1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
|
#include <fenv.h>
#include <fpu_control.h>
#define _FP_W_TYPE_SIZE 64
#define _FP_W_TYPE unsigned long long
#define _FP_WS_TYPE signed long long
#define _FP_I_TYPE long long
#define _FP_MUL_MEAT_S(R,X,Y) \
_FP_MUL_MEAT_1_imm(_FP_WFRACBITS_S,R,X,Y)
#define _FP_MUL_MEAT_D(R,X,Y) \
_FP_MUL_MEAT_1_wide(_FP_WFRACBITS_D,R,X,Y,umul_ppmm)
#define _FP_MUL_MEAT_Q(R,X,Y) \
_FP_MUL_MEAT_2_wide_3mul(_FP_WFRACBITS_Q,R,X,Y,umul_ppmm)
#define _FP_DIV_MEAT_S(R,X,Y) _FP_DIV_MEAT_1_imm(S,R,X,Y,_FP_DIV_HELP_imm)
#define _FP_DIV_MEAT_D(R,X,Y) _FP_DIV_MEAT_1_udiv_norm(D,R,X,Y)
#define _FP_DIV_MEAT_Q(R,X,Y) _FP_DIV_MEAT_2_udiv(Q,R,X,Y)
#define _FP_NANFRAC_S ((_FP_QNANBIT_S << 1) - 1)
#define _FP_NANFRAC_D ((_FP_QNANBIT_D << 1) - 1)
#define _FP_NANFRAC_Q ((_FP_QNANBIT_Q << 1) - 1), -1
#define _FP_NANSIGN_S 0
#define _FP_NANSIGN_D 0
#define _FP_NANSIGN_Q 0
#define _FP_KEEPNANFRACP 1
#define _FP_QNANNEGATEDP 0
/* From my experiments it seems X is chosen unless one of the
NaNs is sNaN, in which case the result is NANSIGN/NANFRAC. */
#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP) \
do { \
if ((_FP_FRAC_HIGH_RAW_##fs(X) | \
_FP_FRAC_HIGH_RAW_##fs(Y)) & _FP_QNANBIT_##fs) \
{ \
R##_s = _FP_NANSIGN_##fs; \
_FP_FRAC_SET_##wc(R,_FP_NANFRAC_##fs); \
} \
else \
{ \
R##_s = X##_s; \
_FP_FRAC_COPY_##wc(R,X); \
} \
R##_c = FP_CLS_NAN; \
} while (0)
#define _FP_DECL_EX fpu_control_t _fcw
#define FP_ROUNDMODE (_fcw & 0x3)
#define FP_RND_NEAREST FE_TONEAREST
#define FP_RND_ZERO FE_TOWARDZERO
#define FP_RND_PINF FE_UPWARD
#define FP_RND_MINF FE_DOWNWARD
#define FP_EX_INVALID FE_INVALID
#define FP_EX_OVERFLOW FE_OVERFLOW
#define FP_EX_UNDERFLOW FE_UNDERFLOW
#define FP_EX_DIVZERO FE_DIVBYZERO
#define FP_EX_INEXACT FE_INEXACT
#define FP_INIT_ROUNDMODE \
do { \
_FPU_GETCW (_fcw); \
} while (0)
#define FP_HANDLE_EXCEPTIONS \
do { \
const float fp_max = __FLT_MAX__; \
const float fp_min = __FLT_MIN__; \
const float fp_1e32 = 1.0e32f; \
const float fp_zero = 0.0; \
const float fp_one = 1.0; \
unsigned fpsr; \
if (_fex & FP_EX_INVALID) \
{ \
__asm__ __volatile__ ("fdiv\ts0, %s0, %s0" \
: \
: "w" (fp_zero) \
: "s0"); \
__asm__ __volatile__ ("mrs\t%0, fpsr" : "=r" (fpsr)); \
} \
if (_fex & FP_EX_DIVZERO) \
{ \
__asm__ __volatile__ ("fdiv\ts0, %s0, %s1" \
: \
: "w" (fp_one), "w" (fp_zero) \
: "s0"); \
__asm__ __volatile__ ("mrs\t%0, fpsr" : "=r" (fpsr)); \
} \
if (_fex & FP_EX_OVERFLOW) \
{ \
__asm__ __volatile__ ("fadd\ts0, %s0, %s1" \
: \
: "w" (fp_max), "w" (fp_1e32) \
: "s0"); \
__asm__ __volatile__ ("mrs\t%0, fpsr" : "=r" (fpsr)); \
} \
if (_fex & FP_EX_UNDERFLOW) \
{ \
__asm__ __volatile__ ("fmul\ts0, %s0, %s0" \
: \
: "w" (fp_min) \
: "s0"); \
__asm__ __volatile__ ("mrs\t%0, fpsr" : "=r" (fpsr)); \
} \
if (_fex & FP_EX_INEXACT) \
{ \
__asm__ __volatile__ ("fsub\ts0, %s0, %s1" \
: \
: "w" (fp_max), "w" (fp_one) \
: "s0"); \
__asm__ __volatile__ ("mrs\t%0, fpsr" : "=r" (fpsr)); \
} \
} while (0)
#define FP_TRAPPING_EXCEPTIONS ((_fcw >> FE_EXCEPT_SHIFT) & FE_ALL_EXCEPT)
|
