aboutsummaryrefslogtreecommitdiff
path: root/tcg/tcg-op-vec.c
blob: cefba3d185bbf24b8ece050f71774a1b1e0180f2 (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
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
/*
 * Tiny Code Generator for QEMU
 *
 * Copyright (c) 2018 Linaro, Inc.
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, see <http://www.gnu.org/licenses/>.
 */

#include "qemu/osdep.h"
#include "qemu-common.h"
#include "cpu.h"
#include "tcg.h"
#include "tcg-op.h"
#include "tcg-mo.h"

/* Reduce the number of ifdefs below.  This assumes that all uses of
   TCGV_HIGH and TCGV_LOW are properly protected by a conditional that
   the compiler can eliminate.  */
#if TCG_TARGET_REG_BITS == 64
extern TCGv_i32 TCGV_LOW_link_error(TCGv_i64);
extern TCGv_i32 TCGV_HIGH_link_error(TCGv_i64);
#define TCGV_LOW  TCGV_LOW_link_error
#define TCGV_HIGH TCGV_HIGH_link_error
#endif

void vec_gen_2(TCGOpcode opc, TCGType type, unsigned vece, TCGArg r, TCGArg a)
{
    TCGOp *op = tcg_emit_op(opc);
    TCGOP_VECL(op) = type - TCG_TYPE_V64;
    TCGOP_VECE(op) = vece;
    op->args[0] = r;
    op->args[1] = a;
}

void vec_gen_3(TCGOpcode opc, TCGType type, unsigned vece,
               TCGArg r, TCGArg a, TCGArg b)
{
    TCGOp *op = tcg_emit_op(opc);
    TCGOP_VECL(op) = type - TCG_TYPE_V64;
    TCGOP_VECE(op) = vece;
    op->args[0] = r;
    op->args[1] = a;
    op->args[2] = b;
}

void vec_gen_4(TCGOpcode opc, TCGType type, unsigned vece,
               TCGArg r, TCGArg a, TCGArg b, TCGArg c)
{
    TCGOp *op = tcg_emit_op(opc);
    TCGOP_VECL(op) = type - TCG_TYPE_V64;
    TCGOP_VECE(op) = vece;
    op->args[0] = r;
    op->args[1] = a;
    op->args[2] = b;
    op->args[3] = c;
}

static void vec_gen_op2(TCGOpcode opc, unsigned vece, TCGv_vec r, TCGv_vec a)
{
    TCGTemp *rt = tcgv_vec_temp(r);
    TCGTemp *at = tcgv_vec_temp(a);
    TCGType type = rt->base_type;

    /* Must enough inputs for the output.  */
    tcg_debug_assert(at->base_type >= type);
    vec_gen_2(opc, type, vece, temp_arg(rt), temp_arg(at));
}

static void vec_gen_op3(TCGOpcode opc, unsigned vece,
                        TCGv_vec r, TCGv_vec a, TCGv_vec b)
{
    TCGTemp *rt = tcgv_vec_temp(r);
    TCGTemp *at = tcgv_vec_temp(a);
    TCGTemp *bt = tcgv_vec_temp(b);
    TCGType type = rt->base_type;

    /* Must enough inputs for the output.  */
    tcg_debug_assert(at->base_type >= type);
    tcg_debug_assert(bt->base_type >= type);
    vec_gen_3(opc, type, vece, temp_arg(rt), temp_arg(at), temp_arg(bt));
}

void tcg_gen_mov_vec(TCGv_vec r, TCGv_vec a)
{
    if (r != a) {
        vec_gen_op2(INDEX_op_mov_vec, 0, r, a);
    }
}

#define MO_REG  (TCG_TARGET_REG_BITS == 64 ? MO_64 : MO_32)

static void do_dupi_vec(TCGv_vec r, unsigned vece, TCGArg a)
{
    TCGTemp *rt = tcgv_vec_temp(r);
    vec_gen_2(INDEX_op_dupi_vec, rt->base_type, vece, temp_arg(rt), a);
}

TCGv_vec tcg_const_zeros_vec(TCGType type)
{
    TCGv_vec ret = tcg_temp_new_vec(type);
    do_dupi_vec(ret, MO_REG, 0);
    return ret;
}

TCGv_vec tcg_const_ones_vec(TCGType type)
{
    TCGv_vec ret = tcg_temp_new_vec(type);
    do_dupi_vec(ret, MO_REG, -1);
    return ret;
}

TCGv_vec tcg_const_zeros_vec_matching(TCGv_vec m)
{
    TCGTemp *t = tcgv_vec_temp(m);
    return tcg_const_zeros_vec(t->base_type);
}

TCGv_vec tcg_const_ones_vec_matching(TCGv_vec m)
{
    TCGTemp *t = tcgv_vec_temp(m);
    return tcg_const_ones_vec(t->base_type);
}

void tcg_gen_dup64i_vec(TCGv_vec r, uint64_t a)
{
    if (TCG_TARGET_REG_BITS == 32 && a == deposit64(a, 32, 32, a)) {
        do_dupi_vec(r, MO_32, a);
    } else if (TCG_TARGET_REG_BITS == 64 || a == (uint64_t)(int32_t)a) {
        do_dupi_vec(r, MO_64, a);
    } else {
        TCGv_i64 c = tcg_const_i64(a);
        tcg_gen_dup_i64_vec(MO_64, r, c);
        tcg_temp_free_i64(c);
    }
}

void tcg_gen_dup32i_vec(TCGv_vec r, uint32_t a)
{
    do_dupi_vec(r, MO_REG, dup_const(MO_32, a));
}

void tcg_gen_dup16i_vec(TCGv_vec r, uint32_t a)
{
    do_dupi_vec(r, MO_REG, dup_const(MO_16, a));
}

void tcg_gen_dup8i_vec(TCGv_vec r, uint32_t a)
{
    do_dupi_vec(r, MO_REG, dup_const(MO_8, a));
}

void tcg_gen_dupi_vec(unsigned vece, TCGv_vec r, uint64_t a)
{
    do_dupi_vec(r, MO_REG, dup_const(vece, a));
}

void tcg_gen_dup_i64_vec(unsigned vece, TCGv_vec r, TCGv_i64 a)
{
    TCGArg ri = tcgv_vec_arg(r);
    TCGTemp *rt = arg_temp(ri);
    TCGType type = rt->base_type;

    if (TCG_TARGET_REG_BITS == 64) {
        TCGArg ai = tcgv_i64_arg(a);
        vec_gen_2(INDEX_op_dup_vec, type, vece, ri, ai);
    } else if (vece == MO_64) {
        TCGArg al = tcgv_i32_arg(TCGV_LOW(a));
        TCGArg ah = tcgv_i32_arg(TCGV_HIGH(a));
        vec_gen_3(INDEX_op_dup2_vec, type, MO_64, ri, al, ah);
    } else {
        TCGArg ai = tcgv_i32_arg(TCGV_LOW(a));
        vec_gen_2(INDEX_op_dup_vec, type, vece, ri, ai);
    }
}

void tcg_gen_dup_i32_vec(unsigned vece, TCGv_vec r, TCGv_i32 a)
{
    TCGArg ri = tcgv_vec_arg(r);
    TCGArg ai = tcgv_i32_arg(a);
    TCGTemp *rt = arg_temp(ri);
    TCGType type = rt->base_type;

    vec_gen_2(INDEX_op_dup_vec, type, vece, ri, ai);
}

static void vec_gen_ldst(TCGOpcode opc, TCGv_vec r, TCGv_ptr b, TCGArg o)
{
    TCGArg ri = tcgv_vec_arg(r);
    TCGArg bi = tcgv_ptr_arg(b);
    TCGTemp *rt = arg_temp(ri);
    TCGType type = rt->base_type;

    vec_gen_3(opc, type, 0, ri, bi, o);
}

void tcg_gen_ld_vec(TCGv_vec r, TCGv_ptr b, TCGArg o)
{
    vec_gen_ldst(INDEX_op_ld_vec, r, b, o);
}

void tcg_gen_st_vec(TCGv_vec r, TCGv_ptr b, TCGArg o)
{
    vec_gen_ldst(INDEX_op_st_vec, r, b, o);
}

void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr b, TCGArg o, TCGType low_type)
{
    TCGArg ri = tcgv_vec_arg(r);
    TCGArg bi = tcgv_ptr_arg(b);
    TCGTemp *rt = arg_temp(ri);
    TCGType type = rt->base_type;

    tcg_debug_assert(low_type >= TCG_TYPE_V64);
    tcg_debug_assert(low_type <= type);
    vec_gen_3(INDEX_op_st_vec, low_type, 0, ri, bi, o);
}

void tcg_gen_add_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b)
{
    vec_gen_op3(INDEX_op_add_vec, vece, r, a, b);
}

void tcg_gen_sub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b)
{
    vec_gen_op3(INDEX_op_sub_vec, vece, r, a, b);
}

void tcg_gen_and_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b)
{
    vec_gen_op3(INDEX_op_and_vec, 0, r, a, b);
}

void tcg_gen_or_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b)
{
    vec_gen_op3(INDEX_op_or_vec, 0, r, a, b);
}

void tcg_gen_xor_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b)
{
    vec_gen_op3(INDEX_op_xor_vec, 0, r, a, b);
}

void tcg_gen_andc_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b)
{
    if (TCG_TARGET_HAS_andc_vec) {
        vec_gen_op3(INDEX_op_andc_vec, 0, r, a, b);
    } else {
        TCGv_vec t = tcg_temp_new_vec_matching(r);
        tcg_gen_not_vec(0, t, b);
        tcg_gen_and_vec(0, r, a, t);
        tcg_temp_free_vec(t);
    }
}

void tcg_gen_orc_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b)
{
    if (TCG_TARGET_HAS_orc_vec) {
        vec_gen_op3(INDEX_op_orc_vec, 0, r, a, b);
    } else {
        TCGv_vec t = tcg_temp_new_vec_matching(r);
        tcg_gen_not_vec(0, t, b);
        tcg_gen_or_vec(0, r, a, t);
        tcg_temp_free_vec(t);
    }
}

void tcg_gen_not_vec(unsigned vece, TCGv_vec r, TCGv_vec a)
{
    if (TCG_TARGET_HAS_not_vec) {
        vec_gen_op2(INDEX_op_not_vec, 0, r, a);
    } else {
        TCGv_vec t = tcg_const_ones_vec_matching(r);
        tcg_gen_xor_vec(0, r, a, t);
        tcg_temp_free_vec(t);
    }
}

void tcg_gen_neg_vec(unsigned vece, TCGv_vec r, TCGv_vec a)
{
    if (TCG_TARGET_HAS_neg_vec) {
        vec_gen_op2(INDEX_op_neg_vec, vece, r, a);
    } else {
        TCGv_vec t = tcg_const_zeros_vec_matching(r);
        tcg_gen_sub_vec(vece, r, t, a);
        tcg_temp_free_vec(t);
    }
}

static void do_shifti(TCGOpcode opc, unsigned vece,
                      TCGv_vec r, TCGv_vec a, int64_t i)
{
    TCGTemp *rt = tcgv_vec_temp(r);
    TCGTemp *at = tcgv_vec_temp(a);
    TCGArg ri = temp_arg(rt);
    TCGArg ai = temp_arg(at);
    TCGType type = rt->base_type;
    int can;

    tcg_debug_assert(at->base_type == type);
    tcg_debug_assert(i >= 0 && i < (8 << vece));

    if (i == 0) {
        tcg_gen_mov_vec(r, a);
        return;
    }

    can = tcg_can_emit_vec_op(opc, type, vece);
    if (can > 0) {
        vec_gen_3(opc, type, vece, ri, ai, i);
    } else {
        /* We leave the choice of expansion via scalar or vector shift
           to the target.  Often, but not always, dupi can feed a vector
           shift easier than a scalar.  */
        tcg_debug_assert(can < 0);
        tcg_expand_vec_op(opc, type, vece, ri, ai, i);
    }
}

void tcg_gen_shli_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i)
{
    do_shifti(INDEX_op_shli_vec, vece, r, a, i);
}

void tcg_gen_shri_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i)
{
    do_shifti(INDEX_op_shri_vec, vece, r, a, i);
}

void tcg_gen_sari_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i)
{
    do_shifti(INDEX_op_sari_vec, vece, r, a, i);
}

void tcg_gen_cmp_vec(TCGCond cond, unsigned vece,
                     TCGv_vec r, TCGv_vec a, TCGv_vec b)
{
    TCGTemp *rt = tcgv_vec_temp(r);
    TCGTemp *at = tcgv_vec_temp(a);
    TCGTemp *bt = tcgv_vec_temp(b);
    TCGArg ri = temp_arg(rt);
    TCGArg ai = temp_arg(at);
    TCGArg bi = temp_arg(bt);
    TCGType type = rt->base_type;
    int can;

    tcg_debug_assert(at->base_type >= type);
    tcg_debug_assert(bt->base_type >= type);
    can = tcg_can_emit_vec_op(INDEX_op_cmp_vec, type, vece);
    if (can > 0) {
        vec_gen_4(INDEX_op_cmp_vec, type, vece, ri, ai, bi, cond);
    } else {
        tcg_debug_assert(can < 0);
        tcg_expand_vec_op(INDEX_op_cmp_vec, type, vece, ri, ai, bi, cond);
    }
}

void tcg_gen_mul_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b)
{
    TCGTemp *rt = tcgv_vec_temp(r);
    TCGTemp *at = tcgv_vec_temp(a);
    TCGTemp *bt = tcgv_vec_temp(b);
    TCGArg ri = temp_arg(rt);
    TCGArg ai = temp_arg(at);
    TCGArg bi = temp_arg(bt);
    TCGType type = rt->base_type;
    int can;

    tcg_debug_assert(at->base_type >= type);
    tcg_debug_assert(bt->base_type >= type);
    can = tcg_can_emit_vec_op(INDEX_op_mul_vec, type, vece);
    if (can > 0) {
        vec_gen_3(INDEX_op_mul_vec, type, vece, ri, ai, bi);
    } else {
        tcg_debug_assert(can < 0);
        tcg_expand_vec_op(INDEX_op_mul_vec, type, vece, ri, ai, bi);
    }
}