View | Details | Raw Unified | Return to bug 196591
Collapse All | Expand All

(-)files/patch-common_arm_asm.S (+40 lines)
Added Link Here
1 
--- common/arm/asm.S.orig	2014-08-27 20:45:08 UTC
2 
+++ common/arm/asm.S
3 
@@ -40,6 +40,12 @@
4 
 #   define ELF @
5 
 #endif
6
7 
+#if HAVE_AS_FUNC
8 
+#   define FUNC
9 
+#else
10 
+#   define FUNC @
11 
+#endif
12 
+
13 
 .macro require8, val=1
14 
 ELF     .eabi_attribute 24, \val
15 
 .endm
16 
@@ -49,17 +55,22 @@ ELF     .eabi_attribute 25, \val
17 
 .endm
18
19 
 .macro function name, export=1
20 
+    .macro endfunc
21 
+ELF     .size   \name, . - \name
22 
+FUNC    .endfunc
23 
+        .purgem endfunc
24 
+    .endm
25 
         .align  2
26 
 .if \export == 1
27 
         .global EXTERN_ASM\name
28 
 ELF     .hidden EXTERN_ASM\name
29 
 ELF     .type   EXTERN_ASM\name, %function
30 
-        .func   EXTERN_ASM\name
31 
+FUNC    .func   EXTERN_ASM\name
32 
 EXTERN_ASM\name:
33 
 .else
34 
 ELF     .hidden \name
35 
 ELF     .type   \name, %function
36 
-        .func   \name
37 
+FUNC    .func   \name
38 
 \name:
39 
 .endif
40 
 .endm
(-)files/patch-common_arm_cpu-a.S (+34 lines)
Added Link Here
1 
--- common/arm/cpu-a.S.orig	2014-08-27 20:45:08 UTC
2 
+++ common/arm/cpu-a.S
3 
@@ -33,7 +33,7 @@
4 
 function x264_cpu_neon_test
5 
     vadd.i16    q0, q0, q0
6 
     bx          lr
7 
-.endfunc
8 
+endfunc
9
10 
 // return: 0 on success
11 
 //         1 if counters were already enabled
12 
@@ -49,14 +49,14 @@ function x264_cpu_enable_armv7_counter,
13 
     mov         r2, #1 << 31                // enable cycle counter
14 
     mcr         p15, 0, r2, c9, c12, 1      // write CNTENS
15 
     bx          lr
16 
-.endfunc
17 
+endfunc
18
19 
 function x264_cpu_disable_armv7_counter, export=0
20 
     mrc         p15, 0, r0, c9, c12, 0      // read PMNC
21 
     bic         r0, r0, #1                  // disable counters
22 
     mcr         p15, 0, r0, c9, c12, 0      // write PMNC
23 
     bx          lr
24 
-.endfunc
25 
+endfunc
26
27
28 
 .macro READ_TIME r
29 
@@ -106,4 +106,4 @@ average_loop:
30 
     cmp         r0, #10
31 
     movgt       r0, #0
32 
     pop         {r4-r6,pc}
33 
-.endfunc
34 
+endfunc
(-)files/patch-common_arm_deblock-a.S (+205 lines)
Added Link Here
1 
--- common/arm/dct-a.S.orig	2014-08-27 20:45:08 UTC
2 
+++ common/arm/dct-a.S
3 
@@ -82,7 +82,7 @@ function x264_dct4x4dc_neon
4 
     vrhadd.s16      d3,  d6,  d7
5 
     vst1.64         {d0-d3}, [r0,:128]
6 
     bx              lr
7 
-.endfunc
8 
+endfunc
9
10 
 function x264_idct4x4dc_neon
11 
     vld1.64         {d0-d3}, [r0,:128]
12 
@@ -94,7 +94,7 @@ function x264_idct4x4dc_neon
13 
     HADAMARD        2, sumsub, d3, d2, d6, d7
14 
     vst1.64         {d0-d3}, [r0,:128]
15 
     bx              lr
16 
-.endfunc
17 
+endfunc
18
19
20 
 .macro DCT_1D d0 d1 d2 d3  d4 d5 d6 d7
21 
@@ -129,7 +129,7 @@ function x264_sub4x4_dct_neon
22 
     DCT_1D          d4, d5, d6, d7, d0, d1, d2, d3
23 
     vst1.64         {d4-d7}, [r0,:128]
24 
     bx              lr
25 
-.endfunc
26 
+endfunc
27
28 
 function x264_sub8x4_dct_neon, export=0
29 
     vld1.64         {d0}, [r1,:64], r3
30 
@@ -165,7 +165,7 @@ function x264_sub8x4_dct_neon, export=0
31 
     vst1.64         {d4-d5}, [r0,:128]!
32 
     vst1.64         {d6-d7}, [r0,:128]!
33 
     bx              lr
34 
-.endfunc
35 
+endfunc
36
37 
 function x264_sub8x8_dct_neon
38 
     push            {lr}
39 
@@ -174,7 +174,7 @@ function x264_sub8x8_dct_neon
40 
     bl              x264_sub8x4_dct_neon
41 
     pop             {lr}
42 
     b               x264_sub8x4_dct_neon
43 
-.endfunc
44 
+endfunc
45
46 
 function x264_sub16x16_dct_neon
47 
     push            {lr}
48 
@@ -195,7 +195,7 @@ function x264_sub16x16_dct_neon
49 
     bl              x264_sub8x4_dct_neon
50 
     pop             {lr}
51 
     b               x264_sub8x4_dct_neon
52 
-.endfunc
53 
+endfunc
54
55
56 
 .macro DCT8_1D type
57 
@@ -279,7 +279,7 @@ function x264_sub8x8_dct8_neon
58 
     vst1.64         {d24-d27}, [r0,:128]!
59 
     vst1.64         {d28-d31}, [r0,:128]!
60 
     bx              lr
61 
-.endfunc
62 
+endfunc
63
64 
 function x264_sub16x16_dct8_neon
65 
     push            {lr}
66 
@@ -294,7 +294,7 @@ function x264_sub16x16_dct8_neon
67 
     sub             r1,  r1,  #FENC_STRIDE*8 - 8
68 
     sub             r2,  r2,  #FDEC_STRIDE*8 - 8
69 
     b               X(x264_sub8x8_dct8_neon)
70 
-.endfunc
71 
+endfunc
72
73
74 
 // First part of IDCT (minus final SUMSUB_BA)
75 
@@ -336,7 +336,7 @@ function x264_add4x4_idct_neon
76 
     vst1.32         {d2[1]}, [r0,:32], r2
77 
     vst1.32         {d2[0]}, [r0,:32], r2
78 
     bx              lr
79 
-.endfunc
80 
+endfunc
81
82 
 function x264_add8x4_idct_neon, export=0
83 
     vld1.64         {d0-d3}, [r1,:128]!
84 
@@ -376,7 +376,7 @@ function x264_add8x4_idct_neon, export=0
85 
     vst1.32         {d2}, [r0,:64], r2
86 
     vst1.32         {d3}, [r0,:64], r2
87 
     bx              lr
88 
-.endfunc
89 
+endfunc
90
91 
 function x264_add8x8_idct_neon
92 
     mov             r2, #FDEC_STRIDE
93 
@@ -384,7 +384,7 @@ function x264_add8x8_idct_neon
94 
     bl              x264_add8x4_idct_neon
95 
     mov             lr, ip
96 
     b               x264_add8x4_idct_neon
97 
-.endfunc
98 
+endfunc
99
100 
 function x264_add16x16_idct_neon
101 
     mov             r2, #FDEC_STRIDE
102 
@@ -401,7 +401,7 @@ function x264_add16x16_idct_neon
103 
     bl              x264_add8x4_idct_neon
104 
     mov             lr, ip
105 
     b               x264_add8x4_idct_neon
106 
-.endfunc
107 
+endfunc
108
109
110 
 .macro IDCT8_1D type
111 
@@ -498,7 +498,7 @@ function x264_add8x8_idct8_neon
112 
     vst1.64         {d6}, [r0,:64], r2
113 
     vst1.64         {d7}, [r0,:64], r2
114 
     bx              lr
115 
-.endfunc
116 
+endfunc
117
118 
 function x264_add16x16_idct8_neon
119 
     mov             ip,  lr
120 
@@ -510,7 +510,7 @@ function x264_add16x16_idct8_neon
121 
     sub             r0,  r0,  #8*FDEC_STRIDE-8
122 
     mov             lr,  ip
123 
     b               X(x264_add8x8_idct8_neon)
124 
-.endfunc
125 
+endfunc
126
127
128 
 function x264_add8x8_idct_dc_neon
129 
@@ -562,7 +562,7 @@ function x264_add8x8_idct_dc_neon
130 
     vst1.64         {d6}, [r0,:64], r2
131 
     vst1.64         {d7}, [r0,:64], r2
132 
     bx              lr
133 
-.endfunc
134 
+endfunc
135
136 
 .macro ADD16x4_IDCT_DC dc
137 
     vld1.64         {d16-d17}, [r0,:128], r3
138 
@@ -610,7 +610,7 @@ function x264_add16x16_idct_dc_neon
139 
     ADD16x4_IDCT_DC d2
140 
     ADD16x4_IDCT_DC d3
141 
     bx              lr
142 
-.endfunc
143 
+endfunc
144
145 
 function x264_sub8x8_dct_dc_neon
146 
     mov             r3,  #FENC_STRIDE
147 
@@ -658,7 +658,7 @@ function x264_sub8x8_dct_dc_neon
148 
     vpadd.s16       d0,  d0,  d1
149 
     vst1.64         {d0}, [r0,:64]
150 
     bx              lr
151 
-.endfunc
152 
+endfunc
153
154
155 
 function x264_zigzag_scan_4x4_frame_neon
156 
@@ -671,4 +671,4 @@ function x264_zigzag_scan_4x4_frame_neon
157 
     vtbl.8      d7, {d2-d3}, d19
158 
     vst1.64     {d4-d7},   [r0,:128]
159 
     bx          lr
160 
-.endfunc
161 
+endfunc
Added Link Here
1 
--- common/arm/deblock-a.S.orig	2014-08-27 20:45:08 UTC
2 
+++ common/arm/deblock-a.S
3 
@@ -142,7 +142,7 @@ function x264_deblock_v_luma_neon
4
5 
     align_pop_regs
6 
     bx              lr
7 
-.endfunc
8 
+endfunc
9
10 
 function x264_deblock_h_luma_neon
11 
     h264_loop_filter_start
12 
@@ -194,7 +194,7 @@ function x264_deblock_h_luma_neon
13
14 
     align_pop_regs
15 
     bx              lr
16 
-.endfunc
17 
+endfunc
18
19 
 .macro h264_loop_filter_chroma
20 
     vdup.8          q11, r2         // alpha
21 
@@ -255,7 +255,7 @@ function x264_deblock_v_chroma_neon
22 
     vst2.8          {d0, d1},  [r0,:128], r1
23
24 
     bx              lr
25 
-.endfunc
26 
+endfunc
27
28 
 function x264_deblock_h_chroma_neon
29 
     h264_loop_filter_start
30 
@@ -303,7 +303,7 @@ function x264_deblock_h_chroma_neon
31 
     vst1.8          {d3},  [r0], r1
32
33 
     bx              lr
34 
-.endfunc
35 
+endfunc
36
37 
 function x264_deblock_strength_neon
38 
     ldr             ip,  [sp]
39 
@@ -409,4 +409,4 @@ lists:
40
41 
     vst1.8          {q8}, [r3,:128]     @ bs[0]
42 
     bx              lr
43 
-.endfunc
44 
+endfunc
(-)files/patch-common_arm_mc-a.S (+386 lines)
Added Link Here
1 
--- common/arm/mc-a.S.orig	2014-08-27 20:45:08 UTC
2 
+++ common/arm/mc-a.S
3 
@@ -50,7 +50,7 @@ function x264_prefetch_ref_arm
4 
     pld         [r3, r1, lsl #1]
5 
     pld         [r3, r2]
6 
     bx          lr
7 
-.endfunc
8 
+endfunc
9
10 
 // void prefetch_fenc( uint8_t *pix_y,  intptr_t stride_y,
11 
 //                     uint8_t *pix_uv, intptr_t stride_uv, int mb_x )
12 
@@ -76,7 +76,7 @@ function x264_prefetch_fenc_arm
13 
     pld         [ip]
14 
     pld         [ip, r3]
15 
     pop         {pc}
16 
-.endfunc
17 
+endfunc
18
19
20 
 // void *x264_memcpy_aligned( void *dst, const void *src, size_t n )
21 
@@ -85,7 +85,7 @@ function x264_memcpy_aligned_neon
22 
     movrel      ip,  memcpy_table
23 
     and         r3,  r3,  #0xc
24 
     ldr         pc,  [ip, r3]
25 
-.endfunc
26 
+endfunc
27
28 
 .macro MEMCPY_ALIGNED srcalign dstalign
29 
 function memcpy_aligned_\dstalign\()_\srcalign\()_neon, export=0
30 
@@ -127,7 +127,7 @@ function memcpy_aligned_\dstalign\()_\sr
31 
     vst1.64     {d0}, [r3,:64]!
32 
 .endif
33 
     bx          lr
34 
-.endfunc
35 
+endfunc
36 
 .endm
37
38 
 MEMCPY_ALIGNED 16, 16
39 
@@ -156,7 +156,7 @@ memzero_loop:
40 
 .endr
41 
     bgt         memzero_loop
42 
     bx          lr
43 
-.endfunc
44 
+endfunc
45
46
47 
 // void pixel_avg( uint8_t *dst,  intptr_t dst_stride,
48 
@@ -175,7 +175,7 @@ function x264_pixel_avg_\w\()x\h\()_neon
49 
     cmp         ip,  #0
50 
     bge         x264_pixel_avg_weight_w\w\()_add_add_neon
51 
     b           x264_pixel_avg_weight_w\w\()_sub_add_neon     // weight < 0
52 
-.endfunc
53 
+endfunc
54 
 .endm
55
56 
 AVGH  4, 2
57 
@@ -253,7 +253,7 @@ function x264_pixel_avg_weight_w4_\ext\(
58 
     vst1.32         {d1[0]}, [r0,:32], r1
59 
     bgt             1b
60 
     pop             {r4-r6,pc}
61 
-.endfunc
62 
+endfunc
63
64 
 function x264_pixel_avg_weight_w8_\ext\()_neon, export=0
65 
     load_weights_\ext
66 
@@ -277,7 +277,7 @@ function x264_pixel_avg_weight_w8_\ext\(
67 
     vst1.64         {d3}, [r0,:64], r1
68 
     bgt             1b
69 
     pop             {r4-r6,pc}
70 
-.endfunc
71 
+endfunc
72
73 
 function x264_pixel_avg_weight_w16_\ext\()_neon, export=0
74 
     load_weights_\ext
75 
@@ -297,7 +297,7 @@ function x264_pixel_avg_weight_w16_\ext\
76 
     vst1.64         {d2-d3}, [r0,:128], r1
77 
     bgt             1b
78 
     pop             {r4-r6,pc}
79 
-.endfunc
80 
+endfunc
81 
 .endm
82
83 
 AVG_WEIGHT add_add
84 
@@ -316,7 +316,7 @@ function x264_pixel_avg_w4_neon, export=
85 
     vst1.32     {d1[0]}, [r0,:32], r1
86 
     bgt         x264_pixel_avg_w4_neon
87 
     pop         {r4-r6,pc}
88 
-.endfunc
89 
+endfunc
90
91 
 function x264_pixel_avg_w8_neon, export=0
92 
     subs        lr,  lr,  #4
93 
@@ -338,7 +338,7 @@ function x264_pixel_avg_w8_neon, export=
94 
     vst1.64     {d3}, [r0,:64], r1
95 
     bgt         x264_pixel_avg_w8_neon
96 
     pop         {r4-r6,pc}
97 
-.endfunc
98 
+endfunc
99
100 
 function x264_pixel_avg_w16_neon, export=0
101 
     subs        lr,  lr,  #4
102 
@@ -360,7 +360,7 @@ function x264_pixel_avg_w16_neon, export
103 
     vst1.64     {d6-d7}, [r0,:128], r1
104 
     bgt         x264_pixel_avg_w16_neon
105 
     pop         {r4-r6,pc}
106 
-.endfunc
107 
+endfunc
108
109
110 
 function x264_pixel_avg2_w4_neon
111 
@@ -379,7 +379,7 @@ avg2_w4_loop:
112 
     vst1.32     {d1[0]}, [r0,:32], r1
113 
     bgt         avg2_w4_loop
114 
     pop         {pc}
115 
-.endfunc
116 
+endfunc
117
118 
 function x264_pixel_avg2_w8_neon
119 
     ldr         ip,  [sp, #4]
120 
@@ -397,7 +397,7 @@ avg2_w8_loop:
121 
     vst1.64     {d1}, [r0,:64], r1
122 
     bgt         avg2_w8_loop
123 
     pop         {pc}
124 
-.endfunc
125 
+endfunc
126
127 
 function x264_pixel_avg2_w16_neon
128 
     ldr         ip,  [sp, #4]
129 
@@ -415,7 +415,7 @@ avg2_w16_loop:
130 
     vst1.64     {d4-d5}, [r0,:128], r1
131 
     bgt         avg2_w16_loop
132 
     pop         {pc}
133 
-.endfunc
134 
+endfunc
135
136 
 function x264_pixel_avg2_w20_neon
137 
     ldr         ip,  [sp, #4]
138 
@@ -438,7 +438,7 @@ avg2_w20_loop:
139 
     vst1.32     {d6[0]},  [r0,:32], r1
140 
     bgt         avg2_w20_loop
141 
     pop         {pc}
142 
-.endfunc
143 
+endfunc
144
145
146 
 .macro weight_prologue type
147 
@@ -499,7 +499,7 @@ weight20_loop:
148 
     vst1.32     {d20[1]},  [r0,:32], r1
149 
     bgt         weight20_loop
150 
     pop         {r4-r5,pc}
151 
-.endfunc
152 
+endfunc
153
154 
 function x264_mc_weight_w16_neon
155 
     weight_prologue full
156 
@@ -531,7 +531,7 @@ weight16_loop:
157 
     vst1.8      {d18-d19}, [r0,:128], r1
158 
     bgt         weight16_loop
159 
     pop         {r4-r5,pc}
160 
-.endfunc
161 
+endfunc
162
163 
 function x264_mc_weight_w8_neon
164 
     weight_prologue full
165 
@@ -553,7 +553,7 @@ weight8_loop:
166 
     vst1.8      {d18}, [r0,:64], r1
167 
     bgt         weight8_loop
168 
     pop         {r4-r5,pc}
169 
-.endfunc
170 
+endfunc
171
172 
 function x264_mc_weight_w4_neon
173 
     weight_prologue full
174 
@@ -572,7 +572,7 @@ weight4_loop:
175 
     vst1.32     {d16[1]}, [r0,:32], r1
176 
     bgt         weight4_loop
177 
     pop         {r4-r5,pc}
178 
-.endfunc
179 
+endfunc
180
181 
 function x264_mc_weight_w20_nodenom_neon
182 
     weight_prologue nodenom
183 
@@ -609,7 +609,7 @@ weight20_nodenom_loop:
184 
     vst1.32     {d20[1]},  [r0,:32], r1
185 
     bgt         weight20_nodenom_loop
186 
     pop         {r4-r5,pc}
187 
-.endfunc
188 
+endfunc
189
190 
 function x264_mc_weight_w16_nodenom_neon
191 
     weight_prologue nodenom
192 
@@ -637,7 +637,7 @@ weight16_nodenom_loop:
193 
     vst1.8      {d18-d19}, [r0,:128], r1
194 
     bgt         weight16_nodenom_loop
195 
     pop         {r4-r5,pc}
196 
-.endfunc
197 
+endfunc
198
199 
 function x264_mc_weight_w8_nodenom_neon
200 
     weight_prologue nodenom
201 
@@ -657,7 +657,7 @@ weight8_nodenom_loop:
202 
     vst1.8      {d17}, [r0,:64], r1
203 
     bgt         weight8_nodenom_loop
204 
     pop         {r4-r5,pc}
205 
-.endfunc
206 
+endfunc
207
208 
 function x264_mc_weight_w4_nodenom_neon
209 
     weight_prologue nodenom
210 
@@ -675,7 +675,7 @@ weight4_nodenom_loop:
211 
     vst1.32     {d16[1]}, [r0,:32], r1
212 
     bgt         weight4_nodenom_loop
213 
     pop         {r4-r5,pc}
214 
-.endfunc
215 
+endfunc
216
217 
 .macro weight_simple_prologue
218 
     push        {lr}
219 
@@ -699,7 +699,7 @@ weight20_\name\()_loop:
220 
     vst1.8      {d19-d21}, [r0,:64], r1
221 
     bgt         weight20_\name\()_loop
222 
     pop         {pc}
223 
-.endfunc
224 
+endfunc
225
226 
 function x264_mc_weight_w16_\name\()_neon
227 
     weight_simple_prologue
228 
@@ -713,7 +713,7 @@ weight16_\name\()_loop:
229 
     vst1.8      {d18-d19}, [r0,:128], r1
230 
     bgt         weight16_\name\()_loop
231 
     pop         {pc}
232 
-.endfunc
233 
+endfunc
234
235 
 function x264_mc_weight_w8_\name\()_neon
236 
     weight_simple_prologue
237 
@@ -726,7 +726,7 @@ weight8_\name\()_loop:
238 
     vst1.8      {d17}, [r0,:64], r1
239 
     bgt         weight8_\name\()_loop
240 
     pop         {pc}
241 
-.endfunc
242 
+endfunc
243
244 
 function x264_mc_weight_w4_\name\()_neon
245 
     weight_simple_prologue
246 
@@ -739,7 +739,7 @@ weight4_\name\()_loop:
247 
     vst1.32     {d17[0]}, [r0,:32], r1
248 
     bgt         weight4_\name\()_loop
249 
     pop         {pc}
250 
-.endfunc
251 
+endfunc
252 
 .endm
253
254 
 weight_simple offsetadd, vqadd.u8
255 
@@ -761,7 +761,7 @@ copy_w4_loop:
256 
     vst1.32     {d3[0]}, [r0,:32], r1
257 
     bgt         copy_w4_loop
258 
     bx          lr
259 
-.endfunc
260 
+endfunc
261
262 
 function x264_mc_copy_w8_neon
263 
     ldr         ip,  [sp]
264 
@@ -777,7 +777,7 @@ copy_w8_loop:
265 
     vst1.32     {d3}, [r0,:64], r1
266 
     bgt         copy_w8_loop
267 
     bx          lr
268 
-.endfunc
269 
+endfunc
270
271 
 function x264_mc_copy_w16_neon
272 
     ldr         ip,  [sp]
273 
@@ -793,7 +793,7 @@ copy_w16_loop:
274 
     vst1.32     {d6-d7}, [r0,:128], r1
275 
     bgt         copy_w16_loop
276 
     bx          lr
277 
-.endfunc
278 
+endfunc
279
280 
 function x264_mc_copy_w16_aligned_neon
281 
     ldr         ip,  [sp]
282 
@@ -809,7 +809,7 @@ copy_w16_aligned_loop:
283 
     vst1.32     {d6-d7}, [r0,:128], r1
284 
     bgt         copy_w16_aligned_loop
285 
     bx          lr
286 
-.endfunc
287 
+endfunc
288
289
290 
 // void x264_mc_chroma_neon( uint8_t *dst, intptr_t i_dst_stride,
291 
@@ -1159,7 +1159,7 @@ mc_chroma_w8:
292 
     vpop            {d8-d11}
293 
     pop             {r4-r8, pc}
294
295 
-.endfunc
296 
+endfunc
297
298
299 
 // hpel_filter_v( uint8_t *dst, uint8_t *src, int16_t *buf, intptr_t stride, int width )
300 
@@ -1200,7 +1200,7 @@ filter_v_loop:
301 
     vst1.64         {d0-d1},   [r0,:128]!
302 
     bgt             filter_v_loop
303 
     pop             {pc}
304 
-.endfunc
305 
+endfunc
306
307 
 // hpel_filter_c( uint8_t *dst, int16_t *buf, int width );
308 
 function x264_hpel_filter_c_neon
309 
@@ -1285,7 +1285,7 @@ filter_c_loop:
310 
     vst1.64         {d30-d31}, [r0,:128]!
311 
     bgt             filter_c_loop
312 
     bx              lr
313 
-.endfunc
314 
+endfunc
315
316 
 // hpel_filter_h( uint8_t *dst, uint8_t *src, int width );
317 
 function x264_hpel_filter_h_neon
318 
@@ -1372,7 +1372,7 @@ filter_h_loop:
319 
     vst1.64         {d6-d7}, [r0,:128]!
320 
     bgt             filter_h_loop
321 
     bx              lr
322 
-.endfunc
323 
+endfunc
324
325
326 
 // frame_init_lowres_core( uint8_t *src0, uint8_t *dst0, uint8_t *dsth, uint8_t *dstv,
327 
@@ -1464,7 +1464,7 @@ lowres_xloop_end:
328
329 
     vpop            {d8-d15}
330 
     pop             {r4-r10,pc}
331 
-.endfunc
332 
+endfunc
333
334 
 function x264_load_deinterleave_chroma_fdec_neon
335 
     mov             ip,  #FDEC_STRIDE/2
336 
@@ -1477,7 +1477,7 @@ function x264_load_deinterleave_chroma_f
337 
     bgt             1b
338
339 
     bx              lr
340 
-.endfunc
341 
+endfunc
342
343 
 function x264_load_deinterleave_chroma_fenc_neon
344 
     mov             ip,  #FENC_STRIDE/2
345 
@@ -1490,7 +1490,7 @@ function x264_load_deinterleave_chroma_f
346 
     bgt             1b
347
348 
     bx              lr
349 
-.endfunc
350 
+endfunc
351
352 
 function x264_plane_copy_deinterleave_neon
353 
     push            {r4-r7, lr}
354 
@@ -1516,7 +1516,7 @@ block:
355 
     bgt             block
356
357 
     pop             {r4-r7, pc}
358 
-.endfunc
359 
+endfunc
360
361 
 function x264_plane_copy_deinterleave_rgb_neon
362 
     push            {r4-r8, r10, r11, lr}
363 
@@ -1568,7 +1568,7 @@ block4:
364 
     bgt             block4
365
366 
     pop             {r4-r8, r10, r11, pc}
367 
-.endfunc
368 
+endfunc
369
370 
 function x264_plane_copy_interleave_neon
371 
     push            {r4-r7, lr}
372 
@@ -1595,7 +1595,7 @@ blocki:
373 
     bgt             blocki
374
375 
     pop             {r4-r7, pc}
376 
-.endfunc
377 
+endfunc
378
379 
 function x264_store_interleave_chroma_neon
380 
     push            {lr}
381 
@@ -1609,4 +1609,4 @@ function x264_store_interleave_chroma_ne
382 
     bgt             1b
383
384 
     pop             {pc}
385 
-.endfunc
386 
+endfunc
(-)files/patch-common_arm_pixel-a.S (+275 lines)
Added Link Here
1 
--- common/arm/pixel-a.S.orig	2014-08-27 20:45:08 UTC
2 
+++ common/arm/pixel-a.S
3 
@@ -29,10 +29,12 @@
4 
 .section .rodata
5 
 .align 4
6
7 
-.rept 16 .byte 0xff
8 
+.rept 16
9 
+        .byte 0xff
10 
 .endr
11 
 mask_ff:
12 
-.rept 16 .byte 0
13 
+.rept 16
14 
+        .byte 0
15 
 .endr
16
17 
 mask_ac4:
18 
@@ -60,7 +62,7 @@ function x264_pixel_sad_4x\h\()_armv6
19 
 .endr
20 
     usada8      r0, r6, lr, ip
21 
     pop         {r4-r6,pc}
22 
-.endfunc
23 
+endfunc
24 
 .endm
25
26 
 SAD4_ARMV6 4
27 
@@ -137,7 +139,7 @@ function x264_pixel_sad\name\()_\w\()x\h
28 
     vpaddl.u16  d0,  d0
29 
     vmov.u32    r0,  d0[0]
30 
     bx          lr
31 
-.endfunc
32 
+endfunc
33 
 .endm
34
35 
 SAD_FUNC  4,  4
36 
@@ -222,7 +224,7 @@ function x264_pixel_sad_aligned_\w\()x\h
37 
     vpaddl.u16  d0,  d0
38 
     vmov.u32    r0,  d0[0]
39 
     bx          lr
40 
-.endfunc
41 
+endfunc
42 
 .endm
43
44 
 SAD_FUNC_DUAL  8,  4
45 
@@ -368,7 +370,7 @@ function x264_pixel_sad_x\x\()_\w\()x\h\
46 
     vst1.32     {d0-d1}, [r7]
47 
 .endif
48 
     pop         {r6-r7,pc}
49 
-.endfunc
50 
+endfunc
51 
 .endm
52
53 
 SAD_X_FUNC  3, 4,  4
54 
@@ -477,7 +479,7 @@ function x264_pixel_ssd_\w\()x\h\()_neon
55 
     vpadd.s32   d0, d0, d0
56 
     vmov.32     r0, d0[0]
57 
     bx          lr
58 
-.endfunc
59 
+endfunc
60 
 .endm
61
62 
 SSD_FUNC   4, 4
63 
@@ -517,7 +519,7 @@ function x264_pixel_var_8x8_neon
64 
     vld1.64         {d26}, [r0,:64], r1
65 
     VAR_SQR_SUM     q2,  q10,  q15, d26
66 
     b               x264_var_end
67 
-.endfunc
68 
+endfunc
69
70 
 function x264_pixel_var_8x16_neon
71 
     vld1.64         {d16}, [r0,:64], r1
72 
@@ -549,7 +551,7 @@ function x264_pixel_var_8x16_neon
73 
 2:
74 
     VAR_SQR_SUM     q2,  q13,  q15, d22
75 
     b               x264_var_end
76 
-.endfunc
77 
+endfunc
78
79 
 function x264_pixel_var_16x16_neon
80 
     vld1.64         {d16-d17}, [r0,:128], r1
81 
@@ -573,7 +575,7 @@ var16_loop:
82 
     VAR_SQR_SUM     q1,  q12,  q14, d18
83 
     VAR_SQR_SUM     q2,  q13,  q15, d19
84 
     bgt             var16_loop
85 
-.endfunc
86 
+endfunc
87
88 
 function x264_var_end, export=0
89 
     vpaddl.u16      q8,  q14
90 
@@ -588,7 +590,7 @@ function x264_var_end, export=0
91
92 
     vmov            r0,  r1,  d0
93 
     bx              lr
94 
-.endfunc
95 
+endfunc
96
97 
 .macro DIFF_SUM diff da db lastdiff
98 
     vld1.64         {\da}, [r0,:64], r1
99 
@@ -633,7 +635,7 @@ function x264_pixel_var2_8x8_neon
100 
     mul             r0,  r0,  r0
101 
     sub             r0,  r1,  r0,  lsr #6
102 
     bx              lr
103 
-.endfunc
104 
+endfunc
105
106 
 function x264_pixel_var2_8x16_neon
107 
     vld1.64         {d16}, [r0,:64], r1
108 
@@ -677,7 +679,7 @@ function x264_pixel_var2_8x16_neon
109 
     mul             r0,  r0,  r0
110 
     sub             r0,  r1,  r0,  lsr #7
111 
     bx              lr
112 
-.endfunc
113 
+endfunc
114
115 
 .macro LOAD_DIFF_8x4 q0 q1 q2 q3
116 
     vld1.32     {d1}, [r2], r3
117 
@@ -714,7 +716,7 @@ function x264_pixel_satd_4x4_neon
118 
     HORIZ_ADD   d0,  d0,  d1
119 
     vmov.32     r0,  d0[0]
120 
     bx          lr
121 
-.endfunc
122 
+endfunc
123
124 
 function x264_pixel_satd_4x8_neon
125 
     vld1.32     {d1[]},  [r2], r3
126 
@@ -741,7 +743,7 @@ function x264_pixel_satd_4x8_neon
127 
     vsubl.u8    q3,  d6,  d7
128 
     SUMSUB_AB   q10, q11, q2,  q3
129 
     b           x264_satd_4x8_8x4_end_neon
130 
-.endfunc
131 
+endfunc
132
133 
 function x264_pixel_satd_8x4_neon
134 
     vld1.64     {d1}, [r2], r3
135 
@@ -758,7 +760,7 @@ function x264_pixel_satd_8x4_neon
136 
     vld1.64     {d6}, [r0,:64], r1
137 
     vsubl.u8    q3,  d6,  d7
138 
     SUMSUB_AB   q10, q11, q2,  q3
139 
-.endfunc
140 
+endfunc
141
142 
 function x264_satd_4x8_8x4_end_neon, export=0
143 
     vadd.s16    q0,  q8,  q10
144 
@@ -785,7 +787,7 @@ function x264_satd_4x8_8x4_end_neon, exp
145 
     HORIZ_ADD   d0,  d0,  d1
146 
     vmov.32     r0,  d0[0]
147 
     bx          lr
148 
-.endfunc
149 
+endfunc
150
151 
 function x264_pixel_satd_8x8_neon
152 
     mov         ip,  lr
153 
@@ -799,7 +801,7 @@ function x264_pixel_satd_8x8_neon
154 
     mov         lr,  ip
155 
     vmov.32     r0,  d0[0]
156 
     bx          lr
157 
-.endfunc
158 
+endfunc
159
160 
 function x264_pixel_satd_8x16_neon
161 
     vpush       {d8-d11}
162 
@@ -821,7 +823,7 @@ function x264_pixel_satd_8x16_neon
163 
     mov         lr,  ip
164 
     vmov.32     r0,  d0[0]
165 
     bx          lr
166 
-.endfunc
167 
+endfunc
168
169 
 function x264_satd_8x8_neon, export=0
170 
     LOAD_DIFF_8x4 q8,  q9,  q10, q11
171 
@@ -841,7 +843,7 @@ function x264_satd_8x8_neon, export=0
172 
     SUMSUB_AB   q9,  q11, q1,  q3
173 
     vld1.64     {d0}, [r0,:64], r1
174 
     vsubl.u8    q15, d0,  d1
175 
-.endfunc
176 
+endfunc
177
178 
 // one vertical hadamard pass and two horizontal
179 
 function x264_satd_8x4v_8x8h_neon, export=0
180 
@@ -870,7 +872,7 @@ function x264_satd_8x4v_8x8h_neon, expor
181 
     vmax.s16    q14, q8,  q10
182 
     vmax.s16    q15, q9,  q11
183 
     bx          lr
184 
-.endfunc
185 
+endfunc
186
187 
 function x264_pixel_satd_16x8_neon
188 
     vpush       {d8-d11}
189 
@@ -892,7 +894,7 @@ function x264_pixel_satd_16x8_neon
190 
     mov         lr,  ip
191 
     vmov.32     r0,  d0[0]
192 
     bx          lr
193 
-.endfunc
194 
+endfunc
195
196 
 function x264_pixel_satd_16x16_neon
197 
     vpush       {d8-d11}
198 
@@ -926,7 +928,7 @@ function x264_pixel_satd_16x16_neon
199 
     mov         lr,  ip
200 
     vmov.32     r0,  d0[0]
201 
     bx          lr
202 
-.endfunc
203 
+endfunc
204
205 
 function x264_satd_16x4_neon, export=0
206 
     vld1.64     {d2-d3}, [r2], r3
207 
@@ -950,7 +952,7 @@ function x264_satd_16x4_neon, export=0
208 
     SUMSUB_AB   q2,  q3,  q10, q11
209 
     SUMSUB_ABCD q8,  q10, q9,  q11, q0,  q2,  q1,  q3
210 
     b           x264_satd_8x4v_8x8h_neon
211 
-.endfunc
212 
+endfunc
213
214
215 
 function x264_pixel_sa8d_8x8_neon
216 
@@ -963,7 +965,7 @@ function x264_pixel_sa8d_8x8_neon
217 
     add             r0,  r0,  #1
218 
     lsr             r0,  r0,  #1
219 
     bx              lr
220 
-.endfunc
221 
+endfunc
222
223 
 function x264_pixel_sa8d_16x16_neon
224 
     vpush           {d8-d11}
225 
@@ -995,7 +997,7 @@ function x264_pixel_sa8d_16x16_neon
226 
     add             r0,  r0,  #1
227 
     lsr             r0,  r0,  #1
228 
     bx              lr
229 
-.endfunc
230 
+endfunc
231
232 
 .macro HADAMARD4_V r1, r2, r3, r4, t1, t2, t3, t4
233 
     SUMSUB_ABCD \t1, \t2, \t3, \t4, \r1, \r2, \r3, \r4
234 
@@ -1058,7 +1060,7 @@ function x264_sa8d_8x8_neon, export=0
235 
     vadd.i16        q8,  q8,  q9
236 
     vadd.i16        q9,  q10, q11
237 
     bx              lr
238 
-.endfunc
239 
+endfunc
240
241
242 
 .macro HADAMARD_AC w h
243 
@@ -1094,7 +1096,7 @@ function x264_pixel_hadamard_ac_\w\()x\h
244 
     lsr             r0,  r0,  #1
245 
     lsr             r1,  r1,  #2
246 
     bx              lr
247 
-.endfunc
248 
+endfunc
249 
 .endm
250
251 
 HADAMARD_AC  8, 8
252 
@@ -1189,7 +1191,7 @@ function x264_hadamard_ac_8x8_neon, expo
253 
     vadd.s16        q2,  q2,  q14
254 
     vpadal.u16      q5,  q2
255 
     bx              lr
256 
-.endfunc
257 
+endfunc
258
259
260 
 .macro SSIM_ITER n ssa s12 ssb lastssa lasts12 lastssb da db dnext
261 
@@ -1243,7 +1245,7 @@ function x264_pixel_ssim_4x4x2_core_neon
262
263 
     vst4.32     {d0-d3}, [ip]
264 
     bx          lr
265 
-.endfunc
266 
+endfunc
267
268 
 // FIXME: see about doing 16x16 -> 32 bit multiplies for s1/s2
269 
 function x264_pixel_ssim_end4_neon
270 
@@ -1314,4 +1316,4 @@ ssim_skip:
271 
     vpadd.f32   d0,  d0,  d0
272 
     vmov.32     r0,  d0[0]
273 
     bx          lr
274 
-.endfunc
275 
+endfunc
(-)files/patch-common_arm_predict-a.S (+242 lines)
Added Link Here
1 
--- common/arm/predict-a.S.orig	2014-08-27 20:45:08 UTC
2 
+++ common/arm/predict-a.S
3 
@@ -77,7 +77,7 @@ function x264_predict_4x4_h_armv6
4 
     add     ip, ip, ip, lsl #16
5 
     str     ip, [r0, #3*FDEC_STRIDE]
6 
     bx      lr
7 
-.endfunc
8 
+endfunc
9
10 
 function x264_predict_4x4_v_armv6
11 
     ldr     r1,  [r0, #0 - 1 * FDEC_STRIDE]
12 
@@ -86,7 +86,7 @@ function x264_predict_4x4_v_armv6
13 
     str     r1,  [r0, #0 + 2 * FDEC_STRIDE]
14 
     str     r1,  [r0, #0 + 3 * FDEC_STRIDE]
15 
     bx      lr
16 
-.endfunc
17 
+endfunc
18
19 
 function x264_predict_4x4_dc_armv6
20 
     mov     ip, #0
21 
@@ -109,7 +109,7 @@ function x264_predict_4x4_dc_armv6
22 
     str     r1, [r0, #2*FDEC_STRIDE]
23 
     str     r1, [r0, #3*FDEC_STRIDE]
24 
     bx      lr
25 
-.endfunc
26 
+endfunc
27
28 
 function x264_predict_4x4_dc_top_neon
29 
     mov         r12, #FDEC_STRIDE
30 
@@ -124,7 +124,7 @@ function x264_predict_4x4_dc_top_neon
31 
     vst1.32     d1[0], [r0,:32], r12
32 
     vst1.32     d1[0], [r0,:32], r12
33 
     bx          lr
34 
-.endfunc
35 
+endfunc
36
37 
 // return a1 = (a1+2*b1+c1+2)>>2  a2 = (a2+2*b2+c2+2)>>2
38 
 .macro PRED4x4_LOWPASS a1 b1 c1 a2 b2 c2 pb_1
39 
@@ -167,7 +167,7 @@ function x264_predict_4x4_ddr_armv6
40 
     add     r5, r5, r4, lsr #8
41 
     str     r5, [r0, #3*FDEC_STRIDE]
42 
     pop     {r4-r6,pc}
43 
-.endfunc
44 
+endfunc
45
46 
 function x264_predict_4x4_ddl_neon
47 
     sub         r0, #FDEC_STRIDE
48 
@@ -186,7 +186,7 @@ function x264_predict_4x4_ddl_neon
49 
     vst1.32     {d2[0]}, [r0,:32], ip
50 
     vst1.32     {d3[0]}, [r0,:32], ip
51 
     bx          lr
52 
-.endfunc
53 
+endfunc
54
55 
 function x264_predict_8x8_dc_neon
56 
     mov     ip, #0
57 
@@ -210,7 +210,7 @@ function x264_predict_8x8_dc_neon
58 
     vst1.64 {d0}, [r0,:64], ip
59 
 .endr
60 
     pop    {r4-r5,pc}
61 
-.endfunc
62 
+endfunc
63
64 
 function x264_predict_8x8_h_neon
65 
     add         r1, r1, #7
66 
@@ -233,7 +233,7 @@ function x264_predict_8x8_h_neon
67 
     vst1.64     {d6}, [r0,:64], ip
68 
     vst1.64     {d7}, [r0,:64], ip
69 
     bx          lr
70 
-.endfunc
71 
+endfunc
72
73 
 function x264_predict_8x8_v_neon
74 
     add         r1, r1, #16
75 
@@ -243,7 +243,7 @@ function x264_predict_8x8_v_neon
76 
     vst1.8      {d0}, [r0,:64], r12
77 
 .endr
78 
     bx          lr
79 
-.endfunc
80 
+endfunc
81
82 
 function x264_predict_8x8_ddl_neon
83 
     add         r1, #16
84 
@@ -271,7 +271,7 @@ function x264_predict_8x8_ddl_neon
85 
     vst1.8      d2, [r0,:64], r12
86 
     vst1.8      d1, [r0,:64], r12
87 
     bx          lr
88 
-.endfunc
89 
+endfunc
90
91 
 function x264_predict_8x8_ddr_neon
92 
     vld1.8      {d0-d3}, [r1,:128]
93 
@@ -301,7 +301,7 @@ function x264_predict_8x8_ddr_neon
94 
     vst1.8      {d4}, [r0,:64], r12
95 
     vst1.8      {d5}, [r0,:64], r12
96 
     bx          lr
97 
-.endfunc
98 
+endfunc
99
100 
 function x264_predict_8x8_vl_neon
101 
     add         r1, #16
102 
@@ -332,7 +332,7 @@ function x264_predict_8x8_vl_neon
103 
     vst1.8      {d3}, [r0,:64], r12
104 
     vst1.8      {d2}, [r0,:64], r12
105 
     bx          lr
106 
-.endfunc
107 
+endfunc
108
109 
 function x264_predict_8x8_vr_neon
110 
     add         r1, #8
111 
@@ -364,7 +364,7 @@ function x264_predict_8x8_vr_neon
112 
     vst1.8      {d6}, [r0,:64], r12
113 
     vst1.8      {d3}, [r0,:64], r12
114 
     bx          lr
115 
-.endfunc
116 
+endfunc
117
118 
 function x264_predict_8x8_hd_neon
119 
     mov         r12, #FDEC_STRIDE
120 
@@ -397,7 +397,7 @@ function x264_predict_8x8_hd_neon
121 
     vst1.8      {d16}, [r0,:64], r12
122
123 
     bx          lr
124 
-.endfunc
125 
+endfunc
126
127 
 function x264_predict_8x8_hu_neon
128 
     mov         r12, #FDEC_STRIDE
129 
@@ -430,7 +430,7 @@ function x264_predict_8x8_hu_neon
130 
     vst1.8      {d7}, [r0,:64], r12
131 
     vst1.8      {d17}, [r0,:64]
132 
     bx          lr
133 
-.endfunc
134 
+endfunc
135
136 
 function x264_predict_8x8c_dc_top_neon
137 
     sub         r2,  r0,  #FDEC_STRIDE
138 
@@ -443,7 +443,7 @@ function x264_predict_8x8c_dc_top_neon
139 
     vdup.8      d0,  d0[0]
140 
     vtrn.32     d0,  d1
141 
     b           pred8x8_dc_end
142 
-.endfunc
143 
+endfunc
144
145 
 function x264_predict_8x8c_dc_left_neon
146 
     mov         r1,  #FDEC_STRIDE
147 
@@ -455,7 +455,7 @@ function x264_predict_8x8c_dc_left_neon
148 
     vdup.8      d1,  d0[1]
149 
     vdup.8      d0,  d0[0]
150 
     b           pred8x8_dc_end
151 
-.endfunc
152 
+endfunc
153
154 
 function x264_predict_8x8c_dc_neon
155 
     sub         r2,  r0,  #FDEC_STRIDE
156 
@@ -481,7 +481,7 @@ pred8x8_dc_end:
157 
     vst1.8      {d1}, [r2,:64], r1
158 
 .endr
159 
     bx          lr
160 
-.endfunc
161 
+endfunc
162
163 
 function x264_predict_8x8c_h_neon
164 
     sub         r1, r0, #1
165 
@@ -493,7 +493,7 @@ function x264_predict_8x8c_h_neon
166 
     vst1.64     {d2}, [r0,:64], ip
167 
 .endr
168 
     bx          lr
169 
-.endfunc
170 
+endfunc
171
172 
 function x264_predict_8x8c_v_neon
173 
     sub         r0, r0, #FDEC_STRIDE
174 
@@ -503,7 +503,7 @@ function x264_predict_8x8c_v_neon
175 
     vst1.64     {d0}, [r0,:64], ip
176 
 .endr
177 
     bx          lr
178 
-.endfunc
179 
+endfunc
180
181 
 function x264_predict_8x8c_p_neon
182 
     sub         r3,  r0,  #FDEC_STRIDE
183 
@@ -556,7 +556,7 @@ function x264_predict_8x8c_p_neon
184 
     subs        r3,  r3,  #1
185 
     bne         1b
186 
     bx          lr
187 
-.endfunc
188 
+endfunc
189
190
191 
 function x264_predict_16x16_dc_top_neon
192 
@@ -567,7 +567,7 @@ function x264_predict_16x16_dc_top_neon
193 
     vrshrn.u16  d0,  q0,  #4
194 
     vdup.8      q0,  d0[0]
195 
     b           pred16x16_dc_end
196 
-.endfunc
197 
+endfunc
198
199 
 function x264_predict_16x16_dc_left_neon
200 
     mov         r1,  #FDEC_STRIDE
201 
@@ -578,7 +578,7 @@ function x264_predict_16x16_dc_left_neon
202 
     vrshrn.u16  d0,  q0,  #4
203 
     vdup.8      q0,  d0[0]
204 
     b           pred16x16_dc_end
205 
-.endfunc
206 
+endfunc
207
208 
 function x264_predict_16x16_dc_neon
209 
     sub         r3, r0, #FDEC_STRIDE
210 
@@ -616,7 +616,7 @@ pred16x16_dc_end:
211 
     vst1.64     {d0-d1}, [r0,:128], r1
212 
 .endr
213 
     bx          lr
214 
-.endfunc
215 
+endfunc
216
217 
 function x264_predict_16x16_h_neon
218 
     sub         r1, r0, #1
219 
@@ -630,7 +630,7 @@ function x264_predict_16x16_h_neon
220 
     vst1.64     {d2-d3}, [r0,:128], ip
221 
 .endr
222 
     bx          lr
223 
-.endfunc
224 
+endfunc
225
226 
 function x264_predict_16x16_v_neon
227 
     sub         r0, r0, #FDEC_STRIDE
228 
@@ -640,7 +640,7 @@ function x264_predict_16x16_v_neon
229 
     vst1.64     {d0-d1}, [r0,:128], ip
230 
 .endr
231 
     bx          lr
232 
-.endfunc
233 
+endfunc
234
235 
 function x264_predict_16x16_p_neon
236 
     sub         r3,  r0,  #FDEC_STRIDE
237 
@@ -697,4 +697,4 @@ function x264_predict_16x16_p_neon
238 
     subs        r3,  r3,  #1
239 
     bne         1b
240 
     bx          lr
241 
-.endfunc
242 
+endfunc
(-)files/patch-common_arm_quant-a.S (+98 lines)
Added Link Here
1 
--- common/arm/quant-a.S.orig	2014-08-27 20:45:08 UTC
2 
+++ common/arm/quant-a.S
3 
@@ -80,7 +80,7 @@ function x264_quant_2x2_dc_neon
4 
     vsub.s16    d3,  d3,  d0
5 
     vst1.64     {d3}, [r0,:64]
6 
     QUANT_END   d3
7 
-.endfunc
8 
+endfunc
9
10 
 // quant_4x4_dc( int16_t dct[16], int mf, int bias )
11 
 function x264_quant_4x4_dc_neon
12 
@@ -92,7 +92,7 @@ function x264_quant_4x4_dc_neon
13 
     QUANT_TWO   q0,  q0,  d4,  d5,  d4,  d5,  q0
14 
     vorr        d0,  d0,  d1
15 
     QUANT_END   d0
16 
-.endfunc
17 
+endfunc
18
19 
 // quant_4x4( int16_t dct[16], uint16_t mf[16], uint16_t bias[16] )
20 
 function x264_quant_4x4_neon
21 
@@ -104,7 +104,7 @@ function x264_quant_4x4_neon
22 
     QUANT_TWO   q0,  q1,  d4,  d5,  d6,  d7, q0
23 
     vorr        d0,  d0,  d1
24 
     QUANT_END   d0
25 
-.endfunc
26 
+endfunc
27
28 
 // quant_4x4x4( int16_t dct[4][16], uint16_t mf[16], uint16_t bias[16] )
29 
 function x264_quant_4x4x4_neon
30 
@@ -145,7 +145,7 @@ function x264_quant_4x4x4_neon
31 
     orrne       r0,  #8
32 
     vpop        {d8-d15}
33 
     bx          lr
34 
-.endfunc
35 
+endfunc
36
37 
 // quant_8x8( int16_t dct[64], uint16_t mf[64], uint16_t bias[64] )
38 
 function x264_quant_8x8_neon
39 
@@ -165,7 +165,7 @@ function x264_quant_8x8_neon
40 
 .endr
41 
     vorr        d0,  d0,  d1
42 
     QUANT_END   d0
43 
-.endfunc
44 
+endfunc
45
46 
 .macro DEQUANT_START mf_size offset dc=no
47 
     mov         r3,  #0x2b
48 
@@ -257,7 +257,7 @@ dequant_\size\()_rshift_loop:
49 
     bgt         dequant_\size\()_rshift_loop
50 
 .endif
51 
     bx          lr
52 
-.endfunc
53 
+endfunc
54 
 .endm
55
56 
 DEQUANT 4x4, 4
57 
@@ -307,7 +307,7 @@ dequant_4x4_dc_rshift:
58 
     vmovn.s32   d3,  q13
59 
     vst1.16     {d0-d3},   [r0,:128]
60 
     bx          lr
61 
-.endfunc
62 
+endfunc
63
64
65 
 // int coeff_last( int16_t *l )
66 
@@ -319,7 +319,7 @@ function x264_coeff_last4_arm
67 
     lsrs        r2,  r2,  #16
68 
     addne       r0,  r0,  #1
69 
     bx          lr
70 
-.endfunc
71 
+endfunc
72
73 
 function x264_coeff_last8_arm
74 
     ldrd        r2,  r3,  [r0, #8]
75 
@@ -333,7 +333,7 @@ function x264_coeff_last8_arm
76 
     lsrs        r2,  r2,  #16
77 
     addne       r0,  r0,  #1
78 
     bx          lr
79 
-.endfunc
80 
+endfunc
81
82 
 .macro COEFF_LAST_1x size
83 
 function x264_coeff_last\size\()_neon
84 
@@ -358,7 +358,7 @@ function x264_coeff_last\size\()_neon
85 
     subslt      r0,  r3,  r0,  lsr #2
86 
     movlt       r0,  #0
87 
     bx          lr
88 
-.endfunc
89 
+endfunc
90 
 .endm
91
92 
 COEFF_LAST_1x 15
93 
@@ -407,4 +407,4 @@ function x264_coeff_last64_neon
94 
     subslt      r0,  ip,  r0
95 
     movlt       r0,  #0
96 
     bx          lr
97 
-.endfunc
98 
+endfunc
(-)files/patch-configure (-9 / +75 lines)
Lines 1-20 Link Here
1 
From 9463ec0004f1bddc49c05ed8e38430a4ce1738fb Mon Sep 17 00:00:00 2001
 1 
--- configure.orig	2014-08-27 22:45:08.000000000 +0200
2 
From: Janne Grunau <janne-x264@jannau.net>
 2 
+++ configure	2015-01-07 13:42:20.868702616 +0100
3 
Date: Sun, 20 Jul 2014 13:40:28 +0200
 3 
@@ -197,8 +197,9 @@
4 
Subject: [PATCH] arm/ppc: use $CC as default assembler
 4
5 


              5
              
 as_check() {

            

            

              6
              
--- configure.orig	2014-08-27 20:45:08 UTC


              6
              
     log_check "whether $AS supports $1"

            

            

              7
              
+++ configure


              7
              
-    echo "$1" > conftest.asm

            

            

              8
              
@@ -648,7 +648,7 @@ case $host_cpu in


              8
              
-    if $AS conftest.asm $ASFLAGS $2 -o conftest.o >conftest.log 2>&1; then

            

            

              
              

              9
              
+    echo "$1" > conftest$AS_EXT

            

            


              10
              
+    as_cmd="$AS conftest$AS_EXT $ASFLAGS $2 -o conftest.o"

            

            


              11
              
+    if $as_cmd >conftest.log 2>&1; then

            

            


              12
              
         res=$?

            

            


              13
              
         log_ok

            

            


              14
              
     else

            

            


              15
              
@@ -206,12 +207,12 @@

            

            


              16
              
         log_fail

            

            


              17
              
         log_msg "Failed commandline was:"

            

            


              18
              
         log_msg "--------------------------------------------------"

            

            


              19
              
-        log_msg "$AS conftest.asm $ASFLAGS $2 -o conftest.o"

            

            


              20
              
+        log_msg "$as_cmd"

            

            


              21
              
         cat conftest.log >> config.log

            

            


              22
              
         log_msg "--------------------------------------------------"

            

            


              23
              
         log_msg "Failed program was:"

            

            


              24
              
         log_msg "--------------------------------------------------"

            

            


              25
              
-        cat conftest.asm >> config.log

            

            


              26
              
+        cat conftest$AS_EXT >> config.log

            

            


              27
              
         log_msg "--------------------------------------------------"

            

            


              28
              
     fi

            

            


              29
              
     return $res

            

            


              30
              
@@ -302,10 +303,13 @@

            

            


              31
              
 cross_prefix=""

            

            


              32
              
 

            

            


              33
              
 EXE=""

            

            


              34
              
+AS_EXT=".S"

            

            


              35
              
+NL="

            

            


              36
              
+"

            

            


              37
              
 

            

            


              38
              
 # list of all preprocessor HAVE values we can define

            

            


              39
              
 CONFIG_HAVE="MALLOC_H ALTIVEC ALTIVEC_H MMX ARMV6 ARMV6T2 NEON BEOSTHREAD POSIXTHREAD WIN32THREAD THREAD LOG2F SWSCALE \

            

            


              40
              
-             LAVF FFMS GPAC AVS GPL VECTOREXT INTERLACED CPU_COUNT OPENCL THP LSMASH X86_INLINE_ASM"

            

            


              41
              
+             LAVF FFMS GPAC AVS GPL VECTOREXT INTERLACED CPU_COUNT OPENCL THP LSMASH X86_INLINE_ASM AS_FUNC"

            

            


              42
              
 

            

            


              43
              
 # parse options

            

            


              44
              
 

            

            


              45
              
@@ -586,6 +590,7 @@

            

            


              46
              
     i*86)

            

            


              47
              
         ARCH="X86"

            

            


              48
              
         AS="yasm"

            

            


              49
              
+        AS_EXT=".asm"

            

            


              50
              
         ASFLAGS="$ASFLAGS -O2 -DARCH_X86_64=0 -I\$(SRCPATH)/common/x86/"

            

            


              51
              
         if [ $compiler = GNU ]; then

            

            


              52
              
             if [[ "$asm" == auto && "$CFLAGS" != *-march* ]]; then

            

            


              53
              
@@ -626,6 +631,7 @@

            

            


              54
              
     x86_64)

            

            


              55
              
         ARCH="X86_64"

            

            


              56
              
         AS="yasm"

            

            


              57
              
+        AS_EXT=".asm"

            

            


              58
              
         ASFLAGS="$ASFLAGS -DARCH_X86_64=1 -I\$(SRCPATH)/common/x86/"

            

            


              59
              
         [ $compiler = GNU ] && CFLAGS="-m64 $CFLAGS" && LDFLAGS="-m64 $LDFLAGS"

            

            


              60
              
         if [ "$SYS" = MACOSX ]; then

            

            


              61
              
@@ -648,7 +654,8 @@

            

        

          9
          
         ARCH="PPC"

          62
          
         ARCH="PPC"

        

        

          10
          
         if [ $asm = auto ] ; then

          63
          
         if [ $asm = auto ] ; then

        

        

          11
          
             define HAVE_ALTIVEC

          64
          
             define HAVE_ALTIVEC

        

        

          12
          
-            AS="${AS-${cross_prefix}gcc}"

          65
          
-            AS="${AS-${cross_prefix}gcc}"

        

        

          13
          
+            AS="${AS-${CC}}"

          66
          
+            AS="${AS-${CC}}"

        

            

              
              
              67
              
+            AS_EXT=".c"

            

        

          14
          
             if [ $SYS = MACOSX ] ; then

          68
          
             if [ $SYS = MACOSX ] ; then

        

        

          15
          
                 CFLAGS="$CFLAGS -faltivec -fastf -mcpu=G4"

          69
          
                 CFLAGS="$CFLAGS -faltivec -fastf -mcpu=G4"

        

        

          16
          
             else

          70
          
             else

        

          
            

              17
              
@@ -674,7 +674,7 @@ case $host_cpu in


              71
              
@@ -674,7 +681,7 @@

            

        

          18
          
                 LDFLAGS="$LDFLAGS -arch armv7"

          72
          
                 LDFLAGS="$LDFLAGS -arch armv7"

        

        

          19
          
             fi

          73
          
             fi

        

        

          20
          
         else

          74
          
         else

        

  

    
      
            Lines 23-25
          Subject: [PATCH] arm/ppc: use $CC as default assembler
      
      
        Link Here
      
    
  

        

          23
          
         fi

          77
          
         fi

        

        

          24
          
         ;;

          78
          
         ;;

        

        

          25
          
     s390|s390x)

          79
          
     s390|s390x)

        

            

              
              
              80
              
@@ -760,6 +767,11 @@

            

            

              81
              
     fi

            

            

              82
              
 fi

            

            

              83
              
 

            

            

              84
              
+if [ $asm = auto -a $ARCH = ARM ] ; then

            

            

              85
              
+    # check if the assembler supports '.func' (clang 3.5 does not)

            

            

              86
              
+    as_check ".func test${NL}.endfunc" && define HAVE_AS_FUNC 1

            

            

              87
              
+fi

            

            

              88
              
+

            

            

              89
              
 [ $asm = no ] && AS=""

            

            

              90
              
 [ "x$AS" = x ] && asm="no" || asm="yes"

            

            

              91
              
 

            






  

  Return to bug 196591