;
+bilinear_taps_coeff
+ DCD 128, 0, 112, 16, 96, 32, 80, 48, 64, 64, 48, 80, 32, 96, 16, 112
+
+;-----------------
+
EXPORT |vp8_sub_pixel_variance16x16_neon_func|
ARM
REQUIRE8
|vp8_sub_pixel_variance16x16_neon_func| PROC
push {r4-r6, lr}
- ldr r12, _BilinearTaps_coeff_
+ adr r12, bilinear_taps_coeff
ldr r4, [sp, #16] ;load *dst_ptr from stack
ldr r5, [sp, #20] ;load dst_pixels_per_line from stack
ldr r6, [sp, #24] ;load *sse from stack
ENDP
-;-----------------
-
-_BilinearTaps_coeff_
- DCD bilinear_taps_coeff
-bilinear_taps_coeff
- DCD 128, 0, 112, 16, 96, 32, 80, 48, 64, 64, 48, 80, 32, 96, 16, 112
-
END
|vp8_sub_pixel_variance8x8_neon| PROC
push {r4-r5, lr}
- ldr r12, _BilinearTaps_coeff_
+ adr r12, bilinear_taps_coeff
ldr r4, [sp, #12] ;load *dst_ptr from stack
ldr r5, [sp, #16] ;load dst_pixels_per_line from stack
ldr lr, [sp, #20] ;load *sse from stack
;-----------------
-_BilinearTaps_coeff_
- DCD bilinear_taps_coeff
bilinear_taps_coeff
DCD 128, 0, 112, 16, 96, 32, 80, 48, 64, 64, 48, 80, 32, 96, 16, 112
vmul.s16 q2, q6, q4 ; x * Dequant
vmul.s16 q3, q7, q5
- ldr r0, _inv_zig_zag_ ; load ptr of inverse zigzag table
+ adr r0, inv_zig_zag ; load ptr of inverse zigzag table
vceq.s16 q8, q8 ; set q8 to all 1
vadd.s16 q12, q14 ; x + Round
vadd.s16 q13, q15
- ldr r0, _inv_zig_zag_ ; load ptr of inverse zigzag table
+ adr r0, inv_zig_zag ; load ptr of inverse zigzag table
vqdmulh.s16 q12, q8 ; y = ((Round+abs(z)) * Quant) >> 16
vqdmulh.s16 q13, q9
ENDP
; default inverse zigzag table is defined in vp8/common/entropy.c
-_inv_zig_zag_
- DCD inv_zig_zag
-
ALIGN 16 ; enable use of @128 bit aligned loads
inv_zig_zag
DCW 0x0001, 0x0002, 0x0006, 0x0007