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
|
// -*- mode:c++ -*-
// Copyright (c) 2003-2005 The Regents of The University of Michigan
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met: redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer;
// redistributions in binary form must reproduce the above copyright
// notice, this list of conditions and the following disclaimer in the
// documentation and/or other materials provided with the distribution;
// neither the name of the copyright holders nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
output exec {{
/// Return opa + opb, summing carry into third arg.
inline uint64_t
addc(uint64_t opa, uint64_t opb, int &carry)
{
uint64_t res = opa + opb;
if (res < opa || res < opb)
++carry;
return res;
}
/// Multiply two 64-bit values (opa * opb), returning the 128-bit
/// product in res_hi and res_lo.
inline void
mul128(uint64_t opa, uint64_t opb, uint64_t &res_hi, uint64_t &res_lo)
{
// do a 64x64 --> 128 multiply using four 32x32 --> 64 multiplies
uint64_t opa_hi = opa<63:32>;
uint64_t opa_lo = opa<31:0>;
uint64_t opb_hi = opb<63:32>;
uint64_t opb_lo = opb<31:0>;
res_lo = opa_lo * opb_lo;
// The middle partial products logically belong in bit
// positions 95 to 32. Thus the lower 32 bits of each product
// sum into the upper 32 bits of the low result, while the
// upper 32 sum into the low 32 bits of the upper result.
uint64_t partial1 = opa_hi * opb_lo;
uint64_t partial2 = opa_lo * opb_hi;
uint64_t partial1_lo = partial1<31:0> << 32;
uint64_t partial1_hi = partial1<63:32>;
uint64_t partial2_lo = partial2<31:0> << 32;
uint64_t partial2_hi = partial2<63:32>;
// Add partial1_lo and partial2_lo to res_lo, keeping track
// of any carries out
int carry_out = 0;
res_lo = addc(partial1_lo, res_lo, carry_out);
res_lo = addc(partial2_lo, res_lo, carry_out);
// Now calculate the high 64 bits...
res_hi = (opa_hi * opb_hi) + partial1_hi + partial2_hi + carry_out;
}
/// Map 8-bit S-floating exponent to 11-bit T-floating exponent.
/// See Table 2-2 of Alpha AHB.
inline int
map_s(int old_exp)
{
int hibit = old_exp<7:>;
int lobits = old_exp<6:0>;
if (hibit == 1) {
return (lobits == 0x7f) ? 0x7ff : (0x400 | lobits);
}
else {
return (lobits == 0) ? 0 : (0x380 | lobits);
}
}
/// Convert a 32-bit S-floating value to the equivalent 64-bit
/// representation to be stored in an FP reg.
inline uint64_t
s_to_t(uint32_t s_val)
{
uint64_t tmp = s_val;
return (tmp<31:> << 63 // sign bit
| (uint64_t)map_s(tmp<30:23>) << 52 // exponent
| tmp<22:0> << 29); // fraction
}
/// Convert a 64-bit T-floating value to the equivalent 32-bit
/// S-floating representation to be stored in memory.
inline int32_t
t_to_s(uint64_t t_val)
{
return (t_val<63:62> << 30 // sign bit & hi exp bit
| t_val<58:29>); // rest of exp & fraction
}
}};
|