History

Unify the indentation in the new aarch64 assembly files

Martin Storsjö committed 12 years ago

Commit ae629091 parent 964e98f2 files · +50 −50Browse files

Showing the changes to codec/processing/src (1 of 2 files). Show all

Unified · Split

codec/processing/src/arm64/vaa_calc_aarch64_neon.S+34−34
@@ -36,19 +36,19 @@ · 35 unmodified lines
36 36
37#ifdef __APPLE__37#ifdef __APPLE__
38.macro ABS_SUB_SUM_16BYTES38.macro ABS_SUB_SUM_16BYTES
39 ld1 {v0.16b}, [x0], x439 ld1 {v0.16b}, [x0], x4
40 ld1 {v1.16b}, [x1], x440 ld1 {v1.16b}, [x1], x4
41 uabal $0, v0.8b, v1.8b41 uabal $0, v0.8b, v1.8b
42 uabal2 $1, v0.16b,v1.16b42 uabal2 $1, v0.16b,v1.16b
43.endm43.endm
44 44
45.macro ABS_SUB_SUM_8x16BYTES45.macro ABS_SUB_SUM_8x16BYTES
46 ld1 {v0.16b}, [x0], x446 ld1 {v0.16b}, [x0], x4
47 ld1 {v1.16b}, [x1], x447 ld1 {v1.16b}, [x1], x4
48 uabdl $0, v0.8b, v1.8b48 uabdl $0, v0.8b, v1.8b
49 uabdl2 $1, v0.16b,v1.16b49 uabdl2 $1, v0.16b,v1.16b
50 50
51 ABS_SUB_SUM_16BYTES $0, $151 ABS_SUB_SUM_16BYTES $0, $1
52 ABS_SUB_SUM_16BYTES $0, $152 ABS_SUB_SUM_16BYTES $0, $1
53 ABS_SUB_SUM_16BYTES $0, $153 ABS_SUB_SUM_16BYTES $0, $1
54 ABS_SUB_SUM_16BYTES $0, $154 ABS_SUB_SUM_16BYTES $0, $1
@@ -58,19 +58,19 @@ · 3 unmodified lines
58.endm58.endm
59#else59#else
60.macro ABS_SUB_SUM_16BYTES arg0, arg160.macro ABS_SUB_SUM_16BYTES arg0, arg1
61 ld1 {v0.16b}, [x0], x461 ld1 {v0.16b}, [x0], x4
62 ld1 {v1.16b}, [x1], x462 ld1 {v1.16b}, [x1], x4
63 uabal \arg0, v0.8b, v1.8b63 uabal \arg0, v0.8b, v1.8b
64 uabal2 \arg1, v0.16b,v1.16b64 uabal2 \arg1, v0.16b,v1.16b
65.endm65.endm
66 66
67.macro ABS_SUB_SUM_8x16BYTES arg0, arg167.macro ABS_SUB_SUM_8x16BYTES arg0, arg1
68 ld1 {v0.16b}, [x0], x468 ld1 {v0.16b}, [x0], x4
69 ld1 {v1.16b}, [x1], x469 ld1 {v1.16b}, [x1], x4
70 uabdl \arg0, v0.8b, v1.8b70 uabdl \arg0, v0.8b, v1.8b
71 uabdl2 \arg1, v0.16b,v1.16b71 uabdl2 \arg1, v0.16b,v1.16b
72 72
73 ABS_SUB_SUM_16BYTES \arg0, \arg173 ABS_SUB_SUM_16BYTES \arg0, \arg1
74 ABS_SUB_SUM_16BYTES \arg0, \arg174 ABS_SUB_SUM_16BYTES \arg0, \arg1
75 ABS_SUB_SUM_16BYTES \arg0, \arg175 ABS_SUB_SUM_16BYTES \arg0, \arg1
76 ABS_SUB_SUM_16BYTES \arg0, \arg176 ABS_SUB_SUM_16BYTES \arg0, \arg1
@@ -82,7 +82,7 @@ · 5 unmodified lines
82 82
83/*83/*
84 * void vaa_calc_sad_neon(uint8_t *cur_data, uint8_t *ref_data, int32_t pic_width, int32_t pic_height, int32_t pic_stride,84 * void vaa_calc_sad_neon(uint8_t *cur_data, uint8_t *ref_data, int32_t pic_width, int32_t pic_height, int32_t pic_stride,
85 * int32_t *psadframe, int32_t *psad8x8)85 * int32_t *psadframe, int32_t *psad8x8)
86 */86 */
87WELS_ASM_AARCH64_FUNC_BEGIN VAACalcSad_AArch64_neon87WELS_ASM_AARCH64_FUNC_BEGIN VAACalcSad_AArch64_neon
88 eor v31.16b, v31.16b, v31.16b88 eor v31.16b, v31.16b, v31.16b
@@ -121,14 +121,14 @@ WELS_ASM_AARCH64_FUNC_END · 32 unmodified lines
121 121
122.macro SAD_SD_MAD_8x16BYTES122.macro SAD_SD_MAD_8x16BYTES
123 ld1 {v0.16b}, [x0], x4123 ld1 {v0.16b}, [x0], x4
124 ld1 {v1.16b}, [x1], x4124 ld1 {v1.16b}, [x1], x4
125 uabd v31.16b, v0.16b, v1.16b125 uabd v31.16b, v0.16b, v1.16b
126 uaddlp v2.8h, v31.16b126 uaddlp v2.8h, v31.16b
127 uaddlp v4.8h, v0.16b127 uaddlp v4.8h, v0.16b
128 uaddlp v5.8h, v1.16b128 uaddlp v5.8h, v1.16b
129.rept 7129.rept 7
130 ld1 {v0.16b}, [x0], x4130 ld1 {v0.16b}, [x0], x4
131 ld1 {v1.16b}, [x1], x4131 ld1 {v1.16b}, [x1], x4
132 uabd v30.16b, v0.16b, v1.16b132 uabd v30.16b, v0.16b, v1.16b
133 umax v31.16b, v31.16b,v30.16b133 umax v31.16b, v31.16b,v30.16b
134 uadalp v2.8h, v30.16b134 uadalp v2.8h, v30.16b
@@ -138,7 +138,7 @@ WELS_ASM_AARCH64_FUNC_END · 3 unmodified lines
138.endm138.endm
139/*139/*
140 * void vaa_calc_sad_bgd_neon(uint8_t *cur_data, uint8_t *ref_data, int32_t pic_width, int32_t pic_height, int32_t pic_stride,140 * void vaa_calc_sad_bgd_neon(uint8_t *cur_data, uint8_t *ref_data, int32_t pic_width, int32_t pic_height, int32_t pic_stride,
141 * int32_t *psadframe, int32_t *psad8x8, int32_t *p_sd8x8, uint8_t *p_mad8x8)141 * int32_t *psadframe, int32_t *psad8x8, int32_t *p_sd8x8, uint8_t *p_mad8x8)
142 */142 */
143WELS_ASM_AARCH64_FUNC_BEGIN VAACalcSadBgd_AArch64_neon143WELS_ASM_AARCH64_FUNC_BEGIN VAACalcSadBgd_AArch64_neon
144 ldr x15, [sp, #0]144 ldr x15, [sp, #0]
@@ -196,7 +196,7 @@ WELS_ASM_AARCH64_FUNC_END · 51 unmodified lines
196 196
197.macro SAD_SSD_BGD_8x16BYTES_1197.macro SAD_SSD_BGD_8x16BYTES_1
198 ld1 {v0.16b}, [x0], x4198 ld1 {v0.16b}, [x0], x4
199 ld1 {v1.16b}, [x1], x4199 ld1 {v1.16b}, [x1], x4
200 uabd v31.16b, v0.16b, v1.16b200 uabd v31.16b, v0.16b, v1.16b
201 umull v30.8h, v31.8b, v31.8b201 umull v30.8h, v31.8b, v31.8b
202 uaddlp v29.4s, v30.8h202 uaddlp v29.4s, v30.8h
@@ -214,7 +214,7 @@ WELS_ASM_AARCH64_FUNC_END · 11 unmodified lines
214 uaddlp v5.8h, v1.16b214 uaddlp v5.8h, v1.16b
215.rept 7215.rept 7
216 ld1 {v0.16b}, [x0], x4216 ld1 {v0.16b}, [x0], x4
217 ld1 {v1.16b}, [x1], x4217 ld1 {v1.16b}, [x1], x4
218 uabd v3.16b, v0.16b, v1.16b218 uabd v3.16b, v0.16b, v1.16b
219 umax v31.16b, v31.16b,v3.16b //p_mad219 umax v31.16b, v31.16b,v3.16b //p_mad
220 umull v30.8h, v3.8b, v3.8b220 umull v30.8h, v3.8b, v3.8b
@@ -236,7 +236,7 @@ WELS_ASM_AARCH64_FUNC_END · 15 unmodified lines
236 236
237.macro SAD_SSD_BGD_8x16BYTES_2237.macro SAD_SSD_BGD_8x16BYTES_2
238 ld1 {v0.16b}, [x0], x4238 ld1 {v0.16b}, [x0], x4
239 ld1 {v1.16b}, [x1], x4239 ld1 {v1.16b}, [x1], x4
240 uabd v26.16b, v0.16b, v1.16b240 uabd v26.16b, v0.16b, v1.16b
241 umull v30.8h, v26.8b, v26.8b241 umull v30.8h, v26.8b, v26.8b
242 uadalp v29.4s, v30.8h242 uadalp v29.4s, v30.8h
@@ -254,7 +254,7 @@ WELS_ASM_AARCH64_FUNC_END · 11 unmodified lines
254 uaddlp v7.8h, v1.16b254 uaddlp v7.8h, v1.16b
255.rept 7255.rept 7
256 ld1 {v0.16b}, [x0], x4256 ld1 {v0.16b}, [x0], x4
257 ld1 {v1.16b}, [x1], x4257 ld1 {v1.16b}, [x1], x4
258 uabd v3.16b, v0.16b, v1.16b258 uabd v3.16b, v0.16b, v1.16b
259 umax v26.16b, v26.16b,v3.16b //p_mad259 umax v26.16b, v26.16b,v3.16b //p_mad
260 umull v30.8h, v3.8b, v3.8b260 umull v30.8h, v3.8b, v3.8b
@@ -347,7 +347,7 @@ WELS_ASM_AARCH64_FUNC_END · 86 unmodified lines
347 347
348.macro SAD_SSD_8x16BYTES_1348.macro SAD_SSD_8x16BYTES_1
349 ld1 {v0.16b}, [x0], x4349 ld1 {v0.16b}, [x0], x4
350 ld1 {v1.16b}, [x1], x4350 ld1 {v1.16b}, [x1], x4
351 uabd v31.16b, v0.16b, v1.16b351 uabd v31.16b, v0.16b, v1.16b
352 umull v30.8h, v31.8b, v31.8b352 umull v30.8h, v31.8b, v31.8b
353 uaddlp v29.4s, v30.8h353 uaddlp v29.4s, v30.8h
@@ -363,7 +363,7 @@ WELS_ASM_AARCH64_FUNC_END · 9 unmodified lines
363 uaddlp v2.8h, v31.16b // p_sad363 uaddlp v2.8h, v31.16b // p_sad
364.rept 7364.rept 7
365 ld1 {v0.16b}, [x0], x4365 ld1 {v0.16b}, [x0], x4
366 ld1 {v1.16b}, [x1], x4366 ld1 {v1.16b}, [x1], x4
367 uabd v3.16b, v0.16b, v1.16b367 uabd v3.16b, v0.16b, v1.16b
368 umull v30.8h, v3.8b, v3.8b368 umull v30.8h, v3.8b, v3.8b
369 uadalp v29.4s, v30.8h369 uadalp v29.4s, v30.8h
@@ -382,7 +382,7 @@ WELS_ASM_AARCH64_FUNC_END · 12 unmodified lines
382 382
383.macro SAD_SSD_8x16BYTES_2383.macro SAD_SSD_8x16BYTES_2
384 ld1 {v0.16b}, [x0], x4384 ld1 {v0.16b}, [x0], x4
385 ld1 {v1.16b}, [x1], x4385 ld1 {v1.16b}, [x1], x4
386 uabd v26.16b, v0.16b, v1.16b386 uabd v26.16b, v0.16b, v1.16b
387 umull v30.8h, v26.8b, v26.8b387 umull v30.8h, v26.8b, v26.8b
388 uadalp v29.4s, v30.8h388 uadalp v29.4s, v30.8h
@@ -400,7 +400,7 @@ WELS_ASM_AARCH64_FUNC_END · 11 unmodified lines
400 uaddlp v7.8h, v1.16b400 uaddlp v7.8h, v1.16b
401.rept 7401.rept 7
402 ld1 {v0.16b}, [x0], x4402 ld1 {v0.16b}, [x0], x4
403 ld1 {v1.16b}, [x1], x4403 ld1 {v1.16b}, [x1], x4
404 uabd v3.16b, v0.16b, v1.16b404 uabd v3.16b, v0.16b, v1.16b
405 umull v30.8h, v3.8b, v3.8b405 umull v30.8h, v3.8b, v3.8b
406 uadalp v29.4s, v30.8h406 uadalp v29.4s, v30.8h
@@ -469,7 +469,7 @@ WELS_ASM_AARCH64_FUNC_END · 62 unmodified lines
469 469
470.macro SAD_VAR_8x16BYTES_1470.macro SAD_VAR_8x16BYTES_1
471 ld1 {v0.16b}, [x0], x4471 ld1 {v0.16b}, [x0], x4
472 ld1 {v1.16b}, [x1], x4472 ld1 {v1.16b}, [x1], x4
473 uabd v31.16b, v0.16b, v1.16b473 uabd v31.16b, v0.16b, v1.16b
474 uaddlp v2.8h, v31.16b // p_sad474 uaddlp v2.8h, v31.16b // p_sad
475 475
@@ -481,7 +481,7 @@ WELS_ASM_AARCH64_FUNC_END · 5 unmodified lines
481 481
482.rept 7482.rept 7
483 ld1 {v0.16b}, [x0], x4483 ld1 {v0.16b}, [x0], x4
484 ld1 {v1.16b}, [x1], x4484 ld1 {v1.16b}, [x1], x4
485 uabd v3.16b, v0.16b, v1.16b485 uabd v3.16b, v0.16b, v1.16b
486 uadalp v2.8h, v3.16b //p_sad486 uadalp v2.8h, v3.16b //p_sad
487 487
@@ -494,7 +494,7 @@ WELS_ASM_AARCH64_FUNC_END · 6 unmodified lines
494.endm494.endm
495.macro SAD_VAR_8x16BYTES_2495.macro SAD_VAR_8x16BYTES_2
496 ld1 {v0.16b}, [x0], x4496 ld1 {v0.16b}, [x0], x4
497 ld1 {v1.16b}, [x1], x4497 ld1 {v1.16b}, [x1], x4
498 uabd v26.16b, v0.16b, v1.16b498 uabd v26.16b, v0.16b, v1.16b
499 uaddlp v16.8h,v26.16b // p_sad499 uaddlp v16.8h,v26.16b // p_sad
500 500
@@ -505,7 +505,7 @@ WELS_ASM_AARCH64_FUNC_END · 4 unmodified lines
505 uadalp v27.4s, v30.8h // p_sqsum505 uadalp v27.4s, v30.8h // p_sqsum
506.rept 7506.rept 7
507 ld1 {v0.16b}, [x0], x4507 ld1 {v0.16b}, [x0], x4
508 ld1 {v1.16b}, [x1], x4508 ld1 {v1.16b}, [x1], x4
509 uabd v3.16b, v0.16b, v1.16b509 uabd v3.16b, v0.16b, v1.16b
510 uadalp v16.8h, v3.16b //p_sad510 uadalp v16.8h, v3.16b //p_sad
511 511

Keyboard shortcuts

General

Show keyboard shortcuts
?
Focus the current search
/

Issues and pull requests

Open filters
f

Issues, pull requests and Inbox

Select next item
j↓
Select previous item
k↑
Open selected item
Enter
Dismiss filters or clear selection
Esc

Repository code

Go to file
t