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
|
/*
* ARM translation: M-profile MVE instructions
*
* Copyright (c) 2021 Linaro, Ltd.
*
* 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 2.1 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 "tcg/tcg-op.h"
#include "tcg/tcg-op-gvec.h"
#include "exec/exec-all.h"
#include "exec/gen-icount.h"
#include "translate.h"
#include "translate-a32.h"
/* Include the generated decoder */
#include "decode-mve.c.inc"
typedef void MVEGenLdStFn(TCGv_ptr, TCGv_ptr, TCGv_i32);
typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr);
/* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */
static inline long mve_qreg_offset(unsigned reg)
{
return offsetof(CPUARMState, vfp.zregs[reg].d[0]);
}
static TCGv_ptr mve_qreg_ptr(unsigned reg)
{
TCGv_ptr ret = tcg_temp_new_ptr();
tcg_gen_addi_ptr(ret, cpu_env, mve_qreg_offset(reg));
return ret;
}
static bool mve_check_qreg_bank(DisasContext *s, int qmask)
{
/*
* Check whether Qregs are in range. For v8.1M only Q0..Q7
* are supported, see VFPSmallRegisterBank().
*/
return qmask < 8;
}
static bool mve_eci_check(DisasContext *s)
{
/*
* This is a beatwise insn: check that ECI is valid (not a
* reserved value) and note that we are handling it.
* Return true if OK, false if we generated an exception.
*/
s->eci_handled = true;
switch (s->eci) {
case ECI_NONE:
case ECI_A0:
case ECI_A0A1:
case ECI_A0A1A2:
case ECI_A0A1A2B0:
return true;
default:
/* Reserved value: INVSTATE UsageFault */
gen_exception_insn(s, s->pc_curr, EXCP_INVSTATE, syn_uncategorized(),
default_exception_el(s));
return false;
}
}
static void mve_update_eci(DisasContext *s)
{
/*
* The helper function will always update the CPUState field,
* so we only need to update the DisasContext field.
*/
if (s->eci) {
s->eci = (s->eci == ECI_A0A1A2B0) ? ECI_A0 : ECI_NONE;
}
}
static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn)
{
TCGv_i32 addr;
uint32_t offset;
TCGv_ptr qreg;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qd) ||
!fn) {
return false;
}
/* CONSTRAINED UNPREDICTABLE: we choose to UNDEF */
if (a->rn == 15 || (a->rn == 13 && a->w)) {
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
offset = a->imm << a->size;
if (!a->a) {
offset = -offset;
}
addr = load_reg(s, a->rn);
if (a->p) {
tcg_gen_addi_i32(addr, addr, offset);
}
qreg = mve_qreg_ptr(a->qd);
fn(cpu_env, qreg, addr);
tcg_temp_free_ptr(qreg);
/*
* Writeback always happens after the last beat of the insn,
* regardless of predication
*/
if (a->w) {
if (!a->p) {
tcg_gen_addi_i32(addr, addr, offset);
}
store_reg(s, a->rn, addr);
} else {
tcg_temp_free_i32(addr);
}
mve_update_eci(s);
return true;
}
static bool trans_VLDR_VSTR(DisasContext *s, arg_VLDR_VSTR *a)
{
static MVEGenLdStFn * const ldstfns[4][2] = {
{ gen_helper_mve_vstrb, gen_helper_mve_vldrb },
{ gen_helper_mve_vstrh, gen_helper_mve_vldrh },
{ gen_helper_mve_vstrw, gen_helper_mve_vldrw },
{ NULL, NULL }
};
return do_ldst(s, a, ldstfns[a->size][a->l]);
}
#define DO_VLDST_WIDE_NARROW(OP, SLD, ULD, ST) \
static bool trans_##OP(DisasContext *s, arg_VLDR_VSTR *a) \
{ \
static MVEGenLdStFn * const ldstfns[2][2] = { \
{ gen_helper_mve_##ST, gen_helper_mve_##SLD }, \
{ NULL, gen_helper_mve_##ULD }, \
}; \
return do_ldst(s, a, ldstfns[a->u][a->l]); \
}
DO_VLDST_WIDE_NARROW(VLDSTB_H, vldrb_sh, vldrb_uh, vstrb_h)
DO_VLDST_WIDE_NARROW(VLDSTB_W, vldrb_sw, vldrb_uw, vstrb_w)
DO_VLDST_WIDE_NARROW(VLDSTH_W, vldrh_sw, vldrh_uw, vstrh_w)
static bool trans_VDUP(DisasContext *s, arg_VDUP *a)
{
TCGv_ptr qd;
TCGv_i32 rt;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qd)) {
return false;
}
if (a->rt == 13 || a->rt == 15) {
/* UNPREDICTABLE; we choose to UNDEF */
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
qd = mve_qreg_ptr(a->qd);
rt = load_reg(s, a->rt);
tcg_gen_dup_i32(a->size, rt, rt);
gen_helper_mve_vdup(cpu_env, qd, rt);
tcg_temp_free_ptr(qd);
tcg_temp_free_i32(rt);
mve_update_eci(s);
return true;
}
static bool do_1op(DisasContext *s, arg_1op *a, MVEGenOneOpFn fn)
{
TCGv_ptr qd, qm;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qd | a->qm) ||
!fn) {
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
qd = mve_qreg_ptr(a->qd);
qm = mve_qreg_ptr(a->qm);
fn(cpu_env, qd, qm);
tcg_temp_free_ptr(qd);
tcg_temp_free_ptr(qm);
mve_update_eci(s);
return true;
}
#define DO_1OP(INSN, FN) \
static bool trans_##INSN(DisasContext *s, arg_1op *a) \
{ \
static MVEGenOneOpFn * const fns[] = { \
gen_helper_mve_##FN##b, \
gen_helper_mve_##FN##h, \
gen_helper_mve_##FN##w, \
NULL, \
}; \
return do_1op(s, a, fns[a->size]); \
}
DO_1OP(VCLZ, vclz)
DO_1OP(VCLS, vcls)
DO_1OP(VABS, vabs)
DO_1OP(VNEG, vneg)
static bool trans_VREV16(DisasContext *s, arg_1op *a)
{
static MVEGenOneOpFn * const fns[] = {
gen_helper_mve_vrev16b,
NULL,
NULL,
NULL,
};
return do_1op(s, a, fns[a->size]);
}
static bool trans_VREV32(DisasContext *s, arg_1op *a)
{
static MVEGenOneOpFn * const fns[] = {
gen_helper_mve_vrev32b,
gen_helper_mve_vrev32h,
NULL,
NULL,
};
return do_1op(s, a, fns[a->size]);
}
static bool trans_VREV64(DisasContext *s, arg_1op *a)
{
static MVEGenOneOpFn * const fns[] = {
gen_helper_mve_vrev64b,
gen_helper_mve_vrev64h,
gen_helper_mve_vrev64w,
NULL,
};
return do_1op(s, a, fns[a->size]);
}
static bool trans_VMVN(DisasContext *s, arg_1op *a)
{
return do_1op(s, a, gen_helper_mve_vmvn);
}
static bool trans_VABS_fp(DisasContext *s, arg_1op *a)
{
static MVEGenOneOpFn * const fns[] = {
NULL,
gen_helper_mve_vfabsh,
gen_helper_mve_vfabss,
NULL,
};
if (!dc_isar_feature(aa32_mve_fp, s)) {
return false;
}
return do_1op(s, a, fns[a->size]);
}
static bool trans_VNEG_fp(DisasContext *s, arg_1op *a)
{
static MVEGenOneOpFn * const fns[] = {
NULL,
gen_helper_mve_vfnegh,
gen_helper_mve_vfnegs,
NULL,
};
if (!dc_isar_feature(aa32_mve_fp, s)) {
return false;
}
return do_1op(s, a, fns[a->size]);
}
static bool do_2op(DisasContext *s, arg_2op *a, MVEGenTwoOpFn fn)
{
TCGv_ptr qd, qn, qm;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qd | a->qn | a->qm) ||
!fn) {
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
qd = mve_qreg_ptr(a->qd);
qn = mve_qreg_ptr(a->qn);
qm = mve_qreg_ptr(a->qm);
fn(cpu_env, qd, qn, qm);
tcg_temp_free_ptr(qd);
tcg_temp_free_ptr(qn);
tcg_temp_free_ptr(qm);
mve_update_eci(s);
return true;
}
#define DO_LOGIC(INSN, HELPER) \
static bool trans_##INSN(DisasContext *s, arg_2op *a) \
{ \
return do_2op(s, a, HELPER); \
}
DO_LOGIC(VAND, gen_helper_mve_vand)
DO_LOGIC(VBIC, gen_helper_mve_vbic)
DO_LOGIC(VORR, gen_helper_mve_vorr)
DO_LOGIC(VORN, gen_helper_mve_vorn)
DO_LOGIC(VEOR, gen_helper_mve_veor)
#define DO_2OP(INSN, FN) \
static bool trans_##INSN(DisasContext *s, arg_2op *a) \
{ \
static MVEGenTwoOpFn * const fns[] = { \
gen_helper_mve_##FN##b, \
gen_helper_mve_##FN##h, \
gen_helper_mve_##FN##w, \
NULL, \
}; \
return do_2op(s, a, fns[a->size]); \
}
DO_2OP(VADD, vadd)
DO_2OP(VSUB, vsub)
DO_2OP(VMUL, vmul)
DO_2OP(VMULH_S, vmulhs)
DO_2OP(VMULH_U, vmulhu)
DO_2OP(VRMULH_S, vrmulhs)
DO_2OP(VRMULH_U, vrmulhu)
DO_2OP(VMAX_S, vmaxs)
DO_2OP(VMAX_U, vmaxu)
DO_2OP(VMIN_S, vmins)
DO_2OP(VMIN_U, vminu)
DO_2OP(VABD_S, vabds)
DO_2OP(VABD_U, vabdu)
|