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
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
|
/*
* Copyright(c) 2019-2021 Qualcomm Innovation Center, Inc. All Rights Reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program 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 General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#include "qemu/osdep.h"
#include "cpu.h"
#include "internal.h"
#include "tcg/tcg-op.h"
#include "tcg/tcg-op-gvec.h"
#include "insn.h"
#include "opcodes.h"
#include "translate.h"
#define QEMU_GENERATE /* Used internally by macros.h */
#include "macros.h"
#include "mmvec/macros.h"
#undef QEMU_GENERATE
#include "gen_tcg.h"
#include "gen_tcg_hvx.h"
static inline void gen_log_predicated_reg_write(int rnum, TCGv val, int slot)
{
TCGv zero = tcg_constant_tl(0);
TCGv slot_mask = tcg_temp_new();
tcg_gen_andi_tl(slot_mask, hex_slot_cancelled, 1 << slot);
tcg_gen_movcond_tl(TCG_COND_EQ, hex_new_value[rnum], slot_mask, zero,
val, hex_new_value[rnum]);
if (HEX_DEBUG) {
/*
* Do this so HELPER(debug_commit_end) will know
*
* Note that slot_mask indicates the value is not written
* (i.e., slot was cancelled), so we create a true/false value before
* or'ing with hex_reg_written[rnum].
*/
tcg_gen_setcond_tl(TCG_COND_EQ, slot_mask, slot_mask, zero);
tcg_gen_or_tl(hex_reg_written[rnum], hex_reg_written[rnum], slot_mask);
}
tcg_temp_free(slot_mask);
}
static inline void gen_log_reg_write(int rnum, TCGv val)
{
tcg_gen_mov_tl(hex_new_value[rnum], val);
if (HEX_DEBUG) {
/* Do this so HELPER(debug_commit_end) will know */
tcg_gen_movi_tl(hex_reg_written[rnum], 1);
}
}
static void gen_log_predicated_reg_write_pair(int rnum, TCGv_i64 val, int slot)
{
TCGv val32 = tcg_temp_new();
TCGv zero = tcg_constant_tl(0);
TCGv slot_mask = tcg_temp_new();
tcg_gen_andi_tl(slot_mask, hex_slot_cancelled, 1 << slot);
/* Low word */
tcg_gen_extrl_i64_i32(val32, val);
tcg_gen_movcond_tl(TCG_COND_EQ, hex_new_value[rnum],
slot_mask, zero,
val32, hex_new_value[rnum]);
/* High word */
tcg_gen_extrh_i64_i32(val32, val);
tcg_gen_movcond_tl(TCG_COND_EQ, hex_new_value[rnum + 1],
slot_mask, zero,
val32, hex_new_value[rnum + 1]);
if (HEX_DEBUG) {
/*
* Do this so HELPER(debug_commit_end) will know
*
* Note that slot_mask indicates the value is not written
* (i.e., slot was cancelled), so we create a true/false value before
* or'ing with hex_reg_written[rnum].
*/
tcg_gen_setcond_tl(TCG_COND_EQ, slot_mask, slot_mask, zero);
tcg_gen_or_tl(hex_reg_written[rnum], hex_reg_written[rnum], slot_mask);
tcg_gen_or_tl(hex_reg_written[rnum + 1], hex_reg_written[rnum + 1],
slot_mask);
}
tcg_temp_free(val32);
tcg_temp_free(slot_mask);
}
static void gen_log_reg_write_pair(int rnum, TCGv_i64 val)
{
/* Low word */
tcg_gen_extrl_i64_i32(hex_new_value[rnum], val);
if (HEX_DEBUG) {
/* Do this so HELPER(debug_commit_end) will know */
tcg_gen_movi_tl(hex_reg_written[rnum], 1);
}
/* High word */
tcg_gen_extrh_i64_i32(hex_new_value[rnum + 1], val);
if (HEX_DEBUG) {
/* Do this so HELPER(debug_commit_end) will know */
tcg_gen_movi_tl(hex_reg_written[rnum + 1], 1);
}
}
static inline void gen_log_pred_write(DisasContext *ctx, int pnum, TCGv val)
{
TCGv base_val = tcg_temp_new();
tcg_gen_andi_tl(base_val, val, 0xff);
/*
* Section 6.1.3 of the Hexagon V67 Programmer's Reference Manual
*
* Multiple writes to the same preg are and'ed together
* If this is the first predicate write in the packet, do a
* straight assignment. Otherwise, do an and.
*/
if (!test_bit(pnum, ctx->pregs_written)) {
tcg_gen_mov_tl(hex_new_pred_value[pnum], base_val);
} else {
tcg_gen_and_tl(hex_new_pred_value[pnum],
hex_new_pred_value[pnum], base_val);
}
tcg_gen_ori_tl(hex_pred_written, hex_pred_written, 1 << pnum);
tcg_temp_free(base_val);
}
static inline void gen_read_p3_0(TCGv control_reg)
{
tcg_gen_movi_tl(control_reg, 0);
for (int i = 0; i < NUM_PREGS; i++) {
tcg_gen_deposit_tl(control_reg, control_reg, hex_pred[i], i * 8, 8);
}
}
/*
* Certain control registers require special handling on read
* HEX_REG_P3_0 aliased to the predicate registers
* -> concat the 4 predicate registers together
* HEX_REG_PC actual value stored in DisasContext
* -> assign from ctx->base.pc_next
* HEX_REG_QEMU_*_CNT changes in current TB in DisasContext
* -> add current TB changes to existing reg value
*/
static inline void gen_read_ctrl_reg(DisasContext *ctx, const int reg_num,
TCGv dest)
{
if (reg_num == HEX_REG_P3_0) {
gen_read_p3_0(dest);
} else if (reg_num == HEX_REG_PC) {
tcg_gen_movi_tl(dest, ctx->base.pc_next);
} else if (reg_num == HEX_REG_QEMU_PKT_CNT) {
tcg_gen_addi_tl(dest, hex_gpr[HEX_REG_QEMU_PKT_CNT],
ctx->num_packets);
} else if (reg_num == HEX_REG_QEMU_INSN_CNT) {
tcg_gen_addi_tl(dest, hex_gpr[HEX_REG_QEMU_INSN_CNT],
ctx->num_insns);
} else if (reg_num == HEX_REG_QEMU_HVX_CNT) {
tcg_gen_addi_tl(dest, hex_gpr[HEX_REG_QEMU_HVX_CNT],
ctx->num_hvx_insns);
} else {
tcg_gen_mov_tl(dest, hex_gpr[reg_num]);
}
}
static inline void gen_read_ctrl_reg_pair(DisasContext *ctx, const int reg_num,
TCGv_i64 dest)
{
if (reg_num == HEX_REG_P3_0) {
TCGv p3_0 = tcg_temp_new();
gen_read_p3_0(p3_0);
tcg_gen_concat_i32_i64(dest, p3_0, hex_gpr[reg_num + 1]);
tcg_temp_free(p3_0);
} else if (reg_num == HEX_REG_PC - 1) {
TCGv pc = tcg_constant_tl(ctx->base.pc_next);
tcg_gen_concat_i32_i64(dest, hex_gpr[reg_num], pc);
} else if (reg_num == HEX_REG_QEMU_PKT_CNT) {
TCGv pkt_cnt = tcg_temp_new();
TCGv insn_cnt = tcg_temp_new();
tcg_gen_addi_tl(pkt_cnt, hex_gpr[HEX_REG_QEMU_PKT_CNT],
ctx->num_packets);
tcg_gen_addi_tl(insn_cnt, hex_gpr[HEX_REG_QEMU_INSN_CNT],
ctx->num_insns);
tcg_gen_concat_i32_i64(dest, pkt_cnt, insn_cnt);
tcg_temp_free(pkt_cnt);
tcg_temp_free(insn_cnt);
} else if (reg_num == HEX_REG_QEMU_HVX_CNT) {
TCGv hvx_cnt = tcg_temp_new();
tcg_gen_addi_tl(hvx_cnt, hex_gpr[HEX_REG_QEMU_HVX_CNT],
ctx->num_hvx_insns);
tcg_gen_concat_i32_i64(dest, hvx_cnt, hex_gpr[reg_num + 1]);
tcg_temp_free(hvx_cnt);
} else {
tcg_gen_concat_i32_i64(dest,
hex_gpr[reg_num],
hex_gpr[reg_num + 1]);
}
}
static inline void gen_write_p3_0(TCGv control_reg)
{
for (int i = 0; i < NUM_PREGS; i++) {
tcg_gen_extract_tl(hex_pred[i], control_reg, i * 8, 8);
}
}
/*
* Certain control registers require special handling on write
* HEX_REG_P3_0 aliased to the predicate registers
* -> break the value across 4 predicate registers
* HEX_REG_QEMU_*_CNT changes in current TB in DisasContext
* -> clear the changes
*/
static inline void gen_write_ctrl_reg(DisasContext *ctx, int reg_num,
TCGv val)
{
if (reg_num == HEX_REG_P3_0) {
gen_write_p3_0(val);
} else {
gen_log_reg_write(reg_num, val);
ctx_log_reg_write(ctx, reg_num);
if (reg_num == HEX_REG_QEMU_PKT_CNT) {
ctx->num_packets = 0;
}
if (reg_num == HEX_REG_QEMU_INSN_CNT) {
ctx->num_insns = 0;
}
if (reg_num == HEX_REG_QEMU_HVX_CNT) {
ctx->num_hvx_insns = 0;
}
}
}
static inline void gen_write_ctrl_reg_pair(DisasContext *ctx, int reg_num,
TCGv_i64 val)
{
if (reg_num == HEX_REG_P3_0) {
TCGv val32 = tcg_temp_new();
tcg_gen_extrl_i64_i32(val32, val);
gen_write_p3_0(val32);
tcg_gen_extrh_i64_i32(val32, val);
gen_log_reg_write(reg_num + 1, val32);
tcg_temp_free(val32);
ctx_log_reg_write(ctx, reg_num + 1);
} else {
gen_log_reg_write_pair(reg_num, val);
ctx_log_reg_write_pair(ctx, reg_num);
if (reg_num == HEX_REG_QEMU_PKT_CNT) {
ctx->num_packets = 0;
ctx->num_insns = 0;
}
if (reg_num == HEX_REG_QEMU_HVX_CNT) {
ctx->num_hvx_insns = 0;
}
}
}
static TCGv gen_get_byte(TCGv result, int N, TCGv src, bool sign)
{
if (sign) {
tcg_gen_sextract_tl(result, src, N * 8, 8);
} else {
tcg_gen_extract_tl(result, src, N * 8, 8);
}
return result;
}
static TCGv gen_get_byte_i64(TCGv result, int N, TCGv_i64 src, bool sign)
{
TCGv_i64 res64 = tcg_temp_new_i64();
if (sign) {
tcg_gen_sextract_i64(res64, src, N * 8, 8);
} else {
tcg_gen_extract_i64(res64, src, N * 8, 8);
}
tcg_gen_extrl_i64_i32(result, res64);
tcg_temp_free_i64(res64);
return result;
}
static inline TCGv gen_get_half(TCGv result, int N, TCGv src, bool sign)
{
if (sign) {
tcg_gen_sextract_tl(result, src, N * 16, 16);
} else {
tcg_gen_extract_tl(result, src, N * 16, 16);
}
return result;
}
static inline void gen_set_half(int N, TCGv result, TCGv src)
{
tcg_gen_deposit_tl(result, result, src, N * 16, 16);
}
static inline void gen_set_half_i64(int N, TCGv_i64 result, TCGv src)
{
TCGv_i64 src64 = tcg_temp_new_i64();
tcg_gen_extu_i32_i64(src64, src);
tcg_gen_deposit_i64(result, result, src64, N * 16, 16);
tcg_temp_free_i64(src64);
}
static void gen_set_byte_i64(int N, TCGv_i64 result, TCGv src)
{
TCGv_i64 src64 = tcg_temp_new_i64();
tcg_gen_extu_i32_i64(src64, src);
tcg_gen_deposit_i64(result, result, src64, N * 8, 8);
tcg_temp_free_i64(src64);
}
static inline void gen_load_locked4u(TCGv dest, TCGv vaddr, int mem_index)
{
tcg_gen_qemu_ld32u(dest, vaddr, mem_index);
tcg_gen_mov_tl(hex_llsc_addr, vaddr);
tcg_gen_mov_tl(hex_llsc_val, dest);
}
static inline void gen_load_locked8u(TCGv_i64 dest, TCGv vaddr, int mem_index)
{
tcg_gen_qemu_ld64(dest, vaddr, mem_index);
tcg_gen_mov_tl(hex_llsc_addr, vaddr);
tcg_gen_mov_i64(hex_llsc_val_i64, dest);
}
static inline void gen_store_conditional4(DisasContext *ctx,
TCGv pred, TCGv vaddr, TCGv src)
{
TCGLabel *fail = gen_new_label();
TCGLabel *done = gen_new_label();
TCGv one, zero, tmp;
tcg_gen_brcond_tl(TCG_COND_NE, vaddr, hex_llsc_addr, fail);
one = tcg_constant_tl(0xff);
zero = tcg_constant_tl(0);
tmp = tcg_temp_new();
tcg_gen_atomic_cmpxchg_tl(tmp, hex_llsc_addr, hex_llsc_val, src,
ctx->mem_idx, MO_32);
tcg_gen_movcond_tl(TCG_COND_EQ, pred, tmp, hex_llsc_val,
one, zero);
tcg_temp_free(tmp);
tcg_gen_br(done);
gen_set_label(fail);
tcg_gen_movi_tl(pred, 0);
gen_set_label(done);
tcg_gen_movi_tl(hex_llsc_addr, ~0);
}
static inline void gen_store_conditional8(DisasContext *ctx,
TCGv pred, TCGv vaddr, TCGv_i64 src)
{
TCGLabel *fail = gen_new_label();
TCGLabel *done = gen_new_label();
TCGv_i64 one, zero, tmp;
tcg_gen_brcond_tl(TCG_COND_NE, vaddr, hex_llsc_addr, fail);
one = tcg_constant_i64(0xff);
zero = tcg_constant_i64(0);
tmp = tcg_temp_new_i64();
tcg_gen_atomic_cmpxchg_i64(tmp, hex_llsc_addr, hex_llsc_val_i64, src,
ctx->mem_idx, MO_64);
tcg_gen_movcond_i64(TCG_COND_EQ, tmp, tmp, hex_llsc_val_i64,
one, zero);
tcg_gen_extrl_i64_i32(pred, tmp);
tcg_temp_free_i64(tmp);
tcg_gen_br(done);
gen_set_label(fail);
tcg_gen_movi_tl(pred, 0);
gen_set_label(done);
tcg_gen_movi_tl(hex_llsc_addr, ~0);
}
static inline void gen_store32(TCGv vaddr, TCGv src, int width, int slot)
{
tcg_gen_mov_tl(hex_store_addr[slot], vaddr);
tcg_gen_movi_tl(hex_store_width[slot], width);
tcg_gen_mov_tl(hex_store_val32[slot], src);
}
static inline void gen_store1(TCGv_env cpu_env, TCGv vaddr, TCGv src,
DisasContext *ctx, int slot)
{
gen_store32(vaddr, src, 1, slot);
ctx->store_width[slot] = 1;
}
static inline void gen_store1i(TCGv_env cpu_env, TCGv vaddr, int32_t src,
DisasContext *ctx, int slot)
{
TCGv tmp = tcg_constant_tl(src);
gen_store1(cpu_env, vaddr, tmp, ctx, slot);
}
static inline void gen_store2(TCGv_env cpu_env, TCGv vaddr, TCGv src,
DisasContext *ctx, int slot)
{
gen_store32(vaddr, src, 2, slot);
ctx->store_width[slot] = 2;
}
static inline void gen_store2i(TCGv_env cpu_env, TCGv vaddr, int32_t src,
DisasContext *ctx, int slot)
{
TCGv tmp = tcg_constant_tl(src);
gen_store2(cpu_env, vaddr, tmp, ctx, slot);
}
static inline void gen_store4(TCGv_env cpu_env, TCGv vaddr, TCGv src,
DisasContext *ctx, int slot)
{
gen_store32(vaddr, src, 4, slot);
ctx->store_width[slot] = 4;
}
static inline void gen_store4i(TCGv_env cpu_env, TCGv vaddr, int32_t src,
DisasContext *ctx, int slot)
{
TCGv tmp = tcg_constant_tl(src);
gen_store4(cpu_env, vaddr, tmp, ctx, slot);
}
static inline void gen_store8(TCGv_env cpu_env, TCGv vaddr, TCGv_i64 src,
DisasContext *ctx, int slot)
{
tcg_gen_mov_tl(hex_store_addr[slot], vaddr);
tcg_gen_movi_tl(hex_store_width[slot], 8);
tcg_gen_mov_i64(hex_store_val64[slot], src);
ctx->store_width[slot] = 8;
}
static inline void gen_store8i(TCGv_env cpu_env, TCGv vaddr, int64_t src,
DisasContext *ctx, int slot)
{
TCGv_i64 tmp = tcg_constant_i64(src);
gen_store8(cpu_env, vaddr, tmp, ctx, slot);
}
static TCGv gen_8bitsof(TCGv result, TCGv value)
{
TCGv zero = tcg_constant_tl(0);
TCGv ones = tcg_constant_tl(0xff);
tcg_gen_movcond_tl(TCG_COND_NE, result, value, zero, ones, zero);
return result;
}
static intptr_t vreg_src_off(DisasContext *ctx, int num)
{
intptr_t offset = offsetof(CPUHexagonState, VRegs[num]);
if (test_bit(num, ctx->vregs_select)) {
offset = ctx_future_vreg_off(ctx, num, 1, false);
}
if (test_bit(num, ctx->vregs_updated_tmp)) {
offset = ctx_tmp_vreg_off(ctx, num, 1, false);
}
return offset;
}
static void gen_log_vreg_write(DisasContext *ctx, intptr_t srcoff, int num,
VRegWriteType type, int slot_num,
bool is_predicated)
{
TCGLabel *label_end = NULL;
intptr_t dstoff;
if (is_predicated) {
TCGv cancelled = tcg_temp_local_new();
label_end = gen_new_label();
/* Don't do anything if the slot was cancelled */
tcg_gen_extract_tl(cancelled, hex_slot_cancelled, slot_num, 1);
tcg_gen_brcondi_tl(TCG_COND_NE, cancelled, 0, label_end);
tcg_temp_free(cancelled);
}
if (type != EXT_TMP) {
dstoff = ctx_future_vreg_off(ctx, num, 1, true);
tcg_gen_gvec_mov(MO_64, dstoff, srcoff,
sizeof(MMVector), sizeof(MMVector));
tcg_gen_ori_tl(hex_VRegs_updated, hex_VRegs_updated, 1 << num);
} else {
dstoff = ctx_tmp_vreg_off(ctx, num, 1, false);
tcg_gen_gvec_mov(MO_64, dstoff, srcoff,
sizeof(MMVector), sizeof(MMVector));
}
if (is_predicated) {
gen_set_label(label_end);
}
}
static void gen_log_vreg_write_pair(DisasContext *ctx, intptr_t srcoff, int num,
VRegWriteType type, int slot_num,
bool is_predicated)
{
gen_log_vreg_write(ctx, srcoff, num ^ 0, type, slot_num, is_predicated);
srcoff += sizeof(MMVector);
gen_log_vreg_write(ctx, srcoff, num ^ 1, type, slot_num, is_predicated);
}
static void gen_log_qreg_write(intptr_t srcoff, int num, int vnew,
int slot_num, bool is_predicated)
{
TCGLabel *label_end = NULL;
intptr_t dstoff;
if (is_predicated) {
TCGv cancelled = tcg_temp_local_new();
label_end = gen_new_label();
/* Don't do anything if the slot was cancelled */
tcg_gen_extract_tl(cancelled, hex_slot_cancelled, slot_num, 1);
tcg_gen_brcondi_tl(TCG_COND_NE, cancelled, 0, label_end);
tcg_temp_free(cancelled);
}
dstoff = offsetof(CPUHexagonState, future_QRegs[num]);
tcg_gen_gvec_mov(MO_64, dstoff, srcoff, sizeof(MMQReg), sizeof(MMQReg));
if (is_predicated) {
tcg_gen_ori_tl(hex_QRegs_updated, hex_QRegs_updated, 1 << num);
gen_set_label(label_end);
}
}
static void gen_vreg_load(DisasContext *ctx, intptr_t dstoff, TCGv src,
bool aligned)
{
TCGv_i64 tmp = tcg_temp_new_i64();
if (aligned) {
tcg_gen_andi_tl(src, src, ~((int32_t)sizeof(MMVector) - 1));
}
for (int i = 0; i < sizeof(MMVector) / 8; i++) {
tcg_gen_qemu_ld64(tmp, src, ctx->mem_idx);
tcg_gen_addi_tl(src, src, 8);
tcg_gen_st_i64(tmp, cpu_env, dstoff + i * 8);
}
tcg_temp_free_i64(tmp);
}
static void gen_vreg_store(DisasContext *ctx, Insn *insn, Packet *pkt,
TCGv EA, intptr_t srcoff, int slot, bool aligned)
{
intptr_t dstoff = offsetof(CPUHexagonState, vstore[slot].data);
intptr_t maskoff = offsetof(CPUHexagonState, vstore[slot].mask);
if (is_gather_store_insn(insn, pkt)) {
TCGv sl = tcg_constant_tl(slot);
gen_helper_gather_store(cpu_env, EA, sl);
return;
}
tcg_gen_movi_tl(hex_vstore_pending[slot], 1);
if (aligned) {
tcg_gen_andi_tl(hex_vstore_addr[slot], EA,
~((int32_t)sizeof(MMVector) - 1));
} else {
tcg_gen_mov_tl(hex_vstore_addr[slot], EA);
}
tcg_gen_movi_tl(hex_vstore_size[slot], sizeof(MMVector));
/* Copy the data to the vstore buffer */
tcg_gen_gvec_mov(MO_64, dstoff, srcoff, sizeof(MMVector), sizeof(MMVector));
/* Set the mask to all 1's */
tcg_gen_gvec_dup_imm(MO_64, maskoff, sizeof(MMQReg), sizeof(MMQReg), ~0LL);
}
static void gen_vreg_masked_store(DisasContext *ctx, TCGv EA, intptr_t srcoff,
intptr_t bitsoff, int slot, bool invert)
{
intptr_t dstoff = offsetof(CPUHexagonState, vstore[slot].data);
intptr_t maskoff = offsetof(CPUHexagonState, vstore[slot].mask);
tcg_gen_movi_tl(hex_vstore_pending[slot], 1);
tcg_gen_andi_tl(hex_vstore_addr[slot], EA,
~((int32_t)sizeof(MMVector) - 1));
tcg_gen_movi_tl(hex_vstore_size[slot], sizeof(MMVector));
/* Copy the data to the vstore buffer */
tcg_gen_gvec_mov(MO_64, dstoff, srcoff, sizeof(MMVector), sizeof(MMVector));
/* Copy the mask */
tcg_gen_gvec_mov(MO_64, maskoff, bitsoff, sizeof(MMQReg), sizeof(MMQReg));
if (invert) {
tcg_gen_gvec_not(MO_64, maskoff, maskoff,
sizeof(MMQReg), sizeof(MMQReg));
}
}
static void vec_to_qvec(size_t size, intptr_t dstoff, intptr_t srcoff)
{
TCGv_i64 tmp = tcg_temp_new_i64();
TCGv_i64 word = tcg_temp_new_i64();
TCGv_i64 bits = tcg_temp_new_i64();
TCGv_i64 mask = tcg_temp_new_i64();
TCGv_i64 zero = tcg_constant_i64(0);
TCGv_i64 ones = tcg_constant_i64(~0);
for (int i = 0; i < sizeof(MMVector) / 8; i++) {
tcg_gen_ld_i64(tmp, cpu_env, srcoff + i * 8);
tcg_gen_movi_i64(mask, 0);
for (int j = 0; j < 8; j += size) {
tcg_gen_extract_i64(word, tmp, j * 8, size * 8);
tcg_gen_movcond_i64(TCG_COND_NE, bits, word, zero, ones, zero);
tcg_gen_deposit_i64(mask, mask, bits, j, size);
}
tcg_gen_st8_i64(mask, cpu_env, dstoff + i);
}
tcg_temp_free_i64(tmp);
tcg_temp_free_i64(word);
tcg_temp_free_i64(bits);
tcg_temp_free_i64(mask);
}
#include "tcg_funcs_generated.c.inc"
#include "tcg_func_table_generated.c.inc"
|