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
|
//===-- Half-precision 2^x function ---------------------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
#include "src/math/exp2f16.h"
#include "expxf16.h"
#include "hdr/errno_macros.h"
#include "hdr/fenv_macros.h"
#include "src/__support/FPUtil/FEnvImpl.h"
#include "src/__support/FPUtil/FPBits.h"
#include "src/__support/FPUtil/cast.h"
#include "src/__support/FPUtil/except_value_utils.h"
#include "src/__support/FPUtil/rounding_mode.h"
#include "src/__support/common.h"
#include "src/__support/macros/config.h"
#include "src/__support/macros/optimization.h"
namespace LIBC_NAMESPACE_DECL {
#ifndef LIBC_MATH_HAS_SKIP_ACCURATE_PASS
static constexpr fputil::ExceptValues<float16, 3> EXP2F16_EXCEPTS = {{
// (input, RZ output, RU offset, RD offset, RN offset)
// x = 0x1.714p-11, exp2f16(x) = 0x1p+0 (RZ)
{0x11c5U, 0x3c00U, 1U, 0U, 1U},
// x = -0x1.558p-4, exp2f16(x) = 0x1.e34p-1 (RZ)
{0xad56U, 0x3b8dU, 1U, 0U, 0U},
// x = -0x1.d5cp-4, exp2f16(x) = 0x1.d8cp-1 (RZ)
{0xaf57U, 0x3b63U, 1U, 0U, 0U},
}};
#endif // !LIBC_MATH_HAS_SKIP_ACCURATE_PASS
LLVM_LIBC_FUNCTION(float16, exp2f16, (float16 x)) {
using FPBits = fputil::FPBits<float16>;
FPBits x_bits(x);
uint16_t x_u = x_bits.uintval();
uint16_t x_abs = x_u & 0x7fffU;
// When |x| >= 16, or x is NaN.
if (LIBC_UNLIKELY(x_abs >= 0x4c00U)) {
// exp2(NaN) = NaN
if (x_bits.is_nan()) {
if (x_bits.is_signaling_nan()) {
fputil::raise_except_if_required(FE_INVALID);
return FPBits::quiet_nan().get_val();
}
return x;
}
// When x >= 16.
if (x_bits.is_pos()) {
// exp2(+inf) = +inf
if (x_bits.is_inf())
return FPBits::inf().get_val();
switch (fputil::quick_get_round()) {
case FE_TONEAREST:
case FE_UPWARD:
fputil::set_errno_if_required(ERANGE);
fputil::raise_except_if_required(FE_OVERFLOW);
return FPBits::inf().get_val();
default:
return FPBits::max_normal().get_val();
}
}
// When x <= -25.
if (x_u >= 0xce40U) {
// exp2(-inf) = +0
if (x_bits.is_inf())
return FPBits::zero().get_val();
fputil::set_errno_if_required(ERANGE);
fputil::raise_except_if_required(FE_UNDERFLOW | FE_INEXACT);
if (fputil::fenv_is_round_up())
return FPBits::min_subnormal().get_val();
return FPBits::zero().get_val();
}
}
#ifndef LIBC_MATH_HAS_SKIP_ACCURATE_PASS
if (auto r = EXP2F16_EXCEPTS.lookup(x_u); LIBC_UNLIKELY(r.has_value()))
return r.value();
#endif // !LIBC_MATH_HAS_SKIP_ACCURATE_PASS
// exp2(x) = exp2(hi + mid) * exp2(lo)
auto [exp2_hi_mid, exp2_lo] = exp2_range_reduction(x);
return fputil::cast<float16>(exp2_hi_mid * exp2_lo);
}
} // namespace LIBC_NAMESPACE_DECL
|
