctlz %1,%0" : "=r"(COUNT) : "r"(X))
-#define count_trailing_zeros(COUNT,X) \
- __asm__("cttz %1,%0" : "=r"(COUNT) : "r"(X))
+#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
-extern const UQItype __clz_tab[];
#define count_leading_zeros(COUNT,X) \
do { \
UDItype __xr = (X), __t, __a; \
- __asm__("cmpbge $31,%1,%0" : "=r"(__t) : "r"(__xr)); \
+ __t = __builtin_alpha_cmpbge (0, __xr); \
__a = __clz_tab[__t ^ 0xff] - 1; \
- __asm__("extbl %1,%2,%0" : "=r"(__t) : "r"(__xr), "r"(__a)); \
+ __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; \
- __asm__("cmpbge $31,%1,%0" : "=r"(__t) : "r"(__xr)); \
+ __t = __builtin_alpha_cmpbge (0, __xr); \
__t = ~__t & -~__t; \
__a = ((__t & 0xCC) != 0) * 2; \
__a += ((__t & 0xF0) != 0) * 4; \
__a += ((__t & 0xAA) != 0); \
- __asm__("extbl %1,%2,%0" : "=r"(__t) : "r"(__xr), "r"(__a)); \
+ __t = __builtin_alpha_extbl (__xr, __a); \
__a <<= 3; \
__t &= -__t; \
__a += ((__t & 0xCC) != 0) * 2; \
"rIJ" ((USItype) (bh)), \
"r" ((USItype) (al)), \
"rIJ" ((USItype) (bl)))
-/* Call libgcc1 routine. */
+/* Call libgcc routine. */
#define umul_ppmm(w1, w0, u, v) \
do { \
DWunion __w; \
UDItype __umulsidi3 (USItype, USItype);
#endif
-#if defined (__arm__) && W_TYPE_SIZE == 32
+#if defined (__arm__) && !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) (ah)), \
"rI" ((USItype) (bh)), \
"%r" ((USItype) (al)), \
- "rI" ((USItype) (bl)))
+ "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) (ah)), \
"rI" ((USItype) (bh)), \
"r" ((USItype) (al)), \
- "rI" ((USItype) (bl)))
+ "rI" ((USItype) (bl)) __CLOBBER_CC)
#define umul_ppmm(xh, xl, a, b) \
{register USItype __t0, __t1, __t2; \
__asm__ ("%@ Inlined umul_ppmm\n" \
"=r" ((USItype) (xl)), \
"=&r" (__t0), "=&r" (__t1), "=r" (__t2) \
: "r" ((USItype) (a)), \
- "r" ((USItype) (b)));}
+ "r" ((USItype) (b)) __CLOBBER_CC );}
#define UMUL_TIME 20
#define UDIV_TIME 100
#endif /* __arm__ */
-#if defined (__clipper__) && W_TYPE_SIZE == 32
-#define umul_ppmm(w1, w0, u, v) \
- ({union {UDItype __ll; \
- struct {USItype __l, __h;} __i; \
- } __xx; \
- __asm__ ("mulwux %2,%0" \
- : "=r" (__xx.__ll) \
- : "%0" ((USItype) (u)), \
- "r" ((USItype) (v))); \
- (w1) = __xx.__i.__h; (w0) = __xx.__i.__l;})
-#define smul_ppmm(w1, w0, u, v) \
- ({union {DItype __ll; \
- struct {SItype __l, __h;} __i; \
- } __xx; \
- __asm__ ("mulwx %2,%0" \
- : "=r" (__xx.__ll) \
- : "%0" ((SItype) (u)), \
- "r" ((SItype) (v))); \
- (w1) = __xx.__i.__h; (w0) = __xx.__i.__l;})
-#define __umulsidi3(u, v) \
- ({UDItype __w; \
- __asm__ ("mulwux %2,%0" \
- : "=r" (__w) \
- : "%0" ((USItype) (u)), \
- "r" ((USItype) (v))); \
- __w; })
-#endif /* __clipper__ */
+#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_LEADING_ZEROS_0 32
+#endif
-#if defined (__gmicro__) && W_TYPE_SIZE == 32
-#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
- __asm__ ("add.w %5,%1\n\taddx %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__ ("sub.w %5,%1\n\tsubx %3,%0" \
- : "=g" ((USItype) (sh)), \
- "=&g" ((USItype) (sl)) \
- : "0" ((USItype) (ah)), \
- "g" ((USItype) (bh)), \
- "1" ((USItype) (al)), \
- "g" ((USItype) (bl)))
-#define umul_ppmm(ph, pl, m0, m1) \
- __asm__ ("mulx %3,%0,%1" \
- : "=g" ((USItype) (ph)), \
- "=r" ((USItype) (pl)) \
- : "%0" ((USItype) (m0)), \
- "g" ((USItype) (m1)))
-#define udiv_qrnnd(q, r, nh, nl, d) \
- __asm__ ("divx %4,%0,%1" \
- : "=g" ((USItype) (q)), \
- "=r" ((USItype) (r)) \
- : "1" ((USItype) (nh)), \
- "0" ((USItype) (nl)), \
- "g" ((USItype) (d)))
-#define count_leading_zeros(count, x) \
- __asm__ ("bsch/1 %1,%0" \
- : "=g" (count) \
- : "g" ((USItype) (x)), \
- "0" ((USItype) 0))
+#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__) && __CRIS_arch_version >= 3
+#define count_leading_zeros(COUNT, X) ((COUNT) = __builtin_clz (X))
+#if __CRIS_arch_version >= 8
+#define count_trailing_zeros(COUNT, X) ((COUNT) = __builtin_ctz (X))
#endif
+#endif /* __CRIS__ */
#if defined (__hppa) && W_TYPE_SIZE == 32
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
} while (0)
#endif
-#if (defined (__i370__) || defined (__mvs__)) && W_TYPE_SIZE == 32
-#define umul_ppmm(xh, xl, m0, m1) \
- do { \
- union {UDItype __ll; \
- struct {USItype __h, __l;} __i; \
- } __xx; \
- USItype __m0 = (m0), __m1 = (m1); \
- __asm__ ("mr %0,%3" \
- : "=r" (__xx.__i.__h), \
- "=r" (__xx.__i.__l) \
- : "%1" (__m0), \
- "r" (__m1)); \
- (xh) = __xx.__i.__h; (xl) = __xx.__i.__l; \
- (xh) += ((((SItype) __m0 >> 31) & __m1) \
- + (((SItype) __m1 >> 31) & __m0)); \
- } while (0)
+#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; \
- } __xx; \
- __asm__ ("mr %0,%3" \
- : "=r" (__xx.__i.__h), \
- "=r" (__xx.__i.__l) \
- : "%1" (m0), \
- "r" (m1)); \
- (xh) = __xx.__i.__h; (xl) = __xx.__i.__l; \
+ } __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; \
- } __xx; \
- __xx.__i.__h = n1; __xx.__i.__l = n0; \
+ } __x; \
+ __x.__i.__h = n1; __x.__i.__l = n0; \
__asm__ ("dr %0,%2" \
- : "=r" (__xx.__ll) \
- : "0" (__xx.__ll), "r" (d)); \
- (q) = __xx.__i.__l; (r) = __xx.__i.__h; \
+ : "=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") = n0; \
+ register SItype r1 __asm__ ("1") = n1; \
+ \
+ __asm__ ("dr\t%%r0,%3" \
+ : "=r" (r0), "=r" (r1) \
+ : "r" (r0), "r" (r1), "r" (d)); \
+ (q) = r0; (r) = r1; \
+ } while (0)
+#endif /* __zarch__ */
#endif
#if (defined (__i386__) || defined (__i486__)) && W_TYPE_SIZE == 32
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
- __asm__ ("addl %5,%1\n\tadcl %3,%0" \
+ __asm__ ("add{l} {%5,%1|%1,%5}\n\tadc{l} {%3,%0|%0,%3}" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "%0" ((USItype) (ah)), \
"%1" ((USItype) (al)), \
"g" ((USItype) (bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
- __asm__ ("subl %5,%1\n\tsbbl %3,%0" \
+ __asm__ ("sub{l} {%5,%1|%1,%5}\n\tsbb{l} {%3,%0|%0,%3}" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "0" ((USItype) (ah)), \
"1" ((USItype) (al)), \
"g" ((USItype) (bl)))
#define umul_ppmm(w1, w0, u, v) \
- __asm__ ("mull %3" \
+ __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__ ("divl %4" \
+ __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) \
- do { \
- USItype __cbtmp; \
- __asm__ ("bsrl %1,%0" \
- : "=r" (__cbtmp) : "rm" ((USItype) (x))); \
- (count) = __cbtmp ^ 31; \
- } while (0)
-#define count_trailing_zeros(count, x) \
- __asm__ ("bsfl %1,%0" : "=r" (count) : "rm" ((USItype)(x)))
+#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 (__i860__) && W_TYPE_SIZE == 32
-#if 0
-/* Make sure these patterns really improve the code before
- switching them on. */
+#if (defined (__x86_64__) || defined (__i386__)) && W_TYPE_SIZE == 64
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
- do { \
- union \
- { \
- DItype __ll; \
- struct {USItype __l, __h;} __i; \
- } __a, __b, __s; \
- __a.__i.__l = (al); \
- __a.__i.__h = (ah); \
- __b.__i.__l = (bl); \
- __b.__i.__h = (bh); \
- __asm__ ("fiadd.dd %1,%2,%0" \
- : "=f" (__s.__ll) \
- : "%f" (__a.__ll), "f" (__b.__ll)); \
- (sh) = __s.__i.__h; \
- (sl) = __s.__i.__l; \
- } while (0)
+ __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) \
- do { \
- union \
- { \
- DItype __ll; \
- struct {USItype __l, __h;} __i; \
- } __a, __b, __s; \
- __a.__i.__l = (al); \
- __a.__i.__h = (ah); \
- __b.__i.__l = (bl); \
- __b.__i.__h = (bh); \
- __asm__ ("fisub.dd %1,%2,%0" \
- : "=f" (__s.__ll) \
- : "%f" (__a.__ll), "f" (__b.__ll)); \
- (sh) = __s.__i.__h; \
- (sl) = __s.__i.__l; \
- } while (0)
-#endif
-#endif /* __i860__ */
+ __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) \
__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 %%5,%1\n\taddx %%3,%0" \
+ __asm__ ("cmp %0,%0\n\taddx %1,%5\n\taddx %0,%3" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
- : "%0" ((USItype) (ah)), \
+ : "0" ((USItype) (ah)), \
"r" ((USItype) (bh)), \
- "%1" ((USItype) (al)), \
+ "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 %5,%1\n\tsubx %3,%0" \
+ __asm__ ("cmp %0,%0\n\tsubx %1,%5\n\tsubx %0,%3" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "0" ((USItype) (ah)), \
"1" ((USItype) (al)), \
"g" ((USItype) (bl)))
-/* The '020, '030, '040 and CPU32 have 32x32->64 and 64/32->32q-32r. */
-#if defined (__mc68020__) || defined(mc68020) \
- || defined(__mc68030__) || defined(mc68030) \
- || defined(__mc68040__) || defined(mc68040) \
- || defined(__mcpu32__) || defined(mcpu32) \
- || defined(__NeXT__)
+/* 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)), \
"1" ((USItype) (n1)), \
"dmi" ((USItype) (d)))
-#else /* not mc68020 */
-#if !defined(__mcf5200__)
+#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" \
: "d0", "d1", "d2", "d3", "d4")
#define UMUL_TIME 100
#define UDIV_TIME 400
-#endif /* not mcf5200 */
+
#endif /* not mc68020 */
-/* The '020, '030, '040 and '060 have bitfield insns. */
-#if defined (__mc68020__) || defined(mc68020) \
- || defined(__mc68030__) || defined(mc68030) \
- || defined(__mc68040__) || defined(mc68040) \
- || defined(__mc68060__) || defined(mc68060) \
- || defined(__NeXT__)
+/* 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 */
#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) \
- __asm__ ("multu %2,%3" \
- : "=l" ((USItype) (w0)), \
- "=h" ((USItype) (w1)) \
- : "d" ((USItype) (u)), \
- "d" ((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)
#define UMUL_TIME 10
#define UDIV_TIME 100
+
+#if (__mips == 32 || __mips == 64) && ! __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
"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))); \
+ do { \
+ __asm__ ("ffsd %2,%0" \
+ : "=r" ((USItype) (count)) \
+ : "0" ((USItype) 0), \
+ "r" ((USItype) (x))); \
} while (0)
#endif /* __ns32000__ */
-#if (defined (_ARCH_PPC) || defined (_IBMR2))
-#if W_TYPE_SIZE == 32
+/* 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 (_ARCH_PWR) /* AIX */ \
+ || defined (_ARCH_COM) /* 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__ ("{a%I4|add%I4c} %1,%3,%4\n\t{aze|addze} %0,%2" \
- : "=r" ((USItype) (sh)), \
- "=&r" ((USItype) (sl)) \
- : "%r" ((USItype) (ah)), \
- "%r" ((USItype) (al)), \
- "rI" ((USItype) (bl))); \
- else if (__builtin_constant_p (bh) && (bh) ==~(USItype) 0) \
+ : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\
+ else if (__builtin_constant_p (bh) && (bh) == ~(USItype) 0) \
__asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{ame|addme} %0,%2" \
- : "=r" ((USItype) (sh)), \
- "=&r" ((USItype) (sl)) \
- : "%r" ((USItype) (ah)), \
- "%r" ((USItype) (al)), \
- "rI" ((USItype) (bl))); \
+ : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\
else \
__asm__ ("{a%I5|add%I5c} %1,%4,%5\n\t{ae|adde} %0,%2,%3" \
- : "=r" ((USItype) (sh)), \
- "=&r" ((USItype) (sl)) \
- : "%r" ((USItype) (ah)), \
- "r" ((USItype) (bh)), \
- "%r" ((USItype) (al)), \
- "rI" ((USItype) (bl))); \
+ : "=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__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfze|subfze} %0,%2" \
- : "=r" ((USItype) (sh)), \
- "=&r" ((USItype) (sl)) \
- : "r" ((USItype) (bh)), \
- "rI" ((USItype) (al)), \
- "r" ((USItype) (bl))); \
- else if (__builtin_constant_p (ah) && (ah) ==~(USItype) 0) \
+ : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\
+ else if (__builtin_constant_p (ah) && (ah) == ~(USItype) 0) \
__asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfme|subfme} %0,%2" \
- : "=r" ((USItype) (sh)), \
- "=&r" ((USItype) (sl)) \
- : "r" ((USItype) (bh)), \
- "rI" ((USItype) (al)), \
- "r" ((USItype) (bl))); \
+ : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\
else if (__builtin_constant_p (bh) && (bh) == 0) \
__asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{ame|addme} %0,%2" \
- : "=r" ((USItype) (sh)), \
- "=&r" ((USItype) (sl)) \
- : "r" ((USItype) (ah)), \
- "rI" ((USItype) (al)), \
- "r" ((USItype) (bl))); \
- else if (__builtin_constant_p (bh) && (bh) ==~(USItype) 0) \
+ : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\
+ else if (__builtin_constant_p (bh) && (bh) == ~(USItype) 0) \
__asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{aze|addze} %0,%2" \
- : "=r" ((USItype) (sh)), \
- "=&r" ((USItype) (sl)) \
- : "r" ((USItype) (ah)), \
- "rI" ((USItype) (al)), \
- "r" ((USItype) (bl))); \
+ : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\
else \
__asm__ ("{sf%I4|subf%I4c} %1,%5,%4\n\t{sfe|subfe} %0,%3,%2" \
- : "=r" ((USItype) (sh)), \
- "=&r" ((USItype) (sl)) \
- : "r" ((USItype) (ah)), \
- "r" ((USItype) (bh)), \
- "rI" ((USItype) (al)), \
- "r" ((USItype) (bl))); \
+ : "=r" (sh), "=&r" (sl) \
+ : "r" (ah), "r" (bh), "rI" (al), "r" (bl)); \
} while (0)
-#endif /* W_TYPE_SIZE */
#define count_leading_zeros(count, x) \
- __asm__ ("{cntlz|cntlzw} %0,%1" \
- : "=r" ((USItype) (count)) \
- : "r" ((USItype) (x)))
+ __asm__ ("{cntlz|cntlzw} %0,%1" : "=r" (count) : "r" (x))
#define COUNT_LEADING_ZEROS_0 32
-#if defined (_ARCH_PPC)
+#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" ((USItype) ph) \
- : "%r" (__m0), \
- "r" (__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" ((SItype) ph) \
- : "%r" (__m0), \
- "r" (__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
#elif defined (_ARCH_PWR)
-#define umul_ppmm(xh, xl, m0, m1) \
- do { \
- USItype __m0 = (m0), __m1 = (m1); \
- __asm__ ("mul %0,%2,%3" \
- : "=r" ((USItype) (xh)), \
- "=q" ((USItype) (xl)) \
- : "r" (__m0), \
- "r" (__m1)); \
- (xh) += ((((SItype) __m0 >> 31) & __m1) \
- + (((SItype) __m1 >> 31) & __m0)); \
- } while (0)
#define UMUL_TIME 8
#define smul_ppmm(xh, xl, m0, m1) \
- __asm__ ("mul %0,%2,%3" \
- : "=r" ((SItype) (xh)), \
- "=q" ((SItype) (xl)) \
- : "r" (m0), \
- "r" (m1))
+ __asm__ ("mul %0,%2,%3" : "=r" (xh), "=q" (xl) : "r" (m0), "r" (m1))
#define SMUL_TIME 4
#define sdiv_qrnnd(q, r, nh, nl, d) \
- __asm__ ("div %0,%2,%4" \
- : "=r" ((SItype) (q)), "=q" ((SItype) (r)) \
- : "r" ((SItype) (nh)), "1" ((SItype) (nl)), "r" ((SItype) (d)))
+ __asm__ ("div %0,%2,%4" : "=r" (q), "=q" (r) : "r" (nh), "1" (nl), "r" (d))
#define UDIV_TIME 100
#endif
-#endif /* Power architecture variants. */
+#endif /* 32-bit POWER architecture variants. */
-#if defined (__pyr__) && W_TYPE_SIZE == 32
+/* 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) \
- __asm__ ("addw %5,%1\n\taddwc %3,%0" \
- : "=r" ((USItype) (sh)), \
- "=&r" ((USItype) (sl)) \
- : "%0" ((USItype) (ah)), \
- "g" ((USItype) (bh)), \
- "%1" ((USItype) (al)), \
- "g" ((USItype) (bl)))
+ do { \
+ if (__builtin_constant_p (bh) && (bh) == 0) \
+ __asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{aze|addze} %0,%2" \
+ : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\
+ else if (__builtin_constant_p (bh) && (bh) == ~(UDItype) 0) \
+ __asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{ame|addme} %0,%2" \
+ : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\
+ else \
+ __asm__ ("{a%I5|add%I5c} %1,%4,%5\n\t{ae|adde} %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) \
- __asm__ ("subw %5,%1\n\tsubwb %3,%0" \
- : "=r" ((USItype) (sh)), \
- "=&r" ((USItype) (sl)) \
- : "0" ((USItype) (ah)), \
- "g" ((USItype) (bh)), \
- "1" ((USItype) (al)), \
- "g" ((USItype) (bl)))
-/* This insn works on Pyramids with AP, XP, or MI CPUs, but not with SP. */
-#define umul_ppmm(w1, w0, u, v) \
- ({union {UDItype __ll; \
- struct {USItype __h, __l;} __i; \
- } __xx; \
- __asm__ ("movw %1,%R0
- uemul %2,%0" \
- : "=&r" (__xx.__ll) \
- : "g" ((USItype) (u)), \
- "g" ((USItype) (v))); \
- (w1) = __xx.__i.__h; (w0) = __xx.__i.__l;})
-#endif /* __pyr__ */
+ do { \
+ if (__builtin_constant_p (ah) && (ah) == 0) \
+ __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfze|subfze} %0,%2" \
+ : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\
+ else if (__builtin_constant_p (ah) && (ah) == ~(UDItype) 0) \
+ __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfme|subfme} %0,%2" \
+ : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\
+ else if (__builtin_constant_p (bh) && (bh) == 0) \
+ __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{ame|addme} %0,%2" \
+ : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\
+ else if (__builtin_constant_p (bh) && (bh) == ~(UDItype) 0) \
+ __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{aze|addze} %0,%2" \
+ : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\
+ else \
+ __asm__ ("{sf%I4|subf%I4c} %1,%5,%4\n\t{sfe|subfe} %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) \
} while (0)
#endif
-#if defined (__sh2__) && W_TYPE_SIZE == 32
+#if defined(__sh__) && !__SHMEDIA__ && W_TYPE_SIZE == 32
+#ifndef __sh1__
#define umul_ppmm(w1, w0, u, v) \
__asm__ ( \
- "dmulu.l %2,%3\n\tsts macl,%1\n\tsts mach,%0" \
- : "=r" ((USItype)(w1)), \
- "=r" ((USItype)(w0)) \
+ "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
+
+#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)
+
+#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 (__SH5__) && __SHMEDIA__ && W_TYPE_SIZE == 32
+#define __umulsidi3(u,v) ((UDItype)(USItype)u*(USItype)v)
+#define count_leading_zeros(count, x) \
+ do \
+ { \
+ UDItype x_ = (USItype)(x); \
+ SItype c_; \
+ \
+ __asm__ ("nsb %1, %0" : "=r" (c_) : "r" (x_)); \
+ (count) = c_ - 31; \
+ } \
+ while (0)
+#define COUNT_LEADING_ZEROS_0 32
+#endif
+
#if defined (__sparc__) && !defined (__arch64__) && !defined (__sparcv9) \
&& W_TYPE_SIZE == 32
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
: "r" ((USItype) (__d)), \
"1" ((USItype) (__n1)), \
"0" ((USItype) (__n0)) : "g1" __AND_CLOBBER_CC)
-#define UDIV_TIME (3+7*32) /* 7 instructions/iteration. 32 iterations. */
+#define UDIV_TIME (3+7*32) /* 7 instructions/iteration. 32 iterations. */
#endif /* __sparclite__ */
#endif /* __sparc_v8__ */
#endif /* sparc32 */
} 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" \
} 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 { \
__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. */ \
+ __x3 += __ll_B; /* yes, add it in the proper pos. */ \
\
(w1) = __x3 + __ll_highpart (__x1); \
(w0) = __ll_lowpart (__x1) * __ll_B + __ll_lowpart (__x0); \
#endif
#if !defined (count_leading_zeros)
-extern const UQItype __clz_tab[];
#define count_leading_zeros(count, x) \
do { \
UWtype __xr = (x); \