The .align directive takes an argument in number of bits, i.e. the actual alignment is 2^n. Previously building with binutils failed, since 16 isn't a valid parameter to .align, the maximum is 15. Thus, this makes the code try to align to 16 bytes, instead of aligning to 65536 bytes. This fixes building for android. This also clears up the same mistake in the aarch64 code, even though that one built just fine.
Unified · Split
| @@ -33,7 +33,7 @@ · 32 unmodified lines | ||
| 33 | 33 | #ifdef HAVE_NEON_AARCH64 |
| 34 | 34 | .text |
| 35 | 35 | #include "arm_arch64_common_macro.S" |
| 36 | −.align 16 | |
| 36 | +.align 4 | |
| 37 | 37 | filter_para: .short 0, 1, -5, 20, 0, 0, 0, 0 |
| 38 | 38 | |
| 39 | 39 | #ifdef __APPLE__ |
| @@ -308,7 +308,7 @@ WELS_ASM_AARCH64_FUNC_BEGIN WelsDecoderIChromaPredDcTop_AArch64_neon · 307 unmodified lines | ||
| 308 | 308 | .endr |
| 309 | 309 | WELS_ASM_AARCH64_FUNC_END |
| 310 | 310 | |
| 311 | −.align 16 | |
| 311 | +.align 4 | |
| 312 | 312 | intra_1_to_4: .short 17*1, 17*2, 17*3, 17*4, 17*1, 17*2, 17*3, 17*4 |
| 313 | 313 | intra_m3_to_p4: .short -3, -2, -1, 0, 1, 2, 3, 4 |
| 314 | 314 | |
| @@ -457,7 +457,7 @@ WELS_ASM_AARCH64_FUNC_BEGIN WelsDecoderI16x16LumaPredDcLeft_AArch64_neon · 142 unmodified lines | ||
| 457 | 457 | WELS_ASM_AARCH64_FUNC_END |
| 458 | 458 | |
| 459 | 459 | |
| 460 | −.align 16 | |
| 460 | +.align 4 | |
| 461 | 461 | intra_1_to_8: .short 5, 10, 15, 20, 25, 30, 35, 40 |
| 462 | 462 | intra_m7_to_p8: .short -7, -6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8 |
| 463 | 463 | |
| @@ -292,7 +292,7 @@ _hash_assign_end: · 291 unmodified lines | ||
| 292 | 292 | ldmia sp!, {r4-r7} |
| 293 | 293 | WELS_ASM_FUNC_END |
| 294 | 294 | |
| 295 | −.align 16 | |
| 295 | +.align 4 | |
| 296 | 296 | mv_x_inc_x4: .short 0x10, 0x10, 0x10, 0x10, 0x00, 0x00, 0x00, 0x00 |
| 297 | 297 | mv_y_inc_x4: .short 0x04, 0x04, 0x04, 0x04, 0x00, 0x00, 0x00, 0x00 |
| 298 | 298 | mx_x_offset_x4: .short 0x00, 0x04, 0x08, 0x0c, 0x00, 0x00, 0x00, 0x00 |
| @@ -294,7 +294,7 @@ WELS_ASM_AARCH64_FUNC_BEGIN WelsIChromaPredDcTop_AArch64_neon · 293 unmodified lines | ||
| 294 | 294 | .endr |
| 295 | 295 | WELS_ASM_AARCH64_FUNC_END |
| 296 | 296 | |
| 297 | −.align 16 | |
| 297 | +.align 4 | |
| 298 | 298 | intra_1_to_4: .short 17*1, 17*2, 17*3, 17*4, 17*1, 17*2, 17*3, 17*4 |
| 299 | 299 | intra_m3_to_p4: .short -3, -2, -1, 0, 1, 2, 3, 4 |
| 300 | 300 | |
| @@ -437,7 +437,7 @@ WELS_ASM_AARCH64_FUNC_BEGIN WelsI16x16LumaPredDcLeft_AArch64_neon · 136 unmodified lines | ||
| 437 | 437 | WELS_ASM_AARCH64_FUNC_END |
| 438 | 438 | |
| 439 | 439 | |
| 440 | −.align 16 | |
| 440 | +.align 4 | |
| 441 | 441 | intra_1_to_8: .short 5, 10, 15, 20, 25, 30, 35, 40 |
| 442 | 442 | intra_m7_to_p8: .short -7, -6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8 |
| 443 | 443 | |
| @@ -271,7 +271,7 @@ _hash_assign_loop_x4_rem: · 270 unmodified lines | ||
| 271 | 271 | _hash_assign_end: |
| 272 | 272 | WELS_ASM_AARCH64_FUNC_END |
| 273 | 273 | |
| 274 | −.align 16 | |
| 274 | +.align 4 | |
| 275 | 275 | mv_x_inc_x4: .short 0x10, 0x10, 0x10, 0x10, 0x00, 0x00, 0x00, 0x00 |
| 276 | 276 | mv_y_inc_x4: .short 0x04, 0x04, 0x04, 0x04, 0x00, 0x00, 0x00, 0x00 |
| 277 | 277 | mx_x_offset_x4: .short 0x00, 0x04, 0x08, 0x0c, 0x00, 0x00, 0x00, 0x00 |