summaryrefslogtreecommitdiff
path: root/arch/s390/include/asm/vx-insn.h
blob: b61846dff70fb7534db6e1b9c573cb880ef7ee5f (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
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
/*
 * Support for Vector Instructions
 *
 * Assembler macros to generate .byte/.word code for particular
 * vector instructions that are supported by recent binutils (>= 2.26) only.
 *
 * Copyright IBM Corp. 2015
 * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
 */

#ifndef __ASM_S390_VX_INSN_H
#define __ASM_S390_VX_INSN_H

#ifdef __ASSEMBLY__


/* Macros to generate vector instruction byte code */

/* GR_NUM - Retrieve general-purpose register number
 *
 * @opd:	Operand to store register number
 * @r64:	String designation register in the format "%rN"
 */
.macro	GR_NUM	opd gr
	\opd = 255
	.ifc \gr,%r0
		\opd = 0
	.endif
	.ifc \gr,%r1
		\opd = 1
	.endif
	.ifc \gr,%r2
		\opd = 2
	.endif
	.ifc \gr,%r3
		\opd = 3
	.endif
	.ifc \gr,%r4
		\opd = 4
	.endif
	.ifc \gr,%r5
		\opd = 5
	.endif
	.ifc \gr,%r6
		\opd = 6
	.endif
	.ifc \gr,%r7
		\opd = 7
	.endif
	.ifc \gr,%r8
		\opd = 8
	.endif
	.ifc \gr,%r9
		\opd = 9
	.endif
	.ifc \gr,%r10
		\opd = 10
	.endif
	.ifc \gr,%r11
		\opd = 11
	.endif
	.ifc \gr,%r12
		\opd = 12
	.endif
	.ifc \gr,%r13
		\opd = 13
	.endif
	.ifc \gr,%r14
		\opd = 14
	.endif
	.ifc \gr,%r15
		\opd = 15
	.endif
	.if \opd == 255
		\opd = \gr
	.endif
.endm

/* VX_NUM - Retrieve vector register number
 *
 * @opd:	Operand to store register number
 * @vxr:	String designation register in the format "%vN"
 *
 * The vector register number is used for as input number to the
 * instruction and, as well as, to compute the RXB field of the
 * instruction.
 */
.macro	VX_NUM	opd vxr
	\opd = 255
	.ifc \vxr,%v0
		\opd = 0
	.endif
	.ifc \vxr,%v1
		\opd = 1
	.endif
	.ifc \vxr,%v2
		\opd = 2
	.endif
	.ifc \vxr,%v3
		\opd = 3
	.endif
	.ifc \vxr,%v4
		\opd = 4
	.endif
	.ifc \vxr,%v5
		\opd = 5
	.endif
	.ifc \vxr,%v6
		\opd = 6
	.endif
	.ifc \vxr,%v7
		\opd = 7
	.endif
	.ifc \vxr,%v8
		\opd = 8
	.endif
	.ifc \vxr,%v9
		\opd = 9
	.endif
	.ifc \vxr,%v10
		\opd = 10
	.endif
	.ifc \vxr,%v11
		\opd = 11
	.endif
	.ifc \vxr,%v12
		\opd = 12
	.endif
	.ifc \vxr,%v13
		\opd = 13
	.endif
	.ifc \vxr,%v14
		\opd = 14
	.endif
	.ifc \vxr,%v15
		\opd = 15
	.endif
	.ifc \vxr,%v16
		\opd = 16
	.endif
	.ifc \vxr,%v17
		\opd = 17
	.endif
	.ifc \vxr,%v18
		\opd = 18
	.endif
	.ifc \vxr,%v19
		\opd = 19
	.endif
	.ifc \vxr,%v20
		\opd = 20
	.endif
	.ifc \vxr,%v21
		\opd = 21
	.endif
	.ifc \vxr,%v22
		\opd = 22
	.endif
	.ifc \vxr,%v23
		\opd = 23
	.endif
	.ifc \vxr,%v24
		\opd = 24
	.endif
	.ifc \vxr,%v25
		\opd = 25
	.endif
	.ifc \vxr,%v26
		\opd = 26
	.endif
	.ifc \vxr,%v27
		\opd = 27
	.endif
	.ifc \vxr,%v28
		\opd = 28
	.endif
	.ifc \vxr,%v29
		\opd = 29
	.endif
	.ifc \vxr,%v30
		\opd = 30
	.endif
	.ifc \vxr,%v31
		\opd = 31
	.endif
	.if \opd == 255
		\opd = \vxr
	.endif
.endm

/* RXB - Compute most significant bit used vector registers
 *
 * @rxb:	Operand to store computed RXB value
 * @v1:		First vector register designated operand
 * @v2:		Second vector register designated operand
 * @v3:		Third vector register designated operand
 * @v4:		Fourth vector register designated operand
 */
.macro	RXB	rxb v1 v2=0 v3=0 v4=0
	\rxb = 0
	.if \v1 & 0x10
		\rxb = \rxb | 0x08
	.endif
	.if \v2 & 0x10
		\rxb = \rxb | 0x04
	.endif
	.if \v3 & 0x10
		\rxb = \rxb | 0x02
	.endif
	.if \v4 & 0x10
		\rxb = \rxb | 0x01
	.endif
.endm

/* MRXB - Generate Element Size Control and RXB value
 *
 * @m:		Element size control
 * @v1:		First vector register designated operand (for RXB)
 * @v2:		Second vector register designated operand (for RXB)
 * @v3:		Third vector register designated operand (for RXB)
 * @v4:		Fourth vector register designated operand (for RXB)
 */
.macro	MRXB	m v1 v2=0 v3=0 v4=0
	rxb = 0
	RXB	rxb, \v1, \v2, \v3, \v4
	.byte	(\m << 4) | rxb
.endm

/* MRXBOPC - Generate Element Size Control, RXB, and final Opcode fields
 *
 * @m:		Element size control
 * @opc:	Opcode
 * @v1:		First vector register designated operand (for RXB)
 * @v2:		Second vector register designated operand (for RXB)
 * @v3:		Third vector register designated operand (for RXB)
 * @v4:		Fourth vector register designated operand (for RXB)
 */
.macro	MRXBOPC	m opc v1 v2=0 v3=0 v4=0
	MRXB	\m, \v1, \v2, \v3, \v4
	.byte	\opc
.endm

/* Vector support instructions */

/* VECTOR GENERATE BYTE MASK */
.macro	VGBM	vr imm2
	VX_NUM	v1, \vr
	.word	(0xE700 | ((v1&15) << 4))
	.word	\imm2
	MRXBOPC	0, 0x44, v1
.endm
.macro	VZERO	vxr
	VGBM	\vxr, 0
.endm
.macro	VONE	vxr
	VGBM	\vxr, 0xFFFF
.endm

/* VECTOR LOAD VR ELEMENT FROM GR */
.macro	VLVG	v, gr, disp, m
	VX_NUM	v1, \v
	GR_NUM	b2, "%r0"
	GR_NUM	r3, \gr
	.word	0xE700 | ((v1&15) << 4) | r3
	.word	(b2 << 12) | (\disp)
	MRXBOPC	\m, 0x22, v1
.endm
.macro	VLVGB	v, gr, index, base
	VLVG	\v, \gr, \index, \base, 0
.endm
.macro	VLVGH	v, gr, index
	VLVG	\v, \gr, \index, 1
.endm
.macro	VLVGF	v, gr, index
	VLVG	\v, \gr, \index, 2
.endm
.macro	VLVGG	v, gr, index
	VLVG	\v, \gr, \index, 3
.endm

/* VECTOR LOAD */
.macro	VL	v, disp, index="%r0", base
	VX_NUM	v1, \v
	GR_NUM	x2, \index
	GR_NUM	b2, \base
	.word	0xE700 | ((v1&15) << 4) | x2
	.word	(b2 << 12) | (\disp)
	MRXBOPC 0, 0x06, v1
.endm

/* VECTOR LOAD ELEMENT */
.macro	VLEx	vr1, disp, index="%r0", base, m3, opc
	VX_NUM	v1, \vr1
	GR_NUM	x2, \index
	GR_NUM	b2, \base
	.word	0xE700 | ((v1&15) << 4) | x2
	.word	(b2 << 12) | (\disp)
	MRXBOPC	\m3, \opc, v1
.endm
.macro	VLEB	vr1, disp, index="%r0", base, m3
	VLEx	\vr1, \disp, \index, \base, \m3, 0x00
.endm
.macro	VLEH	vr1, disp, index="%r0", base, m3
	VLEx	\vr1, \disp, \index, \base, \m3, 0x01
.endm
.macro	VLEF	vr1, disp, index="%r0", base, m3
	VLEx	\vr1, \disp, \index, \base, \m3, 0x03
.endm
.macro	VLEG	vr1, disp, index="%r0", base, m3
	VLEx	\vr1, \disp, \index, \base, \m3, 0x02
.endm

/* VECTOR LOAD ELEMENT IMMEDIATE */
.macro	VLEIx	vr1, imm2, m3, opc
	VX_NUM	v1, \vr1
	.word	0xE700 | ((v1&15) << 4)
	.word	\imm2
	MRXBOPC	\m3, \opc, v1
.endm
.macro	VLEIB	vr1, imm2, index
	VLEIx	\vr1, \imm2, \index, 0x40
.endm
.macro	VLEIH	vr1, imm2, index
	VLEIx	\vr1, \imm2, \index, 0x41
.endm
.macro	VLEIF	vr1, imm2, index
	VLEIx	\vr1, \imm2, \index, 0x43
.endm
.macro	VLEIG	vr1, imm2, index
	VLEIx	\vr1, \imm2, \index, 0x42
.endm

/* VECTOR LOAD GR FROM VR ELEMENT */
.macro	VLGV	gr, vr, disp, base="%r0", m
	GR_NUM	r1, \gr
	GR_NUM	b2, \base
	VX_NUM	v3, \vr
	.word	0xE700 | (r1 << 4) | (v3&15)
	.word	(b2 << 12) | (\disp)
	MRXBOPC	\m, 0x21, v3
.endm
.macro	VLGVB	gr, vr, disp, base="%r0"
	VLGV	\gr, \vr, \disp, \base, 0
.endm
.macro	VLGVH	gr, vr, disp, base="%r0"
	VLGV	\gr, \vr, \disp, \base, 1
.endm
.macro	VLGVF	gr, vr, disp, base="%r0"
	VLGV	\gr, \vr, \disp, \base, 2
.endm
.macro	VLGVG	gr, vr, disp, base="%r0"
	VLGV	\gr, \vr, \disp, \base, 3
.endm

/* VECTOR LOAD MULTIPLE */
.macro	VLM	vfrom, vto, disp, base
	VX_NUM	v1, \vfrom
	VX_NUM	v3, \vto
	GR_NUM	b2, \base	    /* Base register */
	.word	0xE700 | ((v1&15) << 4) | (v3&15)
	.word	(b2 << 12) | (\disp)
	MRXBOPC	0, 0x36, v1, v3
.endm

/* VECTOR STORE MULTIPLE */
.macro	VSTM	vfrom, vto, disp, base
	VX_NUM	v1, \vfrom
	VX_NUM	v3, \vto
	GR_NUM	b2, \base	    /* Base register */
	.word	0xE700 | ((v1&15) << 4) | (v3&15)
	.word	(b2 << 12) | (\disp)
	MRXBOPC	0, 0x3E, v1, v3
.endm

/* VECTOR PERMUTE */
.macro	VPERM	vr1, vr2, vr3, vr4
	VX_NUM	v1, \vr1
	VX_NUM	v2, \vr2
	VX_NUM	v3, \vr3
	VX_NUM	v4, \vr4
	.word	0xE700 | ((v1&15) << 4) | (v2&15)
	.word	((v3&15) << 12)
	MRXBOPC	(v4&15), 0x8C, v1, v2, v3, v4
.endm

/* VECTOR UNPACK LOGICAL LOW */
.macro	VUPLL	vr1, vr2, m3
	VX_NUM	v1, \vr1
	VX_NUM	v2, \vr2
	.word	0xE700 | ((v1&15) << 4) | (v2&15)
	.word	0x0000
	MRXBOPC	\m3, 0xD4, v1, v2
.endm
.macro	VUPLLB	vr1, vr2
	VUPLL	\vr1, \vr2, 0
.endm
.macro	VUPLLH	vr1, vr2
	VUPLL	\vr1, \vr2, 1
.endm
.macro	VUPLLF	vr1, vr2
	VUPLL	\vr1, \vr2, 2
.endm


/* Vector integer instructions */

/* VECTOR EXCLUSIVE OR */
.macro	VX	vr1, vr2, vr3
	VX_NUM	v1, \vr1
	VX_NUM	v2, \vr2
	VX_NUM	v3, \vr3
	.word	0xE700 | ((v1&15) << 4) | (v2&15)
	.word	((v3&15) << 12)
	MRXBOPC	0, 0x6D, v1, v2, v3
.endm

/* VECTOR GALOIS FIELD MULTIPLY SUM */
.macro	VGFM	vr1, vr2, vr3, m4
	VX_NUM	v1, \vr1
	VX_NUM	v2, \vr2
	VX_NUM	v3, \vr3
	.word	0xE700 | ((v1&15) << 4) | (v2&15)
	.word	((v3&15) << 12)
	MRXBOPC	\m4, 0xB4, v1, v2, v3
.endm
.macro	VGFMB	vr1, vr2, vr3
	VGFM	\vr1, \vr2, \vr3, 0
.endm
.macro	VGFMH	vr1, vr2, vr3
	VGFM	\vr1, \vr2, \vr3, 1
.endm
.macro	VGFMF	vr1, vr2, vr3
	VGFM	\vr1, \vr2, \vr3, 2
.endm
.macro	VGFMG	vr1, vr2, vr3
	VGFM	\vr1, \vr2, \vr3, 3
.endm

/* VECTOR GALOIS FIELD MULTIPLY SUM AND ACCUMULATE */
.macro	VGFMA	vr1, vr2, vr3, vr4, m5
	VX_NUM	v1, \vr1
	VX_NUM	v2, \vr2
	VX_NUM	v3, \vr3
	VX_NUM	v4, \vr4
	.word	0xE700 | ((v1&15) << 4) | (v2&15)
	.word	((v3&15) << 12) | (\m5 << 8)
	MRXBOPC	(v4&15), 0xBC, v1, v2, v3, v4
.endm
.macro	VGFMAB	vr1, vr2, vr3, vr4
	VGFMA	\vr1, \vr2, \vr3, \vr4, 0
.endm
.macro	VGFMAH	vr1, vr2, vr3, vr4
	VGFMA	\vr1, \vr2, \vr3, \vr4, 1
.endm
.macro	VGFMAF	vr1, vr2, vr3, vr4
	VGFMA	\vr1, \vr2, \vr3, \vr4, 2
.endm
.macro	VGFMAG	vr1, vr2, vr3, vr4
	VGFMA	\vr1, \vr2, \vr3, \vr4, 3
.endm

/* VECTOR SHIFT RIGHT LOGICAL BY BYTE */
.macro	VSRLB	vr1, vr2, vr3
	VX_NUM	v1, \vr1
	VX_NUM	v2, \vr2
	VX_NUM	v3, \vr3
	.word	0xE700 | ((v1&15) << 4) | (v2&15)
	.word	((v3&15) << 12)
	MRXBOPC	0, 0x7D, v1, v2, v3
.endm


#endif	/* __ASSEMBLY__ */
#endif	/* __ASM_S390_VX_INSN_H */