On Mon, Sep 22, 2014 at 3:45 PM, Roland McGrath <roland@hack.frob.com> wrote:
>> hack_digit becomes longer too due to longer function prologue epilogue:
>
> Clearly that cannot be the only difference. Was the function's code itself
> actually all nearly identical, modulo trivial differences like different
> register allocation choices? Each access to one of the parent's locals
> surely looks different, and how different that code looks is probably where
> the most important differences are.
Another difference is that the compile decided to rearrange the order
of basic blocks, so the calls go in different orders.
I've attached the disassembly for both variants.
>
>> I considered doing such a patch but it turned out a huge textual
>> change that will make the code much less readable.
>> Still, let me do it and send it here anyway, unless you tell me no to.
>
> Of course readability is very subjective, so there really is no substitute
> for each interested person just seeing how things look and giving their
> opinion. The most trivial mechanical change might harm readability in ways
> that can be improved with a little thought.
Attached is a patch with "trivial mechanical change" (not properly
formatted yet).
To me it looks horrible. Does it make sense to invest more time in it?
000000000004a390 <hack_digit.13608>:
4a390: 55 push %rbp
4a391: 53 push %rbx
4a392: 4c 89 d3 mov %r10,%rbx
4a395: 48 83 ec 08 sub $0x8,%rsp
4a399: 41 8b 42 30 mov 0x30(%r10),%eax
4a39d: 85 c0 test %eax,%eax
4a39f: 74 0b je 4a3ac <hack_digit.13608+0x1c>
4a3a1: 41 83 7a 2c 66 cmpl $0x66,0x2c(%r10)
4a3a6: 0f 84 04 01 00 00 je 4a4b0 <hack_digit.13608+0x120>
4a3ac: 4c 8b 4b 20 mov 0x20(%rbx),%r9
4a3b0: 4d 85 c9 test %r9,%r9
4a3b3: 0f 84 c7 00 00 00 je 4a480 <hack_digit.13608+0xf0>
4a3b9: 48 8b 53 18 mov 0x18(%rbx),%rdx
4a3bd: 49 39 d1 cmp %rdx,%r9
4a3c0: 7e 3e jle 4a400 <hack_digit.13608+0x70>
4a3c2: 48 8b 7b 10 mov 0x10(%rbx),%rdi
4a3c6: bd 30 00 00 00 mov $0x30,%ebp
4a3cb: b9 0a 00 00 00 mov $0xa,%ecx
4a3d0: 48 89 fe mov %rdi,%rsi
4a3d3: e8 d8 97 ff ff callq 43bb0 <__mpn_mul_1>
4a3d8: 48 85 c0 test %rax,%rax
4a3db: 74 14 je 4a3f1 <hack_digit.13608+0x61>
4a3dd: 48 8b 53 18 mov 0x18(%rbx),%rdx
4a3e1: 48 8d 4a 01 lea 0x1(%rdx),%rcx
4a3e5: 48 89 4b 18 mov %rcx,0x18(%rbx)
4a3e9: 48 8b 4b 10 mov 0x10(%rbx),%rcx
4a3ed: 48 89 04 d1 mov %rax,(%rcx,%rdx,8)
4a3f1: 48 83 c4 08 add $0x8,%rsp
4a3f5: 89 e8 mov %ebp,%eax
4a3f7: 5b pop %rbx
4a3f8: 5d pop %rbp
4a3f9: c3 retq
4a3fa: 66 0f 1f 44 00 00 nopw 0x0(%rax,%rax,1)
4a400: 48 89 d1 mov %rdx,%rcx
4a403: 48 8b 7b 08 mov 0x8(%rbx),%rdi
4a407: 48 8b 53 10 mov 0x10(%rbx),%rdx
4a40b: 4c 8b 03 mov (%rbx),%r8
4a40e: 31 f6 xor %esi,%esi
4a410: e8 2b 8d ff ff callq 43140 <__mpn_divrem>
4a415: 48 8b 53 20 mov 0x20(%rbx),%rdx
4a419: 48 8b 4b 18 mov 0x18(%rbx),%rcx
4a41d: 48 8b 73 08 mov 0x8(%rbx),%rsi
4a421: 48 29 d1 sub %rdx,%rcx
4a424: 48 85 d2 test %rdx,%rdx
4a427: 48 89 04 ce mov %rax,(%rsi,%rcx,8)
4a42b: 48 8b 2e mov (%rsi),%rbp
4a42e: 48 89 53 18 mov %rdx,0x18(%rbx)
4a432: 74 2f je 4a463 <hack_digit.13608+0xd3>
4a434: 48 8b 7b 10 mov 0x10(%rbx),%rdi
4a438: 48 8d 4a ff lea -0x1(%rdx),%rcx
4a43c: 48 83 7c d7 f8 00 cmpq $0x0,-0x8(%rdi,%rdx,8)
4a442: 74 17 je 4a45b <hack_digit.13608+0xcb>
4a444: e9 93 00 00 00 jmpq 4a4dc <hack_digit.13608+0x14c>
4a449: 0f 1f 80 00 00 00 00 nopl 0x0(%rax)
4a450: 48 8d 49 ff lea -0x1(%rcx),%rcx
4a454: 48 83 3c cf 00 cmpq $0x0,(%rdi,%rcx,8)
4a459: 75 7d jne 4a4d8 <hack_digit.13608+0x148>
4a45b: 48 85 c9 test %rcx,%rcx
4a45e: 48 89 ca mov %rcx,%rdx
4a461: 75 ed jne 4a450 <hack_digit.13608+0xc0>
4a463: 48 c7 43 18 01 00 00 movq $0x1,0x18(%rbx)
4a46a: 00
4a46b: 48 83 c4 08 add $0x8,%rsp
4a46f: 83 c5 30 add $0x30,%ebp
4a472: 5b pop %rbx
4a473: 89 e8 mov %ebp,%eax
4a475: 5d pop %rbp
4a476: c3 retq
4a477: 66 0f 1f 84 00 00 00 nopw 0x0(%rax,%rax,1)
4a47e: 00 00
4a480: 48 8b 53 18 mov 0x18(%rbx),%rdx
4a484: 48 8b 7b 10 mov 0x10(%rbx),%rdi
4a488: b9 0a 00 00 00 mov $0xa,%ecx
4a48d: 48 8d 5c d7 f8 lea -0x8(%rdi,%rdx,8),%rbx
4a492: 48 89 fe mov %rdi,%rsi
4a495: 48 83 ea 01 sub $0x1,%rdx
4a499: 48 8b 2b mov (%rbx),%rbp
4a49c: e8 0f 97 ff ff callq 43bb0 <__mpn_mul_1>
4a4a1: 48 89 03 mov %rax,(%rbx)
4a4a4: 48 83 c4 08 add $0x8,%rsp
4a4a8: 83 c5 30 add $0x30,%ebp
4a4ab: 5b pop %rbx
4a4ac: 89 e8 mov %ebp,%eax
4a4ae: 5d pop %rbp
4a4af: c3 retq
4a4b0: 41 8b 42 28 mov 0x28(%r10),%eax
4a4b4: bd 30 00 00 00 mov $0x30,%ebp
4a4b9: 8d 50 ff lea -0x1(%rax),%edx
4a4bc: 85 c0 test %eax,%eax
4a4be: 41 89 52 28 mov %edx,0x28(%r10)
4a4c2: 0f 8e e4 fe ff ff jle 4a3ac <hack_digit.13608+0x1c>
4a4c8: 48 83 c4 08 add $0x8,%rsp
4a4cc: 89 e8 mov %ebp,%eax
4a4ce: 5b pop %rbx
4a4cf: 5d pop %rbp
4a4d0: c3 retq
4a4d1: 0f 1f 80 00 00 00 00 nopl 0x0(%rax)
4a4d8: 48 89 53 18 mov %rdx,0x18(%rbx)
4a4dc: 83 c5 30 add $0x30,%ebp
4a4df: e9 e7 fe ff ff jmpq 4a3cb <hack_digit.13608+0x3b>
4a4e4: 66 66 66 2e 0f 1f 84 data32 data32 nopw %cs:0x0(%rax,%rax,1)
4a4eb: 00 00 00 00 00
000000000004a390 <hack_digit>:
4a390: 41 55 push %r13
4a392: 41 54 push %r12
4a394: 55 push %rbp
4a395: 4c 89 c5 mov %r8,%rbp
4a398: 4d 89 c8 mov %r9,%r8
4a39b: 53 push %rbx
4a39c: 48 89 cb mov %rcx,%rbx
4a39f: 48 83 ec 08 sub $0x8,%rsp
4a3a3: 85 ff test %edi,%edi
4a3a5: 4c 8b 64 24 30 mov 0x30(%rsp),%r12
4a3aa: 74 24 je 4a3d0 <hack_digit+0x40>
4a3ac: 83 fe 66 cmp $0x66,%esi
4a3af: 75 1f jne 4a3d0 <hack_digit+0x40>
4a3b1: 8b 02 mov (%rdx),%eax
4a3b3: 41 bd 30 00 00 00 mov $0x30,%r13d
4a3b9: 8d 48 ff lea -0x1(%rax),%ecx
4a3bc: 85 c0 test %eax,%eax
4a3be: 89 0a mov %ecx,(%rdx)
4a3c0: 7e 0e jle 4a3d0 <hack_digit+0x40>
4a3c2: 48 83 c4 08 add $0x8,%rsp
4a3c6: 44 89 e8 mov %r13d,%eax
4a3c9: 5b pop %rbx
4a3ca: 5d pop %rbp
4a3cb: 41 5c pop %r12
4a3cd: 41 5d pop %r13
4a3cf: c3 retq
4a3d0: 4d 85 e4 test %r12,%r12
4a3d3: 0f 84 c7 00 00 00 je 4a4a0 <hack_digit+0x110>
4a3d9: 48 8b 4d 00 mov 0x0(%rbp),%rcx
4a3dd: 49 39 cc cmp %rcx,%r12
4a3e0: 7f 76 jg 4a458 <hack_digit+0xc8>
4a3e2: 48 8b 7c 24 38 mov 0x38(%rsp),%rdi
4a3e7: 31 f6 xor %esi,%esi
4a3e9: 48 89 da mov %rbx,%rdx
4a3ec: 4d 89 e1 mov %r12,%r9
4a3ef: e8 4c 8d ff ff callq 43140 <__mpn_divrem>
4a3f4: 48 8b 55 00 mov 0x0(%rbp),%rdx
4a3f8: 48 8b 74 24 38 mov 0x38(%rsp),%rsi
4a3fd: 4d 8d 54 24 ff lea -0x1(%r12),%r10
4a402: 4c 29 e2 sub %r12,%rdx
4a405: 48 89 04 d6 mov %rax,(%rsi,%rdx,8)
4a409: 4c 8b 2e mov (%rsi),%r13
4a40c: 4c 89 65 00 mov %r12,0x0(%rbp)
4a410: 4a 83 7c e3 f8 00 cmpq $0x0,-0x8(%rbx,%r12,8)
4a416: 74 17 je 4a42f <hack_digit+0x9f>
4a418: e9 cc 00 00 00 jmpq 4a4e9 <hack_digit+0x159>
4a41d: 0f 1f 00 nopl (%rax)
4a420: 49 83 ea 01 sub $0x1,%r10
4a424: 4a 83 3c d3 00 cmpq $0x0,(%rbx,%r10,8)
4a429: 0f 85 b1 00 00 00 jne 4a4e0 <hack_digit+0x150>
4a42f: 4d 85 d2 test %r10,%r10
4a432: 4c 89 d2 mov %r10,%rdx
4a435: 4c 89 55 00 mov %r10,0x0(%rbp)
4a439: 75 e5 jne 4a420 <hack_digit+0x90>
4a43b: 48 c7 45 00 01 00 00 movq $0x1,0x0(%rbp)
4a442: 00
4a443: 48 83 c4 08 add $0x8,%rsp
4a447: 41 83 c5 30 add $0x30,%r13d
4a44b: 5b pop %rbx
4a44c: 5d pop %rbp
4a44d: 41 5c pop %r12
4a44f: 44 89 e8 mov %r13d,%eax
4a452: 41 5d pop %r13
4a454: c3 retq
4a455: 0f 1f 00 nopl (%rax)
4a458: 48 89 ca mov %rcx,%rdx
4a45b: 41 bd 30 00 00 00 mov $0x30,%r13d
4a461: b9 0a 00 00 00 mov $0xa,%ecx
4a466: 48 89 de mov %rbx,%rsi
4a469: 48 89 df mov %rbx,%rdi
4a46c: e8 3f 97 ff ff callq 43bb0 <__mpn_mul_1>
4a471: 48 85 c0 test %rax,%rax
4a474: 0f 84 48 ff ff ff je 4a3c2 <hack_digit+0x32>
4a47a: 48 8b 55 00 mov 0x0(%rbp),%rdx
4a47e: 48 8d 4a 01 lea 0x1(%rdx),%rcx
4a482: 48 89 4d 00 mov %rcx,0x0(%rbp)
4a486: 48 89 04 d3 mov %rax,(%rbx,%rdx,8)
4a48a: 48 83 c4 08 add $0x8,%rsp
4a48e: 5b pop %rbx
4a48f: 5d pop %rbp
4a490: 41 5c pop %r12
4a492: 44 89 e8 mov %r13d,%eax
4a495: 41 5d pop %r13
4a497: c3 retq
4a498: 0f 1f 84 00 00 00 00 nopl 0x0(%rax,%rax,1)
4a49f: 00
4a4a0: 48 8b 55 00 mov 0x0(%rbp),%rdx
4a4a4: 48 89 de mov %rbx,%rsi
4a4a7: 48 89 df mov %rbx,%rdi
4a4aa: b9 0a 00 00 00 mov $0xa,%ecx
4a4af: 48 8d 6c d3 f8 lea -0x8(%rbx,%rdx,8),%rbp
4a4b4: 48 83 ea 01 sub $0x1,%rdx
4a4b8: 4c 8b 6d 00 mov 0x0(%rbp),%r13
4a4bc: e8 ef 96 ff ff callq 43bb0 <__mpn_mul_1>
4a4c1: 48 89 45 00 mov %rax,0x0(%rbp)
4a4c5: 48 83 c4 08 add $0x8,%rsp
4a4c9: 5b pop %rbx
4a4ca: 5d pop %rbp
4a4cb: 41 83 c5 30 add $0x30,%r13d
4a4cf: 41 5c pop %r12
4a4d1: 44 89 e8 mov %r13d,%eax
4a4d4: 41 5d pop %r13
4a4d6: c3 retq
4a4d7: 66 0f 1f 84 00 00 00 nopw 0x0(%rax,%rax,1)
4a4de: 00 00
4a4e0: 41 83 c5 30 add $0x30,%r13d
4a4e4: e9 78 ff ff ff jmpq 4a461 <hack_digit+0xd1>
4a4e9: 41 83 c5 30 add $0x30,%r13d
4a4ed: 4c 89 e2 mov %r12,%rdx
4a4f0: e9 6c ff ff ff jmpq 4a461 <hack_digit+0xd1>
4a4f5: 66 66 2e 0f 1f 84 00 data32 nopw %cs:0x0(%rax,%rax,1)
4a4fc: 00 00 00 00
@@ -148,6 +148,63 @@ static wchar_t *group_number (wchar_t *buf, wchar_t *bufend,
wchar_t thousands_sep, int ngroups)
internal_function;
+struct hack_digit_param {
+ /* Sign of the exponent. */
+ int expsign;
+ /* The type of output format that will be used: 'e'/'E' or 'f'. */
+ int type;
+ /* and the exponent. */
+ int exponent;
+ /* The fraction of the floting-point value in question */
+ MPN_VAR(frac);
+ /* Scaling factor. */
+ MPN_VAR(scale);
+ /* Temporary bignum value. */
+ MPN_VAR(tmp);
+};
+
+static wchar_t hack_digit (struct hack_digit_param *p)
+{
+ mp_limb_t hi;
+
+ if (p->expsign != 0 && p->type == 'f' && p->exponent-- > 0)
+ hi = 0;
+ else if (p->scalesize == 0)
+ {
+ hi = p->frac[p->fracsize - 1];
+ p->frac[p->fracsize - 1] = __mpn_mul_1 (p->frac, p->frac,
+ p->fracsize - 1, 10);
+ }
+ else
+ {
+ if (p->fracsize < p->scalesize)
+ hi = 0;
+ else
+ {
+ hi = mpn_divmod (p->tmp, p->frac, p->fracsize,
+ p->scale, p->scalesize);
+ p->tmp[p->fracsize - p->scalesize] = hi;
+ hi = p->tmp[0];
+
+ p->fracsize = p->scalesize;
+ while (p->fracsize != 0 && p->frac[p->fracsize - 1] == 0)
+ --p->fracsize;
+ if (p->fracsize == 0)
+ {
+ /* We're not prepared for an mpn variable with zero
+ limbs. */
+ p->fracsize = 1;
+ return L'0' + hi;
+ }
+ }
+
+ mp_limb_t _cy = __mpn_mul_1 (p->frac, p->frac, p->fracsize, 10);
+ if (_cy != 0)
+ p->frac[p->fracsize++] = _cy;
+ }
+
+ return L'0' + hi;
+}
int
___printf_fp (FILE *fp,
@@ -181,24 +238,10 @@ ___printf_fp (FILE *fp,
/* We need to shift the contents of fp_input by this amount of bits. */
int to_shift = 0;
- /* The fraction of the floting-point value in question */
- MPN_VAR(frac);
- /* and the exponent. */
- int exponent;
- /* Sign of the exponent. */
- int expsign = 0;
+ struct hack_digit_param p;
/* Sign of float number. */
int is_neg = 0;
- /* Scaling factor. */
- MPN_VAR(scale);
-
- /* Temporary bignum value. */
- MPN_VAR(tmp);
-
- /* The type of output format that will be used: 'e'/'E' or 'f'. */
- int type;
-
/* Counter for number of written characters. */
int done = 0;
@@ -213,50 +256,6 @@ ___printf_fp (FILE *fp,
/* Flag whether wbuffer is malloc'ed or not. */
int buffer_malloced = 0;
- auto wchar_t hack_digit (void);
-
- wchar_t hack_digit (void)
- {
- mp_limb_t hi;
-
- if (expsign != 0 && type == 'f' && exponent-- > 0)
- hi = 0;
- else if (scalesize == 0)
- {
- hi = frac[fracsize - 1];
- frac[fracsize - 1] = __mpn_mul_1 (frac, frac, fracsize - 1, 10);
- }
- else
- {
- if (fracsize < scalesize)
- hi = 0;
- else
- {
- hi = mpn_divmod (tmp, frac, fracsize, scale, scalesize);
- tmp[fracsize - scalesize] = hi;
- hi = tmp[0];
-
- fracsize = scalesize;
- while (fracsize != 0 && frac[fracsize - 1] == 0)
- --fracsize;
- if (fracsize == 0)
- {
- /* We're not prepared for an mpn variable with zero
- limbs. */
- fracsize = 1;
- return L'0' + hi;
- }
- }
-
- mp_limb_t _cy = __mpn_mul_1 (frac, frac, fracsize, 10);
- if (_cy != 0)
- frac[fracsize++] = _cy;
- }
-
- return L'0' + hi;
- }
-
-
/* Figure out the decimal point character. */
if (info->extra == 0)
{
@@ -360,12 +359,12 @@ ___printf_fp (FILE *fp,
}
else
{
- fracsize = __mpn_extract_long_double (fp_input,
+ p.fracsize = __mpn_extract_long_double (fp_input,
(sizeof (fp_input) /
sizeof (fp_input[0])),
- &exponent, &is_neg,
+ &p.exponent, &is_neg,
fpnum.ldbl);
- to_shift = 1 + fracsize * BITS_PER_MP_LIMB - LDBL_MANT_DIG;
+ to_shift = 1 + p.fracsize * BITS_PER_MP_LIMB - LDBL_MANT_DIG;
}
}
else
@@ -406,11 +405,11 @@ ___printf_fp (FILE *fp,
}
else
{
- fracsize = __mpn_extract_double (fp_input,
+ p.fracsize = __mpn_extract_double (fp_input,
(sizeof (fp_input)
/ sizeof (fp_input[0])),
- &exponent, &is_neg, fpnum.dbl);
- to_shift = 1 + fracsize * BITS_PER_MP_LIMB - DBL_MANT_DIG;
+ &p.exponent, &is_neg, fpnum.dbl);
+ to_shift = 1 + p.fracsize * BITS_PER_MP_LIMB - DBL_MANT_DIG;
}
}
@@ -441,25 +440,25 @@ ___printf_fp (FILE *fp,
}
- /* We need three multiprecision variables. Now that we have the exponent
+ /* We need three multiprecision variables. Now that we have the p.exponent
of the number we can allocate the needed memory. It would be more
efficient to use variables of the fixed maximum size but because this
would be really big it could lead to memory problems. */
{
- mp_size_t bignum_size = ((ABS (exponent) + BITS_PER_MP_LIMB - 1)
+ mp_size_t bignum_size = ((ABS (p.exponent) + BITS_PER_MP_LIMB - 1)
/ BITS_PER_MP_LIMB
+ (LDBL_MANT_DIG / BITS_PER_MP_LIMB > 2 ? 8 : 4))
* sizeof (mp_limb_t);
- frac = (mp_limb_t *) alloca (bignum_size);
- tmp = (mp_limb_t *) alloca (bignum_size);
- scale = (mp_limb_t *) alloca (bignum_size);
+ p.frac = (mp_limb_t *) alloca (bignum_size);
+ p.tmp = (mp_limb_t *) alloca (bignum_size);
+ p.scale = (mp_limb_t *) alloca (bignum_size);
}
/* We now have to distinguish between numbers with positive and negative
exponents because the method used for the one is not applicable/efficient
for the other. */
- scalesize = 0;
- if (exponent > 2)
+ p.scalesize = 0;
+ if (p.exponent > 2)
{
/* |FP| >= 8.0. */
int scaleexpo = 0;
@@ -468,22 +467,22 @@ ___printf_fp (FILE *fp,
const struct mp_power *powers = &_fpioconst_pow10[explog + 1];
int cnt_h, cnt_l, i;
- if ((exponent + to_shift) % BITS_PER_MP_LIMB == 0)
+ if ((p.exponent + to_shift) % BITS_PER_MP_LIMB == 0)
{
- MPN_COPY_DECR (frac + (exponent + to_shift) / BITS_PER_MP_LIMB,
- fp_input, fracsize);
- fracsize += (exponent + to_shift) / BITS_PER_MP_LIMB;
+ MPN_COPY_DECR (p.frac + (p.exponent + to_shift) / BITS_PER_MP_LIMB,
+ fp_input, p.fracsize);
+ p.fracsize += (p.exponent + to_shift) / BITS_PER_MP_LIMB;
}
else
{
- cy = __mpn_lshift (frac + (exponent + to_shift) / BITS_PER_MP_LIMB,
- fp_input, fracsize,
- (exponent + to_shift) % BITS_PER_MP_LIMB);
- fracsize += (exponent + to_shift) / BITS_PER_MP_LIMB;
+ cy = __mpn_lshift (p.frac + (p.exponent + to_shift) / BITS_PER_MP_LIMB,
+ fp_input, p.fracsize,
+ (p.exponent + to_shift) % BITS_PER_MP_LIMB);
+ p.fracsize += (p.exponent + to_shift) / BITS_PER_MP_LIMB;
if (cy)
- frac[fracsize++] = cy;
+ p.frac[p.fracsize++] = cy;
}
- MPN_ZERO (frac, (exponent + to_shift) / BITS_PER_MP_LIMB);
+ MPN_ZERO (p.frac, (p.exponent + to_shift) / BITS_PER_MP_LIMB);
assert (powers > &_fpioconst_pow10[0]);
do
@@ -492,9 +491,9 @@ ___printf_fp (FILE *fp,
/* The number of the product of two binary numbers with n and m
bits respectively has m+n or m+n-1 bits. */
- if (exponent >= scaleexpo + powers->p_expo - 1)
+ if (p.exponent >= scaleexpo + powers->p_expo - 1)
{
- if (scalesize == 0)
+ if (p.scalesize == 0)
{
#ifndef __NO_LONG_DOUBLE_MATH
if (LDBL_MANT_DIG > _FPIO_CONST_OFFSET * BITS_PER_MP_LIMB
@@ -505,61 +504,61 @@ ___printf_fp (FILE *fp,
- _FPIO_CONST_OFFSET)
/* 64bit const offset is not enough for
IEEE quad long double. */
- tmpsize = powers->arraysize + _FPIO_CONST_SHIFT;
- memcpy (tmp + _FPIO_CONST_SHIFT,
+ p.tmpsize = powers->arraysize + _FPIO_CONST_SHIFT;
+ memcpy (p.tmp + _FPIO_CONST_SHIFT,
&__tens[powers->arrayoff],
- tmpsize * sizeof (mp_limb_t));
- MPN_ZERO (tmp, _FPIO_CONST_SHIFT);
- /* Adjust exponent, as scaleexpo will be this much
+ p.tmpsize * sizeof (mp_limb_t));
+ MPN_ZERO (p.tmp, _FPIO_CONST_SHIFT);
+ /* Adjust p.exponent, as scaleexpo will be this much
bigger too. */
- exponent += _FPIO_CONST_SHIFT * BITS_PER_MP_LIMB;
+ p.exponent += _FPIO_CONST_SHIFT * BITS_PER_MP_LIMB;
}
else
#endif
{
- tmpsize = powers->arraysize;
- memcpy (tmp, &__tens[powers->arrayoff],
- tmpsize * sizeof (mp_limb_t));
+ p.tmpsize = powers->arraysize;
+ memcpy (p.tmp, &__tens[powers->arrayoff],
+ p.tmpsize * sizeof (mp_limb_t));
}
}
else
{
- cy = __mpn_mul (tmp, scale, scalesize,
+ cy = __mpn_mul (p.tmp, p.scale, p.scalesize,
&__tens[powers->arrayoff
+ _FPIO_CONST_OFFSET],
powers->arraysize - _FPIO_CONST_OFFSET);
- tmpsize = scalesize + powers->arraysize - _FPIO_CONST_OFFSET;
+ p.tmpsize = p.scalesize + powers->arraysize - _FPIO_CONST_OFFSET;
if (cy == 0)
- --tmpsize;
+ --p.tmpsize;
}
- if (MPN_GE (frac, tmp))
+ if (MPN_GE (p.frac, p.tmp))
{
int cnt;
- MPN_ASSIGN (scale, tmp);
- count_leading_zeros (cnt, scale[scalesize - 1]);
- scaleexpo = (scalesize - 2) * BITS_PER_MP_LIMB - cnt - 1;
+ MPN_ASSIGN (p.scale, p.tmp);
+ count_leading_zeros (cnt, p.scale[p.scalesize - 1]);
+ scaleexpo = (p.scalesize - 2) * BITS_PER_MP_LIMB - cnt - 1;
exp10 |= 1 << explog;
}
}
--explog;
}
while (powers > &_fpioconst_pow10[0]);
- exponent = exp10;
+ p.exponent = exp10;
/* Optimize number representations. We want to represent the numbers
with the lowest number of bytes possible without losing any
bytes. Also the highest bit in the scaling factor has to be set
(this is a requirement of the MPN division routines). */
- if (scalesize > 0)
+ if (p.scalesize > 0)
{
/* Determine minimum number of zero bits at the end of
both numbers. */
- for (i = 0; scale[i] == 0 && frac[i] == 0; i++)
+ for (i = 0; p.scale[i] == 0 && p.frac[i] == 0; i++)
;
/* Determine number of bits the scaling factor is misplaced. */
- count_leading_zeros (cnt_h, scale[scalesize - 1]);
+ count_leading_zeros (cnt_h, p.scale[p.scalesize - 1]);
if (cnt_h == 0)
{
@@ -567,27 +566,27 @@ ___printf_fp (FILE *fp,
we only have to remove the trailing empty limbs. */
if (i > 0)
{
- MPN_COPY_INCR (scale, scale + i, scalesize - i);
- scalesize -= i;
- MPN_COPY_INCR (frac, frac + i, fracsize - i);
- fracsize -= i;
+ MPN_COPY_INCR (p.scale, p.scale + i, p.scalesize - i);
+ p.scalesize -= i;
+ MPN_COPY_INCR (p.frac, p.frac + i, p.fracsize - i);
+ p.fracsize -= i;
}
}
else
{
- if (scale[i] != 0)
+ if (p.scale[i] != 0)
{
- count_trailing_zeros (cnt_l, scale[i]);
- if (frac[i] != 0)
+ count_trailing_zeros (cnt_l, p.scale[i]);
+ if (p.frac[i] != 0)
{
int cnt_l2;
- count_trailing_zeros (cnt_l2, frac[i]);
+ count_trailing_zeros (cnt_l2, p.frac[i]);
if (cnt_l2 < cnt_l)
cnt_l = cnt_l2;
}
}
else
- count_trailing_zeros (cnt_l, frac[i]);
+ count_trailing_zeros (cnt_l, p.frac[i]);
/* Now shift the numbers to their optimal position. */
if (i == 0 && BITS_PER_MP_LIMB - cnt_h > cnt_l)
@@ -595,10 +594,10 @@ ___printf_fp (FILE *fp,
/* We cannot save any memory. So just roll both numbers
so that the scaling factor has its highest bit set. */
- (void) __mpn_lshift (scale, scale, scalesize, cnt_h);
- cy = __mpn_lshift (frac, frac, fracsize, cnt_h);
+ (void) __mpn_lshift (p.scale, p.scale, p.scalesize, cnt_h);
+ cy = __mpn_lshift (p.frac, p.frac, p.fracsize, cnt_h);
if (cy != 0)
- frac[fracsize++] = cy;
+ p.frac[p.fracsize++] = cy;
}
else if (BITS_PER_MP_LIMB - cnt_h <= cnt_l)
{
@@ -606,31 +605,31 @@ ___printf_fp (FILE *fp,
and by packing the non-zero limbs which gain another
free one. */
- (void) __mpn_rshift (scale, scale + i, scalesize - i,
+ (void) __mpn_rshift (p.scale, p.scale + i, p.scalesize - i,
BITS_PER_MP_LIMB - cnt_h);
- scalesize -= i + 1;
- (void) __mpn_rshift (frac, frac + i, fracsize - i,
+ p.scalesize -= i + 1;
+ (void) __mpn_rshift (p.frac, p.frac + i, p.fracsize - i,
BITS_PER_MP_LIMB - cnt_h);
- fracsize -= frac[fracsize - i - 1] == 0 ? i + 1 : i;
+ p.fracsize -= p.frac[p.fracsize - i - 1] == 0 ? i + 1 : i;
}
else
{
/* We can only save the memory of the limbs which are zero.
The non-zero parts occupy the same number of limbs. */
- (void) __mpn_rshift (scale, scale + (i - 1),
- scalesize - (i - 1),
+ (void) __mpn_rshift (p.scale, p.scale + (i - 1),
+ p.scalesize - (i - 1),
BITS_PER_MP_LIMB - cnt_h);
- scalesize -= i;
- (void) __mpn_rshift (frac, frac + (i - 1),
- fracsize - (i - 1),
+ p.scalesize -= i;
+ (void) __mpn_rshift (p.frac, p.frac + (i - 1),
+ p.fracsize - (i - 1),
BITS_PER_MP_LIMB - cnt_h);
- fracsize -= frac[fracsize - (i - 1) - 1] == 0 ? i : i - 1;
+ p.fracsize -= p.frac[p.fracsize - (i - 1) - 1] == 0 ? i : i - 1;
}
}
}
}
- else if (exponent < 0)
+ else if (p.exponent < 0)
{
/* |FP| < 1.0. */
int exp10 = 0;
@@ -638,48 +637,48 @@ ___printf_fp (FILE *fp,
const struct mp_power *powers = &_fpioconst_pow10[explog + 1];
/* Now shift the input value to its right place. */
- cy = __mpn_lshift (frac, fp_input, fracsize, to_shift);
- frac[fracsize++] = cy;
- assert (cy == 1 || (frac[fracsize - 2] == 0 && frac[0] == 0));
+ cy = __mpn_lshift (p.frac, fp_input, p.fracsize, to_shift);
+ p.frac[p.fracsize++] = cy;
+ assert (cy == 1 || (p.frac[p.fracsize - 2] == 0 && p.frac[0] == 0));
- expsign = 1;
- exponent = -exponent;
+ p.expsign = 1;
+ p.exponent = -p.exponent;
assert (powers != &_fpioconst_pow10[0]);
do
{
--powers;
- if (exponent >= powers->m_expo)
+ if (p.exponent >= powers->m_expo)
{
int i, incr, cnt_h, cnt_l;
mp_limb_t topval[2];
/* The __mpn_mul function expects the first argument to be
bigger than the second. */
- if (fracsize < powers->arraysize - _FPIO_CONST_OFFSET)
- cy = __mpn_mul (tmp, &__tens[powers->arrayoff
+ if (p.fracsize < powers->arraysize - _FPIO_CONST_OFFSET)
+ cy = __mpn_mul (p.tmp, &__tens[powers->arrayoff
+ _FPIO_CONST_OFFSET],
powers->arraysize - _FPIO_CONST_OFFSET,
- frac, fracsize);
+ p.frac, p.fracsize);
else
- cy = __mpn_mul (tmp, frac, fracsize,
+ cy = __mpn_mul (p.tmp, p.frac, p.fracsize,
&__tens[powers->arrayoff + _FPIO_CONST_OFFSET],
powers->arraysize - _FPIO_CONST_OFFSET);
- tmpsize = fracsize + powers->arraysize - _FPIO_CONST_OFFSET;
+ p.tmpsize = p.fracsize + powers->arraysize - _FPIO_CONST_OFFSET;
if (cy == 0)
- --tmpsize;
+ --p.tmpsize;
- count_leading_zeros (cnt_h, tmp[tmpsize - 1]);
- incr = (tmpsize - fracsize) * BITS_PER_MP_LIMB
+ count_leading_zeros (cnt_h, p.tmp[p.tmpsize - 1]);
+ incr = (p.tmpsize - p.fracsize) * BITS_PER_MP_LIMB
+ BITS_PER_MP_LIMB - 1 - cnt_h;
assert (incr <= powers->p_expo);
- /* If we increased the exponent by exactly 3 we have to test
+ /* If we increased the p.exponent by exactly 3 we have to test
for overflow. This is done by comparing with 10 shifted
to the right position. */
- if (incr == exponent + 3)
+ if (incr == p.exponent + 3)
{
if (cnt_h <= BITS_PER_MP_LIMB - 4)
{
@@ -701,32 +700,32 @@ ___printf_fp (FILE *fp,
against 10.0. If it is greater or equal to 10.0 the
multiplication was not valid. This is because we cannot
determine the number of bits in the result in advance. */
- if (incr < exponent + 3
- || (incr == exponent + 3 &&
- (tmp[tmpsize - 1] < topval[1]
- || (tmp[tmpsize - 1] == topval[1]
- && tmp[tmpsize - 2] < topval[0]))))
+ if (incr < p.exponent + 3
+ || (incr == p.exponent + 3 &&
+ (p.tmp[p.tmpsize - 1] < topval[1]
+ || (p.tmp[p.tmpsize - 1] == topval[1]
+ && p.tmp[p.tmpsize - 2] < topval[0]))))
{
/* The factor is right. Adapt binary and decimal
exponents. */
- exponent -= incr;
+ p.exponent -= incr;
exp10 |= 1 << explog;
/* If this factor yields a number greater or equal to
1.0, we must not shift the non-fractional digits down. */
- if (exponent < 0)
- cnt_h += -exponent;
+ if (p.exponent < 0)
+ cnt_h += -p.exponent;
/* Now we optimize the number representation. */
- for (i = 0; tmp[i] == 0; ++i);
+ for (i = 0; p.tmp[i] == 0; ++i);
if (cnt_h == BITS_PER_MP_LIMB - 1)
{
- MPN_COPY (frac, tmp + i, tmpsize - i);
- fracsize = tmpsize - i;
+ MPN_COPY (p.frac, p.tmp + i, p.tmpsize - i);
+ p.fracsize = p.tmpsize - i;
}
else
{
- count_trailing_zeros (cnt_l, tmp[i]);
+ count_trailing_zeros (cnt_l, p.tmp[i]);
/* Now shift the numbers to their optimal position. */
if (i == 0 && BITS_PER_MP_LIMB - 1 - cnt_h > cnt_l)
@@ -735,15 +734,15 @@ ___printf_fp (FILE *fp,
number so that the leading digit is in a
separate limb. */
- cy = __mpn_lshift (frac, tmp, tmpsize, cnt_h + 1);
- fracsize = tmpsize + 1;
- frac[fracsize - 1] = cy;
+ cy = __mpn_lshift (p.frac, p.tmp, p.tmpsize, cnt_h + 1);
+ p.fracsize = p.tmpsize + 1;
+ p.frac[p.fracsize - 1] = cy;
}
else if (BITS_PER_MP_LIMB - 1 - cnt_h <= cnt_l)
{
- (void) __mpn_rshift (frac, tmp + i, tmpsize - i,
+ (void) __mpn_rshift (p.frac, p.tmp + i, p.tmpsize - i,
BITS_PER_MP_LIMB - 1 - cnt_h);
- fracsize = tmpsize - i;
+ p.fracsize = p.tmpsize - i;
}
else
{
@@ -751,41 +750,41 @@ ___printf_fp (FILE *fp,
are zero. The non-zero parts occupy the same
number of limbs. */
- (void) __mpn_rshift (frac, tmp + (i - 1),
- tmpsize - (i - 1),
+ (void) __mpn_rshift (p.frac, p.tmp + (i - 1),
+ p.tmpsize - (i - 1),
BITS_PER_MP_LIMB - 1 - cnt_h);
- fracsize = tmpsize - (i - 1);
+ p.fracsize = p.tmpsize - (i - 1);
}
}
}
}
--explog;
}
- while (powers != &_fpioconst_pow10[1] && exponent > 0);
+ while (powers != &_fpioconst_pow10[1] && p.exponent > 0);
/* All factors but 10^-1 are tested now. */
- if (exponent > 0)
+ if (p.exponent > 0)
{
int cnt_l;
- cy = __mpn_mul_1 (tmp, frac, fracsize, 10);
- tmpsize = fracsize;
- assert (cy == 0 || tmp[tmpsize - 1] < 20);
+ cy = __mpn_mul_1 (p.tmp, p.frac, p.fracsize, 10);
+ p.tmpsize = p.fracsize;
+ assert (cy == 0 || p.tmp[p.tmpsize - 1] < 20);
- count_trailing_zeros (cnt_l, tmp[0]);
- if (cnt_l < MIN (4, exponent))
+ count_trailing_zeros (cnt_l, p.tmp[0]);
+ if (cnt_l < MIN (4, p.exponent))
{
- cy = __mpn_lshift (frac, tmp, tmpsize,
- BITS_PER_MP_LIMB - MIN (4, exponent));
+ cy = __mpn_lshift (p.frac, p.tmp, p.tmpsize,
+ BITS_PER_MP_LIMB - MIN (4, p.exponent));
if (cy != 0)
- frac[tmpsize++] = cy;
+ p.frac[p.tmpsize++] = cy;
}
else
- (void) __mpn_rshift (frac, tmp, tmpsize, MIN (4, exponent));
- fracsize = tmpsize;
+ (void) __mpn_rshift (p.frac, p.tmp, p.tmpsize, MIN (4, p.exponent));
+ p.fracsize = p.tmpsize;
exp10 |= 1;
- assert (frac[fracsize - 1] < 10);
+ assert (p.frac[p.fracsize - 1] < 10);
}
- exponent = exp10;
+ p.exponent = exp10;
}
else
{
@@ -793,13 +792,13 @@ ___printf_fp (FILE *fp,
numbers are in the range of 1.0 <= |fp| < 8.0. We simply
shift it to the right place and divide it by 1.0 to get the
leading digit. (Of course this division is not really made.) */
- assert (0 <= exponent && exponent < 3 &&
- exponent + to_shift < BITS_PER_MP_LIMB);
+ assert (0 <= p.exponent && p.exponent < 3 &&
+ p.exponent + to_shift < BITS_PER_MP_LIMB);
/* Now shift the input value to its right place. */
- cy = __mpn_lshift (frac, fp_input, fracsize, (exponent + to_shift));
- frac[fracsize++] = cy;
- exponent = 0;
+ cy = __mpn_lshift (p.frac, fp_input, p.fracsize, (p.exponent + to_shift));
+ p.frac[p.fracsize++] = cy;
+ p.exponent = 0;
}
{
@@ -817,7 +816,7 @@ ___printf_fp (FILE *fp,
if (spec == 'e')
{
- type = info->spec;
+ p.type = info->spec;
intdig_max = 1;
fracdig_min = fracdig_max = info->prec < 0 ? 6 : info->prec;
chars_needed = 1 + 1 + (size_t) fracdig_max + 1 + 1 + 4;
@@ -827,15 +826,15 @@ ___printf_fp (FILE *fp,
}
else if (spec == 'f')
{
- type = 'f';
+ p.type = 'f';
fracdig_min = fracdig_max = info->prec < 0 ? 6 : info->prec;
dig_max = INT_MAX; /* Unlimited. */
significant = 1; /* Does not matter here. */
- if (expsign == 0)
+ if (p.expsign == 0)
{
- intdig_max = exponent + 1;
+ intdig_max = p.exponent + 1;
/* This can be really big! */ /* XXX Maybe malloc if too big? */
- chars_needed = (size_t) exponent + 1 + 1 + (size_t) fracdig_max;
+ chars_needed = (size_t) p.exponent + 1 + 1 + (size_t) fracdig_max;
}
else
{
@@ -846,27 +845,27 @@ ___printf_fp (FILE *fp,
else
{
dig_max = info->prec < 0 ? 6 : (info->prec == 0 ? 1 : info->prec);
- if ((expsign == 0 && exponent >= dig_max)
- || (expsign != 0 && exponent > 4))
+ if ((p.expsign == 0 && p.exponent >= dig_max)
+ || (p.expsign != 0 && p.exponent > 4))
{
if ('g' - 'G' == 'e' - 'E')
- type = 'E' + (info->spec - 'G');
+ p.type = 'E' + (info->spec - 'G');
else
- type = isupper (info->spec) ? 'E' : 'e';
+ p.type = isupper (info->spec) ? 'E' : 'e';
fracdig_max = dig_max - 1;
intdig_max = 1;
chars_needed = 1 + 1 + (size_t) fracdig_max + 1 + 1 + 4;
}
else
{
- type = 'f';
- intdig_max = expsign == 0 ? exponent + 1 : 0;
+ p.type = 'f';
+ intdig_max = p.expsign == 0 ? p.exponent + 1 : 0;
fracdig_max = dig_max - intdig_max;
/* We need space for the significant digits and perhaps
for leading zeros when < 1.0. The number of leading
zeros can be as many as would be required for
exponential notation with a negative two-digit
- exponent, which is 4. */
+ p.exponent, which is 4. */
chars_needed = (size_t) dig_max + 1 + 4;
}
fracdig_min = info->alt ? fracdig_max : 0;
@@ -908,26 +907,26 @@ ___printf_fp (FILE *fp,
wcp = wstartp = wbuffer + 2; /* Let room for rounding. */
/* Do the real work: put digits in allocated buffer. */
- if (expsign == 0 || type != 'f')
+ if (p.expsign == 0 || p.type != 'f')
{
- assert (expsign == 0 || intdig_max == 1);
+ assert (p.expsign == 0 || intdig_max == 1);
while (intdig_no < intdig_max)
{
++intdig_no;
- *wcp++ = hack_digit ();
+ *wcp++ = hack_digit (&p);
}
significant = 1;
if (info->alt
|| fracdig_min > 0
- || (fracdig_max > 0 && (fracsize > 1 || frac[0] != 0)))
+ || (fracdig_max > 0 && (p.fracsize > 1 || p.frac[0] != 0)))
*wcp++ = decimalwc;
}
else
{
- /* |fp| < 1.0 and the selected type is 'f', so put "0."
+ /* |fp| < 1.0 and the selected p.type is 'f', so put "0."
in the buffer. */
*wcp++ = L'0';
- --exponent;
+ --p.exponent;
*wcp++ = decimalwc;
}
@@ -935,10 +934,10 @@ ___printf_fp (FILE *fp,
int fracdig_no = 0;
int added_zeros = 0;
while (fracdig_no < fracdig_min + added_zeros
- || (fracdig_no < fracdig_max && (fracsize > 1 || frac[0] != 0)))
+ || (fracdig_no < fracdig_max && (p.fracsize > 1 || p.frac[0] != 0)))
{
++fracdig_no;
- *wcp = hack_digit ();
+ *wcp = hack_digit (&p);
if (*wcp++ != L'0')
significant = 1;
else if (significant == 0)
@@ -951,19 +950,19 @@ ___printf_fp (FILE *fp,
/* Do rounding. */
wchar_t last_digit = wcp[-1] != decimalwc ? wcp[-1] : wcp[-2];
- wchar_t next_digit = hack_digit ();
+ wchar_t next_digit = hack_digit (&p);
bool more_bits;
if (next_digit != L'0' && next_digit != L'5')
more_bits = true;
- else if (fracsize == 1 && frac[0] == 0)
+ else if (p.fracsize == 1 && p.frac[0] == 0)
/* Rest of the number is zero. */
more_bits = false;
- else if (scalesize == 0)
+ else if (p.scalesize == 0)
{
/* Here we have to see whether all limbs are zero since no
normalization happened. */
- size_t lcnt = fracsize;
- while (lcnt >= 1 && frac[lcnt - 1] == 0)
+ size_t lcnt = p.fracsize;
+ while (lcnt >= 1 && p.frac[lcnt - 1] == 0)
--lcnt;
more_bits = lcnt > 0;
}
@@ -990,7 +989,7 @@ ___printf_fp (FILE *fp,
if (*wtp != decimalwc)
/* Round up. */
(*wtp)++;
- else if (__builtin_expect (spec == 'g' && type == 'f' && info->alt
+ else if (__builtin_expect (spec == 'g' && p.type == 'f' && info->alt
&& wtp == wstartp + 1
&& wstartp[0] == L'0',
0))
@@ -1015,20 +1014,20 @@ ___printf_fp (FILE *fp,
else
/* It is more critical. All digits were 9's. */
{
- if (type != 'f')
+ if (p.type != 'f')
{
*wstartp = '1';
- exponent += expsign == 0 ? 1 : -1;
+ p.exponent += p.expsign == 0 ? 1 : -1;
- /* The above exponent adjustment could lead to 1.0e-00,
- e.g. for 0.999999999. Make sure exponent 0 always
+ /* The above p.exponent adjustment could lead to 1.0e-00,
+ e.g. for 0.999999999. Make sure p.exponent 0 always
uses + sign. */
- if (exponent == 0)
- expsign = 0;
+ if (p.exponent == 0)
+ p.expsign = 0;
}
else if (intdig_no == dig_max)
{
- /* This is the case where for type %g the number fits
+ /* This is the case where for p.type %g the number fits
really in the range for %f output but after rounding
the number of digits is too big. */
*--wstartp = decimalwc;
@@ -1044,9 +1043,9 @@ ___printf_fp (FILE *fp,
fracdig_no += intdig_no;
intdig_no = 1;
fracdig_max = intdig_max - intdig_no;
- ++exponent;
- /* Now we must print the exponent. */
- type = isupper (info->spec) ? 'E' : 'e';
+ ++p.exponent;
+ /* Now we must print the p.exponent. */
+ p.type = isupper (info->spec) ? 'E' : 'e';
}
else
{
@@ -1091,14 +1090,14 @@ ___printf_fp (FILE *fp,
ngroups);
}
- /* Write the exponent if it is needed. */
- if (type != 'f')
+ /* Write the p.exponent if it is needed. */
+ if (p.type != 'f')
{
- if (__glibc_unlikely (expsign != 0 && exponent == 4 && spec == 'g'))
+ if (__glibc_unlikely (p.expsign != 0 && p.exponent == 4 && spec == 'g'))
{
- /* This is another special case. The exponent of the number is
+ /* This is another special case. The p.exponent of the number is
really smaller than -4, which requires the 'e'/'E' format.
- But after rounding the number has an exponent of -4. */
+ But after rounding the number has an p.exponent of -4. */
assert (wcp >= wstartp + 1);
assert (wstartp[0] == L'1');
__wmemcpy (wstartp, L"0.0001", 6);
@@ -1113,26 +1112,26 @@ ___printf_fp (FILE *fp,
}
else
{
- *wcp++ = (wchar_t) type;
- *wcp++ = expsign ? L'-' : L'+';
+ *wcp++ = (wchar_t) p.type;
+ *wcp++ = p.expsign ? L'-' : L'+';
- /* Find the magnitude of the exponent. */
+ /* Find the magnitude of the p.exponent. */
expscale = 10;
- while (expscale <= exponent)
+ while (expscale <= p.exponent)
expscale *= 10;
- if (exponent < 10)
+ if (p.exponent < 10)
/* Exponent always has at least two digits. */
*wcp++ = L'0';
else
do
{
expscale /= 10;
- *wcp++ = L'0' + (exponent / expscale);
- exponent %= expscale;
+ *wcp++ = L'0' + (p.exponent / expscale);
+ p.exponent %= expscale;
}
while (expscale > 10);
- *wcp++ = L'0' + exponent;
+ *wcp++ = L'0' + p.exponent;
}
}