#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_LEADING_ZEROS_0 32
+#endif
+
+#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) \
__asm__ ("add %4,%5,%1\n\taddc %2,%3,%0" \
#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 (__x86_64__) || defined (__i386__)) && 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_clzl (x))
+#define count_trailing_zeros(count, x) ((count) = __builtin_ctzl (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; \
__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 /* __m88000__ */
#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
|| defined (__powerpc__) /* gcc */ \
|| defined (__POWERPC__) /* BEOS */ \
|| defined (__ppc__) /* Darwin */ \
- || defined (PPC) /* GNU/Linux, SysV */ \
+ || (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 { \
__asm__ ("{cntlz|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 (__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); \
} 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"); \
+ } 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))
+
+#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) \
} while (0)
#endif /* __vax__ */
+#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 (__z8000__) && W_TYPE_SIZE == 16
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
__asm__ ("add %H1,%H5\n\tadc %H0,%H3" \