/* 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) 1991,92,94,95,96,97,98,99,2000,2001 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
#if (defined (__a29k__) || defined (_AM29K)) && W_TYPE_SIZE == 32
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
- __asm__ ("add %1,%4,%5
- addc %0,%2,%3" \
+ __asm__ ("add %1,%4,%5\n" \
+ "addc %0,%2,%3" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "%r" ((USItype) (ah)), \
"%r" ((USItype) (al)), \
"rI" ((USItype) (bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
- __asm__ ("sub %1,%4,%5
- subc %0,%2,%3" \
+ __asm__ ("sub %1,%4,%5\n" \
+ "subc %0,%2,%3" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "r" ((USItype) (ah)), \
#if defined (__arc__) && W_TYPE_SIZE == 32
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
- __asm__ ("add.f %1, %4, %5
- adc %0, %2, %3" \
+ __asm__ ("add.f %1, %4, %5\n" \
+ "adc %0, %2, %3" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "%r" ((USItype) (ah)), \
"%r" ((USItype) (al)), \
"rIJ" ((USItype) (bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
- __asm__ ("sub.f %1, %4, %5
- sbc %0, %2, %3" \
+ __asm__ ("sub.f %1, %4, %5\n" \
+ "sbc %0, %2, %3" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "r" ((USItype) (ah)), \
#if defined (__arm__) && W_TYPE_SIZE == 32
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
- __asm__ ("adds %1, %4, %5
- adc %0, %2, %3" \
+ __asm__ ("adds %1, %4, %5\n" \
+ "adc %0, %2, %3" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "%r" ((USItype) (ah)), \
"%r" ((USItype) (al)), \
"rI" ((USItype) (bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
- __asm__ ("subs %1, %4, %5
- sbc %0, %2, %3" \
+ __asm__ ("subs %1, %4, %5\n" \
+ "sbc %0, %2, %3" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "r" ((USItype) (ah)), \
"rI" ((USItype) (bl)))
#define umul_ppmm(xh, xl, a, b) \
{register USItype __t0, __t1, __t2; \
- __asm__ ("%@ Inlined umul_ppmm
- mov %2, %5, lsr #16
- mov %0, %6, lsr #16
- bic %3, %5, %2, lsl #16
- bic %4, %6, %0, lsl #16
- mul %1, %3, %4
- mul %4, %2, %4
- mul %3, %0, %3
- mul %0, %2, %0
- adds %3, %4, %3
- addcs %0, %0, #65536
- adds %1, %1, %3, lsl #16
- adc %0, %0, %3, lsr #16" \
+ __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) \
#if defined (__gmicro__) && W_TYPE_SIZE == 32
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
- __asm__ ("add.w %5,%1
- addx %3,%0" \
+ __asm__ ("add.w %5,%1\n" \
+ "addx %3,%0" \
: "=g" ((USItype) (sh)), \
"=&g" ((USItype) (sl)) \
: "%0" ((USItype) (ah)), \
"%1" ((USItype) (al)), \
"g" ((USItype) (bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
- __asm__ ("sub.w %5,%1
- subx %3,%0" \
+ __asm__ ("sub.w %5,%1\n" \
+ "subx %3,%0" \
: "=g" ((USItype) (sh)), \
"=&g" ((USItype) (sl)) \
: "0" ((USItype) (ah)), \
#if defined (__hppa) && W_TYPE_SIZE == 32
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
- __asm__ ("add %4,%5,%1
- addc %2,%3,%0" \
+ __asm__ ("add %4,%5,%1\n" \
+ "addc %2,%3,%0" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "%rM" ((USItype) (ah)), \
"%rM" ((USItype) (al)), \
"rM" ((USItype) (bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
- __asm__ ("sub %4,%5,%1
- subb %2,%3,%0" \
+ __asm__ ("sub %4,%5,%1\n" \
+ "subb %2,%3,%0" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "rM" ((USItype) (ah)), \
#endif
#define UDIV_TIME 40
#define count_leading_zeros(count, x) \
- do { \
- USItype __tmp; \
- __asm__ ( \
- "ldi 1,%0
- extru,= %1,15,16,%%r0 ; Bits 31..16 zero?
- extru,tr %1,15,16,%1 ; No. Shift down, skip add.
- ldo 16(%0),%0 ; Yes. Perform add.
- extru,= %1,23,8,%%r0 ; Bits 15..8 zero?
- extru,tr %1,23,8,%1 ; No. Shift down, skip add.
- ldo 8(%0),%0 ; Yes. Perform add.
- extru,= %1,27,4,%%r0 ; Bits 7..4 zero?
- extru,tr %1,27,4,%1 ; No. Shift down, skip add.
- ldo 4(%0),%0 ; Yes. Perform add.
- extru,= %1,29,2,%%r0 ; Bits 3..2 zero?
- extru,tr %1,29,2,%1 ; No. Shift down, skip add.
- ldo 2(%0),%0 ; Yes. Perform add.
- extru %1,30,1,%1 ; Extract bit 1.
- sub %0,%1,%0 ; Subtract it.
- " : "=r" (count), "=r" (__tmp) : "1" (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." \
+ : "=r" (count), "=r" (__tmp) : "1" (x)); \
} while (0)
#endif
#if (defined (__i386__) || defined (__i486__)) && W_TYPE_SIZE == 32
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
- __asm__ ("addl %5,%1
- adcl %3,%0" \
+ __asm__ ("addl %5,%1\n" \
+ "adcl %3,%0" \
: "=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
- sbbl %3,%0" \
+ __asm__ ("subl %5,%1\n" \
+ "sbbl %3,%0" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "0" ((USItype) (ah)), \
{ \
DItype __ll; \
struct {USItype __l, __h;} __i; \
- } __a, __b, __s; \
+ } __a, __b, __s; \
__a.__i.__l = (al); \
__a.__i.__h = (ah); \
__b.__i.__l = (bl); \
{ \
DItype __ll; \
struct {USItype __l, __h;} __i; \
- } __a, __b, __s; \
+ } __a, __b, __s; \
__a.__i.__l = (al); \
__a.__i.__h = (ah); \
__b.__i.__l = (bl); \
#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
- addx %%5,%1
- addx %%3,%0" \
+ __asm__ ("cmp %0,%0\n" \
+ "addx %%5,%1\n" \
+ "addx %%3,%0" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "%0" ((USItype) (ah)), \
: "cbit")
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
/* The cmp clears the condition bit. */ \
- __asm__ ("cmp %0,%0
- subx %5,%1
- subx %3,%0" \
+ __asm__ ("cmp %0,%0\n" \
+ "subx %5,%1\n" \
+ "subx %3,%0" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "0" ((USItype) (ah)), \
#if defined (__mc68000__) && W_TYPE_SIZE == 32
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
- __asm__ ("add%.l %5,%1
- addx%.l %3,%0" \
+ __asm__ ("add%.l %5,%1\n" \
+ "addx%.l %3,%0" \
: "=d" ((USItype) (sh)), \
"=&d" ((USItype) (sl)) \
: "%0" ((USItype) (ah)), \
"%1" ((USItype) (al)), \
"g" ((USItype) (bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
- __asm__ ("sub%.l %5,%1
- subx%.l %3,%0" \
+ __asm__ ("sub%.l %5,%1\n" \
+ "subx%.l %3,%0" \
: "=d" ((USItype) (sh)), \
"=&d" ((USItype) (sl)) \
: "0" ((USItype) (ah)), \
#if !defined(__mcf5200__)
/* %/ inserts REGISTER_PREFIX, %# inserts IMMEDIATE_PREFIX. */
#define umul_ppmm(xh, xl, a, b) \
- __asm__ ("| Inlined umul_ppmm
- move%.l %2,%/d0
- move%.l %3,%/d1
- move%.l %/d0,%/d2
- swap %/d0
- move%.l %/d1,%/d3
- swap %/d1
- move%.w %/d2,%/d4
- mulu %/d3,%/d4
- mulu %/d1,%/d2
- mulu %/d0,%/d3
- mulu %/d0,%/d1
- move%.l %/d4,%/d0
- eor%.w %/d0,%/d0
- swap %/d0
- add%.l %/d0,%/d2
- add%.l %/d3,%/d2
- jcc 1f
- add%.l %#65536,%/d1
-1: swap %/d2
- moveq %#0,%/d0
- move%.w %/d2,%/d0
- move%.w %/d4,%/d2
- move%.l %/d2,%1
- add%.l %/d1,%/d0
- move%.l %/d0,%0" \
+ __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)), \
#if defined (__m88000__) && W_TYPE_SIZE == 32
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
- __asm__ ("addu.co %1,%r4,%r5
- addu.ci %0,%r2,%r3" \
+ __asm__ ("addu.co %1,%r4,%r5\n" \
+ "addu.ci %0,%r2,%r3" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "%rJ" ((USItype) (ah)), \
"%rJ" ((USItype) (al)), \
"rJ" ((USItype) (bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
- __asm__ ("subu.co %1,%r4,%r5
- subu.ci %0,%r2,%r3" \
+ __asm__ ("subu.co %1,%r4,%r5\n" \
+ "subu.ci %0,%r2,%r3" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "rJ" ((USItype) (ah)), \
(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))); \
+ __asm__ ("ffsd %2,%0" \
+ : "=r" ((USItype) (count)) \
+ : "0" ((USItype) 0), \
+ "r" ((USItype) (x))); \
} while (0)
#endif /* __ns32000__ */
#if defined (__pyr__) && W_TYPE_SIZE == 32
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
- __asm__ ("addw %5,%1
- addwc %3,%0" \
+ __asm__ ("addw %5,%1\n" \
+ "addwc %3,%0" \
: "=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__ ("subw %5,%1
- subwb %3,%0" \
+ __asm__ ("subw %5,%1\n" \
+ "subwb %3,%0" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "0" ((USItype) (ah)), \
({union {UDItype __ll; \
struct {USItype __h, __l;} __i; \
} __xx; \
- __asm__ ("movw %1,%R0
- uemul %2,%0" \
+ __asm__ ("movw %1,%R0\n" \
+ "uemul %2,%0" \
: "=&r" (__xx.__ll) \
: "g" ((USItype) (u)), \
"g" ((USItype) (v))); \
#if defined (__ibm032__) /* RT/ROMP */ && W_TYPE_SIZE == 32
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
- __asm__ ("a %1,%5
- ae %0,%3" \
+ __asm__ ("a %1,%5\n" \
+ "ae %0,%3" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "%0" ((USItype) (ah)), \
"%1" ((USItype) (al)), \
"r" ((USItype) (bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
- __asm__ ("s %1,%5
- se %0,%3" \
+ __asm__ ("s %1,%5\n" \
+ "se %0,%3" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "0" ((USItype) (ah)), \
do { \
USItype __m0 = (m0), __m1 = (m1); \
__asm__ ( \
- "s r2,r2
- mts r10,%2
- m r2,%3
- m r2,%3
- m r2,%3
- m r2,%3
- m r2,%3
- m r2,%3
- m r2,%3
- m r2,%3
- m r2,%3
- m r2,%3
- m r2,%3
- m r2,%3
- m r2,%3
- m r2,%3
- m r2,%3
- m r2,%3
- cas %0,r2,r0
- mfs r10,%1" \
+ "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), \
#if defined (__sh2__) && W_TYPE_SIZE == 32
#define umul_ppmm(w1, w0, u, v) \
__asm__ ( \
- "dmulu.l %2,%3
- sts macl,%1
- sts mach,%0" \
+ "dmulu.l %2,%3\n" \
+ "sts macl,%1\n" \
+ "sts mach,%0" \
: "=r" ((USItype)(w1)), \
"=r" ((USItype)(w0)) \
: "r" ((USItype)(u)), \
#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
- addx %r2,%3,%0" \
+ __asm__ ("addcc %r4,%5,%1\n" \
+ "addx %r2,%3,%0" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "%rJ" ((USItype) (ah)), \
"rI" ((USItype) (bl)) \
__CLOBBER_CC)
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
- __asm__ ("subcc %r4,%5,%1
- subx %r2,%3,%0" \
+ __asm__ ("subcc %r4,%5,%1\n" \
+ "subx %r2,%3,%0" \
: "=r" ((USItype) (sh)), \
"=&r" ((USItype) (sl)) \
: "rJ" ((USItype) (ah)), \
: "r" ((USItype) (u)), \
"r" ((USItype) (v)))
#define udiv_qrnnd(q, r, n1, n0, d) \
- __asm__ ("! Inlined udiv_qrnnd
- wr %%g0,%2,%%y ! Not a delayed write for sparclite
- tst %%g0
- divscc %3,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%%g1
- divscc %%g1,%4,%0
- rd %%y,%1
- bl,a 1f
- add %1,%4,%1
-1: ! End of inline udiv_qrnnd" \
+ __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)), \
: "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))); \
+ 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
/* 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
- wr %%g0,%2,%%y ! SPARC has 0-3 delay insn after a wr
- sra %3,31,%%o5 ! Don't move this insn
- and %2,%%o5,%%o5 ! Don't move this insn
- andcc %%g0,0,%%g1 ! Don't move this insn
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,%3,%%g1
- mulscc %%g1,0,%%g1
- add %%g1,%%o5,%0
- rd %%y,%1" \
+ __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)), \
: "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! */
+ The default udiv_qrnnd (in C) is more than 10 times slower! */
#define udiv_qrnnd(q, r, n1, n0, d) \
- __asm__ ("! Inlined udiv_qrnnd
- mov 32,%%g1
- subcc %1,%2,%%g0
-1: bcs 5f
- addxcc %0,%0,%0 ! shift n1n0 and a q-bit in lsb
- sub %1,%2,%1 ! this kills msb of n
- addx %1,%1,%1 ! so this can't give carry
- subcc %%g1,1,%%g1
-2: bne 1b
- subcc %1,%2,%%g0
- bcs 3f
- addxcc %0,%0,%0 ! shift n1n0 and a q-bit in lsb
- b 3f
- sub %1,%2,%1 ! this kills msb of n
-4: sub %1,%2,%1
-5: addxcc %1,%1,%1
- bcc 2b
- subcc %%g1,1,%%g1
-! Got carry from n. Subtract next step to cancel this carry.
- bne 4b
- addcc %0,%0,%0 ! shift n1n0 and a 0-bit in lsb
- sub %1,%2,%1
-3: xnor %0,0,%0
- ! End of inline udiv_qrnnd" \
+ __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)), \
#if ((defined (__sparc__) && defined (__arch64__)) \
|| defined (__sparcv9)) && W_TYPE_SIZE == 64
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
- __asm__ ("addcc %r4,%5,%1
- add %r2,%3,%0
- bcs,a,pn %%xcc, 1f
- add %0, 1, %0
- 1:" \
- : "=r" ((UDItype)(sh)), \
- "=&r" ((UDItype)(sl)) \
- : "%rJ" ((UDItype)(ah)), \
- "rI" ((UDItype)(bh)), \
- "%rJ" ((UDItype)(al)), \
- "rI" ((UDItype)(bl)) \
+ __asm__ ("addcc %r4,%5,%1\n" \
+ "add %r2,%3,%0\n" \
+ "bcs,a,pn %%xcc, 1f\n" \
+ "add %0, 1, %0\n" \
+ "1:" \
+ : "=r" ((UDItype)(sh)), \
+ "=&r" ((UDItype)(sl)) \
+ : "%rJ" ((UDItype)(ah)), \
+ "rI" ((UDItype)(bh)), \
+ "%rJ" ((UDItype)(al)), \
+ "rI" ((UDItype)(bl)) \
__CLOBBER_CC)
-#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
- __asm__ ("subcc %r4,%5,%1
- sub %r2,%3,%0
- bcs,a,pn %%xcc, 1f
- sub %0, 1, %0
- 1:" \
- : "=r" ((UDItype)(sh)), \
- "=&r" ((UDItype)(sl)) \
- : "rJ" ((UDItype)(ah)), \
- "rI" ((UDItype)(bh)), \
- "rJ" ((UDItype)(al)), \
- "rI" ((UDItype)(bl)) \
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+ __asm__ ("subcc %r4,%5,%1\n" \
+ "sub %r2,%3,%0\n" \
+ "bcs,a,pn %%xcc, 1f\n" \
+ "sub %0, 1, %0\n" \
+ "1:" \
+ : "=r" ((UDItype)(sh)), \
+ "=&r" ((UDItype)(sl)) \
+ : "rJ" ((UDItype)(ah)), \
+ "rI" ((UDItype)(bh)), \
+ "rJ" ((UDItype)(al)), \
+ "rI" ((UDItype)(bl)) \
__CLOBBER_CC)
#define umul_ppmm(wh, wl, u, v) \
do { \
UDItype tmp1, tmp2, tmp3, tmp4; \
__asm__ __volatile__ ( \
- "srl %7,0,%3
- mulx %3,%6,%1
- srlx %6,32,%2
- mulx %2,%3,%4
- sllx %4,32,%5
- srl %6,0,%3
- sub %1,%5,%5
- srlx %5,32,%5
- addcc %4,%5,%4
- srlx %7,32,%5
- mulx %3,%5,%3
- mulx %2,%5,%5
- sethi %%hi(0x80000000),%2
- addcc %4,%3,%4
- srlx %4,32,%4
- add %2,%2,%2
- movcc %%xcc,%%g0,%2
- addcc %5,%4,%5
- sllx %3,32,%3
- add %1,%3,%1
- add %5,%2,%0" \
+ "srl %7,0,%3\n" \
+ "mulx %3,%6,%1\n" \
+ "srlx %6,32,%2\n" \
+ "mulx %2,%3,%4\n" \
+ "sllx %4,32,%5\n" \
+ "srl %6,0,%3\n" \
+ "sub %1,%5,%5\n" \
+ "srlx %5,32,%5\n" \
+ "addcc %4,%5,%4\n" \
+ "srlx %7,32,%5\n" \
+ "mulx %3,%5,%3\n" \
+ "mulx %2,%5,%5\n" \
+ "sethi %%hi(0x80000000),%2\n" \
+ "addcc %4,%3,%4\n" \
+ "srlx %4,32,%4\n" \
+ "add %2,%2,%2\n" \
+ "movcc %%xcc,%%g0,%2\n" \
+ "addcc %5,%4,%5\n" \
+ "sllx %3,32,%3\n" \
+ "add %1,%3,%1\n" \
+ "add %5,%2,%0" \
: "=r" ((UDItype)(wh)), \
"=&r" ((UDItype)(wl)), \
"=&r" (tmp1), "=&r" (tmp2), "=&r" (tmp3), "=&r" (tmp4) \
#if defined (__vax__) && W_TYPE_SIZE == 32
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
- __asm__ ("addl2 %5,%1
- adwc %3,%0" \
+ __asm__ ("addl2 %5,%1\n" \
+ "adwc %3,%0" \
: "=g" ((USItype) (sh)), \
"=&g" ((USItype) (sl)) \
: "%0" ((USItype) (ah)), \
"%1" ((USItype) (al)), \
"g" ((USItype) (bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
- __asm__ ("subl2 %5,%1
- sbwc %3,%0" \
+ __asm__ ("subl2 %5,%1\n" \
+ "sbwc %3,%0" \
: "=g" ((USItype) (sh)), \
"=&g" ((USItype) (sl)) \
: "0" ((USItype) (ah)), \
projects / platform / upstream / glibc.git / commitdiff