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
|
From b0a64ddebb517a1678c44d9baf24d8bbe39d02cd Mon Sep 17 00:00:00 2001
From: Khem Raj <raj.khem@gmail.com>
Date: Tue, 29 Jan 2019 13:15:07 -0800
Subject: [PATCH] asm: Delete .func/.endfunc directives
These are useful only with stabs debug format, which is not used on
linux systems, gas ignores them silently, but clang assembler does not
and rightly so.
Signed-off-by: Khem Raj <raj.khem@gmail.com>
---
aarch64-asm.S | 14 +-------------
arm-neon.S | 24 ------------------------
mips-32.S | 5 ++---
x86-sse2.S | 21 ++++++++++-----------
4 files changed, 13 insertions(+), 51 deletions(-)
diff --git a/aarch64-asm.S b/aarch64-asm.S
index 842b9e2..165c8ac 100644
--- a/aarch64-asm.S
+++ b/aarch64-asm.S
@@ -31,8 +31,7 @@
.macro asm_function function_name
.global \function_name
- .type \function_name,%function
-.func \function_name
+ .type \function_name,%function
\function_name:
DST .req x0
SRC .req x1
@@ -54,7 +53,6 @@ asm_function aligned_block_copy_ldpstp_x_aarch64
subs SIZE, SIZE, #64
bgt 0b
ret
-.endfunc
asm_function aligned_block_copy_ldpstp_q_aarch64
0:
@@ -67,7 +65,6 @@ asm_function aligned_block_copy_ldpstp_q_aarch64
subs SIZE, SIZE, #64
bgt 0b
ret
-.endfunc
asm_function aligned_block_copy_ldpstp_q_pf32_l2strm_aarch64
0:
@@ -82,7 +79,6 @@ asm_function aligned_block_copy_ldpstp_q_pf32_l2strm_aarch64
subs SIZE, SIZE, #64
bgt 0b
ret
-.endfunc
asm_function aligned_block_copy_ldpstp_q_pf64_l2strm_aarch64
0:
@@ -96,7 +92,6 @@ asm_function aligned_block_copy_ldpstp_q_pf64_l2strm_aarch64
subs SIZE, SIZE, #64
bgt 0b
ret
-.endfunc
asm_function aligned_block_copy_ldpstp_q_pf32_l1keep_aarch64
0:
@@ -111,7 +106,6 @@ asm_function aligned_block_copy_ldpstp_q_pf32_l1keep_aarch64
subs SIZE, SIZE, #64
bgt 0b
ret
-.endfunc
asm_function aligned_block_copy_ldpstp_q_pf64_l1keep_aarch64
0:
@@ -125,7 +119,6 @@ asm_function aligned_block_copy_ldpstp_q_pf64_l1keep_aarch64
subs SIZE, SIZE, #64
bgt 0b
ret
-.endfunc
asm_function aligned_block_fill_stp_x_aarch64
0:
@@ -137,7 +130,6 @@ asm_function aligned_block_fill_stp_x_aarch64
subs SIZE, SIZE, #64
bgt 0b
ret
-.endfunc
asm_function aligned_block_fill_stp_q_aarch64
0:
@@ -147,7 +139,6 @@ asm_function aligned_block_fill_stp_q_aarch64
subs SIZE, SIZE, #64
bgt 0b
ret
-.endfunc
asm_function aligned_block_fill_stnp_x_aarch64
0:
@@ -159,7 +150,6 @@ asm_function aligned_block_fill_stnp_x_aarch64
subs SIZE, SIZE, #64
bgt 0b
ret
-.endfunc
asm_function aligned_block_fill_stnp_q_aarch64
0:
@@ -169,7 +159,6 @@ asm_function aligned_block_fill_stnp_q_aarch64
subs SIZE, SIZE, #64
bgt 0b
ret
-.endfunc
asm_function aligned_block_copy_ld1st1_aarch64
0:
@@ -180,6 +169,5 @@ asm_function aligned_block_copy_ld1st1_aarch64
subs SIZE, SIZE, #64
bgt 0b
ret
-.endfunc
#endif
diff --git a/arm-neon.S b/arm-neon.S
index 4db78ce..9631d82 100644
--- a/arm-neon.S
+++ b/arm-neon.S
@@ -32,7 +32,6 @@
.macro asm_function function_name
.global \function_name
-.func \function_name
\function_name:
DST .req r0
SRC .req r1
@@ -66,7 +65,6 @@ asm_function aligned_block_read_neon
vpadd.u32 d31, d31, d31
vmov.u32 r0, d31[0]
bx lr
-.endfunc
/* Actually this calculates a sum of 32-bit values */
asm_function aligned_block_read_pf32_neon
@@ -97,7 +95,6 @@ asm_function aligned_block_read_pf32_neon
vpadd.u32 d31, d31, d31
vmov.u32 r0, d31[0]
bx lr
-.endfunc
/* Actually this calculates a sum of 32-bit values */
asm_function aligned_block_read_pf64_neon
@@ -127,7 +124,6 @@ asm_function aligned_block_read_pf64_neon
vpadd.u32 d31, d31, d31
vmov.u32 r0, d31[0]
bx lr
-.endfunc
/* Actually this calculates a sum of 32-bit values */
asm_function aligned_block_read2_neon
@@ -156,7 +152,6 @@ asm_function aligned_block_read2_neon
vpadd.u32 d31, d31, d31
vmov.u32 r0, d31[0]
bx lr
-.endfunc
/* Actually this calculates a sum of 32-bit values */
asm_function aligned_block_read2_pf32_neon
@@ -187,7 +182,6 @@ asm_function aligned_block_read2_pf32_neon
vpadd.u32 d31, d31, d31
vmov.u32 r0, d31[0]
bx lr
-.endfunc
/* Actually this calculates a sum of 32-bit values */
asm_function aligned_block_read2_pf64_neon
@@ -217,7 +211,6 @@ asm_function aligned_block_read2_pf64_neon
vpadd.u32 d31, d31, d31
vmov.u32 r0, d31[0]
bx lr
-.endfunc
asm_function aligned_block_copy_neon
0:
@@ -226,7 +219,6 @@ asm_function aligned_block_copy_neon
subs SIZE, SIZE, #32
bgt 0b
bx lr
-.endfunc
asm_function aligned_block_copy_unrolled_neon
vpush {d8-d15}
@@ -244,7 +236,6 @@ asm_function aligned_block_copy_unrolled_neon
bgt 0b
vpop {d8-d15}
bx lr
-.endfunc
asm_function aligned_block_copy_pf32_neon
0:
@@ -254,7 +245,6 @@ asm_function aligned_block_copy_pf32_neon
subs SIZE, SIZE, #32
bgt 0b
bx lr
-.endfunc
asm_function aligned_block_copy_unrolled_pf32_neon
vpush {d8-d15}
@@ -280,7 +270,6 @@ asm_function aligned_block_copy_unrolled_pf32_neon
bgt 0b
vpop {d8-d15}
bx lr
-.endfunc
asm_function aligned_block_copy_pf64_neon
0:
@@ -292,7 +281,6 @@ asm_function aligned_block_copy_pf64_neon
subs SIZE, SIZE, #64
bgt 0b
bx lr
-.endfunc
asm_function aligned_block_copy_unrolled_pf64_neon
vpush {d8-d15}
@@ -314,7 +302,6 @@ asm_function aligned_block_copy_unrolled_pf64_neon
bgt 0b
vpop {d8-d15}
bx lr
-.endfunc
asm_function aligned_block_copy_backwards_neon
add SRC, SRC, SIZE
@@ -328,7 +315,6 @@ asm_function aligned_block_copy_backwards_neon
subs SIZE, SIZE, #32
bgt 0b
bx lr
-.endfunc
asm_function aligned_block_copy_backwards_pf32_neon
add SRC, SRC, SIZE
@@ -343,7 +329,6 @@ asm_function aligned_block_copy_backwards_pf32_neon
subs SIZE, SIZE, #32
bgt 0b
bx lr
-.endfunc
asm_function aligned_block_copy_backwards_pf64_neon
add SRC, SRC, SIZE
@@ -360,7 +345,6 @@ asm_function aligned_block_copy_backwards_pf64_neon
subs SIZE, SIZE, #64
bgt 0b
bx lr
-.endfunc
asm_function aligned_block_fill_neon
vld1.8 {d0, d1, d2, d3}, [SRC]!
@@ -370,7 +354,6 @@ asm_function aligned_block_fill_neon
subs SIZE, SIZE, #64
bgt 0b
bx lr
-.endfunc
asm_function aligned_block_fill_backwards_neon
add SRC, SRC, SIZE
@@ -383,7 +366,6 @@ asm_function aligned_block_fill_backwards_neon
subs SIZE, SIZE, #32
bgt 0b
bx lr
-.endfunc
/* some code for older ARM processors */
@@ -398,7 +380,6 @@ asm_function aligned_block_fill_stm4_armv4
subs SIZE, SIZE, #64
bgt 0b
pop {r4-r12, pc}
-.endfunc
asm_function aligned_block_fill_stm8_armv4
push {r4-r12, lr}
@@ -409,7 +390,6 @@ asm_function aligned_block_fill_stm8_armv4
subs SIZE, SIZE, #64
bgt 0b
pop {r4-r12, pc}
-.endfunc
asm_function aligned_block_fill_strd_armv5te
push {r4-r12, lr}
@@ -426,7 +406,6 @@ asm_function aligned_block_fill_strd_armv5te
subs SIZE, SIZE, #64
bgt 0b
pop {r4-r12, pc}
-.endfunc
asm_function aligned_block_copy_incr_armv5te
push {r4-r12, lr}
@@ -442,7 +421,6 @@ asm_function aligned_block_copy_incr_armv5te
stmia DST!, {r8-r11}
bgt 0b
pop {r4-r12, pc}
-.endfunc
asm_function aligned_block_copy_wrap_armv5te
push {r4-r12, lr}
@@ -458,7 +436,6 @@ asm_function aligned_block_copy_wrap_armv5te
stmia DST!, {r8-r11}
bgt 0b
pop {r4-r12, pc}
-.endfunc
asm_function aligned_block_copy_vfp
push {r4-r12, lr}
@@ -470,6 +447,5 @@ asm_function aligned_block_copy_vfp
bgt 0b
vpop {d8-d15}
pop {r4-r12, pc}
-.endfunc
#endif
diff --git a/mips-32.S b/mips-32.S
index 17b2b7f..4f7ddae 100644
--- a/mips-32.S
+++ b/mips-32.S
@@ -32,7 +32,6 @@
.macro asm_function function_name
.global \function_name
.type \function_name, @function
- .func \function_name
\function_name:
.endm
@@ -93,7 +92,7 @@ asm_function aligned_block_fill_pf32_mips32
2:
jr $ra
nop
-.endfunc
+
/*
* void aligned_block_copy_pf32_mips32(int64_t *dst, int64_t *src, int size)
@@ -178,6 +177,6 @@ asm_function aligned_block_copy_pf32_mips32
lw $s7, 28($sp)
jr $ra
addi $sp, $sp, 32
-.endfunc
+
#endif
diff --git a/x86-sse2.S b/x86-sse2.S
index d8840e4..409031b 100644
--- a/x86-sse2.S
+++ b/x86-sse2.S
@@ -30,7 +30,6 @@
.macro asm_function_helper function_name
.global \function_name
-.func \function_name
\function_name:
#ifdef __amd64__
#ifdef _WIN64
@@ -90,7 +89,7 @@ asm_function aligned_block_copy_movsb
pop3 edi esi ecx
#endif
ret
-.endfunc
+
asm_function aligned_block_copy_movsd
0:
@@ -110,7 +109,7 @@ asm_function aligned_block_copy_movsd
pop3 edi esi ecx
#endif
ret
-.endfunc
+
asm_function aligned_block_copy_sse2
0:
@@ -127,7 +126,7 @@ asm_function aligned_block_copy_sse2
sub SIZE, 64
jg 0b
ret
-.endfunc
+
asm_function aligned_block_copy_nt_sse2
0:
@@ -144,7 +143,7 @@ asm_function aligned_block_copy_nt_sse2
sub SIZE, 64
jg 0b
ret
-.endfunc
+
asm_function aligned_block_copy_pf32_sse2
0:
@@ -163,7 +162,7 @@ asm_function aligned_block_copy_pf32_sse2
sub SIZE, 64
jg 0b
ret
-.endfunc
+
asm_function aligned_block_copy_nt_pf32_sse2
0:
@@ -182,7 +181,7 @@ asm_function aligned_block_copy_nt_pf32_sse2
sub SIZE, 64
jg 0b
ret
-.endfunc
+
asm_function aligned_block_copy_pf64_sse2
0:
@@ -200,7 +199,7 @@ asm_function aligned_block_copy_pf64_sse2
sub SIZE, 64
jg 0b
ret
-.endfunc
+
asm_function aligned_block_copy_nt_pf64_sse2
0:
@@ -218,7 +217,7 @@ asm_function aligned_block_copy_nt_pf64_sse2
sub SIZE, 64
jg 0b
ret
-.endfunc
+
asm_function aligned_block_fill_sse2
movdqa xmm0, [SRC + 0]
@@ -231,7 +230,7 @@ asm_function aligned_block_fill_sse2
sub SIZE, 64
jg 0b
ret
-.endfunc
+
asm_function aligned_block_fill_nt_sse2
movdqa xmm0, [SRC + 0]
@@ -244,7 +243,7 @@ asm_function aligned_block_fill_nt_sse2
sub SIZE, 64
jg 0b
ret
-.endfunc
+
/*****************************************************************************/
|
