summaryrefslogtreecommitdiffstats
path: root/js/src/jit/riscv64/AssemblerMatInt.cpp
blob: 81c7fa7c40dfb84f4bb82636d7a49d2dc92a4098 (plain)
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
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
/* -*- Mode: C++; tab-width: 8; indent-tabs-mode: nil; c-basic-offset: 2 -*-
 * vim: set ts=8 sts=2 et sw=2 tw=80:
 * This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this
 * file, You can obtain one at http://mozilla.org/MPL/2.0/. */
//===- RISCVMatInt.cpp - Immediate materialisation -------------*- C++
//-*--===//
//
//  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 "mozilla/MathAlgorithms.h"
#include "mozilla/Maybe.h"

#include "gc/Marking.h"
#include "jit/AutoWritableJitCode.h"
#include "jit/ExecutableAllocator.h"
#include "jit/riscv64/Assembler-riscv64.h"
#include "jit/riscv64/disasm/Disasm-riscv64.h"
#include "vm/Realm.h"
namespace js {
namespace jit {
void Assembler::RecursiveLi(Register rd, int64_t val) {
  if (val > 0 && RecursiveLiImplCount(val) > 2) {
    unsigned LeadingZeros = mozilla::CountLeadingZeroes64((uint64_t)val);
    uint64_t ShiftedVal = (uint64_t)val << LeadingZeros;
    int countFillZero = RecursiveLiImplCount(ShiftedVal) + 1;
    if (countFillZero < RecursiveLiImplCount(val)) {
      RecursiveLiImpl(rd, ShiftedVal);
      srli(rd, rd, LeadingZeros);
      return;
    }
  }
  RecursiveLiImpl(rd, val);
}

int Assembler::RecursiveLiCount(int64_t val) {
  if (val > 0 && RecursiveLiImplCount(val) > 2) {
    unsigned LeadingZeros = mozilla::CountLeadingZeroes64((uint64_t)val);
    uint64_t ShiftedVal = (uint64_t)val << LeadingZeros;
    // Fill in the bits that will be shifted out with 1s. An example where
    // this helps is trailing one masks with 32 or more ones. This will
    // generate ADDI -1 and an SRLI.
    int countFillZero = RecursiveLiImplCount(ShiftedVal) + 1;
    if (countFillZero < RecursiveLiImplCount(val)) {
      return countFillZero;
    }
  }
  return RecursiveLiImplCount(val);
}

inline int64_t signExtend(uint64_t V, int N) {
  return int64_t(V << (64 - N)) >> (64 - N);
}

void Assembler::RecursiveLiImpl(Register rd, int64_t Val) {
  if (is_int32(Val)) {
    // Depending on the active bits in the immediate Value v, the following
    // instruction sequences are emitted:
    //
    // v == 0                        : ADDI
    // v[0,12) != 0 && v[12,32) == 0 : ADDI
    // v[0,12) == 0 && v[12,32) != 0 : LUI
    // v[0,32) != 0                  : LUI+ADDI(W)
    int64_t Hi20 = ((Val + 0x800) >> 12) & 0xFFFFF;
    int64_t Lo12 = Val << 52 >> 52;

    if (Hi20) {
      lui(rd, (int32_t)Hi20);
    }

    if (Lo12 || Hi20 == 0) {
      if (Hi20) {
        addiw(rd, rd, Lo12);
      } else {
        addi(rd, zero_reg, Lo12);
      }
    }
    return;
  }

  // In the worst case, for a full 64-bit constant, a sequence of 8
  // instructions (i.e., LUI+ADDIW+SLLI+ADDI+SLLI+ADDI+SLLI+ADDI) has to be
  // emitted. Note that the first two instructions (LUI+ADDIW) can contribute
  // up to 32 bits while the following ADDI instructions contribute up to 12
  // bits each.
  //
  // On the first glance, implementing this seems to be possible by simply
  // emitting the most significant 32 bits (LUI+ADDIW) followed by as many
  // left shift (SLLI) and immediate additions (ADDI) as needed. However, due
  // to the fact that ADDI performs a sign extended addition, doing it like
  // that would only be possible when at most 11 bits of the ADDI instructions
  // are used. Using all 12 bits of the ADDI instructions, like done by GAS,
  // actually requires that the constant is processed starting with the least
  // significant bit.
  //
  // In the following, constants are processed from LSB to MSB but instruction
  // emission is performed from MSB to LSB by recursively calling
  // generateInstSeq. In each recursion, first the lowest 12 bits are removed
  // from the constant and the optimal shift amount, which can be greater than
  // 12 bits if the constant is sparse, is determined. Then, the shifted
  // remaining constant is processed recursively and gets emitted as soon as
  // it fits into 32 bits. The emission of the shifts and additions is
  // subsequently performed when the recursion returns.

  int64_t Lo12 = Val << 52 >> 52;
  int64_t Hi52 = ((uint64_t)Val + 0x800ull) >> 12;
  int ShiftAmount = 12 + mozilla::CountTrailingZeroes64((uint64_t)Hi52);
  Hi52 = signExtend(Hi52 >> (ShiftAmount - 12), 64 - ShiftAmount);

  // If the remaining bits don't fit in 12 bits, we might be able to reduce
  // the shift amount in order to use LUI which will zero the lower 12 bits.
  bool Unsigned = false;
  if (ShiftAmount > 12 && !is_int12(Hi52)) {
    if (is_int32((uint64_t)Hi52 << 12)) {
      // Reduce the shift amount and add zeros to the LSBs so it will match
      // LUI.
      ShiftAmount -= 12;
      Hi52 = (uint64_t)Hi52 << 12;
    }
  }
  RecursiveLi(rd, Hi52);

  if (Unsigned) {
  } else {
    slli(rd, rd, ShiftAmount);
  }
  if (Lo12) {
    addi(rd, rd, Lo12);
  }
}

int Assembler::RecursiveLiImplCount(int64_t Val) {
  int count = 0;
  if (is_int32(Val)) {
    // Depending on the active bits in the immediate Value v, the following
    // instruction sequences are emitted:
    //
    // v == 0                        : ADDI
    // v[0,12) != 0 && v[12,32) == 0 : ADDI
    // v[0,12) == 0 && v[12,32) != 0 : LUI
    // v[0,32) != 0                  : LUI+ADDI(W)
    int64_t Hi20 = ((Val + 0x800) >> 12) & 0xFFFFF;
    int64_t Lo12 = Val << 52 >> 52;

    if (Hi20) {
      // lui(rd, (int32_t)Hi20);
      count++;
    }

    if (Lo12 || Hi20 == 0) {
      //   unsigned AddiOpc = (IsRV64 && Hi20) ? RISCV::ADDIW : RISCV::ADDI;
      //   Res.push_back(RISCVMatInt::Inst(AddiOpc, Lo12));
      count++;
    }
    return count;
  }

  // In the worst case, for a full 64-bit constant, a sequence of 8
  // instructions (i.e., LUI+ADDIW+SLLI+ADDI+SLLI+ADDI+SLLI+ADDI) has to be
  // emitted. Note that the first two instructions (LUI+ADDIW) can contribute
  // up to 32 bits while the following ADDI instructions contribute up to 12
  // bits each.
  //
  // On the first glance, implementing this seems to be possible by simply
  // emitting the most significant 32 bits (LUI+ADDIW) followed by as many
  // left shift (SLLI) and immediate additions (ADDI) as needed. However, due
  // to the fact that ADDI performs a sign extended addition, doing it like
  // that would only be possible when at most 11 bits of the ADDI instructions
  // are used. Using all 12 bits of the ADDI instructions, like done by GAS,
  // actually requires that the constant is processed starting with the least
  // significant bit.
  //
  // In the following, constants are processed from LSB to MSB but instruction
  // emission is performed from MSB to LSB by recursively calling
  // generateInstSeq. In each recursion, first the lowest 12 bits are removed
  // from the constant and the optimal shift amount, which can be greater than
  // 12 bits if the constant is sparse, is determined. Then, the shifted
  // remaining constant is processed recursively and gets emitted as soon as
  // it fits into 32 bits. The emission of the shifts and additions is
  // subsequently performed when the recursion returns.

  int64_t Lo12 = Val << 52 >> 52;
  int64_t Hi52 = ((uint64_t)Val + 0x800ull) >> 12;
  int ShiftAmount = 12 + mozilla::CountTrailingZeroes64((uint64_t)Hi52);
  Hi52 = signExtend(Hi52 >> (ShiftAmount - 12), 64 - ShiftAmount);

  // If the remaining bits don't fit in 12 bits, we might be able to reduce
  // the shift amount in order to use LUI which will zero the lower 12 bits.
  bool Unsigned = false;
  if (ShiftAmount > 12 && !is_int12(Hi52)) {
    if (is_int32((uint64_t)Hi52 << 12)) {
      // Reduce the shift amount and add zeros to the LSBs so it will match
      // LUI.
      ShiftAmount -= 12;
      Hi52 = (uint64_t)Hi52 << 12;
    }
  }

  count += RecursiveLiImplCount(Hi52);

  if (Unsigned) {
  } else {
    // slli(rd, rd, ShiftAmount);
    count++;
  }
  if (Lo12) {
    // addi(rd, rd, Lo12);
    count++;
  }
  return count;
}

}  // namespace jit
}  // namespace js